modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-30 12:27:52
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 528
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-30 12:27:19
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
bagassword21/mynita
|
bagassword21
| 2023-06-23T16:19:57Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T16:19:18Z |
---
license: creativeml-openrail-m
---
|
hidude562/Maestro-0.5
|
hidude562
| 2023-06-23T16:08:56Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"music",
"en",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-23T16:04:55Z |
---
license: mit
language:
- en
metrics:
- accuracy
library_name: transformers
pipeline_tag: text-generation
tags:
- music
---
|
c72599/dqn-SpaceInvadersNoFrameskip-v4
|
c72599
| 2023-06-23T16:07:57Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T16:07:18Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 747.00 +/- 210.70
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga c72599 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga c72599 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga c72599
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
johacbeg/spanish-gpt2-finetuned-rap-lyrics-finetuned-TASS2020
|
johacbeg
| 2023-06-23T16:05:38Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-23T15:54:46Z |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: spanish-gpt2-finetuned-rap-lyrics-finetuned-TASS2020
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# spanish-gpt2-finetuned-rap-lyrics-finetuned-TASS2020
This model is a fine-tuned version of [Narrativa/spanish-gpt2-finetuned-rap-lyrics](https://huggingface.co/Narrativa/spanish-gpt2-finetuned-rap-lyrics) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 5.2864
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 100 | 5.3694 |
| No log | 2.0 | 200 | 5.3025 |
| No log | 3.0 | 300 | 5.2864 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
TheBloke/mpt-30B-GGML
|
TheBloke
| 2023-06-23T15:57:30Z | 5 | 17 |
transformers
|
[
"transformers",
"mpt",
"Composer",
"MosaicML",
"llm-foundry",
"StreamingDatasets",
"dataset:allenai/c4",
"dataset:mc4",
"dataset:togethercomputer/RedPajama-Data-1T",
"dataset:bigcode/the-stack-dedup",
"dataset:allenai/s2orc",
"arxiv:2108.12409",
"arxiv:2302.13971",
"arxiv:2205.14135",
"arxiv:2010.04245",
"arxiv:1909.08053",
"arxiv:2302.06675",
"license:apache-2.0",
"region:us"
] | null | 2023-06-23T14:21:47Z |
---
license: apache-2.0
tags:
- Composer
- MosaicML
- llm-foundry
- StreamingDatasets
datasets:
- allenai/c4
- mc4
- togethercomputer/RedPajama-Data-1T
- bigcode/the-stack-dedup
- allenai/s2orc
inference: false
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# MosaicML's MPT-30B GGML
These files are GGML format model files for [MosaicML's MPT-30B](https://huggingface.co/mosaicml/mpt-30b).
Please note that these GGMLs are **not compatible with llama.cpp, or currently with text-generation-webui**. Please see below for a list of tools known to work with these model files.
[KoboldCpp](https://github.com/LostRuins/koboldcpp) just added GPU accelerated (OpenCL) support for MPT models, so that is the client I recommend using for these models.
**Note**: Please use version 1.32.1 or later of KoboldCpp, as there was a bug in 1.32 that affected loading of MPT models.
## Repositories available
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/mpt-30B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mosaicml/mpt-30b)
## Prompt template
This is a non-fine-tuned base model. So it is designed for text completion, not following instructions, such as in the following example:
```
The meaning of life is
```
## A note regarding context length: 8K
The base model has an 8K context length. It is not yet confirmed if the 8K context of this model works with the quantised files.
If it does, [KoboldCpp](https://github.com/LostRuins/koboldcpp) supports 8K context if you manually set it to 8K by adjusting the text box above the slider:
It is currently unknown as to increased context is compatible with other MPT GGML clients.
If you have feedback on this, please let me know.
<!-- compatibility_ggml start -->
## Compatibilty
These files are **not** compatible with text-generation-webui, llama.cpp, or llama-cpp-python.
Currently they can be used with:
* KoboldCpp, a powerful inference engine based on llama.cpp, with good UI and GPU accelerated support for MPT models: [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* The ctransformers Python library, which includes LangChain support: [ctransformers](https://github.com/marella/ctransformers)
* The LoLLMS Web UI which uses ctransformers: [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [rustformers' llm](https://github.com/rustformers/llm)
* The example `mpt` binary provided with [ggml](https://github.com/ggerganov/ggml)
As other options become available I will endeavour to update them here (do let me know in the Community tab if I've missed something!)
## Tutorial for using LoLLMS Web UI
* [Text tutorial, written by **Lucas3DCG**](https://huggingface.co/TheBloke/MPT-7B-Storywriter-GGML/discussions/2#6475d914e9b57ce0caa68888)
* [Video tutorial, by LoLLMS Web UI's author **ParisNeo**](https://www.youtube.com/watch?v=ds_U0TDzbzI)
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| mpt-30b.ggmlv0.q4_0.bin | q4_0 | 4 | 16.85 GB | 19.35 GB | Original llama.cpp quant method, 4-bit. |
| mpt-30b.ggmlv0.q4_1.bin | q4_1 | 4 | 18.73 GB | 21.23 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| mpt-30b.ggmlv0.q5_0.bin | q5_0 | 5 | 20.60 GB | 23.10 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| mpt-30b.ggmlv0.q5_1.bin | q5_1 | 5 | 22.47 GB | 24.97 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| mpt-30b.ggmlv0.q8_0.bin | q8_0 | 8 | 31.83 GB | 34.33 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: Mano Prime, Fen Risland, Derek Yates, Preetika Verma, webtim, Sean Connelly, Alps Aficionado, Karl Bernard, Junyu Yang, Nathan LeClaire, Chris McCloskey, Lone Striker, Asp the Wyvern, Eugene Pentland, Imad Khwaja, trip7s trip, WelcomeToTheClub, John Detwiler, Artur Olbinski, Khalefa Al-Ahmad, Trenton Dambrowitz, Talal Aujan, Kevin Schuppel, Luke Pendergrass, Pyrater, Joseph William Delisle, terasurfer , vamX, Gabriel Puliatti, David Flickinger, Jonathan Leane, Iucharbius , Luke, Deep Realms, Cory Kujawski, ya boyyy, Illia Dulskyi, senxiiz, Johann-Peter Hartmann, John Villwock, K, Ghost , Spiking Neurons AB, Nikolai Manek, Rainer Wilmers, Pierre Kircher, biorpg, Space Cruiser, Ai Maven, subjectnull, Willem Michiel, Ajan Kanaga, Kalila, chris gileta, Oscar Rangel.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: MosaicML's MPT-30B
# MPT-30B
MPT-30B is a decoder-style transformer pretrained from scratch on 1T tokens of English text and code.
This model was trained by [MosaicML](https://www.mosaicml.com).
MPT-30B is part of the family of Mosaic Pretrained Transformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference.
MPT-30B comes with special features that differentiate it from other LLMs, including an 8k token context window (which can be further extended via finetuning; see [MPT-7B-StoryWriter](https://huggingface.co/mosaicml/mpt-7b-storywriter)), support for context-length extrapolation via [ALiBi](https://arxiv.org/abs/2108.12409), and efficient inference + training via FlashAttention. It also has strong coding abilities thanks to its pretraining mix. MPT models can also be served efficiently with both standard HuggingFace pipelines and NVIDIA's [FasterTransformer](https://github.com/NVIDIA/FasterTransformer).
The size of MPT-30B was also specifically chosen to make it easy to deploy on a single GPU—either 1xA100-80GB in 16-bit precision or 1xA100-40GB in 8-bit precision.
This model uses the MosaicML LLM codebase, which can be found in the [llm-foundry repository](https://github.com/mosaicml/llm-foundry). It was trained by MosaicML’s NLP team on the [MosaicML platform](https://www.mosaicml.com/training) for LLM pretraining, finetuning, and inference.
### How is this model different?
MPT-30B is:
* **Licensed for the possibility of commercial use** (unlike [LLaMA](https://arxiv.org/abs/2302.13971)).
* **Trained on a large amount of data** (1T tokens like [LLaMA](https://arxiv.org/abs/2302.13971) vs. 300B for [Pythia](https://github.com/EleutherAI/pythia), 300B for [OpenLLaMA](https://github.com/openlm-research/open_llama), and 800B for [StableLM](https://github.com/Stability-AI/StableLM)).
* **Prepared to handle extremely long inputs** thanks to [ALiBi](https://arxiv.org/abs/2108.12409).
* **Capable of fast training and inference** (via [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf) and [FasterTransformer](https://github.com/NVIDIA/FasterTransformer))
* **Equipped with highly efficient open-source training code** via the [llm-foundry repository](https://github.com/mosaicml/llm-foundry)
### Models finetuned off MPT-30B:
The following models are finetuned on MPT-30B:
* [MPT-30B-Instruct](https://huggingface.co/mosaicml/mpt-30b-instruct): a model for short-form instruction following.
Built by finetuning MPT-30B on several carefully curated datasets.
* License: _CC-By-NC-SA-3.0_
* [MPT-30B-Chat](https://huggingface.co/mosaicml/mpt-30b-chat): a chatbot-like model for dialogue generation.
Built by finetuning MPT-30B on [ShareGPT-Vicuna](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered), [Camel-AI](https://huggingface.co/camel-ai),
[GPTeacher](https://github.com/teknium1/GPTeacher), [Guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco), [Baize](https://github.com/project-baize/baize-chatbot) and some generated datasets.
* License: _CC-By-NC-SA-4.0_
* [Demo on Hugging Face Spaces](https://huggingface.co/spaces/mosaicml/mpt-30b-chat)
## Model Date
June 22, 2023
## Model License
Apache-2.0
## Documentation
* [Blog post: MPT-30B: Raising the bar for open-source foundation models](https://www.mosaicml.com/blog/mpt-30b)
* [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/)
* Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)!
## How to Use
This model is best used with the MosaicML [llm-foundry repository](https://github.com/mosaicml/llm-foundry) for training and finetuning.
```python
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
'mosaicml/mpt-30b',
trust_remote_code=True
)
```
Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method.
This is because we use a custom `MPT` model architecture that is not yet part of the Hugging Face `transformers` package.
`MPT` includes options for many training efficiency features such as [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), [QK LayerNorm](https://arxiv.org/abs/2010.04245), and more.
To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision:
```python
import torch
import transformers
name = 'mosaicml/mpt-30b'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.attn_config['attn_impl'] = 'triton' # change this to use triton-based FlashAttention
config.init_device = 'cuda:0' # For fast initialization directly on GPU!
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
torch_dtype=torch.bfloat16, # Load model weights in bfloat16
trust_remote_code=True
)
```
The model was trained initially with a sequence length of 4096 with an additional pretraining stage for sequence length adapation up to 8192. However, ALiBi enables users to increase the maximum sequence length even further during finetuning and/or inference. For example:
```python
import transformers
name = 'mosaicml/mpt-30b'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.max_seq_len = 16384 # (input + output) tokens can now be up to 16384
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
trust_remote_code=True
)
```
This model was trained with the MPT-30B tokenizer which is identical to the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer.
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('mosaicml/mpt-30b')
```
The model can then be used, for example, within a text-generation pipeline.
Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html).
```python
from transformers import pipeline
with torch.autocast('cuda', dtype=torch.bfloat16):
inputs = tokenizer('Here is a recipe for vegan banana bread:\n', return_tensors="pt").to('cuda')
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
# or using the HF pipeline
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0')
with torch.autocast('cuda', dtype=torch.bfloat16):
print(
pipe('Here is a recipe for vegan banana bread:\n',
max_new_tokens=100,
do_sample=True,
use_cache=True))
```
## Model Description
The architecture is a modification of a standard decoder-only transformer.
The model has been modified from a standard transformer in the following ways:
* It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf)
* It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings
* It does not use biases
| Hyperparameter | Value |
|----------------|-------|
|n_parameters | 29.95B |
|n_layers | 48 |
| n_heads | 64 |
| d_model | 7168 |
| vocab size | 50432 |
| sequence length | 8192 |
## Training Data
### Streaming Datasets
Data was formatted using the MosaicML [StreamingDataset](https://github.com/mosaicml/streaming) library to host our data in object storage and efficiently stream it to our compute cluster during training.
StreamingDataset obviates the need to download the whole dataset before starting training, and allows instant resumption of training from any point in the dataset.
### Data Mix
The model was trained for 1T tokens on the following data mix:
| Data Source | Number of Tokens in Source | Proportion | Effective Number of Tokens | Epochs |
|-------------|----------------------------|------------|----------------------------|--------|
| mC4 3.1.0 - English (200+ words) | 2417.99 B | 33.50% | 335 B | 0.14 |
| c4 - English - SemDedup 80% | 100.42 B | 29.90% | 299 B | 2.98 |
| RedPajama - CommonCrawl | 878.45 B | 8.50% | 85 B | 0.097 |
| The Stack - Selected Languages | 463.78 B | 10.00% | 100 B | 0.22 |
| RedPajama - Wikipedia | 4.87 B | 4.00% | 40 B | 8.21 |
| The Stack - Markdown | 107.07 B | 4.50% | 45 B | 0.42 |
| Semantic Scholar ORC | 48.95 B | 3.30% | 33 B | 0.67 |
| RedPajama - Books | 26.02 B | 3.00% | 30 B | 1.15 |
| RedPajama - arXiv | 28.10 B | 1.90% | 19 B | 0.68 |
| RedPajama - StackExchange | 20.54 B | 1.40% | 14 B |0.68 |
Samples for each batch were selected from one of the datasets with the probability specified above. The examples were shuffled within each dataset, and each example was constructed from as many sequences from that dataset as were necessary to fill the sequence length. To build 8k support into MPT-30B efficiently, we first pre-trained on 1T tokens using sequences that were 2k tokens long, and then trained for an additional 50B tokens using sequences that were 8k tokens long.
The data was tokenized using the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer. This BPE tokenizer has a number of desirable characteristics,
most of which are relevant for tokenizing code:
(1) It was trained on a diverse mix of data that includes code (The Pile)
(2) It applies consistent space delimitation, unlike the GPT2 tokenizer which tokenizes inconsistently depending on the presence of prefix spaces
(3) It contains tokens for repeated space characters, which allows superior compression of text with large amounts of repeated space characters.
The model vocabulary size of 50432 was set to be a multiple of 128 (as in [MEGATRON-LM](https://arxiv.org/abs/1909.08053)).
### Training Configuration
The model was trained in three stages using the [MosaicML Platform](https://www.mosaicml.com/platform):
(i) First it was trained on 440 A100-40GBs with a batch size of 1760.
(ii) Then, on 216 A100-40GBs with a batch size of 1728.
(iii) Training was completed on 256 H100-80GBs with a batch size of 512 with 8k context length and 50B tokens.
The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the [LION](https://arxiv.org/abs/2302.06675) optimizer.
## Limitations and Biases
_The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_
MPT-30B (Base) is **not** intended for deployment without finetuning.
It should not be used for human-facing interactions without further guardrails and user consent.
MPT-30B can produce factually incorrect output, and should not be relied on to produce factually accurate information.
MPT-30B was trained on various public datasets.
While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
## MosaicML Platform
If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-30b).
## Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
## Citation
Please cite this model using the following format:
```
@online{MosaicML2023Introducing,
author = {MosaicML NLP Team},
title = {Introducing MPT-30B: Raising the bar
for open-source foundation models},
year = {2023},
url = {www.mosaicml.com/blog/mpt-30b},
note = {Accessed: 2023-06-22},
urldate = {2023-06-22}
}
```
|
TheBloke/mpt-30B-instruct-GGML
|
TheBloke
| 2023-06-23T15:54:56Z | 13 | 43 |
transformers
|
[
"transformers",
"mpt",
"Composer",
"MosaicML",
"llm-foundry",
"arxiv:2205.14135",
"arxiv:2108.12409",
"license:cc-by-sa-3.0",
"region:us"
] | null | 2023-06-22T15:46:54Z |
---
license: cc-by-sa-3.0
datasets:
- competition_math
- conceptofmind/cot_submix_original/cot_gsm8k
- knkarthick/dialogsum
- mosaicml/dolly_hhrlhf
- duorc
- tau/scrolls/qasper
- emozilla/quality
- scrolls/summ_screen_fd
- spider
tags:
- Composer
- MosaicML
- llm-foundry
inference: false
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# MosaicML's MPT-30B-Instruct GGML
These files are GGML format model files for [MosaicML's MPT-30B-Instruct](https://huggingface.co/mosaicml/mpt-30b-instruct).
Please note that these GGMLs are **not compatible with llama.cpp, or currently with text-generation-webui**. Please see below for a list of tools known to work with these model files.
[KoboldCpp](https://github.com/LostRuins/koboldcpp) just added GPU accelerated (OpenCL) support for MPT models, so that is the client I recommend using for these models.
**Note**: Please use version 1.32.1 or later of KoboldCpp, as there was a bug in 1.32 that affected loading of MPT models.
## Repositories available
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/mpt-30B-instruct-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mosaicml/mpt-30b-instruct)
## Prompt template
```
Below is an instruction that describes a task. Write a response that appropriately completes the request
### Instruction: prompt
### Response:
```
## A note regarding context length: 8K
The base model has an 8K context length. It is not yet confirmed if the 8K context of this model works with the quantised files.
If it does, [KoboldCpp](https://github.com/LostRuins/koboldcpp) supports 8K context if you manually set it to 8K by adjusting the text box above the slider:
It is currently unknown as to increased context is compatible with other MPT GGML clients.
If you have feedback on this, please let me know.
<!-- compatibility_ggml start -->
## Compatibilty
These files are **not** compatible with text-generation-webui, llama.cpp, or llama-cpp-python.
Currently they can be used with:
* KoboldCpp, a powerful inference engine based on llama.cpp, with good UI and GPU accelerated support for MPT models: [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* The ctransformers Python library, which includes LangChain support: [ctransformers](https://github.com/marella/ctransformers)
* The LoLLMS Web UI which uses ctransformers: [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [rustformers' llm](https://github.com/rustformers/llm)
* The example `mpt` binary provided with [ggml](https://github.com/ggerganov/ggml)
As other options become available I will endeavour to update them here (do let me know in the Community tab if I've missed something!)
## Tutorial for using LoLLMS Web UI
* [Text tutorial, written by **Lucas3DCG**](https://huggingface.co/TheBloke/MPT-7B-Storywriter-GGML/discussions/2#6475d914e9b57ce0caa68888)
* [Video tutorial, by LoLLMS Web UI's author **ParisNeo**](https://www.youtube.com/watch?v=ds_U0TDzbzI)
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| mpt-30b-instruct.ggmlv0.q4_0.bin | q4_0 | 4 | 16.85 GB | 19.35 GB | Original llama.cpp quant method, 4-bit. |
| mpt-30b-instruct.ggmlv0.q4_1.bin | q4_1 | 4 | 18.73 GB | 21.23 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| mpt-30b-instruct.ggmlv0.q5_0.bin | q5_0 | 5 | 20.60 GB | 23.10 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| mpt-30b-instruct.ggmlv0.q5_1.bin | q5_1 | 5 | 22.47 GB | 24.97 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| mpt-30b-instruct.ggmlv0.q8_0.bin | q8_0 | 8 | 31.83 GB | 34.33 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: Mano Prime, Fen Risland, Derek Yates, Preetika Verma, webtim, Sean Connelly, Alps Aficionado, Karl Bernard, Junyu Yang, Nathan LeClaire, Chris McCloskey, Lone Striker, Asp the Wyvern, Eugene Pentland, Imad Khwaja, trip7s trip, WelcomeToTheClub, John Detwiler, Artur Olbinski, Khalefa Al-Ahmad, Trenton Dambrowitz, Talal Aujan, Kevin Schuppel, Luke Pendergrass, Pyrater, Joseph William Delisle, terasurfer , vamX, Gabriel Puliatti, David Flickinger, Jonathan Leane, Iucharbius , Luke, Deep Realms, Cory Kujawski, ya boyyy, Illia Dulskyi, senxiiz, Johann-Peter Hartmann, John Villwock, K, Ghost , Spiking Neurons AB, Nikolai Manek, Rainer Wilmers, Pierre Kircher, biorpg, Space Cruiser, Ai Maven, subjectnull, Willem Michiel, Ajan Kanaga, Kalila, chris gileta, Oscar Rangel.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: MosaicML's MPT-30B-Instruct
# MPT-30B-Instruct
MPT-30B-Instruct is a model for short-form instruction following.
It is built by finetuning [MPT-30B](https://huggingface.co/mosaicml/mpt-30b) on [Dolly HHRLHF](https://huggingface.co/datasets/mosaicml/dolly_hhrlhf) derived from the [Databricks Dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the [Anthropic Helpful and Harmless (HH-RLHF)](https://huggingface.co/datasets/Anthropic/hh-rlhf) datasets. It is also trained on [Competition Math](https://huggingface.co/datasets/competition_math), [Duorc](https://huggingface.co/datasets/duorc), [CoT GSM8k](https://huggingface.co/datasets/conceptofmind/cot_submix_original), [Qasper](https://huggingface.co/datasets/allenai/qasper), [Quality](https://huggingface.co/datasets/emozilla/quality), [Summ Screen FD](https://huggingface.co/datasets/tau/scrolls) and [Spider](https://huggingface.co/datasets/spider).
* License: _CC-By-SA-3.0_
This model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture.
## Model Date
June 22, 2023
## Model License
CC-By-SA-3.0
## Documentation
* [Blog post: Raising the bar for open-source foundation models](https://www.mosaicml.com/blog/mpt-30b)
* [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/)
* Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)!
### Example Question/Instruction
**Bespokenizer46**
> I need to convince my friend, Phyllis, that she should train a custom LLM for her Fortune 500 company using the MosaicML Platform.
> Please write an email that explains why MosaicML's emphasis on cutting edge methodology, data privacy, and efficiency are so important.
> End the email with a friendly inquiry about Phyllis's family.
**MPT-30B-Instruct**:
> Phyllis -
> I know you're always looking for ways to improve efficiency at work and I think I've found a solution that you'll be very interested in.
> LLMs are only as good as the data they're trained on and the training process can be very time consuming and resource intensive. MosaicML uses cutting edge methodology to efficiently train high quality models without compromising data privacy.
> They also provide tools to easily connect to and use the model in your daily workflow.
> I think you'd really enjoy speaking with their founder, we can set up a call if you're interested.
> Also, I know it's been a tough year for your family, how are things?
> Best,
> Your Friend
## How to Use
Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method. This is because we use a custom model architecture that is not yet part of the `transformers` package.
It includes options for many training efficiency features such as [FlashAttention (Dao et al. 2022)](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), QK LayerNorm, and more.
```python
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
'mosaicml/mpt-30b-instruct',
trust_remote_code=True
)
```
To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision:
```python
import torch
import transformers
name = 'mosaicml/mpt-30b-instruct'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.attn_config['attn_impl'] = 'triton' # change this to use triton-based FlashAttention
config.init_device = 'cuda:0' # For fast initialization directly on GPU!
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
torch_dtype=torch.bfloat16, # Load model weights in bfloat16
trust_remote_code=True
)
```
The model was trained initially on a sequence length of 2048. An additional pre-training phase was included for sequence length adaptation to 8192. However, ALiBi further enables users to increase the maximum sequence length during finetuning and/or inference. For example:
```python
import transformers
name = 'mosaicml/mpt-30b-instruct'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.max_seq_len = 16384 # (input + output) tokens can now be up to 16384
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
trust_remote_code=True
)
```
This model was trained with the MPT-30B tokenizer which is based on the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer and includes additional padding and eos tokens.
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('mosaicml/mpt-30b')
```
The model can then be used, for example, within a text-generation pipeline.
Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html).
```python
from transformers import pipeline
with torch.autocast('cuda', dtype=torch.bfloat16):
inputs = tokenizer('Here is a recipe for vegan banana bread:\n', return_tensors="pt").to('cuda')
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
# or using the HF pipeline
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0')
with torch.autocast('cuda', dtype=torch.bfloat16):
print(
pipe('Here is a recipe for vegan banana bread:\n',
max_new_tokens=100,
do_sample=True,
use_cache=True))
```
### Formatting
This model was trained on data formatted as follows:
```python
def format_prompt(instruction):
template = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n###Instruction\n{instruction}\n\n### Response\n"
return template.format(instruction=instruction)
)
example = "Tell me a funny joke.\nDon't make it too funny though."
fmt_ex = format_prompt(instruction=example)
```
In the above example, `fmt_ex` is ready to be tokenized and sent through the model.
## Model Description
The architecture is a modification of a standard decoder-only transformer.
The model has been modified from a standard transformer in the following ways:
* It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf)
* It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings
* It does not use biases
| Hyperparameter | Value |
|----------------|-------|
|n_parameters | 29.95B |
|n_layers | 48 |
| n_heads | 64 |
| d_model | 7168 |
| vocab size | 50432 |
| sequence length | 8192 |
## Data Mix
The model was trained on the following data mix:
| Data Source | Number of Tokens in Source | Proportion |
|-------------|----------------------------|------------|
| competition_math | 1.6 M | 3.01% |
| cot_gsm8k | 3.36 M | 6.32% |
| dialogsum | 0.1 M | 0.19% |
| dolly_hhrlhf | 5.89 M | 11.07% |
| duorc | 8.2 M | 15.51% |
| qasper | 10.97 M | 20.63% |
| quality | 11.31 M | 21.28% |
| scrolls/summ_screen_fd | 11.56 M | 21.82% |
| spider | 0.089 M | 0.16% |
## PreTraining Data
For more details on the pretraining process, see [MPT-30B](https://huggingface.co/mosaicml/mpt-30b).
The data was tokenized using the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer.
### Training Configuration
This model was trained on 72 A100 40GB GPUs for 8 hours using the [MosaicML Platform](https://www.mosaicml.com/platform).
The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the AdamW optimizer.
## Limitations and Biases
_The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_
MPT-30B-Instruct can produce factually incorrect output, and should not be relied on to produce factually accurate information.
MPT-30B-Instruct was trained on various public datasets.
While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
## Acknowledgements
This model was finetuned by Sam Havens, Alex Trott, and the MosaicML NLP team
## MosaicML Platform
If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-30b).
## Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
## Citation
Please cite this model using the following format:
```
@online{MosaicML2023Introducing,
author = {MosaicML NLP Team},
title = {Introducing MPT-30B: Raising the bar
for open-source foundation models},
year = {2023},
url = {www.mosaicml.com/blog/mpt-30b},
note = {Accessed: 2023-06-22},
urldate = {2023-06-22}
}
```
|
advaithS7857/my_new_qa_model
|
advaithS7857
| 2023-06-23T15:54:50Z | 114 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-23T15:27:23Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: my_new_qa_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_new_qa_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5928
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 250 | 2.1904 |
| 2.6017 | 2.0 | 500 | 1.6544 |
| 2.6017 | 3.0 | 750 | 1.5956 |
| 1.122 | 4.0 | 1000 | 1.5928 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
gokuls/model_v1_complete_training_wt_init_48_tiny
|
gokuls
| 2023-06-23T15:51:59Z | 45 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"hybridbert",
"fill-mask",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-06-20T10:08:52Z |
---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: model_v1_complete_training_wt_init_48_tiny
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# model_v1_complete_training_wt_init_48_tiny
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.6497
- Accuracy: 0.3896
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-------:|:---------------:|:--------:|
| 6.0224 | 0.33 | 30000 | 5.9447 | 0.1517 |
| 5.1853 | 0.66 | 60000 | 4.9635 | 0.2615 |
| 4.9483 | 0.98 | 90000 | 4.7016 | 0.2830 |
| 4.7679 | 1.31 | 120000 | 4.5154 | 0.2992 |
| 4.6448 | 1.64 | 150000 | 4.3884 | 0.3100 |
| 4.5688 | 1.97 | 180000 | 4.3095 | 0.3175 |
| 4.5102 | 2.29 | 210000 | 4.2511 | 0.3236 |
| 4.4662 | 2.62 | 240000 | 4.2038 | 0.3294 |
| 4.4269 | 2.95 | 270000 | 4.1677 | 0.3336 |
| 4.3982 | 3.28 | 300000 | 4.1367 | 0.3370 |
| 4.3714 | 3.6 | 330000 | 4.1103 | 0.3399 |
| 4.3493 | 3.93 | 360000 | 4.0869 | 0.3423 |
| 4.3303 | 4.26 | 390000 | 4.0680 | 0.3439 |
| 4.3131 | 4.59 | 420000 | 4.0467 | 0.3461 |
| 4.2875 | 4.92 | 450000 | 4.0292 | 0.3477 |
| 4.2629 | 5.24 | 480000 | 4.0109 | 0.3497 |
| 4.2413 | 5.57 | 510000 | 3.9931 | 0.3515 |
| 4.2282 | 5.9 | 540000 | 3.9759 | 0.3536 |
| 4.2003 | 6.23 | 570000 | 3.9608 | 0.3551 |
| 4.1867 | 6.55 | 600000 | 3.9445 | 0.3571 |
| 4.1607 | 6.88 | 630000 | 3.9273 | 0.3590 |
| 4.1511 | 7.21 | 660000 | 3.9130 | 0.3606 |
| 4.1335 | 7.54 | 690000 | 3.8971 | 0.3622 |
| 4.1158 | 7.87 | 720000 | 3.8798 | 0.3642 |
| 4.097 | 8.19 | 750000 | 3.8635 | 0.3663 |
| 4.0831 | 8.52 | 780000 | 3.8494 | 0.3679 |
| 4.0756 | 8.85 | 810000 | 3.8334 | 0.3696 |
| 4.0533 | 9.18 | 840000 | 3.8201 | 0.3712 |
| 4.0517 | 9.5 | 870000 | 3.8080 | 0.3724 |
| 4.0325 | 9.83 | 900000 | 3.7975 | 0.3734 |
| 4.0142 | 10.16 | 930000 | 3.7872 | 0.3748 |
| 4.0124 | 10.49 | 960000 | 3.7788 | 0.3759 |
| 4.0076 | 10.81 | 990000 | 3.7679 | 0.3767 |
| 3.9919 | 11.14 | 1020000 | 3.7609 | 0.3775 |
| 3.9888 | 11.47 | 1050000 | 3.7550 | 0.3783 |
| 3.9796 | 11.8 | 1080000 | 3.7481 | 0.3789 |
| 3.9742 | 12.13 | 1110000 | 3.7414 | 0.3796 |
| 3.9667 | 12.45 | 1140000 | 3.7370 | 0.3802 |
| 3.9652 | 12.78 | 1170000 | 3.7289 | 0.3810 |
| 3.9548 | 13.11 | 1200000 | 3.7278 | 0.3812 |
| 3.9556 | 13.44 | 1230000 | 3.7213 | 0.3817 |
| 3.9444 | 13.76 | 1260000 | 3.7152 | 0.3825 |
| 3.9428 | 14.09 | 1290000 | 3.7120 | 0.3827 |
| 3.9424 | 14.42 | 1320000 | 3.7072 | 0.3834 |
| 3.9389 | 14.75 | 1350000 | 3.7047 | 0.3836 |
| 3.936 | 15.07 | 1380000 | 3.6998 | 0.3844 |
| 3.9246 | 15.4 | 1410000 | 3.6968 | 0.3847 |
| 3.9281 | 15.73 | 1440000 | 3.6925 | 0.3851 |
| 3.9177 | 16.06 | 1470000 | 3.6916 | 0.3849 |
| 3.9216 | 16.39 | 1500000 | 3.6870 | 0.3855 |
| 3.9141 | 16.71 | 1530000 | 3.6822 | 0.3863 |
| 3.9154 | 17.04 | 1560000 | 3.6804 | 0.3864 |
| 3.9145 | 17.37 | 1590000 | 3.6795 | 0.3863 |
| 3.9103 | 17.7 | 1620000 | 3.6734 | 0.3869 |
| 3.9079 | 18.02 | 1650000 | 3.6724 | 0.3873 |
| 3.901 | 18.35 | 1680000 | 3.6707 | 0.3872 |
| 3.9015 | 18.68 | 1710000 | 3.6695 | 0.3873 |
| 3.8987 | 19.01 | 1740000 | 3.6672 | 0.3877 |
| 3.8929 | 19.33 | 1770000 | 3.6647 | 0.3878 |
| 3.892 | 19.66 | 1800000 | 3.6609 | 0.3884 |
| 3.8906 | 19.99 | 1830000 | 3.6595 | 0.3886 |
| 3.8923 | 20.32 | 1860000 | 3.6594 | 0.3885 |
| 3.8901 | 20.65 | 1890000 | 3.6541 | 0.3893 |
| 3.8853 | 20.97 | 1920000 | 3.6539 | 0.3891 |
| 3.8808 | 21.3 | 1950000 | 3.6527 | 0.3894 |
| 3.8835 | 21.63 | 1980000 | 3.6497 | 0.3896 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
|
romankovsv/test3
|
romankovsv
| 2023-06-23T15:48:54Z | 4 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-23T15:47:51Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
Curiolearner/ppo-SnowballTarget
|
Curiolearner
| 2023-06-23T15:45:02Z | 1 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2023-06-23T15:44:55Z |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: Curiolearner/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
TheHappyDrone/DialoGPT-medium-salesman
|
TheHappyDrone
| 2023-06-23T15:41:07Z | 110 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"gpt2",
"text-generation",
"conversational",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-12-31T07:24:54Z |
---
language:
- en
tags:
- conversational
---
Less powerful version of what is now /DialoGPT-medium-Nexus-Nova. Go there instead
|
karinthommen/spontaneous-whisper-v6
|
karinthommen
| 2023-06-23T15:31:17Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-06-23T05:29:06Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: spontaneous-whisper-v6
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# spontaneous-whisper-v6
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 4000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
consciousAI/cai-stellaris-text-embeddings
|
consciousAI
| 2023-06-23T15:27:38Z | 175 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"feature-extraction",
"sentence-similarity",
"mteb",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-06-23T15:01:50Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- mteb
model-index:
- name: cai-stellaris-text-embeddings
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 64.86567164179104
- type: ap
value: 28.30760041689409
- type: f1
value: 59.08589995918376
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 65.168625
- type: ap
value: 60.131922961382166
- type: f1
value: 65.02463910192814
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 31.016
- type: f1
value: 30.501226228002924
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.609
- type: map_at_10
value: 38.793
- type: map_at_100
value: 40.074
- type: map_at_1000
value: 40.083
- type: map_at_3
value: 33.736
- type: map_at_5
value: 36.642
- type: mrr_at_1
value: 25.533
- type: mrr_at_10
value: 39.129999999999995
- type: mrr_at_100
value: 40.411
- type: mrr_at_1000
value: 40.42
- type: mrr_at_3
value: 34.033
- type: mrr_at_5
value: 36.956
- type: ndcg_at_1
value: 24.609
- type: ndcg_at_10
value: 47.288000000000004
- type: ndcg_at_100
value: 52.654999999999994
- type: ndcg_at_1000
value: 52.88699999999999
- type: ndcg_at_3
value: 36.86
- type: ndcg_at_5
value: 42.085
- type: precision_at_1
value: 24.609
- type: precision_at_10
value: 7.468
- type: precision_at_100
value: 0.979
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 15.315000000000001
- type: precision_at_5
value: 11.721
- type: recall_at_1
value: 24.609
- type: recall_at_10
value: 74.68
- type: recall_at_100
value: 97.866
- type: recall_at_1000
value: 99.644
- type: recall_at_3
value: 45.946
- type: recall_at_5
value: 58.606
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 42.014046191286525
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 31.406159641263052
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 60.35266033223575
- type: mrr
value: 72.66796376907179
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 74.12337662337661
- type: f1
value: 73.12122145084057
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 34.72513663347855
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 29.280150859689826
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 21.787
- type: map_at_10
value: 30.409000000000002
- type: map_at_100
value: 31.947
- type: map_at_1000
value: 32.09
- type: map_at_3
value: 27.214
- type: map_at_5
value: 28.810999999999996
- type: mrr_at_1
value: 27.039
- type: mrr_at_10
value: 35.581
- type: mrr_at_100
value: 36.584
- type: mrr_at_1000
value: 36.645
- type: mrr_at_3
value: 32.713
- type: mrr_at_5
value: 34.272999999999996
- type: ndcg_at_1
value: 27.039
- type: ndcg_at_10
value: 36.157000000000004
- type: ndcg_at_100
value: 42.598
- type: ndcg_at_1000
value: 45.207
- type: ndcg_at_3
value: 30.907
- type: ndcg_at_5
value: 33.068
- type: precision_at_1
value: 27.039
- type: precision_at_10
value: 7.295999999999999
- type: precision_at_100
value: 1.303
- type: precision_at_1000
value: 0.186
- type: precision_at_3
value: 14.926
- type: precision_at_5
value: 11.044
- type: recall_at_1
value: 21.787
- type: recall_at_10
value: 47.693999999999996
- type: recall_at_100
value: 75.848
- type: recall_at_1000
value: 92.713
- type: recall_at_3
value: 32.92
- type: recall_at_5
value: 38.794000000000004
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.560000000000002
- type: map_at_10
value: 34.756
- type: map_at_100
value: 36.169000000000004
- type: map_at_1000
value: 36.298
- type: map_at_3
value: 31.592
- type: map_at_5
value: 33.426
- type: mrr_at_1
value: 31.274
- type: mrr_at_10
value: 40.328
- type: mrr_at_100
value: 41.125
- type: mrr_at_1000
value: 41.171
- type: mrr_at_3
value: 37.866
- type: mrr_at_5
value: 39.299
- type: ndcg_at_1
value: 31.338
- type: ndcg_at_10
value: 40.696
- type: ndcg_at_100
value: 45.922000000000004
- type: ndcg_at_1000
value: 47.982
- type: ndcg_at_3
value: 36.116
- type: ndcg_at_5
value: 38.324000000000005
- type: precision_at_1
value: 31.338
- type: precision_at_10
value: 8.083
- type: precision_at_100
value: 1.4040000000000001
- type: precision_at_1000
value: 0.189
- type: precision_at_3
value: 18.089
- type: precision_at_5
value: 13.159
- type: recall_at_1
value: 24.560000000000002
- type: recall_at_10
value: 51.832
- type: recall_at_100
value: 74.26899999999999
- type: recall_at_1000
value: 87.331
- type: recall_at_3
value: 38.086999999999996
- type: recall_at_5
value: 44.294
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGamingRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 27.256999999999998
- type: map_at_10
value: 38.805
- type: map_at_100
value: 40.04
- type: map_at_1000
value: 40.117000000000004
- type: map_at_3
value: 35.425000000000004
- type: map_at_5
value: 37.317
- type: mrr_at_1
value: 31.912000000000003
- type: mrr_at_10
value: 42.045
- type: mrr_at_100
value: 42.956
- type: mrr_at_1000
value: 43.004
- type: mrr_at_3
value: 39.195
- type: mrr_at_5
value: 40.866
- type: ndcg_at_1
value: 31.912000000000003
- type: ndcg_at_10
value: 44.826
- type: ndcg_at_100
value: 49.85
- type: ndcg_at_1000
value: 51.562
- type: ndcg_at_3
value: 38.845
- type: ndcg_at_5
value: 41.719
- type: precision_at_1
value: 31.912000000000003
- type: precision_at_10
value: 7.768
- type: precision_at_100
value: 1.115
- type: precision_at_1000
value: 0.131
- type: precision_at_3
value: 18.015
- type: precision_at_5
value: 12.814999999999998
- type: recall_at_1
value: 27.256999999999998
- type: recall_at_10
value: 59.611999999999995
- type: recall_at_100
value: 81.324
- type: recall_at_1000
value: 93.801
- type: recall_at_3
value: 43.589
- type: recall_at_5
value: 50.589
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGisRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 15.588
- type: map_at_10
value: 22.936999999999998
- type: map_at_100
value: 24.015
- type: map_at_1000
value: 24.127000000000002
- type: map_at_3
value: 20.47
- type: map_at_5
value: 21.799
- type: mrr_at_1
value: 16.723
- type: mrr_at_10
value: 24.448
- type: mrr_at_100
value: 25.482
- type: mrr_at_1000
value: 25.568999999999996
- type: mrr_at_3
value: 21.94
- type: mrr_at_5
value: 23.386000000000003
- type: ndcg_at_1
value: 16.723
- type: ndcg_at_10
value: 27.451999999999998
- type: ndcg_at_100
value: 33.182
- type: ndcg_at_1000
value: 36.193999999999996
- type: ndcg_at_3
value: 22.545
- type: ndcg_at_5
value: 24.837
- type: precision_at_1
value: 16.723
- type: precision_at_10
value: 4.5760000000000005
- type: precision_at_100
value: 0.7929999999999999
- type: precision_at_1000
value: 0.11
- type: precision_at_3
value: 9.944
- type: precision_at_5
value: 7.321999999999999
- type: recall_at_1
value: 15.588
- type: recall_at_10
value: 40.039
- type: recall_at_100
value: 67.17699999999999
- type: recall_at_1000
value: 90.181
- type: recall_at_3
value: 26.663999999999998
- type: recall_at_5
value: 32.144
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackMathematicaRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 12.142999999999999
- type: map_at_10
value: 18.355
- type: map_at_100
value: 19.611
- type: map_at_1000
value: 19.750999999999998
- type: map_at_3
value: 16.073999999999998
- type: map_at_5
value: 17.187
- type: mrr_at_1
value: 15.547
- type: mrr_at_10
value: 22.615
- type: mrr_at_100
value: 23.671
- type: mrr_at_1000
value: 23.759
- type: mrr_at_3
value: 20.149
- type: mrr_at_5
value: 21.437
- type: ndcg_at_1
value: 15.547
- type: ndcg_at_10
value: 22.985
- type: ndcg_at_100
value: 29.192
- type: ndcg_at_1000
value: 32.448
- type: ndcg_at_3
value: 18.503
- type: ndcg_at_5
value: 20.322000000000003
- type: precision_at_1
value: 15.547
- type: precision_at_10
value: 4.49
- type: precision_at_100
value: 0.8840000000000001
- type: precision_at_1000
value: 0.129
- type: precision_at_3
value: 8.872
- type: precision_at_5
value: 6.741
- type: recall_at_1
value: 12.142999999999999
- type: recall_at_10
value: 33.271
- type: recall_at_100
value: 60.95399999999999
- type: recall_at_1000
value: 83.963
- type: recall_at_3
value: 20.645
- type: recall_at_5
value: 25.34
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackPhysicsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 22.09
- type: map_at_10
value: 30.220000000000002
- type: map_at_100
value: 31.741999999999997
- type: map_at_1000
value: 31.878
- type: map_at_3
value: 27.455000000000002
- type: map_at_5
value: 28.808
- type: mrr_at_1
value: 27.718999999999998
- type: mrr_at_10
value: 35.476
- type: mrr_at_100
value: 36.53
- type: mrr_at_1000
value: 36.602000000000004
- type: mrr_at_3
value: 33.157
- type: mrr_at_5
value: 34.36
- type: ndcg_at_1
value: 27.718999999999998
- type: ndcg_at_10
value: 35.547000000000004
- type: ndcg_at_100
value: 42.079
- type: ndcg_at_1000
value: 44.861000000000004
- type: ndcg_at_3
value: 30.932
- type: ndcg_at_5
value: 32.748
- type: precision_at_1
value: 27.718999999999998
- type: precision_at_10
value: 6.795
- type: precision_at_100
value: 1.194
- type: precision_at_1000
value: 0.163
- type: precision_at_3
value: 14.758
- type: precision_at_5
value: 10.549
- type: recall_at_1
value: 22.09
- type: recall_at_10
value: 46.357
- type: recall_at_100
value: 74.002
- type: recall_at_1000
value: 92.99199999999999
- type: recall_at_3
value: 33.138
- type: recall_at_5
value: 38.034
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackProgrammersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 16.904
- type: map_at_10
value: 25.075999999999997
- type: map_at_100
value: 26.400000000000002
- type: map_at_1000
value: 26.525
- type: map_at_3
value: 22.191
- type: map_at_5
value: 23.947
- type: mrr_at_1
value: 21.461
- type: mrr_at_10
value: 29.614
- type: mrr_at_100
value: 30.602
- type: mrr_at_1000
value: 30.677
- type: mrr_at_3
value: 27.017000000000003
- type: mrr_at_5
value: 28.626
- type: ndcg_at_1
value: 21.461
- type: ndcg_at_10
value: 30.304
- type: ndcg_at_100
value: 36.521
- type: ndcg_at_1000
value: 39.366
- type: ndcg_at_3
value: 25.267
- type: ndcg_at_5
value: 27.918
- type: precision_at_1
value: 21.461
- type: precision_at_10
value: 5.868
- type: precision_at_100
value: 1.072
- type: precision_at_1000
value: 0.151
- type: precision_at_3
value: 12.291
- type: precision_at_5
value: 9.429
- type: recall_at_1
value: 16.904
- type: recall_at_10
value: 41.521
- type: recall_at_100
value: 68.919
- type: recall_at_1000
value: 88.852
- type: recall_at_3
value: 27.733999999999998
- type: recall_at_5
value: 34.439
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 18.327916666666667
- type: map_at_10
value: 26.068
- type: map_at_100
value: 27.358833333333333
- type: map_at_1000
value: 27.491583333333335
- type: map_at_3
value: 23.45508333333333
- type: map_at_5
value: 24.857916666666664
- type: mrr_at_1
value: 22.05066666666667
- type: mrr_at_10
value: 29.805083333333332
- type: mrr_at_100
value: 30.80283333333333
- type: mrr_at_1000
value: 30.876166666666666
- type: mrr_at_3
value: 27.381083333333333
- type: mrr_at_5
value: 28.72441666666667
- type: ndcg_at_1
value: 22.056000000000004
- type: ndcg_at_10
value: 31.029416666666666
- type: ndcg_at_100
value: 36.90174999999999
- type: ndcg_at_1000
value: 39.716249999999995
- type: ndcg_at_3
value: 26.35533333333333
- type: ndcg_at_5
value: 28.471500000000006
- type: precision_at_1
value: 22.056000000000004
- type: precision_at_10
value: 5.7645833333333325
- type: precision_at_100
value: 1.0406666666666666
- type: precision_at_1000
value: 0.14850000000000002
- type: precision_at_3
value: 12.391416666666666
- type: precision_at_5
value: 9.112499999999999
- type: recall_at_1
value: 18.327916666666667
- type: recall_at_10
value: 42.15083333333333
- type: recall_at_100
value: 68.38666666666666
- type: recall_at_1000
value: 88.24183333333333
- type: recall_at_3
value: 29.094416666666667
- type: recall_at_5
value: 34.48716666666666
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackStatsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 15.009
- type: map_at_10
value: 21.251
- type: map_at_100
value: 22.337
- type: map_at_1000
value: 22.455
- type: map_at_3
value: 19.241
- type: map_at_5
value: 20.381
- type: mrr_at_1
value: 17.638
- type: mrr_at_10
value: 24.184
- type: mrr_at_100
value: 25.156
- type: mrr_at_1000
value: 25.239
- type: mrr_at_3
value: 22.29
- type: mrr_at_5
value: 23.363999999999997
- type: ndcg_at_1
value: 17.638
- type: ndcg_at_10
value: 25.269000000000002
- type: ndcg_at_100
value: 30.781999999999996
- type: ndcg_at_1000
value: 33.757
- type: ndcg_at_3
value: 21.457
- type: ndcg_at_5
value: 23.293
- type: precision_at_1
value: 17.638
- type: precision_at_10
value: 4.294
- type: precision_at_100
value: 0.771
- type: precision_at_1000
value: 0.11100000000000002
- type: precision_at_3
value: 9.815999999999999
- type: precision_at_5
value: 7.086
- type: recall_at_1
value: 15.009
- type: recall_at_10
value: 35.014
- type: recall_at_100
value: 60.45399999999999
- type: recall_at_1000
value: 82.416
- type: recall_at_3
value: 24.131
- type: recall_at_5
value: 28.846
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackTexRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 12.518
- type: map_at_10
value: 18.226
- type: map_at_100
value: 19.355
- type: map_at_1000
value: 19.496
- type: map_at_3
value: 16.243
- type: map_at_5
value: 17.288999999999998
- type: mrr_at_1
value: 15.382000000000001
- type: mrr_at_10
value: 21.559
- type: mrr_at_100
value: 22.587
- type: mrr_at_1000
value: 22.677
- type: mrr_at_3
value: 19.597
- type: mrr_at_5
value: 20.585
- type: ndcg_at_1
value: 15.382000000000001
- type: ndcg_at_10
value: 22.198
- type: ndcg_at_100
value: 27.860000000000003
- type: ndcg_at_1000
value: 31.302999999999997
- type: ndcg_at_3
value: 18.541
- type: ndcg_at_5
value: 20.089000000000002
- type: precision_at_1
value: 15.382000000000001
- type: precision_at_10
value: 4.178
- type: precision_at_100
value: 0.8380000000000001
- type: precision_at_1000
value: 0.132
- type: precision_at_3
value: 8.866999999999999
- type: precision_at_5
value: 6.476
- type: recall_at_1
value: 12.518
- type: recall_at_10
value: 31.036
- type: recall_at_100
value: 56.727000000000004
- type: recall_at_1000
value: 81.66799999999999
- type: recall_at_3
value: 20.610999999999997
- type: recall_at_5
value: 24.744
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackUnixRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 18.357
- type: map_at_10
value: 25.384
- type: map_at_100
value: 26.640000000000004
- type: map_at_1000
value: 26.762999999999998
- type: map_at_3
value: 22.863
- type: map_at_5
value: 24.197
- type: mrr_at_1
value: 21.735
- type: mrr_at_10
value: 29.069
- type: mrr_at_100
value: 30.119
- type: mrr_at_1000
value: 30.194
- type: mrr_at_3
value: 26.663999999999998
- type: mrr_at_5
value: 27.904
- type: ndcg_at_1
value: 21.735
- type: ndcg_at_10
value: 30.153999999999996
- type: ndcg_at_100
value: 36.262
- type: ndcg_at_1000
value: 39.206
- type: ndcg_at_3
value: 25.365
- type: ndcg_at_5
value: 27.403
- type: precision_at_1
value: 21.735
- type: precision_at_10
value: 5.354
- type: precision_at_100
value: 0.958
- type: precision_at_1000
value: 0.134
- type: precision_at_3
value: 11.567
- type: precision_at_5
value: 8.469999999999999
- type: recall_at_1
value: 18.357
- type: recall_at_10
value: 41.205000000000005
- type: recall_at_100
value: 68.30000000000001
- type: recall_at_1000
value: 89.294
- type: recall_at_3
value: 27.969
- type: recall_at_5
value: 32.989000000000004
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWebmastersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 18.226
- type: map_at_10
value: 25.766
- type: map_at_100
value: 27.345000000000002
- type: map_at_1000
value: 27.575
- type: map_at_3
value: 22.945999999999998
- type: map_at_5
value: 24.383
- type: mrr_at_1
value: 21.542
- type: mrr_at_10
value: 29.448
- type: mrr_at_100
value: 30.509999999999998
- type: mrr_at_1000
value: 30.575000000000003
- type: mrr_at_3
value: 26.482
- type: mrr_at_5
value: 28.072999999999997
- type: ndcg_at_1
value: 21.542
- type: ndcg_at_10
value: 31.392999999999997
- type: ndcg_at_100
value: 37.589
- type: ndcg_at_1000
value: 40.717
- type: ndcg_at_3
value: 26.179000000000002
- type: ndcg_at_5
value: 28.557
- type: precision_at_1
value: 21.542
- type: precision_at_10
value: 6.462
- type: precision_at_100
value: 1.415
- type: precision_at_1000
value: 0.234
- type: precision_at_3
value: 12.187000000000001
- type: precision_at_5
value: 9.605
- type: recall_at_1
value: 18.226
- type: recall_at_10
value: 42.853
- type: recall_at_100
value: 70.97200000000001
- type: recall_at_1000
value: 91.662
- type: recall_at_3
value: 28.555999999999997
- type: recall_at_5
value: 34.203
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWordpressRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 15.495999999999999
- type: map_at_10
value: 21.631
- type: map_at_100
value: 22.705000000000002
- type: map_at_1000
value: 22.823999999999998
- type: map_at_3
value: 19.747
- type: map_at_5
value: 20.75
- type: mrr_at_1
value: 16.636
- type: mrr_at_10
value: 23.294
- type: mrr_at_100
value: 24.312
- type: mrr_at_1000
value: 24.401999999999997
- type: mrr_at_3
value: 21.503
- type: mrr_at_5
value: 22.52
- type: ndcg_at_1
value: 16.636
- type: ndcg_at_10
value: 25.372
- type: ndcg_at_100
value: 30.984
- type: ndcg_at_1000
value: 33.992
- type: ndcg_at_3
value: 21.607000000000003
- type: ndcg_at_5
value: 23.380000000000003
- type: precision_at_1
value: 16.636
- type: precision_at_10
value: 4.011
- type: precision_at_100
value: 0.741
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 9.365
- type: precision_at_5
value: 6.654
- type: recall_at_1
value: 15.495999999999999
- type: recall_at_10
value: 35.376000000000005
- type: recall_at_100
value: 61.694
- type: recall_at_1000
value: 84.029
- type: recall_at_3
value: 25.089
- type: recall_at_5
value: 29.43
- task:
type: Retrieval
dataset:
type: climate-fever
name: MTEB ClimateFEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.662
- type: map_at_10
value: 8.638
- type: map_at_100
value: 9.86
- type: map_at_1000
value: 10.032
- type: map_at_3
value: 6.793
- type: map_at_5
value: 7.761
- type: mrr_at_1
value: 10.684000000000001
- type: mrr_at_10
value: 17.982
- type: mrr_at_100
value: 19.152
- type: mrr_at_1000
value: 19.231
- type: mrr_at_3
value: 15.113999999999999
- type: mrr_at_5
value: 16.658
- type: ndcg_at_1
value: 10.684000000000001
- type: ndcg_at_10
value: 13.483
- type: ndcg_at_100
value: 19.48
- type: ndcg_at_1000
value: 23.232
- type: ndcg_at_3
value: 9.75
- type: ndcg_at_5
value: 11.208
- type: precision_at_1
value: 10.684000000000001
- type: precision_at_10
value: 4.573
- type: precision_at_100
value: 1.085
- type: precision_at_1000
value: 0.17600000000000002
- type: precision_at_3
value: 7.514
- type: precision_at_5
value: 6.241
- type: recall_at_1
value: 4.662
- type: recall_at_10
value: 18.125
- type: recall_at_100
value: 39.675
- type: recall_at_1000
value: 61.332
- type: recall_at_3
value: 9.239
- type: recall_at_5
value: 12.863
- task:
type: Retrieval
dataset:
type: dbpedia-entity
name: MTEB DBPedia
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 3.869
- type: map_at_10
value: 8.701
- type: map_at_100
value: 11.806999999999999
- type: map_at_1000
value: 12.676000000000002
- type: map_at_3
value: 6.3100000000000005
- type: map_at_5
value: 7.471
- type: mrr_at_1
value: 38.5
- type: mrr_at_10
value: 48.754
- type: mrr_at_100
value: 49.544
- type: mrr_at_1000
value: 49.568
- type: mrr_at_3
value: 46.167
- type: mrr_at_5
value: 47.679
- type: ndcg_at_1
value: 30.5
- type: ndcg_at_10
value: 22.454
- type: ndcg_at_100
value: 25.380999999999997
- type: ndcg_at_1000
value: 31.582
- type: ndcg_at_3
value: 25.617
- type: ndcg_at_5
value: 24.254
- type: precision_at_1
value: 38.5
- type: precision_at_10
value: 18.4
- type: precision_at_100
value: 6.02
- type: precision_at_1000
value: 1.34
- type: precision_at_3
value: 29.083
- type: precision_at_5
value: 24.85
- type: recall_at_1
value: 3.869
- type: recall_at_10
value: 12.902
- type: recall_at_100
value: 30.496000000000002
- type: recall_at_1000
value: 51.066
- type: recall_at_3
value: 7.396
- type: recall_at_5
value: 9.852
- task:
type: Classification
dataset:
type: mteb/emotion
name: MTEB EmotionClassification
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 36.705000000000005
- type: f1
value: 32.72625967901387
- task:
type: Classification
dataset:
type: mteb/imdb
name: MTEB ImdbClassification
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 66.89840000000001
- type: ap
value: 61.43175045563333
- type: f1
value: 66.67945656405962
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (en)
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 89.12676698586411
- type: f1
value: 88.48426641357668
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (en)
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 62.61513907888736
- type: f1
value: 40.96251281624023
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (en)
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 61.95359784801614
- type: f1
value: 58.85654625260125
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (en)
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.1983860121049
- type: f1
value: 68.73455379435487
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-p2p
name: MTEB MedrxivClusteringP2P
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 31.772017072895846
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-s2s
name: MTEB MedrxivClusteringS2S
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 30.944581802089044
- task:
type: Reranking
dataset:
type: mteb/mind_small
name: MTEB MindSmallReranking
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 30.977328237697133
- type: mrr
value: 32.02612207306447
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering
name: MTEB RedditClustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 43.08588418858767
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering-p2p
name: MTEB RedditClusteringP2P
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 56.53785276450797
- task:
type: Reranking
dataset:
type: mteb/scidocs-reranking
name: MTEB SciDocsRR
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 81.44882719207659
- type: mrr
value: 94.71082022552609
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.77821782178218
- type: cos_sim_ap
value: 93.22909989796688
- type: cos_sim_f1
value: 88.41778697001035
- type: cos_sim_precision
value: 91.54175588865097
- type: cos_sim_recall
value: 85.5
- type: dot_accuracy
value: 99.77821782178218
- type: dot_ap
value: 93.2290998979669
- type: dot_f1
value: 88.41778697001035
- type: dot_precision
value: 91.54175588865097
- type: dot_recall
value: 85.5
- type: euclidean_accuracy
value: 99.77821782178218
- type: euclidean_ap
value: 93.2290998979669
- type: euclidean_f1
value: 88.41778697001035
- type: euclidean_precision
value: 91.54175588865097
- type: euclidean_recall
value: 85.5
- type: manhattan_accuracy
value: 99.77524752475247
- type: manhattan_ap
value: 93.18492132451668
- type: manhattan_f1
value: 88.19552782111285
- type: manhattan_precision
value: 91.87432286023835
- type: manhattan_recall
value: 84.8
- type: max_accuracy
value: 99.77821782178218
- type: max_ap
value: 93.2290998979669
- type: max_f1
value: 88.41778697001035
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering
name: MTEB StackExchangeClustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 48.225188905490285
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering-p2p
name: MTEB StackExchangeClusteringP2P
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 34.76195959924048
- task:
type: Reranking
dataset:
type: mteb/stackoverflowdupquestions-reranking
name: MTEB StackOverflowDupQuestions
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 48.16986372261003
- type: mrr
value: 48.7718837535014
- task:
type: Classification
dataset:
type: mteb/toxic_conversations_50k
name: MTEB ToxicConversationsClassification
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 63.567200000000014
- type: ap
value: 11.412292644030266
- type: f1
value: 49.102043399207716
- task:
type: Classification
dataset:
type: mteb/tweet_sentiment_extraction
name: MTEB TweetSentimentExtractionClassification
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 51.04414261460101
- type: f1
value: 51.22880449155832
- task:
type: Clustering
dataset:
type: mteb/twentynewsgroups-clustering
name: MTEB TwentyNewsgroupsClustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 34.35595440606073
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 84.6754485307266
- type: cos_sim_ap
value: 69.6007143804539
- type: cos_sim_f1
value: 65.99822312476202
- type: cos_sim_precision
value: 63.58522866226461
- type: cos_sim_recall
value: 68.60158311345647
- type: dot_accuracy
value: 84.6754485307266
- type: dot_ap
value: 69.60070881520775
- type: dot_f1
value: 65.99822312476202
- type: dot_precision
value: 63.58522866226461
- type: dot_recall
value: 68.60158311345647
- type: euclidean_accuracy
value: 84.6754485307266
- type: euclidean_ap
value: 69.60071394457518
- type: euclidean_f1
value: 65.99822312476202
- type: euclidean_precision
value: 63.58522866226461
- type: euclidean_recall
value: 68.60158311345647
- type: manhattan_accuracy
value: 84.6754485307266
- type: manhattan_ap
value: 69.57324451019119
- type: manhattan_f1
value: 65.7235045917101
- type: manhattan_precision
value: 62.04311152764761
- type: manhattan_recall
value: 69.86807387862797
- type: max_accuracy
value: 84.6754485307266
- type: max_ap
value: 69.6007143804539
- type: max_f1
value: 65.99822312476202
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 87.63922847052432
- type: cos_sim_ap
value: 83.48934190421085
- type: cos_sim_f1
value: 75.42265503384861
- type: cos_sim_precision
value: 71.17868124359413
- type: cos_sim_recall
value: 80.20480443486295
- type: dot_accuracy
value: 87.63922847052432
- type: dot_ap
value: 83.4893468701264
- type: dot_f1
value: 75.42265503384861
- type: dot_precision
value: 71.17868124359413
- type: dot_recall
value: 80.20480443486295
- type: euclidean_accuracy
value: 87.63922847052432
- type: euclidean_ap
value: 83.48934073168017
- type: euclidean_f1
value: 75.42265503384861
- type: euclidean_precision
value: 71.17868124359413
- type: euclidean_recall
value: 80.20480443486295
- type: manhattan_accuracy
value: 87.66251406838204
- type: manhattan_ap
value: 83.46319621504654
- type: manhattan_f1
value: 75.41883304448297
- type: manhattan_precision
value: 71.0089747076421
- type: manhattan_recall
value: 80.41268863566368
- type: max_accuracy
value: 87.66251406838204
- type: max_ap
value: 83.4893468701264
- type: max_f1
value: 75.42265503384861
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 15607 with parameters:
```
{'batch_size': 48, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 10,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 1000,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
zappi234orga/testrepo
|
zappi234orga
| 2023-06-23T15:26:37Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T15:26:16Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 251.43 +/- 19.26
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
leon1165/my_awesome_model
|
leon1165
| 2023-06-23T15:23:25Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-23T08:25:50Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7085
- Accuracy: 0.7119
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.8466 | 1.0 | 597 | 0.7455 | 0.7035 |
| 0.7525 | 2.0 | 1194 | 0.7085 | 0.7119 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
mxtsai/deep-rl-hw1
|
mxtsai
| 2023-06-23T15:14:36Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T15:14:19Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 278.28 +/- 27.94
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
jakelcoop/ppo-LunarLander-v2
|
jakelcoop
| 2023-06-23T15:14:35Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T15:14:10Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: ppo
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 266.96 +/- 16.15
name: mean_reward
verified: false
---
# **ppo** Agent playing **LunarLander-v2**
This is a trained model of a **ppo** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
Joaking1/Model_tete
|
Joaking1
| 2023-06-23T15:11:04Z | 0 | 0 | null |
[
"license:cc-by-nc-sa-4.0",
"region:us"
] | null | 2023-06-23T15:11:04Z |
---
license: cc-by-nc-sa-4.0
---
|
Tyrranen/q-FrozenLake-v1-4x4
|
Tyrranen
| 2023-06-23T15:10:55Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T15:10:53Z |
---
tags:
- FrozenLake-v1-4x4
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4
type: FrozenLake-v1-4x4
metrics:
- type: mean_reward
value: 0.47 +/- 0.50
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="Tyrranen/q-FrozenLake-v1-4x4", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
luodian/OTTER-Video-LLaMA7B-DenseCaption
|
luodian
| 2023-06-23T15:06:28Z | 10 | 18 |
transformers
|
[
"transformers",
"pytorch",
"otter",
"text2text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-13T02:06:11Z |
---
license: mit
---
<p align="center" width="100%">
<img src="https://i.postimg.cc/MKmyP9wH/new-banner.png" width="80%" height="80%">
</p>
<div>
<div align="center">
<a href='https://brianboli.com/' target='_blank'>Bo Li*<sup>1</sup></a> 
<a href='https://zhangyuanhan-ai.github.io/' target='_blank'>Yuanhan Zhang*<sup>,1</sup></a> 
<a href='https://cliangyu.com/' target='_blank'>Liangyu Chen*<sup>,1</sup></a> 
<a href='https://king159.github.io/' target='_blank'>Jinghao Wang*<sup>,1</sup></a> 
<a href='https://pufanyi.github.io/' target='_blank'>Fanyi Pu*<sup>,1</sup></a> 
</br>
<a href='https://jingkang50.github.io/' target='_blank'>Jingkang Yang<sup>1</sup></a> 
<a href='https://chunyuan.li/' target='_blank'>Chunyuan Li<sup>2</sup></a> 
<a href='https://liuziwei7.github.io/' target='_blank'>Ziwei Liu<sup>1</sup></a>
</div>
<div>
<div align="center">
<sup>1</sup>S-Lab, Nanyang Technological University 
<sup>2</sup>Microsoft Research, Redmond
</div>
-----------------
[](https://hits.seeyoufarm.com)
An example of using this model to run on your video.
Please first clone [Otter](https://github.com/Luodian/Otter) to your local disk.
Place following script inside the `Otter` folder to make sure it has the access to `otter/modeling_otter.py`.
```python
import mimetypes
import os
from typing import Union
import cv2
import requests
import torch
import transformers
from PIL import Image
import sys
# make sure you can properly access the otter folder
from otter.modeling_otter import OtterForConditionalGeneration
# Disable warnings
requests.packages.urllib3.disable_warnings()
# ------------------- Utility Functions -------------------
def get_content_type(file_path):
content_type, _ = mimetypes.guess_type(file_path)
return content_type
# ------------------- Image and Video Handling Functions -------------------
def extract_frames(video_path, num_frames=16):
video = cv2.VideoCapture(video_path)
total_frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT))
frame_step = total_frames // num_frames
frames = []
for i in range(num_frames):
video.set(cv2.CAP_PROP_POS_FRAMES, i * frame_step)
ret, frame = video.read()
if ret:
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame = Image.fromarray(frame).convert("RGB")
frames.append(frame)
video.release()
return frames
def get_image(url: str) -> Union[Image.Image, list]:
if "://" not in url: # Local file
content_type = get_content_type(url)
else: # Remote URL
content_type = requests.head(url, stream=True, verify=False).headers.get("Content-Type")
if "image" in content_type:
if "://" not in url: # Local file
return Image.open(url)
else: # Remote URL
return Image.open(requests.get(url, stream=True, verify=False).raw)
elif "video" in content_type:
video_path = "temp_video.mp4"
if "://" not in url: # Local file
video_path = url
else: # Remote URL
with open(video_path, "wb") as f:
f.write(requests.get(url, stream=True, verify=False).content)
frames = extract_frames(video_path)
if "://" in url: # Only remove the temporary video file if it was downloaded
os.remove(video_path)
return frames
else:
raise ValueError("Invalid content type. Expected image or video.")
# ------------------- OTTER Prompt and Response Functions -------------------
def get_formatted_prompt(prompt: str) -> str:
return f"<image>User: {prompt} GPT:<answer>"
def get_response(input_data, prompt: str, model=None, image_processor=None, tensor_dtype=None) -> str:
if isinstance(input_data, Image.Image):
vision_x = image_processor.preprocess([input_data], return_tensors="pt")["pixel_values"].unsqueeze(1).unsqueeze(0)
elif isinstance(input_data, list): # list of video frames
vision_x = image_processor.preprocess(input_data, return_tensors="pt")["pixel_values"].unsqueeze(0).unsqueeze(0)
else:
raise ValueError("Invalid input data. Expected PIL Image or list of video frames.")
lang_x = model.text_tokenizer(
[
get_formatted_prompt(prompt),
],
return_tensors="pt",
)
bad_words_id = model.text_tokenizer(["User:", "GPT1:", "GFT:", "GPT:"], add_special_tokens=False).input_ids
generated_text = model.generate(
vision_x=vision_x.to(model.device, dtype=tensor_dtype),
lang_x=lang_x["input_ids"].to(model.device),
attention_mask=lang_x["attention_mask"].to(model.device),
max_new_tokens=512,
num_beams=3,
no_repeat_ngram_size=3,
bad_words_ids=bad_words_id,
)
parsed_output = (
model.text_tokenizer.decode(generated_text[0])
.split("<answer>")[-1]
.lstrip()
.rstrip()
.split("<|endofchunk|>")[0]
.lstrip()
.rstrip()
.lstrip('"')
.rstrip('"')
)
return parsed_output
# ------------------- Main Function -------------------
load_bit = "fp32"
if load_bit == "fp16":
precision = {"torch_dtype": torch.float16}
elif load_bit == "bf16":
precision = {"torch_dtype": torch.bfloat16}
elif load_bit == "fp32":
precision = {"torch_dtype": torch.float32}
# This model version is trained on MIMIC-IT DC dataset.
model = OtterForConditionalGeneration.from_pretrained("luodian/OTTER-9B-DenseCaption", device_map="auto", **precision)
tensor_dtype = {"fp16": torch.float16, "bf16": torch.bfloat16, "fp32": torch.float32}[load_bit]
model.text_tokenizer.padding_side = "left"
tokenizer = model.text_tokenizer
image_processor = transformers.CLIPImageProcessor()
model.eval()
while True:
video_url = input("Enter video path: ") # Replace with the path to your video file, could be any common format.
frames_list = get_image(video_url)
while True:
prompts_input = input("Enter prompts: ")
if prompts_input.lower() == "quit":
break
print(f"\nPrompt: {prompts_input}")
response = get_response(frames_list, prompts_input, model, image_processor, tensor_dtype)
print(f"Response: {response}")
```
|
Joaking1/distilbert-base-uncased-finetuned-squad
|
Joaking1
| 2023-06-23T15:04:06Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-23T09:17:04Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: distilbert-base-uncased-finetuned-squad
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-squad
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1572
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.2169 | 1.0 | 5533 | 1.1573 |
| 0.9517 | 2.0 | 11066 | 1.1252 |
| 0.754 | 3.0 | 16599 | 1.1572 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
AlgorithmicResearchGroup/led_large_16384_billsum_summarization
|
AlgorithmicResearchGroup
| 2023-06-23T15:03:10Z | 116 | 2 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"led",
"text2text-generation",
"summarization",
"en",
"dataset:billsum",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2022-11-26T01:10:32Z |
---
language: en
tags:
- summarization
datasets: billsum
widget:
- text: 'The people of the State of California do enact as follows: SECTIONHEADER
Section 1170.02 is added to the Penal Code, to read: 1170.02. A prisoner is not
eligible for resentence or recall pursuant to subdivision (e) of Section 1170
if he or she was convicted of first-degree murder if the victim was a peace officer,
as defined in Section 830.1, 830.2, 830.3, 830.31, 830.32, 830.33, 830.34, 830.35,
830.36, 830.37, 830.4, 830.5, 830.6, 830.10, 830.11, or 830.12, who was killed
while engaged in the performance of his or her duties, and the individual knew,
or reasonably should have known, that the victim was a peace officer engaged in
the performance of his or her duties, or the victim was a peace officer or a former
peace officer under any of the above-enumerated sections, and was intentionally
killed in retaliation for the performance of his or her official duties. SECTIONHEADER
Section 3550 of the Penal Code is amended to read: 3550. Notwithstanding any other
law, except as provided in subdivision (b), if the head physician of an institution
in which a prisoner is incarcerated determines, as provided in this section, that
the prisoner is permanently medically incapacitated with a medical condition that
renders him or her permanently unable to perform activities of basic daily living,
and results in the prisoner requiring 24-hour care, and that incapacitation did
not exist at the time of sentencing, the prisoner shall be granted medical parole
if the Board of Parole Hearings determines that the conditions under which he
or she would be released would not reasonably pose a threat to public safety.
This section does not alter or diminish the rights conferred under the Victims
Bill of Rights Act of 2008 . Subdivision (a) does not apply to any of the following:
A prisoner sentenced to death or life in prison without possibility of parole.
A prisoner who is serving a sentence for which parole, pursuant to subdivision
(a), is prohibited by any initiative statute. A prisoner who was convicted of
first-degree murder if the victim was a peace officer, as defined in Section 830.1,
830.2, 830.3, 830.31, 830.32, 830.33, 830.34, 830.35, 830.36, 830.37, 830.4, 830.5,
830.6, 830.10, 830.11, or 830.12, who was killed while engaged in the performance
of his or her duties, and the individual knew, or reasonably should have known,
that the victim was a peace officer engaged in the performance of his or her duties,
or the victim was a peace officer or a former peace officer under any of the above-enumerated
sections, and was intentionally killed in retaliation for the performance of his
or her official duties. When a physician employed by the Department of Corrections
and Rehabilitation who is the primary care provider for a prisoner identifies
a prisoner that he or she believes meets the medical criteria for medical parole
specified in subdivision (a), the primary care physician shall recommend to the
head physician of the institution where the prisoner is located that the prisoner
be referred to the Board of Parole Hearings for consideration for medical parole.
Within 30 days of receiving that recommendation, if the head physician of the
institution concurs in the recommendation of the primary care physician, he or
she shall refer the matter to the Board of Parole Hearings using a standardized
form and format developed by the department, and if the head physician of the
institution does not concur in the recommendation, he or she shall provide the
primary care physician with a written explanation of the reasons for denying the
referral. Notwithstanding any other provisions of this section, the prisoner or
his or her family member or designee may independently request consideration for
medical parole by contacting the head physician at the prison or the department.
Within 30 days of receiving the request, the head physician of the institution
shall, in consultation with the prisoners primary care physician, make a determination
regarding whether the prisoner meets the criteria for medical parole as specified
in subdivision (a) and, if the head physician of the institution determines that
the prisoner satisfies the criteria set forth in subdivision (a), he or she shall
refer the matter to the Board of Parole Hearings using a standardized form and
format developed by the department. If the head physician of the institution does
not concur in the recommendation, he or she shall provide the prisoner or his
or her family member or designee with a written explanation of the reasons for
denying the application. The Department of Corrections and Rehabilitation shall
complete parole plans for inmates referred to the Board of Parole Hearings for
medical parole consideration. The parole plans shall include, but not be limited
to, the inmates plan for residency and medical care. Notwithstanding any other
law, medical parole hearings shall be conducted by two-person panels consisting
of at least one commissioner. In the event of a tie vote, the matter shall be
referred to the full board for a decision. Medical parole hearings may be heard
in absentia. Upon receiving a recommendation from the head physician of the institution
where a prisoner is located for the prisoner to be granted medical parole pursuant
to subdivision (c) or (d), the board, as specified in subdivision (f), shall make
an independent judgment regarding whether the conditions under which the inmate
would be released pose a reasonable threat to public safety, and make written
findings related thereto. Notwithstanding any other law, the board or the Division
of Adult Parole Operations shall have the authority to impose any reasonable conditions
on prisoners subject to medical parole supervision pursuant to subdivision (a),
including, but not limited to, the requirement that the parolee submit to electronic
monitoring. As a further condition of medical parole, pursuant to subdivision
(a), the parolee may be required to submit to an examination by a physician selected
by the board for the purpose of diagnosing the parolees current medical condition.
In the event such an examination takes place, a report of the examination and
diagnosis shall be submitted to the board by the examining physician. If the board
determines, based on that medical examination, that the persons medical condition
has improved to the extent that the person no longer qualifies for medical parole,
the board shall return the person to the custody of the department. Notwithstanding
any other law establishing maximum periods for parole, a prisoner sentenced to
a determinate term who is placed on medical parole supervision prior to the earliest
possible release date and who remains eligible for medical parole, shall remain
on medical parole, pursuant to subdivision (a), until that earliest possible release
date, at which time the parolee shall commence serving that period of parole provided
by, and under the provisions of, Chapter 8 of Title 1. Notwithstanding any other
law establishing maximum periods for parole, a prisoner sentenced to an indeterminate
term who is placed on medical parole supervision prior to the prisoners minimum
eligible parole date, and who remains eligible for medical parole, shall remain
on medical parole pursuant to subdivision (a) until that minimum eligible parole
date, at which time the parolee shall be eligible for parole consideration under
all other provisions of Chapter 8 of Title 1. The Department of Corrections and
Rehabilitation shall, at the time a prisoner is placed on medical parole supervision
pursuant to subdivision (a), ensure that the prisoner has applied for any federal
entitlement programs for which the prisoner is eligible, and has in his or her
possession a discharge medical summary, full medical records, parole medications,
and all property belonging to the prisoner that was under the control of the department.
Any additional records shall be sent to the prisoners forwarding address after
release to health care-related parole supervision. The provisions for medical
parole set forth in this title shall not affect an inmates eligibility for any
other form of parole or release provided by law. (1) Notwithstanding any other
law, the Department of Corrections and Rehabilitation shall give notice to the
county of commitment and the proposed county of release, if that county is different
than the county of commitment, of any medical parole hearing as described in subdivision
(f), and of any medical parole release as described in subdivision (g). Notice
shall be made at least 30 days, or as soon as feasible, prior to the time any
medical parole hearing or medical parole release is scheduled for an inmate receiving
medical parole consideration, regardless of whether the inmate is sentenced either
determinately or indeterminately.'
train-eval-index:
- config: default
task: summarization
task_id: summarization
splits:
eval_split: test
col_mapping:
text: text
summary: target
model-index:
- name: Artifact-AI/led_large_16384_billsum_summarization
results:
- task:
type: summarization
name: Summarization
dataset:
name: billsum
type: billsum
config: default
split: test
metrics:
- type: rouge
value: 47.8432
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmU2ZDc5MjNjMTEwOTA5ZjYxODY1MjJlNDFhYTM4NzE4YTM1MTY0MDhhYjkzYTlkNWU2NWU1NDA1NDgzMDE0NSIsInZlcnNpb24iOjF9.Dm86XdSyIx0m7USfpRWxCrEu3WWBqMaNcDrXKXWGi14Nvj_WSC8ua9h-vBPm9lSShm2k9BZ0_URw452DsJeBCw
- type: rouge
value: 26.3424
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzcwZDhlYTJmMzQ0ZDgwMmQwNGUyOTE2MGIwZWMzZWZhNWQxNTA5YmE5NmY1YjBiMTM0NjVjZWVkM2U1NmQwNSIsInZlcnNpb24iOjF9.6TC2fIaSpQqDaoirE9uDmIbzGlkVRgliIo1g7HuowjR3vmhKN4Bm9EZxohsYsZp5fp72UpZZmfTm2FuZ3aiVAw
- type: rouge
value: 34.2299
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDYyNzQ3ZmNiNTRjZGIxNTQ5YmI5MjIxNTM3ZDk3NDE1MzE5ZGQwNGRlMTcxMjcxMTY0MzZjN2FlMzUzMjgxYiIsInZlcnNpb24iOjF9.jmaScJhaq7TjiuRlvZqJdZRbqJBtmTyJTgp3oRF38GRCsoQE9QS6MZaWlh9dphoU-tdmGeR9x-Tlm1DlkP1VDg
- type: rouge
value: 41.6889
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWU3NTkxZGI3ZWYyZDg4ZTNjNTM1ODhmNTFjOGNmYjJmMjI0M2JhY2YwZjgzYzg3MWRmYWIxNTQ0YTA1MGU5NSIsInZlcnNpb24iOjF9.Fy_1tkSDARRQAkj7G3IqOKeak3uBwEwHAFzImqcOpM71Sy5_YCtk_upqrxQywamtKxlLdiXxkt5c5oyFNMffDQ
- type: loss
value: 2.076857805252075
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2IxMWU4ZjIzMDVmMWJiYjA4NDNhZmQ2MjMyZTQzNTRmNmFlNjQzNDYxODc0ZTk2NDUwOWJhZWI0MWQzMzkzMSIsInZlcnNpb24iOjF9.ogmKZV1UkHnekUrrsTEWepnD_VfETCQJWxORne7MESBSPSgdwRu4_hUaE8Z-uK3ph6JDmKCXW5WXKBjg8gqJAw
- type: gen_len
value: 140.324
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGNkMWYzMzFiM2U3NTViYWZkODFhZmYyNDU4N2QzMmZmNzE5N2E3NmU2NWMwMjUzODQwOTMzMjE2NzlhYWJmMiIsInZlcnNpb24iOjF9._vtwj0OXD8cYyHNGC21xlcH9xo2MlnRu1CUYklsjW1XLbDfUQMwBpHPKTHj7r-R-Iv4rVLhnodED_5v848maAg
---
# Longformer Encoder-Decoder (LED) fine-tuned on Billsum
This model is a fine-tuned version of led-large-16384 on the billsum dataset.
As described in Longformer: The Long-Document Transformer by Iz Beltagy, Matthew E. Peters, Arman Cohan, led-large-16384 was initialized from bart-base since both models share the exact same architecture. To be able to process 16K tokens, bart-base's position embedding matrix was simply copied 16 times.
# Use In Transformers
```
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Artifact-AI/led_large_16384_billsum_summarization")
model = AutoModelForSeq2SeqLM.from_pretrained("Artifact-AI/led_large_16384_billsum_summarization")
```
### Results
| Model | Rouge-1 | Rouge-2 | Rouge-L | Rouge-Lsum |
| --- | --- | --- | --- | --- |
| LED Large | 47.843 | 26.342 | 34.230 | 41.689 |
| LED Base | 47.672 | 26.737 | 34.568 | 41.529 |
The model is trained on the BillSum summarization dataset found [here](https://huggingface.co/datasets/billsum)
### Test The Model
Please find a notebook to test the model below:
[](https://colab.research.google.com/drive/1TX4IVyvwduDqsok6XuS6i9VIOs9pTXra?usp=sharing)
## Citing & Authors
```
@misc{led_large_16384_billsum_summarization,
title={led_large_16384_billsum_summarization},
author={Matthew Kenney},
year={2023}
}
```
|
tuanluong/Kobayashi
|
tuanluong
| 2023-06-23T14:52:14Z | 0 | 0 |
allennlp
|
[
"allennlp",
"chemistry",
"text-classification",
"ab",
"dataset:tiiuae/falcon-refinedweb",
"arxiv:1910.09700",
"license:bigscience-openrail-m",
"region:us"
] |
text-classification
| 2023-06-23T14:43:20Z |
---
'[object Object]': null
license: bigscience-openrail-m
datasets:
- tiiuae/falcon-refinedweb
language:
- ab
metrics:
- accuracy
library_name: allennlp
pipeline_tag: text-classification
tags:
- chemistry
---
# Model Card for {{ model_id | default("Model ID", true) }}
<!-- Provide a quick summary of what the model is/does. -->
{{ model_summary | default("", true) }}
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
{{ model_description | default("", true) }}
- **Developed by:** {{ developers | default("[More Information Needed]", true)}}
- **Shared by [optional]:** {{ shared_by | default("[More Information Needed]", true)}}
- **Model type:** {{ model_type | default("[More Information Needed]", true)}}
- **Language(s) (NLP):** {{ language | default("[More Information Needed]", true)}}
- **License:** {{ license | default("[More Information Needed]", true)}}
- **Finetuned from model [optional]:** {{ finetuned_from | default("[More Information Needed]", true)}}
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** {{ repo | default("[More Information Needed]", true)}}
- **Paper [optional]:** {{ paper | default("[More Information Needed]", true)}}
- **Demo [optional]:** {{ demo | default("[More Information Needed]", true)}}
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
{{ direct_use | default("[More Information Needed]", true)}}
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
{{ downstream_use | default("[More Information Needed]", true)}}
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
{{ out_of_scope_use | default("[More Information Needed]", true)}}
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
{{ bias_risks_limitations | default("[More Information Needed]", true)}}
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
{{ bias_recommendations | default("Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", true)}}
## How to Get Started with the Model
Use the code below to get started with the model.
{{ get_started_code | default("[More Information Needed]", true)}}
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
{{ training_data | default("[More Information Needed]", true)}}
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
{{ preprocessing | default("[More Information Needed]", true)}}
#### Training Hyperparameters
- **Training regime:** {{ training_regime | default("[More Information Needed]", true)}} <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
{{ speeds_sizes_times | default("[More Information Needed]", true)}}
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
{{ testing_data | default("[More Information Needed]", true)}}
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
{{ testing_factors | default("[More Information Needed]", true)}}
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
{{ testing_metrics | default("[More Information Needed]", true)}}
### Results
{{ results | default("[More Information Needed]", true)}}
#### Summary
{{ results_summary | default("", true) }}
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
{{ model_examination | default("[More Information Needed]", true)}}
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** {{ hardware | default("[More Information Needed]", true)}}
- **Hours used:** {{ hours_used | default("[More Information Needed]", true)}}
- **Cloud Provider:** {{ cloud_provider | default("[More Information Needed]", true)}}
- **Compute Region:** {{ cloud_region | default("[More Information Needed]", true)}}
- **Carbon Emitted:** {{ co2_emitted | default("[More Information Needed]", true)}}
## Technical Specifications [optional]
### Model Architecture and Objective
{{ model_specs | default("[More Information Needed]", true)}}
### Compute Infrastructure
{{ compute_infrastructure | default("[More Information Needed]", true)}}
#### Hardware
{{ hardware | default("[More Information Needed]", true)}}
#### Software
{{ software | default("[More Information Needed]", true)}}
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
{{ citation_bibtex | default("[More Information Needed]", true)}}
**APA:**
{{ citation_apa | default("[More Information Needed]", true)}}
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
{{ glossary | default("[More Information Needed]", true)}}
## More Information [optional]
{{ more_information | default("[More Information Needed]", true)}}
## Model Card Authors [optional]
{{ model_card_authors | default("[More Information Needed]", true)}}
## Model Card Contact
{{ model_card_contact | default("[More Information Needed]", true)}}
|
yasamingol/test_trainer
|
yasamingol
| 2023-06-23T14:52:05Z | 161 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-23T12:15:03Z |
---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test_trainer
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# test_trainer
This model is a fine-tuned version of [HooshvareLab/bert-base-parsbert-uncased](https://huggingface.co/HooshvareLab/bert-base-parsbert-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4347
- Accuracy: {'accuracy': 0.8962962962962963}
- F1 Weighted: {'f1': 0.8943267815916415}
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted |
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|:--------------------------:|
| No log | 1.0 | 270 | 0.4668 | {'accuracy': 0.8851851851851852} | {'f1': 0.8812450190293216} |
| 0.6057 | 2.0 | 540 | 0.4347 | {'accuracy': 0.8962962962962963} | {'f1': 0.8943267815916415} |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
chencjiajy/Reinforce-cartpole-v0
|
chencjiajy
| 2023-06-23T14:49:29Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T14:49:21Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-cartpole-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 455.60 +/- 54.20
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
J4m35M4xw3ll/ppo-Huggy
|
J4m35M4xw3ll
| 2023-06-23T14:41:57Z | 4 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-06-23T14:41:53Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: J4m35M4xw3ll/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
KPrashanth/ppo-Huggy
|
KPrashanth
| 2023-06-23T14:30:11Z | 2 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-06-23T14:30:03Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: KPrashanth/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
HxLab/ppo-Huggy
|
HxLab
| 2023-06-23T14:27:58Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-06-23T14:27:44Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: HxLab/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Tyrranen/Taxi
|
Tyrranen
| 2023-06-23T14:22:55Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T14:22:54Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="Tyrranen/Taxi", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
NasimB/gpt2-2_left_out_gutenberg
|
NasimB
| 2023-06-23T14:12:28Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-23T10:45:16Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-2_left_out_gutenberg
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gpt2-2_left_out_gutenberg
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 3.9287
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 5.8917 | 0.26 | 500 | 5.0150 |
| 4.6559 | 0.53 | 1000 | 4.6338 |
| 4.3512 | 0.79 | 1500 | 4.4091 |
| 4.1461 | 1.06 | 2000 | 4.2691 |
| 3.9654 | 1.32 | 2500 | 4.1719 |
| 3.8972 | 1.59 | 3000 | 4.0869 |
| 3.8271 | 1.85 | 3500 | 4.0113 |
| 3.6889 | 2.12 | 4000 | 3.9762 |
| 3.586 | 2.38 | 4500 | 3.9376 |
| 3.5724 | 2.65 | 5000 | 3.8870 |
| 3.5435 | 2.91 | 5500 | 3.8480 |
| 3.3888 | 3.17 | 6000 | 3.8520 |
| 3.3327 | 3.44 | 6500 | 3.8282 |
| 3.3538 | 3.7 | 7000 | 3.8039 |
| 3.3427 | 3.97 | 7500 | 3.7743 |
| 3.1287 | 4.23 | 8000 | 3.8093 |
| 3.1293 | 4.5 | 8500 | 3.7959 |
| 3.1508 | 4.76 | 9000 | 3.7735 |
| 3.1169 | 5.03 | 9500 | 3.7815 |
| 2.8937 | 5.29 | 10000 | 3.8078 |
| 2.9281 | 5.56 | 10500 | 3.7999 |
| 2.9357 | 5.82 | 11000 | 3.7869 |
| 2.8489 | 6.08 | 11500 | 3.8165 |
| 2.6858 | 6.35 | 12000 | 3.8367 |
| 2.7074 | 6.61 | 12500 | 3.8300 |
| 2.7252 | 6.88 | 13000 | 3.8234 |
| 2.5862 | 7.14 | 13500 | 3.8661 |
| 2.4957 | 7.41 | 14000 | 3.8772 |
| 2.5091 | 7.67 | 14500 | 3.8791 |
| 2.5155 | 7.94 | 15000 | 3.8773 |
| 2.3794 | 8.2 | 15500 | 3.9064 |
| 2.349 | 8.47 | 16000 | 3.9130 |
| 2.3595 | 8.73 | 16500 | 3.9154 |
| 2.3579 | 8.99 | 17000 | 3.9160 |
| 2.2743 | 9.26 | 17500 | 3.9268 |
| 2.2753 | 9.52 | 18000 | 3.9287 |
| 2.2734 | 9.79 | 18500 | 3.9287 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
jahnavikalyani/jk-finance
|
jahnavikalyani
| 2023-06-23T14:03:42Z | 77 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-06-22T12:24:10Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: jk-finance
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# jk-finance
This model is a fine-tuned version of [openai/whisper-small.en](https://huggingface.co/openai/whisper-small.en) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0154
- Wer: 1.1611
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.0001 | 142.86 | 1000 | 0.0154 | 1.1611 |
| 0.0001 | 285.71 | 2000 | 0.0154 | 1.1611 |
| 0.0001 | 428.57 | 3000 | 0.0154 | 1.1611 |
| 0.0001 | 571.43 | 4000 | 0.0154 | 1.1611 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
|
jackie68/semantic_segmentation
|
jackie68
| 2023-06-23T14:03:35Z | 51 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"segformer",
"generated_from_trainer",
"dataset:scene_parse_150",
"license:other",
"endpoints_compatible",
"region:us"
] | null | 2023-06-23T12:58:22Z |
---
license: other
tags:
- generated_from_trainer
datasets:
- scene_parse_150
model-index:
- name: semantic_segmentation
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# semantic_segmentation
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the scene_parse_150 dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1757
- Mean Iou: 0.1304
- Mean Accuracy: 0.2321
- Overall Accuracy: 0.4229
- Per Category Iou: [0.22150017755715537, 0.5590869674464826, 0.8364981896677761, 0.21143228725471633, 0.4199449932704533, 0.028304212146720555, 0.8896023646625641, 0.0, 0.0, 0.39826663958291014, nan, 0.0, 0.0, 0.0, 0.06262780865397885, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5293724129280428, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.7992381312177308, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan]
- Per Category Accuracy: [0.5812470100462446, 0.8245734777411526, 0.8791209287822161, 0.6412788852449106, 0.9244858762355366, 0.04943506266702407, 0.9595426561125769, nan, nan, 0.8407661520869067, nan, 0.0, 0.0, 0.0, 0.07189147152855785, 0.0, nan, 0.0, nan, 0.0, 0.622712964784576, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.7995359896699963, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan]
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 6e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| 4.891 | 1.0 | 20 | 4.9474 | 0.0046 | 0.0254 | 0.0704 | [0.024187363738948475, 0.16416376944334038, 0.0647381730225545, 0.03634000299711365, 0.0, 0.005314493785397839, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.005088979497668475, 0.0, 0.0, 0.0, 0.002815960720958149, 0.08204028426054413, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.12754115308859834, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan] | [0.04400713602296284, 0.29116082598894927, 0.07450774813696735, 0.08429428567110493, 0.0, 0.009519864187603057, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.009531961572981418, nan, 0.0, nan, 0.029736942432329393, 0.09595711194176668, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.15023121781715684, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 4.5492 | 2.0 | 40 | 4.7495 | 0.0189 | 0.0890 | 0.2302 | [0.12462756129009017, 0.3978829042615255, 0.016434690221426, 0.10039489387227182, 0.10564817271002101, 2.7409876326638013e-05, 0.0006838974411912719, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0007060453467615165, 0.0, 0.0, 0.0, 0.0, 0.0008646325966488936, 0.2689913228605529, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.49634440063513585, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan] | [0.4137547839260086, 0.8152391673237835, 0.016707414621360363, 0.24283252981093295, 0.12126996767695696, 4.0613755066565945e-05, 0.0007283421284080914, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0007632708315331662, 0.0, nan, 0.0, nan, 0.006290507052992757, 0.41014164863269725, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.7301496485804119, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 4.5521 | 3.0 | 60 | 4.5072 | 0.0376 | 0.1384 | 0.2859 | [0.13911128044221424, 0.44626900756181176, 0.157819434711516, 0.16044540535778523, 0.37829203636991066, 0.008742984650753939, 0.054376268460487855, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.00012975926242103465, 0.0, 0.0, 0.0, 0.024363052103485588, 0.24814640128289783, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.4102499243406343, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan] | [0.5331187210971137, 0.8146373132789622, 0.17098323835519863, 0.6605936494022701, 0.8473204665760997, 0.010502717060213954, 0.05854221635883905, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.00015789648638766081, nan, 0.0, nan, 0.07081585970263057, 0.6469112728703521, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.4767338711793946, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 3.8217 | 4.0 | 80 | 4.3020 | 0.0548 | 0.1633 | 0.3578 | [0.19134656693728727, 0.5025166756633244, 0.6339876382753764, 0.199677780922224, 0.2834972396603318, 0.011340395406156589, 0.33447748338411304, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.016315294749563582, 0.15834556569241345, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.2986357279911542, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan] | [0.6924832562589699, 0.8793366230972636, 0.6855824547290976, 0.6771351277827315, 0.9297559376024734, 0.014052359253031816, 0.35754727352682497, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.02316050324056424, 0.41914223883533347, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.3856009826101106, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 3.8991 | 5.0 | 100 | 4.1173 | 0.0614 | 0.1655 | 0.3473 | [0.20461006789798616, 0.5039799426651824, 0.7399043093453518, 0.16574507820545417, 0.236484529613361, 0.0422240255490694, 0.47135920413722315, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0015157661023462352, 0.0, 0.0, 0.0, 0.0009119095385737735, 0.24106181234557472, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.09407324000164113, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan] | [0.6355196539626854, 0.8552763931110002, 0.819074561978317, 0.684729547961975, 0.9180212676254275, 0.052407989537896695, 0.49224934036939316, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.001770102715819566, nan, 0.0, nan, 0.0009531071292413268, 0.5614302577218179, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.10831806753344916, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 3.4768 | 6.0 | 120 | 4.0152 | 0.0554 | 0.1576 | 0.3426 | [0.22527468198656567, 0.512340953864634, 0.7799315612435397, 0.15983846290320597, 0.2337615259576794, 0.0573658549037627, 0.1539293583494692, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.005393457117595048, 0.16000621547936886, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.03687035020272132, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.712451164088662, 0.8485501168878573, 0.8477035778361255, 0.6876010700197984, 0.9515622804141097, 0.07301540885867225, 0.1584075417766051, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.005813953488372093, 0.5571021050560693, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.04424894889062689, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 3.5641 | 7.0 | 140 | 3.8656 | 0.0539 | 0.1495 | 0.3392 | [0.23866238429740494, 0.5423301812128158, 0.6520376175548589, 0.16882836303203766, 0.23905629988212745, 0.0742010258433616, 0.07386488566402814, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.10221099328636159, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.06656160805792183, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5521148939563069, 0.8859319403384315, 0.8817104198771687, 0.6908957637493011, 0.9334332693118471, 0.09776543119623754, 0.07386488566402814, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.42381467637222114, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.09511161967949694, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 3.6626 | 8.0 | 160 | 3.6815 | 0.0541 | 0.1496 | 0.3391 | [0.23102979623191136, 0.5233513472787299, 0.711249445176058, 0.17787270214047723, 0.23177617698387662, 0.05659562594669289, 0.030741534740545296, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.13260673459428285, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.015147133693106609, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.7208778504225801, 0.8516039688930622, 0.8762376908789357, 0.6894297761724122, 0.9378835433550382, 0.06919771588241505, 0.030741534740545296, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.4410289199291757, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.019520977571084386, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.7468 | 9.0 | 180 | 3.7395 | 0.0640 | 0.1604 | 0.3623 | [0.24077148651703972, 0.5737477965368796, 0.7180615895487191, 0.1961609578856175, 0.25636620727603104, 0.04439031180400891, 0.10651660070360598, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.13827126373246734, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.15761803016752668, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.7111056848987403, 0.9168828418656361, 0.8462800356111515, 0.6878277691296265, 0.9385042394715886, 0.05180690596291152, 0.10651660070360598, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.4921306315168208, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.2210977728553957, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 3.1967 | 10.0 | 200 | 3.6281 | 0.0697 | 0.1692 | 0.3784 | [0.23180915034148517, 0.574025758973184, 0.7022844944100585, 0.14051028039080926, 0.36457117852975496, 0.034250019339367214, 0.0016731361263552403, 0.0, 0.0, 0.0026872498570611777, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.14495245672342774, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.5209795730263242, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6168473927603253, 0.8306756090289252, 0.9157986071882104, 0.701391932534345, 0.93671241860683, 0.043156176133732974, 0.0017177880386983289, nan, nan, 0.0026872498570611777, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.5555774149124533, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.6408486559972285, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 3.1566 | 11.0 | 220 | 3.8054 | 0.0749 | 0.1713 | 0.3375 | [0.19421561065608767, 0.4252199697850628, 0.5062159552784963, 0.16467682400206837, 0.40263469259444445, 0.04894529433111676, 0.023289468345528072, 0.0, 0.0, 0.30698645017437537, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.16626429073257967, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.6840112355799725, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6913869398819965, 0.6109375827201017, 0.5757889361394438, 0.6786388985445917, 0.9524874689651942, 0.0777834637034871, 0.02366424802110818, nan, nan, 0.3070040022870212, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.6401731261066299, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.7528672584023137, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 3.0807 | 12.0 | 240 | 3.4939 | 0.0865 | 0.1835 | 0.3805 | [0.2143323747145, 0.5672948309160185, 0.7620331309805536, 0.16709044543305474, 0.2942868671169825, 0.03433445673894241, 0.18142814199437052, 0.0, 0.0, 0.5542096391737851, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.13797934570665127, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.3732072610076307, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6785351219901132, 0.9052191333859027, 0.8367490814763263, 0.6783290764278266, 0.9224949641635827, 0.04675455483263072, 0.18247031662269128, nan, nan, 0.5545740423098914, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.46985048199881957, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.4133208757407631, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.3271 | 13.0 | 260 | 3.5085 | 0.0728 | 0.1657 | 0.3552 | [0.23285434588721055, 0.5309590382316115, 0.7880097944765575, 0.13540366977902088, 0.2859982356012459, 0.05312225965754373, 0.07097354510393435, 0.0, 0.0, 0.20560320182961692, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.18317318604827115, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.2814292053890332, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.653120515069367, 0.7857399600435787, 0.8871560337854021, 0.6921350522163616, 0.9301775425118284, 0.08414357774691132, 0.079155672823219, nan, nan, 0.20560320182961692, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.4762935274444226, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.3428637415819393, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 3.4236 | 14.0 | 280 | 3.5354 | 0.1021 | 0.1982 | 0.3675 | [0.18407396289848113, 0.35504435614761004, 0.8284947228199611, 0.17998180315690185, 0.4184593671845003, 0.04233771919157526, 0.2621136920124413, 0.0, 0.0, 0.5641406228525879, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.3773042920489723, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.6662398521549733, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.7639630840376336, 0.4815250312769058, 0.9134712286299197, 0.6517448274819774, 0.9444886869349323, 0.070700424819878, 0.27215259454705365, nan, nan, 0.586735277301315, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.6654042888058234, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.7947646617291209, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.8569 | 15.0 | 300 | 3.4929 | 0.0916 | 0.1896 | 0.3720 | [0.2163566657334632, 0.544495409120061, 0.600316418987717, 0.16698964598504185, 0.26571585768834155, 0.05409944180417593, 0.7218503065509331, 0.0, 0.0, 0.5751527611215808, nan, 0.0, 0.0, 0.0, 0.002926843129733032, 0.0, 0.0, 0.0, 0.0, 0.0, 0.11635309498095833, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.21807497041122684, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.46598429277627174, 0.9344118409210596, 0.8419551787562308, 0.653120135414935, 0.9445472431723427, 0.06463272981293304, 0.7394184256816183, nan, nan, 0.5758433390508862, nan, 0.0, 0.0, 0.0, 0.002966675307468533, 0.0, nan, 0.0, nan, 0.0, 0.40271493212669685, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.2504920924031431, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.7317 | 16.0 | 320 | 3.5028 | 0.1043 | 0.2093 | 0.3931 | [0.24440867984386225, 0.5442738966010062, 0.6804932540661495, 0.1651594332879151, 0.32317360877064294, 0.06375522091888172, 0.7869966642095926, 0.0, 0.0, 0.5327658115751586, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.17097412676036283, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.4506695317208669, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5781723409344602, 0.7916024642579502, 0.885072691037107, 0.6512536460773497, 0.9545369372745585, 0.09708312011111923, 0.8656552330694811, nan, nan, 0.5331618067467124, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.590546921109581, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.541632329552314, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.2949 | 17.0 | 340 | 3.3983 | 0.1198 | 0.2213 | 0.4295 | [0.20937985316700186, 0.5680047932893948, 0.7553237179737464, 0.21684766202889438, 0.39751202143306374, 0.04424554117653032, 0.8717100550874497, 0.0, 0.0, 0.576288072872189, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.29272276505760536, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.6218221547480102, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.7195523042576941, 0.863760863326191, 0.8742447317639722, 0.6568304441791225, 0.9400618353867054, 0.07078977508102444, 0.9198548812664907, nan, nan, 0.5787592910234419, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.4936061381074169, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.7438704970264496, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.6068 | 18.0 | 360 | 3.4716 | 0.1120 | 0.2149 | 0.3984 | [0.23387987863334025, 0.5366594637734627, 0.8052287689540812, 0.15896235256930943, 0.37721041222999696, 0.04599510920640231, 0.6706191002855012, 0.0, 0.0, 0.6675650433622415, nan, 0.0, 0.0, 0.0, 0.004422019388854243, 0.0, 0.0, 0.0, 0.0, 0.0, 0.18169042360971693, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.5740425491445472, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5896238638175729, 0.7944194755510726, 0.8821894531338266, 0.653649100004534, 0.9293226214456364, 0.07593147647245169, 0.7166062005277045, nan, nan, 0.715180102915952, nan, 0.0, 0.0, 0.0, 0.0044932169705348655, 0.0, nan, 0.0, nan, 0.0, 0.6676667322447374, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.6336575456792974, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.5756 | 19.0 | 380 | 3.4749 | 0.1163 | 0.2155 | 0.3992 | [0.20025056700227745, 0.5486162983475742, 0.8070171677500129, 0.19460426912514886, 0.32124920785804817, 0.021096525731796986, 0.8987516399096528, 0.0, 0.0, 0.6719136848140522, nan, 0.0, 0.0, 0.0, 0.01355494150479097, 0.0, 0.0, 0.0, 0.0, 0.0, 0.29950986885680225, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.44257600510769346, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6340246770849944, 0.839056983875327, 0.8505958541027391, 0.6581301857421373, 0.9498875720241721, 0.03332764740762401, 0.9131898636763413, nan, nan, 0.73704974271012, nan, 0.0, 0.0, 0.0, 0.014199717733805697, 0.0, nan, 0.0, nan, 0.0, 0.5560200668896321, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.4948428716150604, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.3829 | 20.0 | 400 | 3.4541 | 0.1184 | 0.2274 | 0.3961 | [0.23101834784334854, 0.4724549792090804, 0.7793240723280324, 0.16976028596904655, 0.4177389041491976, 0.05686391028120875, 0.7918975621992657, 0.0, 0.0, 0.7119648462021343, nan, 0.0, 0.0, 0.0, 0.0025354046141562426, 0.0, 0.0, 0.0, 0.0, 0.0, 0.19777745206465108, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.6679108632400428, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6089339818210812, 0.6698997745833694, 0.8404502912612584, 0.6445282391524476, 0.9475101887853095, 0.11581418394781945, 0.9544167766051012, nan, nan, 0.8105774728416237, nan, 0.0, 0.0, 0.0, 0.002606641896367983, 0.0, nan, 0.0, nan, 0.0, 0.7300314774739327, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.7241658049581918, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.344 | 21.0 | 420 | 3.4330 | 0.1092 | 0.2089 | 0.3770 | [0.21576935396270558, 0.5533096259392261, 0.797950656167979, 0.17785718462579464, 0.3285285870231269, 0.0361096199766766, 0.8169827877151535, 0.0, 0.0, 0.624385031499744, nan, 0.0, 0.0, 0.0, 0.022552667694789117, 0.0, 0.0, 0.0, 0.0, 0.0, 0.28774181237029794, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.29029304955643, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6176746132993143, 0.7946813935150226, 0.8586987468309238, 0.6435458763431923, 0.9481074624068956, 0.06338182615688281, 0.8316567722075637, nan, nan, 0.8018296169239566, nan, 0.0, 0.0, 0.0, 0.022955730291771077, 0.0, nan, 0.0, nan, 0.0, 0.5933012000786937, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.3012655304362432, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.3151 | 22.0 | 440 | 3.3985 | 0.1075 | 0.2153 | 0.3840 | [0.21691310706643793, 0.5694534584520001, 0.6706321822893195, 0.17998809619289233, 0.2815267333207138, 0.043476929671473624, 0.9086277579504597, 0.0, 0.0, 0.546533677184466, nan, 0.0, 0.0, 0.0, 0.027217255569745993, 0.0, 0.0, 0.0, 0.0, 0.0, 0.3155081519086205, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.32639989884350895, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.529924453835114, 0.8312356676539674, 0.8608182430325516, 0.6444148895975336, 0.9579683327868085, 0.06920583863342837, 0.9411554529463501, nan, nan, 0.8239565465980561, nan, 0.0, 0.0, 0.0, 0.027621763299634207, 0.0, nan, 0.0, nan, 0.0, 0.6357957898878615, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.35228567079411904, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.5617 | 23.0 | 460 | 3.3389 | 0.1162 | 0.2199 | 0.4075 | [0.2303508380718772, 0.5260143321132134, 0.770340296621967, 0.18188436558135587, 0.39942117304174585, 0.05610954696698234, 0.892929850138566, 0.0, 0.0, 0.5768117778763492, nan, 0.0, 0.0, 0.0, 0.02070271407532085, 0.0, 0.0, 0.0, 0.0, 0.0, 0.22771826791844163, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.5349131429127536, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.617729429118163, 0.8528856950996263, 0.8377523398063079, 0.6475508939501564, 0.9180446901203916, 0.08903347385692587, 0.9342705584872472, nan, nan, 0.780674671240709, nan, 0.0, 0.0, 0.0, 0.021256372591376478, 0.0, nan, 0.0, nan, 0.0, 0.5416092858548102, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.5770209906935485, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.1818 | 24.0 | 480 | 3.3950 | 0.1122 | 0.2235 | 0.3969 | [0.2210184553965973, 0.5050926507861762, 0.8022411144115539, 0.18428008286629044, 0.3512189396442296, 0.050577789106975954, 0.897487154030884, 0.0, 0.0, 0.4789700969608083, nan, 0.0, 0.0, 0.0, 0.02049123965123635, 0.0, 0.0, 0.0, 0.0, 0.0, 0.3683404940923738, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.4955620915374127, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6737113299314303, 0.7501609123661501, 0.884887404588777, 0.6432813940483927, 0.9461868178198342, 0.0773610806507948, 0.9193051890941073, nan, nan, 0.8402515723270441, nan, 0.0, 0.0, 0.0, 0.021457991301592788, 0.0, nan, 0.0, nan, 0.0, 0.6746507967735589, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.49791877719630684, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.2623 | 25.0 | 500 | 3.3180 | 0.1164 | 0.2259 | 0.4170 | [0.2282295895445365, 0.5113128836848646, 0.6854427847662072, 0.18815217079114407, 0.39536157961326573, 0.06643817982879578, 0.9083441248413975, 0.0, 0.0, 0.45671918147137225, nan, 0.0, 0.0, 0.0, 0.019680888451535813, 0.0, 0.0, 0.0, 0.0, 0.0, 0.26592963860044605, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.6966255794731735, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.561991707861585, 0.841506195474392, 0.8749316473772929, 0.6435383197061979, 0.9295451351477959, 0.10061651680191047, 0.9542930958663148, nan, nan, 0.8179817038307604, nan, 0.0, 0.0, 0.0, 0.020161871021630806, 0.0, nan, 0.0, nan, 0.0, 0.5453964194373402, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.7122611055413541, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.8252 | 26.0 | 520 | 3.2752 | 0.1181 | 0.2293 | 0.4230 | [0.23178046640438404, 0.5062953715765939, 0.6591172311868068, 0.18009993528160906, 0.43548976001593254, 0.0685813226935672, 0.9053266804252985, 0.0, 0.0, 0.4410814304179233, nan, 0.0, 0.0, 0.0, 0.053070022946943886, 0.0, 0.0, 0.0, 0.0, 0.0, 0.18441253044427647, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8225392062154441, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5305025115611545, 0.8435820346567621, 0.8384302170562955, 0.6476869134160533, 0.9219094017894787, 0.11839721877005305, 0.9524791116974495, nan, nan, 0.8194682675814752, nan, 0.0, 0.0, 0.0, 0.054955499870387975, 0.0, nan, 0.0, nan, 0.0, 0.5399862286051544, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8402366242723593, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.3062 | 27.0 | 540 | 3.2598 | 0.1198 | 0.2244 | 0.4189 | [0.21508680044255887, 0.49804152042911065, 0.7485757067417215, 0.2158032840238191, 0.4634298014828988, 0.046382539324782604, 0.8073761879188363, 0.0, 0.0, 0.5587955946246337, nan, 0.0, 0.0, 0.0, 0.011024046023266688, 0.0, 0.0, 0.0, 0.0, 0.0, 0.29936930623686053, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.6885795878463558, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6732877531494179, 0.8382405800089721, 0.8449694729278422, 0.6413695648888419, 0.9076685248512671, 0.07187822371680841, 0.9503490545294635, nan, nan, 0.7905088622069754, nan, 0.0, 0.0, 0.0, 0.01120423975344912, 0.0, nan, 0.0, nan, 0.0, 0.5252803462522133, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.7024297554497594, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.8991 | 28.0 | 560 | 3.3240 | 0.1091 | 0.2196 | 0.3893 | [0.22611724819492363, 0.5166300770489228, 0.7160648965634288, 0.2013978680850963, 0.35384231777041897, 0.04217368383867479, 0.8969093388918912, 0.0, 0.0, 0.49687600535058163, nan, 0.0, 0.0, 0.0, 0.010359984735629584, 0.0, 0.0, 0.0, 0.0, 0.0, 0.27863996393843776, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.40502411068191574, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6407819725721575, 0.7514370658500771, 0.8961627628469037, 0.6414753578067617, 0.9472993863306319, 0.06303254786331035, 0.9579210642040458, nan, nan, 0.8389079473985135, nan, 0.0, 0.0, 0.0, 0.01055617961346813, 0.0, nan, 0.0, nan, 0.0, 0.6384517017509345, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.4210368846220468, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.8309 | 29.0 | 580 | 3.2645 | 0.1170 | 0.2234 | 0.4110 | [0.2531158279807733, 0.518578306826317, 0.7370145622009748, 0.17167057127410343, 0.4519757280144006, 0.0650204787245284, 0.9264705882352942, 0.0, 0.0, 0.4474756281207894, nan, 0.0, 0.0, 0.0, 0.00343012348444544, 0.0, 0.0, 0.0, 0.0, 0.0, 0.25955775986774127, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.6126038643032234, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5930573273800032, 0.823492369549529, 0.8924751106069713, 0.6478607160669215, 0.9115683702628004, 0.12495227883779679, 0.9523416886543535, nan, nan, 0.8070040022870212, nan, 0.0, 0.0, 0.0, 0.0035283274287853912, 0.0, nan, 0.0, nan, 0.0, 0.5559708833366123, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.6126038643032234, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.992 | 30.0 | 600 | 3.3789 | 0.1045 | 0.2124 | 0.3788 | [0.2312877350016793, 0.5344400727515682, 0.7247051846958767, 0.18470551622528014, 0.2815685129776935, 0.06123772182401111, 0.9287744322599673, 0.0, 0.0, 0.4395254008645798, nan, 0.0, 0.0, 0.0, 0.014283077534678347, 0.0, 0.0, 0.0, 0.0, 0.0, 0.3138911411607773, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.25579356789300467, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5902567373624621, 0.8023801098383632, 0.8726042688190022, 0.641346894977859, 0.9489038272356771, 0.0974323984046917, 0.9520805848724714, nan, nan, 0.8196683819325329, nan, 0.0, 0.0, 0.0, 0.014487744462686138, 0.0, nan, 0.0, nan, 0.0, 0.5902518197914617, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.25579356789300467, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.7357 | 31.0 | 620 | 3.2390 | 0.1271 | 0.2368 | 0.4321 | [0.25440306717060046, 0.5647957386189572, 0.741886922546541, 0.17693211640035877, 0.48506944234684324, 0.05157919757068916, 0.8066495105923441, 0.0, 0.0, 0.5028213166144201, nan, 0.0, 0.0, 0.0, 0.031297793314398074, 0.0, 0.0, 0.0, 0.0, 0.0, 0.3416863053155276, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.873923786040801, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5819695822037952, 0.8219125026818728, 0.8752615476389536, 0.6439690480148714, 0.9403546165737574, 0.08636921152455913, 0.9649021547933158, nan, nan, 0.8483133218982276, nan, 0.0, 0.0, 0.0, 0.03300786312969844, 0.0, nan, 0.0, nan, 0.0, 0.6417961833562856, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.9041535223318093, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.7793 | 32.0 | 640 | 3.3145 | 0.1147 | 0.2245 | 0.3965 | [0.22272081142861003, 0.5376374266326036, 0.7861582671882319, 0.20379904604395868, 0.35146677687942895, 0.03310143568097136, 0.9199973626953254, 0.0, 0.0, 0.4405628123082318, nan, 0.0, 0.0, 0.0, 0.037790216731925216, 0.0, 0.0, 0.0, 0.0, 0.0, 0.34680268723563074, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.4788132047446706, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.657421065220858, 0.7845808337350337, 0.8419371020295645, 0.6425181737119712, 0.9560828219421933, 0.051595714436565375, 0.9587730870712401, nan, nan, 0.8620068610634648, nan, 0.0, 0.0, 0.0, 0.03947406319306432, 0.0, nan, 0.0, nan, 0.0, 0.6855203619909502, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.4805498837349682, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.9864 | 33.0 | 660 | 3.2053 | 0.1328 | 0.2385 | 0.4352 | [0.22426000759852174, 0.5674209289092988, 0.7969320148823144, 0.19742652019560494, 0.5046044879348327, 0.02916021104643859, 0.9095200219060907, 0.0, 0.0, 0.40883468834688347, nan, 0.0, 0.0, 0.0, 0.00043458775277389216, 0.0, 0.0, 0.0, 0.0, 0.0, 0.46724210662945775, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.9390944394211018, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5824130920108436, 0.8252505635415767, 0.9050700699117403, 0.6412788852449106, 0.9227877453506348, 0.04525184589516777, 0.9585532102022867, nan, nan, 0.8625500285877644, nan, 0.0, 0.0, 0.0, 0.00046084276620870417, 0.0, nan, 0.0, nan, 0.0, 0.7081939799331104, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.9431167426894752, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.0793 | 34.0 | 680 | 3.2505 | 0.1301 | 0.2344 | 0.4253 | [0.2179250208855472, 0.5504574021047934, 0.757137292490032, 0.2069161631530082, 0.47782386918615166, 0.032417448107638615, 0.9137725804130858, 0.0, 0.0, 0.4149170335252286, nan, 0.0, 0.0, 0.0, 0.01745382585751979, 0.0, 0.0, 0.0, 0.0, 0.0, 0.4541177234083977, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.9005923268643176, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6239584994418753, 0.8248939092927936, 0.7817867940473339, 0.6433267338703583, 0.9281046517074999, 0.05062910706598111, 0.9599961521547933, nan, nan, 0.8406518010291595, nan, 0.0, 0.0, 0.0, 0.01905296811544111, 0.0, nan, 0.0, nan, 0.0, 0.6883238245130828, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.9066100476082997, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.6533 | 35.0 | 700 | 3.3026 | 0.1239 | 0.2253 | 0.3988 | [0.22385881541942132, 0.5422924700629186, 0.800951066891142, 0.19551704435495018, 0.4096064211501187, 0.040736417868757605, 0.9091697854210642, 0.0, 0.0, 0.42765567765567764, nan, 0.0, 0.0, 0.0, 0.015504746924330093, 0.0, 0.0, 0.0, 0.0, 0.0, 0.577238452346615, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.5652737608457166, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.608465555732738, 0.774260151410874, 0.8578446214959395, 0.6412788852449106, 0.9478732374572539, 0.06633850752572881, 0.9648059586631487, nan, nan, 0.8544311034877072, nan, 0.0, 0.0, 0.0, 0.015899075434200292, 0.0, nan, 0.0, nan, 0.0, 0.689012394255361, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.5652737608457166, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.1814 | 36.0 | 720 | 3.2419 | 0.1263 | 0.2318 | 0.4187 | [0.21407400770540275, 0.5653274502053318, 0.7976949025487257, 0.2190646070606214, 0.42204604910560306, 0.03418060615900333, 0.9005738843996088, 0.0, 0.0, 0.40761380513127954, nan, 0.0, 0.0, 0.0, 0.037137935178879054, 0.0, 0.0, 0.0, 0.0, 0.0, 0.4582608992057811, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.7449586180574799, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5953197257215755, 0.808961495272938, 0.8848512511354444, 0.6412788852449106, 0.9314540684873753, 0.058142651753295804, 0.9618101363236587, nan, nan, 0.8552315608919383, nan, 0.0, 0.0, 0.0, 0.040050116650825196, 0.0, nan, 0.0, nan, 0.0, 0.6612236867991343, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.7479069669786313, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.5975 | 37.0 | 740 | 3.2304 | 0.1332 | 0.2371 | 0.4284 | [0.2125380841724761, 0.5464970884866449, 0.8104551262824438, 0.21108967747054388, 0.46024708665556824, 0.017005781578361207, 0.9098245431353152, 0.0, 0.0, 0.4047998461411655, nan, 0.0, 0.0, 0.0, 0.07256335408540208, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5399273005548115, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8749129448973928, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6153025833200446, 0.7952303066947903, 0.891413102915324, 0.6433342905073526, 0.9227526116081886, 0.02852710155875592, 0.9605870712401056, nan, nan, 0.8423956546598056, nan, 0.0, 0.0, 0.0, 0.08090670814251563, 0.0, nan, 0.0, nan, 0.0, 0.6940291166633877, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8770162666064782, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.6611 | 38.0 | 760 | 3.2088 | 0.1353 | 0.2372 | 0.4277 | [0.21700874098471884, 0.5669435087809519, 0.7716808913276435, 0.19226950226571105, 0.4800950216397882, 0.03635858871203413, 0.9021164703152793, 0.0, 0.0, 0.39577791239760846, nan, 0.0, 0.0, 0.0, 0.061716229532538705, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5932811898961405, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.9244753270383035, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5036527268378249, 0.7986742492846017, 0.9177282977598417, 0.6438254719119803, 0.9301658312643463, 0.060636336314382956, 0.9617963940193491, nan, nan, 0.8591480846197828, nan, 0.0, 0.0, 0.0, 0.0658429102220686, 0.0, nan, 0.0, nan, 0.0, 0.6827168994688176, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.9281098927632235, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.9762 | 39.0 | 780 | 3.1755 | 0.1321 | 0.2352 | 0.4310 | [0.223072431082741, 0.5688620196937222, 0.8433919676547557, 0.20833557473653325, 0.4432905971020942, 0.027932226313021263, 0.9168266827998001, 0.0, 0.0, 0.40809544563085637, nan, 0.0, 0.0, 0.0, 0.011542100283822139, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5318375273749019, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8356211825451798, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6624541540424175, 0.8164428754134263, 0.8898991770570185, 0.6438481418229631, 0.9333512905794725, 0.04831412302718685, 0.9579760334212841, nan, nan, 0.8566037735849057, nan, 0.0, 0.0, 0.0, 0.012298741323194792, 0.0, nan, 0.0, nan, 0.0, 0.6330415109187487, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8358799661965325, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.7469 | 40.0 | 800 | 3.1768 | 0.1351 | 0.2379 | 0.4300 | [0.2334581560162901, 0.5743166246957696, 0.7216581459368632, 0.20160326710628743, 0.4731674616169526, 0.03319404005813106, 0.9018428560413293, 0.0, 0.0, 0.41478297422268023, nan, 0.0, 0.0, 0.0, 0.052963170942160985, 0.0, 0.0, 0.0, 0.0, 0.0, 0.59894913458142, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.9279366762373171, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5464788311274119, 0.7962333967694927, 0.912219415308276, 0.6438632550969516, 0.9340773879233616, 0.05361827943888036, 0.9643799472295514, nan, nan, 0.8744711263579188, nan, 0.0, 0.0, 0.0, 0.055689968029033095, 0.0, nan, 0.0, nan, 0.0, 0.6671748967145387, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.9279366762373171, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.9068 | 41.0 | 820 | 3.2244 | 0.1325 | 0.2339 | 0.4239 | [0.21458822630181915, 0.5577441338186324, 0.8451891491624225, 0.22359906411053612, 0.4186719360130825, 0.02433046028971531, 0.9142913231252454, 0.0, 0.0, 0.40097740746675214, nan, 0.0, 0.0, 0.0, 0.04993983948380955, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5757177295638835, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8097994049836554, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.615576662414288, 0.8027116868352787, 0.8871967064204014, 0.6412788852449106, 0.9354710263737294, 0.03934660590848909, 0.9600511213720316, nan, nan, 0.8584905660377359, nan, 0.0, 0.0, 0.0, 0.05439384774907111, 0.0, nan, 0.0, nan, 0.0, 0.6460259689159945, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8100969487646512, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.776 | 42.0 | 840 | 3.1907 | 0.1309 | 0.2346 | 0.4331 | [0.22651550705582682, 0.5506689512808488, 0.765441236306426, 0.22478240370403726, 0.4504349620052952, 0.026541688183882063, 0.9025046574208239, 0.0, 0.0, 0.39146078837896764, nan, 0.0, 0.0, 0.0, 0.0488441511504946, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5176636834667923, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8687714878093589, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6301576702280338, 0.8310016133032034, 0.8926694354186344, 0.6412788852449106, 0.9205040520916288, 0.04425274752053025, 0.9586631486367634, nan, nan, 0.8366495140080046, nan, 0.0, 0.0, 0.0, 0.0525504766842363, 0.0, nan, 0.0, nan, 0.0, 0.5945799724572103, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8687806081474755, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.8984 | 43.0 | 860 | 3.1816 | 0.1384 | 0.2382 | 0.4323 | [0.22788525946648805, 0.5629986363422624, 0.7739591348208943, 0.20712833038164374, 0.46555097477464885, 0.03189621537261022, 0.888850863183512, 0.0, 0.0, 0.4087266732429766, nan, 0.0, 0.0, 0.0, 0.04694527859006806, 0.0, nan, 0.0, 0.0, 0.0, 0.5750604281767956, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.9319231092084278, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5764132514750439, 0.8006609249047761, 0.9000673358068321, 0.6433947436033067, 0.9363142361924393, 0.058435070789775084, 0.9636790897097626, nan, nan, 0.8646941109205261, nan, 0.0, 0.0, 0.0, 0.05155678446959878, 0.0, nan, 0.0, nan, 0.0, 0.65527247688373, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.9323878160545475, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.504 | 44.0 | 880 | 3.2069 | 0.1334 | 0.2342 | 0.4242 | [0.21064409638306406, 0.5597251625729397, 0.8022601880620752, 0.2000478959811985, 0.4296942238677514, 0.03285552086290094, 0.9111122709953546, 0.0, 0.0, 0.4104417447388174, nan, 0.0, 0.0, 0.0, 0.10876163496560097, 0.0, 0.0, 0.0, 0.0, 0.0, 0.54348478997726, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8610202198170988, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5103452399936215, 0.8221381979486808, 0.8844987549654508, 0.6438632550969516, 0.9296739588700988, 0.0564125057874601, 0.9595426561125769, nan, nan, 0.8441395082904517, nan, 0.0, 0.0, 0.0, 0.12385149341858924, 0.0, nan, 0.0, nan, 0.0, 0.6230080661026952, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8618834410250219, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.5104 | 45.0 | 900 | 3.1914 | 0.1353 | 0.2353 | 0.4288 | [0.20801604675765414, 0.5592936073216008, 0.8500119552222585, 0.22430650085241916, 0.4459038240010842, 0.02321248350283363, 0.9097398021765796, 0.0, 0.0, 0.3957482697224862, nan, 0.0, 0.0, 0.0, 0.0915657322556077, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5683129055515501, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8642398174617745, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5937898660500718, 0.8176800198388926, 0.8836084761771339, 0.6412788852449106, 0.9247903686700707, 0.038859240847690296, 0.9580722295514512, nan, nan, 0.8451114922813036, nan, 0.0, 0.0, 0.0, 0.10734756185374003, 0.0, nan, 0.0, nan, 0.0, 0.6203029706866025, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8648386199366972, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 2.1051 | 46.0 | 920 | 3.1576 | 0.1313 | 0.2358 | 0.4312 | [0.2172020087256044, 0.5573826010588531, 0.7879493678894983, 0.23805623269552825, 0.45538869512581787, 0.022801613110570444, 0.8807856791431707, 0.0, 0.0, 0.3886508791757563, nan, 0.0, 0.0, 0.0, 0.06113372531282979, 0.0, 0.0, 0.0, 0.0, 0.0, 0.48994169659060194, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8914251530941548, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6011252192632754, 0.8116977020878205, 0.9004876197018244, 0.6412788852449106, 0.925118283599569, 0.03889985460275686, 0.959473944591029, nan, nan, 0.8454545454545455, nan, 0.0, 0.0, 0.0, 0.07007690313661108, 0.0, nan, 0.0, nan, 0.0, 0.6240901042691324, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8916871814521844, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.4532 | 47.0 | 940 | 3.1460 | 0.1300 | 0.2348 | 0.4265 | [0.2214450287175756, 0.5572135850453451, 0.8422500829300241, 0.21254065748060083, 0.42425625404642375, 0.03157980118424254, 0.8897939991612551, 0.0, 0.0, 0.3984132459468782, nan, 0.0, 0.0, 0.0, 0.056277212047065595, 0.0, 0.0, 0.0, 0.0, 0.0, 0.477008685190059, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8306655964241308, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.6006069606123425, 0.8053141483068675, 0.8950013331585916, 0.641430017984796, 0.9362673912025109, 0.056924239101298825, 0.9621949208443272, nan, nan, 0.8584905660377359, nan, 0.0, 0.0, 0.0, 0.06757107059535125, 0.0, nan, 0.0, nan, 0.0, 0.6239917371630926, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8310928912987565, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.4026 | 48.0 | 960 | 3.1488 | 0.1324 | 0.2349 | 0.4282 | [0.22014090719343432, 0.5675525213726254, 0.7892808479624818, 0.21346024136262315, 0.4472028923090872, 0.030869074749836727, 0.8905485941320294, 0.0, 0.0, 0.3923270572192794, nan, 0.0, 0.0, 0.0, 0.05784060041967585, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5539198756691418, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8697198801660048, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5571230664965715, 0.8209428489429939, 0.9005147347918239, 0.6433116205963698, 0.9242165175434487, 0.054901674098983846, 0.9610405672823219, nan, nan, 0.8554030874785592, nan, 0.0, 0.0, 0.0, 0.06470520464299087, 0.0, nan, 0.0, nan, 0.0, 0.631074168797954, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8701033525271241, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.8242 | 49.0 | 980 | 3.1640 | 0.1328 | 0.2361 | 0.4299 | [0.22131253285375674, 0.5697434900893898, 0.7924987357196045, 0.21230379974698355, 0.4575545239047404, 0.025656680524225872, 0.8851194090265129, 0.0, 0.0, 0.397265174702866, nan, 0.0, 0.0, 0.0, 0.055206031457168854, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5417714215059968, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.8897775215534184, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5727655078934779, 0.8169332750055031, 0.8994120544651775, 0.641679387005607, 0.924556143720429, 0.044715744328289106, 0.961604001759015, nan, nan, 0.8571183533447685, nan, 0.0, 0.0, 0.0, 0.061162475877761455, 0.0, nan, 0.0, nan, 0.0, 0.6465178044461932, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.8911412869462976, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
| 1.7663 | 50.0 | 1000 | 3.1757 | 0.1304 | 0.2321 | 0.4229 | [0.22150017755715537, 0.5590869674464826, 0.8364981896677761, 0.21143228725471633, 0.4199449932704533, 0.028304212146720555, 0.8896023646625641, 0.0, 0.0, 0.39826663958291014, nan, 0.0, 0.0, 0.0, 0.06262780865397885, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5293724129280428, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.7992381312177308, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] | [0.5812470100462446, 0.8245734777411526, 0.8791209287822161, 0.6412788852449106, 0.9244858762355366, 0.04943506266702407, 0.9595426561125769, nan, nan, 0.8407661520869067, nan, 0.0, 0.0, 0.0, 0.07189147152855785, 0.0, nan, 0.0, nan, 0.0, 0.622712964784576, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.7995359896699963, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
mariololo/taxi-v3
|
mariololo
| 2023-06-23T14:02:48Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T14:02:46Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.50 +/- 2.69
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="mariololo/taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
wesleyacheng/hate-speech-multilabel-classification-with-bert
|
wesleyacheng
| 2023-06-23T13:56:28Z | 245,375 | 2 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"distilbert",
"text-classification",
"en",
"dataset:ucberkeley-dlab/measuring-hate-speech",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-21T05:15:42Z |
---
license: apache-2.0
datasets:
- ucberkeley-dlab/measuring-hate-speech
language:
- en
metrics:
- f1
- accuracy
pipeline_tag: text-classification
widget:
- text: Yellow peril.
example_title: Race Hate Example
- text: Nietzsche said 'God is dead'.
example_title: Religion Hate Example
- text: Go back to where you came from.
example_title: Origin Hate Example
- text: You're being emotional.
example_title: Gender Hate Example
- text: I identify as a sandwich.
example_title: Sexuality Hate Example
- text: Old fart.
example_title: Age Hate Example
- text: Confined to a wheelchair.
example_title: Disability Hate Example
---
First posted on [Kaggle](https://www.kaggle.com/code/wesleyacheng/hate-speech-multilabel-classification-with-bert).
I've recently stumbled upon a very comprehensive dataset on measurement of hate speech from my alma mater, UC Berkeley. It aggregated social media comments from Youtube, Reddit, and Twitter.
The interesting thing about the dataset is the annotator's profile with attributes such as ideology, income, race, and etc. is included in the dataset. This is, unfortunately, uncommon in most social media dataset and so I was intrigued about this.
I also find the paper's idea of data perspectivism interesting as it argues that the disagreement of the annotator on the attributes of a hate speech is informative, rather than throwing it away.
Although, we are not leveraging the annotator's information in this model, I encourage you to explore the dataset and maybe leverage the annotator's information to make variations of this classifier.
Here I made a Hate Speech MultiLabel Classifier to classify independent targets of race, religion, origin, gender, sexuality, age, disability by doing transfer learning on [BERT](https://huggingface.co/datasets/ucberkeley-dlab/measuring-hate-speech) with the [UC Berkeley D-Lab's Hate Speech Dataset](https://huggingface.co/datasets/ucberkeley-dlab/measuring-hate-speech) from the paper [The Measuring Hate Speech Corpus: Leveraging Rasch Measurement Theory for Data Perspectivism](https://aclanthology.org/2022.nlperspectives-1.11.pdf).
|
heon98/my_awesome_pokemon_model
|
heon98
| 2023-06-23T13:50:10Z | 194 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:pokemon-classification",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-06-23T11:40:02Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- pokemon-classification
metrics:
- accuracy
model-index:
- name: my_awesome_pokemon_model
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: pokemon-classification
type: pokemon-classification
config: full
split: train
args: full
metrics:
- name: Accuracy
type: accuracy
value: 0.5852156057494866
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_pokemon_model
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the pokemon-classification dataset.
It achieves the following results on the evaluation set:
- Loss: 4.3447
- Accuracy: 0.5852
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 4.7732 | 1.0 | 61 | 4.7448 | 0.1992 |
| 4.443 | 2.0 | 122 | 4.4606 | 0.4897 |
| 4.2705 | 3.0 | 183 | 4.3447 | 0.5852 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
qiqiTony/pii-v1
|
qiqiTony
| 2023-06-23T13:46:31Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-23T13:33:42Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0.dev0
|
mariololo/q-FrozenLake-v1-4x4-noSlippery
|
mariololo
| 2023-06-23T13:44:18Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T13:44:15Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="mariololo/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
nordGARA/IA-LLAMA
|
nordGARA
| 2023-06-23T13:44:09Z | 101 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"question-answering",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-23T13:42:07Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: IA-LLAMA
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# IA-LLAMA
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.3820
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 1 | 5.6450 |
| No log | 2.0 | 2 | 5.4711 |
| No log | 3.0 | 3 | 5.3820 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.3
|
paumena/QA-Electra_Base
|
paumena
| 2023-06-23T13:37:37Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"electra",
"question-answering",
"generated_from_keras_callback",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-23T07:59:27Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: paumena/QA-Electra_Base
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# paumena/QA-Electra_Base
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.3170
- Epoch: 4
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
{'exact_match': 84.66414380321665, 'f1': 91.59502747403307}
## Training procedure
GPU V100 Standard RAM
2443s 439ms/step
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 27660, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
### Training results
| Train Loss | Epoch |
|:----------:|:-----:|
| 1.0689 | 0 |
| 0.6768 | 1 |
| 0.5085 | 2 |
| 0.3933 | 3 |
| 0.3170 | 4 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
isarth/roberta-news-chatgpt
|
isarth
| 2023-06-23T13:37:14Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-06-23T12:30:58Z |
---
tags:
- generated_from_trainer
datasets:
- tmp/cnn_clean_chatgpt_data/
metrics:
- accuracy
model-index:
- name: chatgpt-mlm
results:
- task:
name: Masked Language Modeling
type: fill-mask
dataset:
name: tmp/cnn_clean_chatgpt_data/
type: tmp/cnn_clean_chatgpt_data/
config: 1.0.0
split: train
args: 1.0.0
metrics:
- name: Accuracy
type: accuracy
value: 0.701455194792215
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# chatgpt-mlm
This model is a fine-tuned version of [](https://huggingface.co/) on the tmp/cnn_clean_chatgpt_data/ dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4969
- Accuracy: 0.7015
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 6
- num_epochs: 75.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:------:|:---------------:|:--------:|
| 7.2061 | 0.2 | 500 | 6.6958 | 0.1161 |
| 6.6051 | 0.4 | 1000 | 6.5527 | 0.1303 |
| 6.5016 | 0.6 | 1500 | 6.4720 | 0.1382 |
| 6.4189 | 0.8 | 2000 | 6.3796 | 0.1424 |
| 6.3648 | 1.0 | 2500 | 6.3224 | 0.1448 |
| 6.2787 | 1.2 | 3000 | 6.2787 | 0.1411 |
| 6.2583 | 1.4 | 3500 | 6.2467 | 0.1446 |
| 6.2211 | 1.6 | 4000 | 6.2162 | 0.1475 |
| 6.1897 | 1.8 | 4500 | 6.1933 | 0.1466 |
| 6.1625 | 2.0 | 5000 | 6.1704 | 0.1483 |
| 6.1412 | 2.2 | 5500 | 6.1527 | 0.1484 |
| 6.1062 | 2.4 | 6000 | 6.1296 | 0.1492 |
| 6.1003 | 2.6 | 6500 | 6.1275 | 0.1483 |
| 6.0944 | 2.8 | 7000 | 6.0983 | 0.1496 |
| 6.077 | 3.0 | 7500 | 6.0839 | 0.1509 |
| 6.0419 | 3.2 | 8000 | 6.0747 | 0.1504 |
| 6.0264 | 3.4 | 8500 | 6.0729 | 0.1506 |
| 6.0222 | 3.6 | 9000 | 6.0585 | 0.1504 |
| 6.0067 | 3.8 | 9500 | 6.0518 | 0.1500 |
| 6.0045 | 4.0 | 10000 | 6.0300 | 0.1504 |
| 5.9659 | 4.2 | 10500 | 6.0248 | 0.1504 |
| 5.9542 | 4.4 | 11000 | 6.0143 | 0.1512 |
| 5.9479 | 4.6 | 11500 | 5.9891 | 0.1514 |
| 5.9506 | 4.8 | 12000 | 5.9827 | 0.1517 |
| 5.9358 | 5.0 | 12500 | 5.9973 | 0.1509 |
| 5.9114 | 5.2 | 13000 | 5.9761 | 0.1505 |
| 5.9089 | 5.4 | 13500 | 5.9637 | 0.1516 |
| 5.9008 | 5.6 | 14000 | 5.9535 | 0.1515 |
| 5.9007 | 5.8 | 14500 | 5.9343 | 0.1530 |
| 5.8734 | 6.0 | 15000 | 5.9255 | 0.1532 |
| 5.8519 | 6.2 | 15500 | 5.9213 | 0.1527 |
| 5.8383 | 6.4 | 16000 | 5.9126 | 0.1513 |
| 5.8461 | 6.6 | 16500 | 5.9041 | 0.1525 |
| 5.8387 | 6.8 | 17000 | 5.8923 | 0.1517 |
| 5.831 | 7.0 | 17500 | 5.8782 | 0.1558 |
| 5.8003 | 7.2 | 18000 | 5.8660 | 0.1554 |
| 5.7832 | 7.4 | 18500 | 5.8508 | 0.1560 |
| 5.7902 | 7.6 | 19000 | 5.8495 | 0.1558 |
| 5.7707 | 7.8 | 19500 | 5.8376 | 0.1553 |
| 5.7638 | 8.0 | 20000 | 5.8289 | 0.1564 |
| 5.741 | 8.2 | 20500 | 5.8230 | 0.1574 |
| 5.7291 | 8.4 | 21000 | 5.8110 | 0.1574 |
| 5.7206 | 8.6 | 21500 | 5.8014 | 0.1575 |
| 5.6974 | 8.8 | 22000 | 5.7644 | 0.1605 |
| 5.6954 | 9.0 | 22500 | 5.7404 | 0.1638 |
| 5.6467 | 9.2 | 23000 | 5.7040 | 0.1668 |
| 5.6134 | 9.4 | 23500 | 5.6656 | 0.1738 |
| 5.5855 | 9.6 | 24000 | 5.6262 | 0.1787 |
| 5.5374 | 9.8 | 24500 | 5.5587 | 0.1883 |
| 5.4678 | 10.0 | 25000 | 5.4388 | 0.2009 |
| 5.3324 | 10.2 | 25500 | 5.2703 | 0.2203 |
| 5.1849 | 10.4 | 26000 | 5.0908 | 0.2434 |
| 5.0273 | 10.6 | 26500 | 4.9103 | 0.2657 |
| 4.8718 | 10.8 | 27000 | 4.7637 | 0.2844 |
| 4.7523 | 11.0 | 27500 | 4.6064 | 0.3023 |
| 4.5814 | 11.2 | 28000 | 4.4398 | 0.3220 |
| 4.4627 | 11.4 | 28500 | 4.3005 | 0.3376 |
| 4.3228 | 11.6 | 29000 | 4.1771 | 0.3520 |
| 4.1885 | 11.8 | 29500 | 4.0783 | 0.3632 |
| 4.0772 | 12.0 | 30000 | 3.9658 | 0.3765 |
| 3.9602 | 12.2 | 30500 | 3.8686 | 0.3880 |
| 3.8622 | 12.4 | 31000 | 3.7886 | 0.3968 |
| 3.7958 | 12.6 | 31500 | 3.6968 | 0.4074 |
| 3.7245 | 12.8 | 32000 | 3.6480 | 0.4129 |
| 3.6503 | 13.0 | 32500 | 3.5771 | 0.4204 |
| 3.5569 | 13.2 | 33000 | 3.5103 | 0.4286 |
| 3.5151 | 13.4 | 33500 | 3.4611 | 0.4358 |
| 3.4388 | 13.6 | 34000 | 3.4119 | 0.4410 |
| 3.41 | 13.8 | 34500 | 3.3570 | 0.4486 |
| 3.3447 | 14.0 | 35000 | 3.3158 | 0.4518 |
| 3.2678 | 14.2 | 35500 | 3.2717 | 0.4585 |
| 3.2395 | 14.4 | 36000 | 3.2234 | 0.4629 |
| 3.2033 | 14.6 | 36500 | 3.1723 | 0.4697 |
| 3.1739 | 14.8 | 37000 | 3.1409 | 0.4747 |
| 3.1467 | 15.0 | 37500 | 3.1042 | 0.4782 |
| 3.0736 | 15.2 | 38000 | 3.0561 | 0.4839 |
| 3.0468 | 15.4 | 38500 | 3.0275 | 0.4869 |
| 3.0105 | 15.6 | 39000 | 3.0051 | 0.4898 |
| 2.9828 | 15.8 | 39500 | 2.9689 | 0.4950 |
| 2.9523 | 16.0 | 40000 | 2.9481 | 0.4959 |
| 2.8951 | 16.2 | 40500 | 2.8918 | 0.5039 |
| 2.8614 | 16.4 | 41000 | 2.8734 | 0.5054 |
| 2.8422 | 16.6 | 41500 | 2.8487 | 0.5083 |
| 2.8184 | 16.8 | 42000 | 2.8223 | 0.5138 |
| 2.7806 | 17.0 | 42500 | 2.7965 | 0.5167 |
| 2.7356 | 17.2 | 43000 | 2.7596 | 0.5209 |
| 2.7357 | 17.4 | 43500 | 2.7407 | 0.5250 |
| 2.7015 | 17.6 | 44000 | 2.7135 | 0.5272 |
| 2.688 | 17.8 | 44500 | 2.6935 | 0.5289 |
| 2.6582 | 18.0 | 45000 | 2.6572 | 0.5342 |
| 2.6186 | 18.2 | 45500 | 2.6396 | 0.5357 |
| 2.6071 | 18.4 | 46000 | 2.6270 | 0.5377 |
| 2.5891 | 18.6 | 46500 | 2.6110 | 0.5407 |
| 2.558 | 18.8 | 47000 | 2.5874 | 0.5435 |
| 2.5521 | 19.0 | 47500 | 2.5540 | 0.5465 |
| 2.5086 | 19.2 | 48000 | 2.5296 | 0.5504 |
| 2.4933 | 19.4 | 48500 | 2.5199 | 0.5523 |
| 2.4924 | 19.6 | 49000 | 2.5037 | 0.5550 |
| 2.4633 | 19.8 | 49500 | 2.4792 | 0.5567 |
| 2.4426 | 20.0 | 50000 | 2.4724 | 0.5600 |
| 2.4106 | 20.2 | 50500 | 2.4396 | 0.5626 |
| 2.4103 | 20.4 | 51000 | 2.4259 | 0.5631 |
| 2.3783 | 20.6 | 51500 | 2.4072 | 0.5672 |
| 2.3712 | 20.8 | 52000 | 2.4055 | 0.5679 |
| 2.3616 | 21.0 | 52500 | 2.3781 | 0.5724 |
| 2.3274 | 21.2 | 53000 | 2.3627 | 0.5746 |
| 2.3133 | 21.4 | 53500 | 2.3586 | 0.5751 |
| 2.3076 | 21.6 | 54000 | 2.3207 | 0.5785 |
| 2.2991 | 21.8 | 54500 | 2.3152 | 0.5796 |
| 2.2831 | 22.0 | 55000 | 2.3001 | 0.5815 |
| 2.2461 | 22.2 | 55500 | 2.2944 | 0.5822 |
| 2.2467 | 22.4 | 56000 | 2.2849 | 0.5856 |
| 2.2199 | 22.6 | 56500 | 2.2776 | 0.5863 |
| 2.2279 | 22.8 | 57000 | 2.2577 | 0.5885 |
| 2.2048 | 23.0 | 57500 | 2.2566 | 0.5886 |
| 2.1704 | 23.2 | 58000 | 2.2453 | 0.5914 |
| 2.1682 | 23.4 | 58500 | 2.2314 | 0.5927 |
| 2.1592 | 23.6 | 59000 | 2.2097 | 0.5961 |
| 2.1547 | 23.8 | 59500 | 2.1984 | 0.5972 |
| 2.1558 | 24.0 | 60000 | 2.1866 | 0.5993 |
| 2.1189 | 24.2 | 60500 | 2.1675 | 0.6009 |
| 2.1088 | 24.4 | 61000 | 2.1613 | 0.6028 |
| 2.1164 | 24.6 | 61500 | 2.1531 | 0.6046 |
| 2.094 | 24.8 | 62000 | 2.1507 | 0.6041 |
| 2.0977 | 25.0 | 62500 | 2.1299 | 0.6063 |
| 2.0657 | 25.2 | 63000 | 2.1218 | 0.6071 |
| 2.051 | 25.4 | 63500 | 2.1233 | 0.6083 |
| 2.0482 | 25.6 | 64000 | 2.1069 | 0.6100 |
| 2.04 | 25.8 | 64500 | 2.0985 | 0.6120 |
| 2.0341 | 26.0 | 65000 | 2.0929 | 0.6128 |
| 2.0207 | 26.2 | 65500 | 2.0767 | 0.6151 |
| 2.0044 | 26.4 | 66000 | 2.0672 | 0.6162 |
| 2.0037 | 26.6 | 66500 | 2.0623 | 0.6159 |
| 2.0081 | 26.8 | 67000 | 2.0614 | 0.6164 |
| 1.9847 | 27.0 | 67500 | 2.0499 | 0.6186 |
| 1.9465 | 27.2 | 68000 | 2.0399 | 0.6200 |
| 1.9573 | 27.4 | 68500 | 2.0353 | 0.6210 |
| 1.9682 | 27.6 | 69000 | 2.0187 | 0.6227 |
| 1.9573 | 27.8 | 69500 | 2.0251 | 0.6229 |
| 1.9491 | 28.0 | 70000 | 2.0086 | 0.6245 |
| 1.903 | 28.2 | 70500 | 2.0067 | 0.6246 |
| 1.9152 | 28.4 | 71000 | 1.9929 | 0.6264 |
| 1.9188 | 28.6 | 71500 | 1.9857 | 0.6274 |
| 1.9232 | 28.8 | 72000 | 1.9796 | 0.6287 |
| 1.9011 | 29.0 | 72500 | 1.9791 | 0.6289 |
| 1.8733 | 29.2 | 73000 | 1.9700 | 0.6289 |
| 1.8731 | 29.4 | 73500 | 1.9584 | 0.6303 |
| 1.8812 | 29.6 | 74000 | 1.9573 | 0.6323 |
| 1.8674 | 29.8 | 74500 | 1.9501 | 0.6318 |
| 1.8572 | 30.0 | 75000 | 1.9454 | 0.6333 |
| 1.849 | 30.2 | 75500 | 1.9375 | 0.6352 |
| 1.8332 | 30.4 | 76000 | 1.9344 | 0.6343 |
| 1.8413 | 30.6 | 76500 | 1.9293 | 0.6340 |
| 1.8298 | 30.8 | 77000 | 1.9228 | 0.6371 |
| 1.8336 | 31.0 | 77500 | 1.9215 | 0.6372 |
| 1.8122 | 31.2 | 78000 | 1.9133 | 0.6387 |
| 1.8001 | 31.4 | 78500 | 1.9119 | 0.6383 |
| 1.7934 | 31.6 | 79000 | 1.9088 | 0.6387 |
| 1.8079 | 31.8 | 79500 | 1.8940 | 0.6417 |
| 1.8017 | 32.0 | 80000 | 1.8889 | 0.6410 |
| 1.7789 | 32.2 | 80500 | 1.8883 | 0.6423 |
| 1.7739 | 32.4 | 81000 | 1.8836 | 0.6419 |
| 1.7602 | 32.6 | 81500 | 1.8795 | 0.6433 |
| 1.7731 | 32.8 | 82000 | 1.8769 | 0.6439 |
| 1.7784 | 33.0 | 82500 | 1.8590 | 0.6467 |
| 1.7506 | 33.2 | 83000 | 1.8664 | 0.6447 |
| 1.7307 | 33.4 | 83500 | 1.8553 | 0.6472 |
| 1.748 | 33.6 | 84000 | 1.8523 | 0.6470 |
| 1.7285 | 33.8 | 84500 | 1.8397 | 0.6491 |
| 1.7426 | 34.0 | 85000 | 1.8321 | 0.6492 |
| 1.7128 | 34.2 | 85500 | 1.8220 | 0.6507 |
| 1.7155 | 34.4 | 86000 | 1.8487 | 0.6479 |
| 1.7143 | 34.6 | 86500 | 1.8267 | 0.6504 |
| 1.7197 | 34.8 | 87000 | 1.8368 | 0.6499 |
| 1.7043 | 35.0 | 87500 | 1.8128 | 0.6524 |
| 1.6931 | 35.2 | 88000 | 1.8212 | 0.6517 |
| 1.6873 | 35.4 | 88500 | 1.8110 | 0.6531 |
| 1.684 | 35.6 | 89000 | 1.8145 | 0.6529 |
| 1.6802 | 35.8 | 89500 | 1.8046 | 0.6537 |
| 1.6807 | 36.0 | 90000 | 1.8016 | 0.6550 |
| 1.6612 | 36.2 | 90500 | 1.7997 | 0.6539 |
| 1.6586 | 36.4 | 91000 | 1.8014 | 0.6537 |
| 1.658 | 36.6 | 91500 | 1.7938 | 0.6565 |
| 1.6623 | 36.8 | 92000 | 1.7776 | 0.6586 |
| 1.6618 | 37.0 | 92500 | 1.7884 | 0.6573 |
| 1.6453 | 37.2 | 93000 | 1.7871 | 0.6571 |
| 1.6462 | 37.4 | 93500 | 1.7781 | 0.6585 |
| 1.6353 | 37.6 | 94000 | 1.7808 | 0.6583 |
| 1.6507 | 37.8 | 94500 | 1.7666 | 0.6603 |
| 1.6383 | 38.0 | 95000 | 1.7624 | 0.6606 |
| 1.6299 | 38.2 | 95500 | 1.7653 | 0.6605 |
| 1.6085 | 38.4 | 96000 | 1.7523 | 0.6610 |
| 1.6155 | 38.6 | 96500 | 1.7521 | 0.6612 |
| 1.6106 | 38.8 | 97000 | 1.7634 | 0.6605 |
| 1.6201 | 39.0 | 97500 | 1.7461 | 0.6625 |
| 1.5835 | 39.2 | 98000 | 1.7505 | 0.6617 |
| 1.5885 | 39.4 | 98500 | 1.7477 | 0.6623 |
| 1.5988 | 39.6 | 99000 | 1.7445 | 0.6635 |
| 1.6013 | 39.8 | 99500 | 1.7407 | 0.6637 |
| 1.594 | 40.0 | 100000 | 1.7336 | 0.6656 |
| 1.5741 | 40.2 | 100500 | 1.7348 | 0.6637 |
| 1.5744 | 40.4 | 101000 | 1.7242 | 0.6653 |
| 1.5809 | 40.6 | 101500 | 1.7262 | 0.6661 |
| 1.5723 | 40.8 | 102000 | 1.7257 | 0.6665 |
| 1.5695 | 41.0 | 102500 | 1.7182 | 0.6664 |
| 1.5462 | 41.2 | 103000 | 1.7257 | 0.6660 |
| 1.5545 | 41.4 | 103500 | 1.7101 | 0.6686 |
| 1.5574 | 41.6 | 104000 | 1.7108 | 0.6684 |
| 1.5485 | 41.8 | 104500 | 1.7164 | 0.6665 |
| 1.5487 | 42.0 | 105000 | 1.7080 | 0.6694 |
| 1.5278 | 42.2 | 105500 | 1.7092 | 0.6686 |
| 1.5282 | 42.4 | 106000 | 1.7052 | 0.6690 |
| 1.5468 | 42.6 | 106500 | 1.7058 | 0.6704 |
| 1.5375 | 42.8 | 107000 | 1.7020 | 0.6689 |
| 1.5301 | 43.0 | 107500 | 1.6950 | 0.6710 |
| 1.5224 | 43.2 | 108000 | 1.6990 | 0.6702 |
| 1.5105 | 43.4 | 108500 | 1.6919 | 0.6715 |
| 1.5179 | 43.6 | 109000 | 1.6845 | 0.6724 |
| 1.518 | 43.8 | 109500 | 1.6838 | 0.6721 |
| 1.5191 | 44.0 | 110000 | 1.6877 | 0.6715 |
| 1.4984 | 44.2 | 110500 | 1.6923 | 0.6712 |
| 1.5051 | 44.4 | 111000 | 1.6842 | 0.6722 |
| 1.4993 | 44.6 | 111500 | 1.6768 | 0.6741 |
| 1.5035 | 44.8 | 112000 | 1.6817 | 0.6727 |
| 1.5047 | 45.0 | 112500 | 1.6728 | 0.6733 |
| 1.4788 | 45.2 | 113000 | 1.6825 | 0.6720 |
| 1.4841 | 45.4 | 113500 | 1.6770 | 0.6735 |
| 1.4863 | 45.6 | 114000 | 1.6588 | 0.6753 |
| 1.4859 | 45.8 | 114500 | 1.6681 | 0.6741 |
| 1.4839 | 46.0 | 115000 | 1.6658 | 0.6740 |
| 1.4633 | 46.2 | 115500 | 1.6601 | 0.6765 |
| 1.4725 | 46.4 | 116000 | 1.6587 | 0.6753 |
| 1.4703 | 46.6 | 116500 | 1.6643 | 0.6756 |
| 1.4763 | 46.8 | 117000 | 1.6583 | 0.6759 |
| 1.4825 | 47.0 | 117500 | 1.6488 | 0.6766 |
| 1.4496 | 47.2 | 118000 | 1.6490 | 0.6772 |
| 1.457 | 47.4 | 118500 | 1.6462 | 0.6778 |
| 1.4541 | 47.6 | 119000 | 1.6368 | 0.6799 |
| 1.4561 | 47.8 | 119500 | 1.6404 | 0.6778 |
| 1.4547 | 48.0 | 120000 | 1.6385 | 0.6790 |
| 1.4406 | 48.2 | 120500 | 1.6374 | 0.6799 |
| 1.4374 | 48.4 | 121000 | 1.6319 | 0.6799 |
| 1.4395 | 48.6 | 121500 | 1.6425 | 0.6787 |
| 1.4347 | 48.8 | 122000 | 1.6252 | 0.6814 |
| 1.4392 | 49.0 | 122500 | 1.6360 | 0.6801 |
| 1.439 | 49.2 | 123000 | 1.6233 | 0.6826 |
| 1.4223 | 49.4 | 123500 | 1.6262 | 0.6809 |
| 1.4292 | 49.6 | 124000 | 1.6292 | 0.6811 |
| 1.4237 | 49.8 | 124500 | 1.6227 | 0.6812 |
| 1.4241 | 50.0 | 125000 | 1.6230 | 0.6810 |
| 1.4118 | 50.2 | 125500 | 1.6256 | 0.6822 |
| 1.4225 | 50.4 | 126000 | 1.6251 | 0.6817 |
| 1.4122 | 50.6 | 126500 | 1.6178 | 0.6827 |
| 1.4081 | 50.8 | 127000 | 1.6190 | 0.6813 |
| 1.4058 | 51.0 | 127500 | 1.6183 | 0.6836 |
| 1.3985 | 51.2 | 128000 | 1.6199 | 0.6817 |
| 1.3967 | 51.4 | 128500 | 1.6168 | 0.6829 |
| 1.4113 | 51.6 | 129000 | 1.6123 | 0.6832 |
| 1.3876 | 51.8 | 129500 | 1.6078 | 0.6841 |
| 1.4027 | 52.0 | 130000 | 1.6028 | 0.6847 |
| 1.3939 | 52.2 | 130500 | 1.6081 | 0.6845 |
| 1.391 | 52.4 | 131000 | 1.6034 | 0.6849 |
| 1.3895 | 52.6 | 131500 | 1.6016 | 0.6850 |
| 1.3858 | 52.8 | 132000 | 1.6010 | 0.6847 |
| 1.3852 | 53.0 | 132500 | 1.5886 | 0.6862 |
| 1.3716 | 53.2 | 133000 | 1.5964 | 0.6862 |
| 1.3727 | 53.4 | 133500 | 1.5952 | 0.6875 |
| 1.3656 | 53.6 | 134000 | 1.6031 | 0.6850 |
| 1.3873 | 53.8 | 134500 | 1.5927 | 0.6867 |
| 1.3742 | 54.0 | 135000 | 1.5970 | 0.6858 |
| 1.3687 | 54.2 | 135500 | 1.5954 | 0.6863 |
| 1.359 | 54.4 | 136000 | 1.5854 | 0.6873 |
| 1.3696 | 54.6 | 136500 | 1.5902 | 0.6878 |
| 1.38 | 54.8 | 137000 | 1.5870 | 0.6871 |
| 1.3529 | 55.0 | 137500 | 1.5888 | 0.6879 |
| 1.3479 | 55.2 | 138000 | 1.5720 | 0.6889 |
| 1.3558 | 55.4 | 138500 | 1.5810 | 0.6877 |
| 1.3565 | 55.6 | 139000 | 1.5687 | 0.6909 |
| 1.351 | 55.8 | 139500 | 1.5762 | 0.6897 |
| 1.3698 | 56.0 | 140000 | 1.5785 | 0.6881 |
| 1.3388 | 56.2 | 140500 | 1.5767 | 0.6882 |
| 1.3433 | 56.4 | 141000 | 1.5752 | 0.6896 |
| 1.3505 | 56.6 | 141500 | 1.5754 | 0.6890 |
| 1.3429 | 56.8 | 142000 | 1.5772 | 0.6896 |
| 1.337 | 57.0 | 142500 | 1.5732 | 0.6900 |
| 1.3398 | 57.2 | 143000 | 1.5681 | 0.6904 |
| 1.3334 | 57.4 | 143500 | 1.5696 | 0.6900 |
| 1.3384 | 57.6 | 144000 | 1.5674 | 0.6908 |
| 1.33 | 57.8 | 144500 | 1.5592 | 0.6916 |
| 1.327 | 58.0 | 145000 | 1.5498 | 0.6924 |
| 1.3234 | 58.2 | 145500 | 1.5626 | 0.6910 |
| 1.3266 | 58.4 | 146000 | 1.5743 | 0.6893 |
| 1.3152 | 58.6 | 146500 | 1.5680 | 0.6912 |
| 1.3279 | 58.8 | 147000 | 1.5581 | 0.6919 |
| 1.3172 | 59.0 | 147500 | 1.5645 | 0.6917 |
| 1.3073 | 59.2 | 148000 | 1.5579 | 0.6924 |
| 1.307 | 59.4 | 148500 | 1.5468 | 0.6939 |
| 1.3164 | 59.6 | 149000 | 1.5519 | 0.6930 |
| 1.3037 | 59.8 | 149500 | 1.5628 | 0.6917 |
| 1.3171 | 60.0 | 150000 | 1.5489 | 0.6934 |
| 1.3035 | 60.2 | 150500 | 1.5499 | 0.6931 |
| 1.3109 | 60.4 | 151000 | 1.5608 | 0.6922 |
| 1.304 | 60.6 | 151500 | 1.5612 | 0.6915 |
| 1.3104 | 60.8 | 152000 | 1.5511 | 0.6933 |
| 1.3071 | 61.0 | 152500 | 1.5469 | 0.6935 |
| 1.2935 | 61.2 | 153000 | 1.5485 | 0.6942 |
| 1.2866 | 61.4 | 153500 | 1.5463 | 0.6940 |
| 1.2926 | 61.6 | 154000 | 1.5406 | 0.6956 |
| 1.3029 | 61.8 | 154500 | 1.5424 | 0.6945 |
| 1.2921 | 62.0 | 155000 | 1.5446 | 0.6944 |
| 1.2765 | 62.2 | 155500 | 1.5397 | 0.6953 |
| 1.275 | 62.4 | 156000 | 1.5469 | 0.6945 |
| 1.2909 | 62.6 | 156500 | 1.5427 | 0.6945 |
| 1.2869 | 62.8 | 157000 | 1.5388 | 0.6949 |
| 1.2883 | 63.0 | 157500 | 1.5375 | 0.6948 |
| 1.2673 | 63.2 | 158000 | 1.5423 | 0.6948 |
| 1.2754 | 63.4 | 158500 | 1.5360 | 0.6957 |
| 1.2772 | 63.6 | 159000 | 1.5331 | 0.6952 |
| 1.283 | 63.8 | 159500 | 1.5354 | 0.6955 |
| 1.2737 | 64.0 | 160000 | 1.5388 | 0.6961 |
| 1.2681 | 64.2 | 160500 | 1.5382 | 0.6952 |
| 1.2769 | 64.4 | 161000 | 1.5350 | 0.6958 |
| 1.2668 | 64.6 | 161500 | 1.5345 | 0.6956 |
| 1.2795 | 64.8 | 162000 | 1.5198 | 0.6984 |
| 1.2632 | 65.0 | 162500 | 1.5324 | 0.6965 |
| 1.2646 | 65.2 | 163000 | 1.5420 | 0.6963 |
| 1.2739 | 65.4 | 163500 | 1.5308 | 0.6972 |
| 1.2667 | 65.6 | 164000 | 1.5220 | 0.6978 |
| 1.26 | 65.8 | 164500 | 1.5283 | 0.6961 |
| 1.2714 | 66.0 | 165000 | 1.5235 | 0.6977 |
| 1.2652 | 66.2 | 165500 | 1.5270 | 0.6973 |
| 1.2554 | 66.4 | 166000 | 1.5356 | 0.6959 |
| 1.2666 | 66.6 | 166500 | 1.5231 | 0.6968 |
| 1.2634 | 66.8 | 167000 | 1.5170 | 0.6994 |
| 1.2485 | 67.0 | 167500 | 1.5205 | 0.6988 |
| 1.2397 | 67.2 | 168000 | 1.5263 | 0.6982 |
| 1.2416 | 67.4 | 168500 | 1.5133 | 0.7001 |
| 1.2615 | 67.6 | 169000 | 1.5150 | 0.6990 |
| 1.254 | 67.8 | 169500 | 1.5213 | 0.6990 |
| 1.2463 | 68.0 | 170000 | 1.5157 | 0.6995 |
| 1.2412 | 68.2 | 170500 | 1.5082 | 0.7000 |
| 1.248 | 68.4 | 171000 | 1.5168 | 0.6992 |
| 1.2468 | 68.6 | 171500 | 1.5187 | 0.6991 |
| 1.246 | 68.8 | 172000 | 1.5094 | 0.7001 |
| 1.2443 | 69.0 | 172500 | 1.5186 | 0.6984 |
| 1.2451 | 69.2 | 173000 | 1.5157 | 0.6988 |
| 1.2375 | 69.4 | 173500 | 1.5102 | 0.7002 |
| 1.2441 | 69.6 | 174000 | 1.5143 | 0.7000 |
| 1.2335 | 69.8 | 174500 | 1.5173 | 0.6985 |
| 1.2361 | 70.0 | 175000 | 1.5102 | 0.7001 |
| 1.23 | 70.2 | 175500 | 1.5155 | 0.6997 |
| 1.2401 | 70.4 | 176000 | 1.5027 | 0.7005 |
| 1.2346 | 70.6 | 176500 | 1.5123 | 0.6995 |
| 1.2306 | 70.8 | 177000 | 1.5151 | 0.6984 |
| 1.2333 | 71.0 | 177500 | 1.5125 | 0.7000 |
| 1.2248 | 71.2 | 178000 | 1.5199 | 0.6992 |
| 1.2385 | 71.4 | 178500 | 1.5108 | 0.7000 |
| 1.2278 | 71.6 | 179000 | 1.5092 | 0.7000 |
| 1.2278 | 71.8 | 179500 | 1.5163 | 0.6989 |
| 1.2242 | 72.0 | 180000 | 1.5056 | 0.7010 |
| 1.2208 | 72.2 | 180500 | 1.4968 | 0.7023 |
| 1.2216 | 72.4 | 181000 | 1.5097 | 0.7006 |
| 1.2271 | 72.6 | 181500 | 1.4988 | 0.7013 |
| 1.2302 | 72.8 | 182000 | 1.5141 | 0.6997 |
| 1.2268 | 73.0 | 182500 | 1.4996 | 0.7016 |
| 1.2258 | 73.2 | 183000 | 1.5016 | 0.7008 |
| 1.2244 | 73.4 | 183500 | 1.5032 | 0.7012 |
| 1.2117 | 73.6 | 184000 | 1.5097 | 0.7003 |
| 1.2279 | 73.8 | 184500 | 1.5058 | 0.7012 |
| 1.2274 | 74.0 | 185000 | 1.5030 | 0.7015 |
| 1.2117 | 74.2 | 185500 | 1.5086 | 0.7008 |
| 1.2223 | 74.4 | 186000 | 1.4998 | 0.7018 |
| 1.227 | 74.6 | 186500 | 1.5059 | 0.7014 |
| 1.2168 | 74.8 | 187000 | 1.4984 | 0.7011 |
| 1.2093 | 75.0 | 187500 | 1.5077 | 0.7018 |
### Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2
|
SMD00/QA_model-roberta
|
SMD00
| 2023-06-23T13:32:10Z | 110 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-23T13:10:11Z |
---
license: cc-by-4.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: QA_model-roberta
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# QA_model-roberta
This model is a fine-tuned version of [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5617
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 250 | 0.5069 |
| 0.4837 | 2.0 | 500 | 0.5113 |
| 0.4837 | 3.0 | 750 | 0.5617 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
rashmikamath01/qamodel-distillbert-squad-small
|
rashmikamath01
| 2023-06-23T13:30:09Z | 116 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-23T13:26:44Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: qamodel-distillbert-squad-small
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# qamodel-distillbert-squad-small
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 3.7360
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 50 | 4.2729 |
| No log | 2.0 | 100 | 3.8175 |
| No log | 3.0 | 150 | 3.7360 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Guilherme34/Jennifer_Gptneox_20b
|
Guilherme34
| 2023-06-23T13:28:40Z | 3 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-23T13:26:37Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
LarryAIDraw/oregairu_girl2
|
LarryAIDraw
| 2023-06-23T13:27:26Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T13:18:40Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/95127/oregairu-8-heroine-pack-lora
|
LarryAIDraw/eriri_v1.1_FB
|
LarryAIDraw
| 2023-06-23T13:27:14Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T13:19:20Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/95701/sawamura-spencer-eriri-5-in-onesaekanolorafb
|
LarryAIDraw/eikotsukimi
|
LarryAIDraw
| 2023-06-23T13:27:02Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T13:18:59Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/95600/eiko-tsukimi-paripi-koumei
|
LarryAIDraw/BocchiHD
|
LarryAIDraw
| 2023-06-23T13:26:25Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T13:18:02Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/95540/hitori-gotoh-bocchi-the-rock-or-character-lora-semestaai
|
LarryAIDraw/kitagawa_marin_v1-1
|
LarryAIDraw
| 2023-06-23T13:26:01Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T13:17:23Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/91455/kitagawa-marin-sono-bisque-doll-wa-koi-wo-suru
|
LarryAIDraw/augustmaid-000002
|
LarryAIDraw
| 2023-06-23T13:25:50Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T13:16:59Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/7398/august-von-parseval-maid
|
aarnphm/opt-6-7b-quotes
|
aarnphm
| 2023-06-23T13:18:17Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-23T13:18:16Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
getrajeev03/flan-t5-base-samsum
|
getrajeev03
| 2023-06-23T13:16:15Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:samsum",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-21T07:45:33Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
model-index:
- name: flan-t5-base-samsum
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: samsum
type: samsum
config: samsum
split: test
args: samsum
metrics:
- name: Rouge1
type: rouge
value: 46.7348
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# flan-t5-base-samsum
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the samsum dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3861
- Rouge1: 46.7348
- Rouge2: 23.2044
- Rougel: 39.1916
- Rougelsum: 43.1409
- Gen Len: 17.1880
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 1.4378 | 1.0 | 1842 | 1.3861 | 46.7348 | 23.2044 | 39.1916 | 43.1409 | 17.1880 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1
- Datasets 2.13.1
- Tokenizers 0.11.0
|
romankovsv/test2
|
romankovsv
| 2023-06-23T13:05:54Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-20T20:06:09Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
natope/mT5-tfidf-10pass-all-questions-QA-22-06-2023-without-ams-with-nonfactual
|
natope
| 2023-06-23T13:04:33Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-23T09:12:59Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mT5-tfidf-10pass-all-questions-QA-22-06-2023-without-ams-with-nonfactual
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mT5-tfidf-10pass-all-questions-QA-22-06-2023-without-ams-with-nonfactual
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0171
- Rouge1: 0.1497
- Rouge2: 0.0386
- Rougel: 0.1189
- Rougelsum: 0.1189
- Gen Len: 18.9316
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 2.6643 | 1.0 | 7356 | 2.0955 | 0.1434 | 0.0364 | 0.115 | 0.1148 | 18.7652 |
| 2.5667 | 2.0 | 14712 | 2.0301 | 0.1494 | 0.0387 | 0.1188 | 0.1187 | 18.9123 |
| 2.5061 | 3.0 | 22068 | 2.0171 | 0.1497 | 0.0386 | 0.1189 | 0.1189 | 18.9316 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
openmmlab/upernet-swin-small
|
openmmlab
| 2023-06-23T13:00:02Z | 3,427 | 5 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"upernet",
"vision",
"image-segmentation",
"en",
"arxiv:1807.10221",
"arxiv:2103.14030",
"license:mit",
"endpoints_compatible",
"region:us"
] |
image-segmentation
| 2023-01-13T14:33:22Z |
---
language: en
license: mit
tags:
- vision
- image-segmentation
model_name: openmmlab/upernet-swin-small
---
# UperNet, Swin Transformer small-sized backbone
UperNet framework for semantic segmentation, leveraging a Swin Transformer backbone. UperNet was introduced in the paper [Unified Perceptual Parsing for Scene Understanding](https://arxiv.org/abs/1807.10221) by Xiao et al.
Combining UperNet with a Swin Transformer backbone was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030).
Disclaimer: The team releasing UperNet + Swin Transformer did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) and a Pyramid Pooling Module (PPM).
Any visual backbone can be plugged into the UperNet framework. The framework predicts a semantic label per pixel.
## Intended uses & limitations
You can use the raw model for semantic segmentation. See the [model hub](https://huggingface.co/models?search=openmmlab/upernet) to look for
fine-tuned versions (with various backbones) on a task that interests you.
### How to use
For code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/upernet#transformers.UperNetForSemanticSegmentation).
|
rashmikamath01/summarizer-small-500
|
rashmikamath01
| 2023-06-23T12:39:52Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:billsum",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-23T12:37:32Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- billsum
metrics:
- rouge
model-index:
- name: summarizer-small-500
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: billsum
type: billsum
config: default
split: train[:500]
args: default
metrics:
- name: Rouge1
type: rouge
value: 0.1498
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# summarizer-small-500
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the billsum dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5741
- Rouge1: 0.1498
- Rouge2: 0.0801
- Rougel: 0.129
- Rougelsum: 0.1289
- Gen Len: 19.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 50 | 2.7400 | 0.1519 | 0.0812 | 0.1298 | 0.1291 | 19.0 |
| No log | 2.0 | 100 | 2.5741 | 0.1498 | 0.0801 | 0.129 | 0.1289 | 19.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
DionnisB/NOVA
|
DionnisB
| 2023-06-23T12:35:49Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T11:22:35Z |
---
license: creativeml-openrail-m
---
|
manetov/ControlNet_qrcode
|
manetov
| 2023-06-23T12:30:04Z | 0 | 0 |
diffusers
|
[
"diffusers",
"graph-ml",
"region:us"
] |
graph-ml
| 2023-06-23T12:25:55Z |
---
library_name: diffusers
pipeline_tag: graph-ml
---
|
Wade007/colab
|
Wade007
| 2023-06-23T12:23:24Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T12:09:48Z |
---
license: creativeml-openrail-m
---
|
HarshV9/finetuning-sentiment-model-8-labels
|
HarshV9
| 2023-06-23T12:21:51Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-22T16:07:12Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: finetuning-sentiment-model-8-labels
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetuning-sentiment-model-8-labels
This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 1.1854
- eval_accuracy: 0.5598
- eval_f1: 0.5598
- eval_runtime: 190.081
- eval_samples_per_second: 198.205
- eval_steps_per_second: 6.197
- epoch: 2.88
- step: 13550
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Framework versions
- Transformers 4.30.2
- Pytorch 1.13.1+cu116
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Rajashekhar03/autotrain-sampledata-69267137750
|
Rajashekhar03
| 2023-06-23T12:14:32Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"deberta",
"text-classification",
"autotrain",
"en",
"dataset:Rajashekhar03/autotrain-data-sampledata",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-23T12:13:20Z |
---
tags:
- autotrain
- text-classification
language:
- en
widget:
- text: "I love AutoTrain"
datasets:
- Rajashekhar03/autotrain-data-sampledata
co2_eq_emissions:
emissions: 0.04226297716010436
---
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 69267137750
- CO2 Emissions (in grams): 0.0423
## Validation Metrics
- Loss: 0.495
- Accuracy: 1.000
- Macro F1: 1.000
- Micro F1: 1.000
- Weighted F1: 1.000
- Macro Precision: 1.000
- Micro Precision: 1.000
- Weighted Precision: 1.000
- Macro Recall: 1.000
- Micro Recall: 1.000
- Weighted Recall: 1.000
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/Rajashekhar03/autotrain-sampledata-69267137750
```
Or Python API:
```
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("Rajashekhar03/autotrain-sampledata-69267137750", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("Rajashekhar03/autotrain-sampledata-69267137750", use_auth_token=True)
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)
```
|
gowthamijatapati/autotrain-ai-training-session-69260137747
|
gowthamijatapati
| 2023-06-23T11:54:00Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"deberta",
"text-classification",
"autotrain",
"en",
"dataset:gowthamijatapati/autotrain-data-ai-training-session",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-23T11:53:30Z |
---
tags:
- autotrain
- text-classification
language:
- en
widget:
- text: "I love AutoTrain"
datasets:
- gowthamijatapati/autotrain-data-ai-training-session
co2_eq_emissions:
emissions: 0.01929809783216031
---
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 69260137747
- CO2 Emissions (in grams): 0.0193
## Validation Metrics
- Loss: 1.039
- Accuracy: 0.333
- Macro F1: 0.167
- Micro F1: 0.333
- Weighted F1: 0.167
- Macro Precision: 0.111
- Micro Precision: 0.333
- Weighted Precision: 0.111
- Macro Recall: 0.333
- Micro Recall: 0.333
- Weighted Recall: 0.333
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/gowthamijatapati/autotrain-ai-training-session-69260137747
```
Or Python API:
```
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("gowthamijatapati/autotrain-ai-training-session-69260137747", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("gowthamijatapati/autotrain-ai-training-session-69260137747", use_auth_token=True)
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)
```
|
DionnisB/MOVA
|
DionnisB
| 2023-06-23T11:48:34Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T11:27:53Z |
---
license: creativeml-openrail-m
---
|
piotrtrochim/action_from_text_model
|
piotrtrochim
| 2023-06-23T11:46:39Z | 101 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-23T11:23:30Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
model-index:
- name: action_from_text_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.93076
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# action_from_text_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2310
- Accuracy: 0.9308
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.231 | 1.0 | 1563 | 0.1863 | 0.9277 |
| 0.1518 | 2.0 | 3126 | 0.2310 | 0.9308 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
jasscr/debertav3-finetuned-squad
|
jasscr
| 2023-06-23T11:40:30Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"deberta-v2",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:mit",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-23T08:18:09Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: debertav3-finetuned-squad
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# debertav3-finetuned-squad
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the squad dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Angel3245/PHS-BERT-finetuned-MentalFAQ
|
Angel3245
| 2023-06-23T11:16:14Z | 0 | 0 | null |
[
"license:gpl-3.0",
"region:us"
] | null | 2023-06-23T11:00:52Z |
---
license: gpl-3.0
---
Aplicación de técnicas de aprendizaje profundo al desarrollo de un bot conversacional para contribuír a la mejora de la salud mental
=======
# Proyecto
https://github.com/Angel3245/mental_semanticbot
|
Jacobolus/Basketball.pdf
|
Jacobolus
| 2023-06-23T11:14:21Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-06-23T11:13:08Z |
create a poster about basketball
|
elsliew/autotrain-skillsync2-69166137722
|
elsliew
| 2023-06-23T10:58:06Z | 406 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"deberta",
"text-classification",
"autotrain",
"en",
"dataset:elsliew/autotrain-data-skillsync2",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-23T10:56:13Z |
---
tags:
- autotrain
- text-classification
language:
- en
widget:
- text: "I love AutoTrain"
datasets:
- elsliew/autotrain-data-skillsync2
co2_eq_emissions:
emissions: 0.3593924337756782
---
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 69166137722
- CO2 Emissions (in grams): 0.3594
## Validation Metrics
- Loss: 0.884
- Accuracy: 0.685
- Macro F1: 0.643
- Micro F1: 0.685
- Weighted F1: 0.677
- Macro Precision: 0.677
- Micro Precision: 0.685
- Weighted Precision: 0.689
- Macro Recall: 0.642
- Micro Recall: 0.685
- Weighted Recall: 0.685
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/elsliew/autotrain-skillsync2-69166137722
```
Or Python API:
```
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("elsliew/autotrain-skillsync2-69166137722", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("elsliew/autotrain-skillsync2-69166137722", use_auth_token=True)
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)
```
|
lflo14/super-cool-model
|
lflo14
| 2023-06-23T10:56:18Z | 0 | 0 |
keras
|
[
"keras",
"en",
"dataset:OpenAssistant/oasst1",
"dataset:fka/awesome-chatgpt-prompts",
"license:apache-2.0",
"region:us"
] | null | 2023-06-22T21:04:32Z |
---
license: apache-2.0
datasets:
- OpenAssistant/oasst1
- fka/awesome-chatgpt-prompts
language:
- en
metrics:
- code_eval
- bertscore
- accuracy
library_name: keras
---
|
mkhan149/output.txt
|
mkhan149
| 2023-06-23T10:55:20Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"fill-mask",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-06-23T08:00:57Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: mkhan149/output.txt
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# mkhan149/output.txt
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.5283
- Validation Loss: 1.2025
- Epoch: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -446, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 1.5283 | 1.2025 | 0 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.11.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
adkhamboy/llm-7b_v2
|
adkhamboy
| 2023-06-23T10:52:33Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-23T10:52:32Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
Vecc3nz/dqn-SpaceInvadersNoFrameskip-v4
|
Vecc3nz
| 2023-06-23T10:40:04Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T10:39:33Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 430.50 +/- 136.32
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Vecc3nz -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Vecc3nz -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Vecc3nz
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 50000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 50000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
izumi-lab/llama-7b-japanese-lora-v0-5ep
|
izumi-lab
| 2023-06-23T10:33:45Z | 0 | 3 | null |
[
"llama",
"causal-lm",
"ja",
"dataset:izumi-lab/llm-japanese-dataset",
"license:cc-by-sa-4.0",
"region:us"
] | null | 2023-06-17T06:02:27Z |
---
license: cc-by-sa-4.0
datasets:
- izumi-lab/llm-japanese-dataset
language:
- ja
tags:
- llama
- causal-lm
---
This repo contains a low-rank adapter for LLaMA-7b
fit on the [llm-japanese-dataset](https://github.com/masanorihirano/llm-japanese-dataset) dataset.
This version of the weights was trained with the following hyperparameters:
- Epochs: 5
- Batch size: 128
- Cutoff length: 256
- Learning rate: 3e-4
- Lora _r_: 4
- Lora target modules: q_proj, v_proj
```python
import torch
from transformers import LlamaForCausalLM, LlamaTokenizer
from peft import PeftModel
base_model = "decapoda-research/llama-7b-hf"
# Please note that the special license of decapoda-research/llama-7b-hf is applied.
model = LlamaForCausalLM.from_pretrained(base_model, torch_dtype=torch.float16)
tokenizer = LlamaTokenizer.from_pretrained(base_model)
model = PeftModel.from_pretrained(
model,
"izumi-lab/llama-7b-japanese-lora-v0",
torch_dtype=torch.float16,
)
```
To see more latest information, please go to [llm.msuzuki.me](https://llm.msuzuki.me).
## Details
- Japanese Paper: [https://jxiv.jst.go.jp/index.php/jxiv/preprint/view/422](https://jxiv.jst.go.jp/index.php/jxiv/preprint/view/422)
- English Paper:
- GitHub: [https://github.com/retarfi/jallm]
- Website: [llm.msuzuki.me](https://llm.msuzuki.me).
Citation:
```
@preprint{Suzuki2023-llmj,
title={{日本語インストラクションデータを用いた対話可能な日本語大規模言語モデルのLoRAチューニング}},
author={鈴木 雅弘 and 平野 正徳 and 坂地 泰紀},
doi={10.51094/jxiv.422},
archivePrefix={Jxiv},
year={2023}
}
```
If you have any inquiries, such as joint research, data provision, various types of support, please email to izumi-llm@socsim.org .
|
Shubham09/falcon_medical
|
Shubham09
| 2023-06-23T10:32:12Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-23T10:26:12Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0.dev0
|
KJH97/my_awesome_qa_model
|
KJH97
| 2023-06-23T10:30:09Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-23T10:12:20Z |
---
license: cc-by-4.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: my_awesome_qa_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_qa_model
This model is a fine-tuned version of [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5920
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 250 | 0.5114 |
| 0.4791 | 2.0 | 500 | 0.5327 |
| 0.4791 | 3.0 | 750 | 0.5920 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
cointegrated/rubert-base-cased-dp-paraphrase-detection
|
cointegrated
| 2023-06-23T10:19:25Z | 134 | 4 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bert",
"text-classification",
"sentence-similarity",
"ru",
"dataset:merionum/ru_paraphraser",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2022-03-02T23:29:05Z |
---
language: ["ru"]
tags:
- sentence-similarity
- text-classification
datasets:
- merionum/ru_paraphraser
---
This is a version of paraphrase detector by DeepPavlov ([details in the documentation](http://docs.deeppavlov.ai/en/master/features/overview.html#ranking-model-docs)) ported to the `Transformers` format.
All credit goes to the authors of DeepPavlov.
The model has been trained on the dataset from http://paraphraser.ru/.
It classifies texts as paraphrases (class 1) or non-paraphrases (class 0).
```python
import torch
from transformers import AutoModelForSequenceClassification, BertTokenizer
model_name = 'cointegrated/rubert-base-cased-dp-paraphrase-detection'
model = AutoModelForSequenceClassification.from_pretrained(model_name).cuda()
tokenizer = BertTokenizer.from_pretrained(model_name)
def compare_texts(text1, text2):
batch = tokenizer(text1, text2, return_tensors='pt').to(model.device)
with torch.inference_mode():
proba = torch.softmax(model(**batch).logits, -1).cpu().numpy()
return proba[0] # p(non-paraphrase), p(paraphrase)
print(compare_texts('Сегодня на улице хорошая погода', 'Сегодня на улице отвратительная погода'))
# [0.7056226 0.2943774]
print(compare_texts('Сегодня на улице хорошая погода', 'Отличная погодка сегодня выдалась'))
# [0.16524374 0.8347562 ]
```
P.S. In the DeepPavlov repository, the tokenizer uses `max_seq_length=64`.
This model, however, uses `model_max_length=512`.
Therefore, the results on long texts may be inadequate.
|
ngonidzashe/jd_predictor
|
ngonidzashe
| 2023-06-23T10:10:17Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-23T09:06:07Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0.dev0
|
dhiruHF/falcon7b-FT-email2
|
dhiruHF
| 2023-06-23T10:08:06Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-23T10:08:05Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
Pranjal-666/taxi
|
Pranjal-666
| 2023-06-23T10:07:33Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T10:07:31Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="Pranjal-666/taxi", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
jojoUla/bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-16
|
jojoUla
| 2023-06-23T09:56:26Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"fill-mask",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-05-01T13:40:28Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-16
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-16
This model is a fine-tuned version of [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 6.0621
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.6621 | 1.0 | 1 | 1.5158 |
| 2.3951 | 2.0 | 2 | 1.4433 |
| 3.5547 | 3.0 | 3 | 0.5852 |
| 1.2934 | 4.0 | 4 | 0.0264 |
| 1.0317 | 5.0 | 5 | 0.0003 |
| 1.0012 | 6.0 | 6 | 2.3232 |
| 2.1186 | 7.0 | 7 | 0.0290 |
| 0.8258 | 8.0 | 8 | 1.9368 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Pranjal-666/q-FrozenLake-v1-4x4-noSlippery
|
Pranjal-666
| 2023-06-23T09:55:20Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T09:55:15Z |
---
tags:
- FrozenLake-v1-4x4
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4
type: FrozenLake-v1-4x4
metrics:
- type: mean_reward
value: 0.45 +/- 0.50
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="Pranjal-666/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
jojoUla/bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-15
|
jojoUla
| 2023-06-23T09:36:43Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"fill-mask",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-05-01T13:28:01Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-15
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-15
This model is a fine-tuned version of [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9209
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.704 | 1.0 | 1 | 3.6799 |
| 1.5679 | 2.0 | 2 | 2.3616 |
| 2.8253 | 3.0 | 3 | 3.3474 |
| 1.0532 | 4.0 | 4 | 0.0082 |
| 1.1286 | 5.0 | 5 | 1.8183 |
| 1.5832 | 6.0 | 6 | 1.0919 |
| 0.9621 | 7.0 | 7 | 0.6262 |
| 1.1494 | 8.0 | 8 | 0.0290 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Chy084/my_awesome_eli5_clm-model
|
Chy084
| 2023-06-23T09:35:41Z | 164 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-23T07:22:26Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_clm-model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_clm-model
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.7181
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.8802 | 1.0 | 1131 | 3.7365 |
| 3.7765 | 2.0 | 2262 | 3.7214 |
| 3.7424 | 3.0 | 3393 | 3.7181 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
alaeddinehamroun/distilbert-base-uncased-finetunde-emotion
|
alaeddinehamroun
| 2023-06-23T09:33:47Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-23T09:08:57Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetunde-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9215
- name: F1
type: f1
value: 0.9217368692620141
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetunde-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2251
- Accuracy: 0.9215
- F1: 0.9217
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8304 | 1.0 | 250 | 0.3266 | 0.9005 | 0.8970 |
| 0.2538 | 2.0 | 500 | 0.2251 | 0.9215 | 0.9217 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
BerserkerMother/q-FrozenLake-v1-4x4-noSlippery
|
BerserkerMother
| 2023-06-23T09:29:33Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-22T09:22:34Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="BerserkerMother/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
|
antoniogosling/How-Do-I-Import-Apple-Mail-Folders-Into-Outlook
|
antoniogosling
| 2023-06-23T09:20:08Z | 0 | 0 | null |
[
"Convert MBOX file into PST format",
"en",
"region:us"
] | null | 2023-06-23T09:14:03Z |
---
language:
- en
tags:
- Convert MBOX file into PST format
---
<h1>How Do I Import Apple Mail Folders Into Outlook?</h1>
Apple Mail is the email service in several Apple products like MacBook, macOS systems, iPhone, iPad, etc. It provides threaded messaging features that allow the user to reply to the messages directly without starting a new email creation. The messages are arranged as conversations and clicking on a message will bring up the entire discussion.
If you are going to buy a new Windows device and want to move the email to a new platform, consider changing the email to a Windows-supported application like Outlook. You need to transfer files from Apple Mail to Outlook using <a href="https://www.bitrecover.com/mbox/outlook-pst/">MBOX to PST converter</a>.
<h2>Reason To Open Apple Mail Folders In Outlook</h2>
<ul><li>Apple Mail is not good for archiving emails, which is why sometimes the archived emails show up in the inbox folders.</li>
<li>Apple Mail does not offer an email forwarding feature, making it difficult for users to work with.</li>
<li>There are no new updates in recent years, while other email clients like Outlook are fully equipped with new updated features and enhanced privacy.</li>
<li>According to the study, Outlook is one of the safest and most secure email clients compared to others.</li>
</ul>
<h2>How To Import Apple Mail Folders Into Outlook?</h2>
It's not good, but actually, there is no official solution to complete the migration. So we recommend you opt for the <a href="https://www.bitrecover.com/mbox-converter/">MBOX converter</a> to make the process easier and more precise. This software development is completed with strong coding to bring safe output with no challenges.
<ul><li>Install MBOX Converter on your Windows computer and click on it.</li>
<li>Browse MBOX files and add them to the software interface.</li>
<li>Click on the PST option to see the different export options.</li>
<li>Finally, browse the path required for the output and click "Convert" to get the output immediately</li>.</ul>
<h3>Why Is Professional Tool The Best Decision?</h3>
<ul><li>It retained the same mailbox data structure as the original. In addition, the <a href="https://www.bitrecover.com/pst-converter/">PST converter</a> offers advanced security to prevent changes to the input data.</li>
<li>This software is very easy to use without having to acquire extensive technical knowledge.</li>
<li>You can also use a filter feature to convert specific data by date range, subject, sender, and recipient and also skip spam files.</li>
<li>There is no need to download another wizard to complete the solution.</li>
</ul>
<h4>The Verge</h4>
In this informative guide, we have shared the best solution to import Apple mail folders to Outlook. This is one of the most frequently asked questions from Mac Outlook users. In this post, we have shared a very simple technique to help you import Apple mail folders to Outlook in a few clicks. From now on, users will not have any problems during the conversion process, saving time and energy. Now the question has been fully resolved here. If you have any other questions, you can contact our live technical support anytime, anywhere to get a solution.
|
jojoUla/bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-14
|
jojoUla
| 2023-06-23T09:18:59Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"fill-mask",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-04-30T08:42:16Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-14
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-14
This model is a fine-tuned version of [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9961
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.6369 | 1.0 | 1 | 1.2944 |
| 3.0519 | 2.0 | 2 | 0.5090 |
| 2.2117 | 3.0 | 3 | 0.5746 |
| 1.089 | 4.0 | 4 | 1.1467 |
| 1.0017 | 5.0 | 5 | 2.2230 |
| 0.6632 | 6.0 | 6 | 4.0928 |
| 1.5898 | 7.0 | 7 | 2.4577 |
| 2.0795 | 8.0 | 8 | 1.0336 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
jojoUla/bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-13
|
jojoUla
| 2023-06-23T08:56:35Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"fill-mask",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-04-30T08:30:07Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-13
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-13
This model is a fine-tuned version of [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1273
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.1428 | 1.0 | 1 | 1.5195 |
| 2.1681 | 2.0 | 2 | 1.9558 |
| 2.6919 | 3.0 | 3 | 1.6578 |
| 0.8728 | 4.0 | 4 | 0.2374 |
| 0.7828 | 5.0 | 5 | 0.2211 |
| 1.0572 | 6.0 | 6 | 0.7112 |
| 1.6896 | 7.0 | 7 | 0.1832 |
| 1.1446 | 8.0 | 8 | 0.8925 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
heon98/my_awesome_qa_model
|
heon98
| 2023-06-23T08:55:36Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-23T05:44:19Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: my_awesome_qa_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_qa_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6203
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 250 | 1.9706 |
| 2.5663 | 2.0 | 500 | 1.6454 |
| 2.5663 | 3.0 | 750 | 1.6203 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Noopy/train_model_yonsei
|
Noopy
| 2023-06-23T08:47:29Z | 191 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-06-22T16:49:44Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: train_model_yonsei
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: dataset
split: test
args: dataset
metrics:
- name: Accuracy
type: accuracy
value: 0.87
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# train_model_yonsei
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5148
- Accuracy: 0.87
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.5711 | 0.98 | 11 | 1.4796 | 0.69 |
| 1.3855 | 1.96 | 22 | 1.2302 | 0.74 |
| 1.1544 | 2.93 | 33 | 1.0229 | 0.77 |
| 0.9292 | 4.0 | 45 | 0.8371 | 0.8 |
| 0.7715 | 4.98 | 56 | 0.7186 | 0.84 |
| 0.6521 | 5.96 | 67 | 0.6353 | 0.85 |
| 0.5736 | 6.93 | 78 | 0.5895 | 0.86 |
| 0.4745 | 8.0 | 90 | 0.5891 | 0.85 |
| 0.4361 | 8.98 | 101 | 0.5370 | 0.87 |
| 0.4431 | 9.78 | 110 | 0.5148 | 0.87 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
c72599/q-FrozenLake-v1-4x4-noSlippery
|
c72599
| 2023-06-23T08:43:29Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-23T08:43:27Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="c72599/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
seyon0924/my_awesome_albert_clm-model
|
seyon0924
| 2023-06-23T08:42:57Z | 162 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-22T14:17:45Z |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: my_awesome_albert_clm-model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_albert_clm-model
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3143
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 27 | 1.5941 |
| No log | 2.0 | 54 | 1.3638 |
| No log | 3.0 | 81 | 1.3143 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
TheBloke/wizardLM-7B-GGML
|
TheBloke
| 2023-06-23T08:33:56Z | 0 | 157 | null |
[
"license:other",
"region:us"
] | null | 2023-04-26T07:16:54Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# WizardLM's WizardLM 7B GGML
These files are GGML format model files for [WizardLM's WizardLM 7B](https://huggingface.co/WizardLM/WizardLM-7B-V1.0).
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [ParisNeo/GPT4All-UI](https://github.com/ParisNeo/gpt4all-ui)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/wizardLM-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/wizardLM-7B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/wizardLM-7B-HF)
<!-- compatibility_ggml start -->
## Compatibility
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
They should be compatible with all current UIs and libraries that use llama.cpp, such as those listed at the top of this README.
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
These new quantisation methods are only compatible with llama.cpp as of June 6th, commit `2d43387`.
They will NOT be compatible with koboldcpp, text-generation-ui, and other UIs and libraries yet. Support is expected to come over the next few days.
## Explanation of the new k-quant methods
**Note**: k-quants are currently not supported for this model, as it uses an unusual Vocab size which k-quant does not currently support.
This is being looked at by the llama.cpp team and should be resolved in the future.
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| wizardLM-7B.ggmlv3.q4_0.bin | q4_0 | 4 | 3.79 GB | 6.29 GB | Original llama.cpp quant method, 4-bit. |
| wizardLM-7B.ggmlv3.q4_1.bin | q4_1 | 4 | 4.21 GB | 6.71 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| wizardLM-7B.ggmlv3.q5_0.bin | q5_0 | 5 | 4.63 GB | 7.13 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| wizardLM-7B.ggmlv3.q5_1.bin | q5_1 | 5 | 5.06 GB | 7.56 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| wizardLM-7B.ggmlv3.q8_0.bin | q8_0 | 8 | 7.16 GB | 9.66 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 10 -ngl 32 -m wizardLM-7B.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
```
Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: Oscar Rangel, Eugene Pentland, Talal Aujan, Cory Kujawski, Luke, Asp the Wyvern, Ai Maven, Pyrater, Alps Aficionado, senxiiz, Willem Michiel, Junyu Yang, trip7s trip, Sebastain Graf, Joseph William Delisle, Lone Striker, Jonathan Leane, Johann-Peter Hartmann, David Flickinger, Spiking Neurons AB, Kevin Schuppel, Mano Prime, Dmitriy Samsonov, Sean Connelly, Nathan LeClaire, Alain Rossmann, Fen Risland, Derek Yates, Luke Pendergrass, Nikolai Manek, Khalefa Al-Ahmad, Artur Olbinski, John Detwiler, Ajan Kanaga, Imad Khwaja, Trenton Dambrowitz, Kalila, vamX, webtim, Illia Dulskyi.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: WizardLM's WizardLM 7B
The WizardLM delta weights.
|
dipesh1111/Redpajama-7b-chat-lora-wiseyak-retrained-again-epoch-44
|
dipesh1111
| 2023-06-23T08:16:43Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-23T08:16:22Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
jojoUla/bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-10
|
jojoUla
| 2023-06-23T08:01:53Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"fill-mask",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-04-28T16:18:58Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-10
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-10
This model is a fine-tuned version of [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8704
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.3031 | 1.0 | 1 | 4.8955 |
| 1.3131 | 2.0 | 2 | 2.3064 |
| 2.3224 | 3.0 | 3 | 2.9597 |
| 1.0301 | 4.0 | 4 | 2.3126 |
| 1.4955 | 5.0 | 5 | 1.6768 |
| 0.6759 | 6.0 | 6 | 5.2817 |
| 0.6935 | 7.0 | 7 | 2.5742 |
| 1.4726 | 8.0 | 8 | 0.1827 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
PNAKTEMPORAL/falcon-7b-genscript-v1
|
PNAKTEMPORAL
| 2023-06-23T07:55:53Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-21T04:08:27Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
|
rahmas/abusive_content_identification
|
rahmas
| 2023-06-23T07:54:37Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-23T07:47:11Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: abusive_content_identification
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# abusive_content_identification
This model is a fine-tuned version of [indolem/indobertweet-base-uncased](https://huggingface.co/indolem/indobertweet-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0073
- Accuracy: 0.9982
- Precision: 0.9963
- Recall: 1.0
- F1: 0.9981
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.0666 | 1.0 | 547 | 0.0149 | 0.9973 | 0.9944 | 1.0 | 0.9972 |
| 0.0086 | 2.0 | 1094 | 0.0073 | 0.9982 | 0.9963 | 1.0 | 0.9981 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Peyerra1/KIA_Emotion
|
Peyerra1
| 2023-06-23T07:51:50Z | 0 | 0 |
keras
|
[
"keras",
"tf-keras",
"image-classification",
"region:us"
] |
image-classification
| 2023-06-23T07:48:53Z |
---
metrics:
- accuracy
library_name: keras
pipeline_tag: image-classification
---
|
dhiruHF/falcon7b-FT-email
|
dhiruHF
| 2023-06-23T07:31:42Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-23T07:07:31Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
muhualing/vit
|
muhualing
| 2023-06-23T07:25:14Z | 112 | 0 |
transformers
|
[
"transformers",
"pytorch",
"vision-encoder-decoder",
"image-text-to-text",
"image-to-text",
"image-captioning",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
image-to-text
| 2023-06-23T07:01:51Z |
---
tags:
- image-to-text
- image-captioning
license: apache-2.0
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
example_title: Savanna
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
example_title: Football Match
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg
example_title: Airport
---
# nlpconnect/vit-gpt2-image-captioning
This is an image captioning model trained by @ydshieh in [flax ](https://github.com/huggingface/transformers/tree/main/examples/flax/image-captioning) this is pytorch version of [this](https://huggingface.co/ydshieh/vit-gpt2-coco-en-ckpts).
# The Illustrated Image Captioning using transformers
* https://ankur3107.github.io/blogs/the-illustrated-image-captioning-using-transformers/
# Sample running code
```python
from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
import torch
from PIL import Image
model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_extractor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
max_length = 16
num_beams = 4
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
def predict_step(image_paths):
images = []
for image_path in image_paths:
i_image = Image.open(image_path)
if i_image.mode != "RGB":
i_image = i_image.convert(mode="RGB")
images.append(i_image)
pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
pixel_values = pixel_values.to(device)
output_ids = model.generate(pixel_values, **gen_kwargs)
preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
preds = [pred.strip() for pred in preds]
return preds
predict_step(['doctor.e16ba4e4.jpg']) # ['a woman in a hospital bed with a woman in a hospital bed']
```
# Sample running code using transformers pipeline
```python
from transformers import pipeline
image_to_text = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
image_to_text("https://ankur3107.github.io/assets/images/image-captioning-example.png")
# [{'generated_text': 'a soccer game with a player jumping to catch the ball '}]
```
# Contact for any help
* https://huggingface.co/ankur310794
* https://twitter.com/ankur310794
* http://github.com/ankur3107
* https://www.linkedin.com/in/ankur310794
|
jojoUla/bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-8
|
jojoUla
| 2023-06-23T07:21:02Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"fill-mask",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-04-28T15:03:38Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-8
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-8-fast-8
This model is a fine-tuned version of [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4353
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 5.2742 | 1.0 | 1 | 0.0308 |
| 2.0636 | 2.0 | 2 | 0.0073 |
| 3.1637 | 3.0 | 3 | 0.3457 |
| 1.0108 | 4.0 | 4 | 0.5501 |
| 1.712 | 5.0 | 5 | 1.6957 |
| 0.9181 | 6.0 | 6 | 0.3911 |
| 1.8551 | 7.0 | 7 | 0.1100 |
| 0.6861 | 8.0 | 8 | 7.1835 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.