|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: BitLlama2-jp-127M-optim-2 |
|
|
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. --> |
|
|
|
|
|
# BitLlama2-jp-127M-optim-2 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.3899 |
|
|
|
|
|
## 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: 0.0024 |
|
|
- train_batch_size: 96 |
|
|
- eval_batch_size: 96 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 500 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 6.8239 | 0.07 | 200 | 4.8920 | |
|
|
| 4.5399 | 0.15 | 400 | 4.3733 | |
|
|
| 4.2276 | 0.22 | 600 | 4.1616 | |
|
|
| 4.0264 | 0.29 | 800 | 3.9917 | |
|
|
| 3.8798 | 0.37 | 1000 | 3.8848 | |
|
|
| 3.78 | 0.44 | 1200 | 3.7981 | |
|
|
| 3.703 | 0.52 | 1400 | 3.7259 | |
|
|
| 3.6279 | 0.59 | 1600 | 3.6482 | |
|
|
| 3.5665 | 0.66 | 1800 | 3.5918 | |
|
|
| 3.5093 | 0.74 | 2000 | 3.5408 | |
|
|
| 3.4519 | 0.81 | 2200 | 3.4849 | |
|
|
| 3.3962 | 0.88 | 2400 | 3.4375 | |
|
|
| 3.3558 | 0.96 | 2600 | 3.3899 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.38.2 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
