|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: existential-there-quantifier-transformer-0 |
|
|
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. --> |
|
|
|
|
|
# existential-there-quantifier-transformer-0 |
|
|
|
|
|
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: 3.8835 |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 0 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- training_steps: 3052726 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2546 | 0.03 | 76320 | 4.2173 | |
|
|
| 4.0456 | 1.03 | 152640 | 4.0479 | |
|
|
| 3.9375 | 0.03 | 228960 | 3.9722 | |
|
|
| 3.8623 | 1.03 | 305280 | 3.9304 | |
|
|
| 3.8127 | 0.03 | 381600 | 3.9056 | |
|
|
| 3.7712 | 1.03 | 457920 | 3.8892 | |
|
|
| 3.7382 | 0.03 | 534240 | 3.8785 | |
|
|
| 3.7136 | 1.03 | 610560 | 3.8711 | |
|
|
| 3.6834 | 0.03 | 686880 | 3.8678 | |
|
|
| 3.662 | 1.03 | 763200 | 3.8651 | |
|
|
| 3.6372 | 0.03 | 839520 | 3.8623 | |
|
|
| 3.6129 | 1.03 | 915840 | 3.8620 | |
|
|
| 3.5966 | 0.03 | 992160 | 3.8628 | |
|
|
| 3.5783 | 1.03 | 1068480 | 3.8637 | |
|
|
| 3.5567 | 0.03 | 1144800 | 3.8642 | |
|
|
| 3.5491 | 1.03 | 1221120 | 3.8651 | |
|
|
| 3.5327 | 0.03 | 1297440 | 3.8676 | |
|
|
| 3.5175 | 1.03 | 1373760 | 3.8687 | |
|
|
| 3.5057 | 0.03 | 1450080 | 3.8702 | |
|
|
| 3.4924 | 0.03 | 1526400 | 3.8721 | |
|
|
| 3.4828 | 1.03 | 1602720 | 3.8730 | |
|
|
| 3.473 | 0.03 | 1679040 | 3.8742 | |
|
|
| 3.4664 | 0.03 | 1755360 | 3.8755 | |
|
|
| 3.4601 | 0.03 | 1831680 | 3.8762 | |
|
|
| 3.4455 | 1.03 | 1908000 | 3.8786 | |
|
|
| 3.4387 | 0.03 | 1984320 | 3.8797 | |
|
|
| 3.4248 | 1.03 | 2060640 | 3.8817 | |
|
|
| 3.4112 | 0.03 | 2136960 | 3.8819 | |
|
|
| 3.4015 | 1.03 | 2213280 | 3.8829 | |
|
|
| 3.3893 | 0.03 | 2289600 | 3.8840 | |
|
|
| 3.3756 | 1.03 | 2365920 | 3.8845 | |
|
|
| 3.3723 | 0.03 | 2442240 | 3.8853 | |
|
|
| 3.3601 | 1.03 | 2518560 | 3.8860 | |
|
|
| 3.3485 | 0.03 | 2594880 | 3.8865 | |
|
|
| 3.3415 | 1.03 | 2671200 | 3.8873 | |
|
|
| 3.3286 | 0.03 | 2747520 | 3.8864 | |
|
|
| 3.3243 | 1.03 | 2823840 | 3.8858 | |
|
|
| 3.3171 | 0.03 | 2900160 | 3.8852 | |
|
|
| 3.3134 | 1.03 | 2976480 | 3.8841 | |
|
|
| 3.3113 | 0.02 | 3052726 | 3.8835 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
