|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- bleu |
|
|
model-index: |
|
|
- name: gpt2-medium-wikitext |
|
|
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-medium-wikitext |
|
|
|
|
|
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: 3.1666 |
|
|
- Accuracy: 0.4218 |
|
|
- Perplexity: 23.7262 |
|
|
- Bleu: 0.1462 |
|
|
|
|
|
## 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: 64 |
|
|
- eval_batch_size: 64 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Perplexity | Bleu | |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:----------:|:------:| |
|
|
| 6.078 | 0.2806 | 500 | 5.9534 | 0.1875 | 385.0606 | 0.0310 | |
|
|
| 5.0653 | 0.5612 | 1000 | 4.9232 | 0.2616 | 137.4410 | 0.0633 | |
|
|
| 4.3357 | 0.8418 | 1500 | 4.2163 | 0.3222 | 67.7828 | 0.0857 | |
|
|
| 3.9453 | 1.1223 | 2000 | 3.8824 | 0.3534 | 48.5418 | 0.1107 | |
|
|
| 3.7572 | 1.4029 | 2500 | 3.7058 | 0.3684 | 40.6810 | 0.1217 | |
|
|
| 3.6475 | 1.6835 | 3000 | 3.5827 | 0.3788 | 35.9700 | 0.1306 | |
|
|
| 3.5431 | 1.9641 | 3500 | 3.4927 | 0.3878 | 32.8733 | 0.1347 | |
|
|
| 3.4221 | 2.2447 | 4000 | 3.4283 | 0.3939 | 30.8231 | 0.1356 | |
|
|
| 3.36 | 2.5253 | 4500 | 3.3719 | 0.3996 | 29.1351 | 0.1384 | |
|
|
| 3.3281 | 2.8058 | 5000 | 3.3257 | 0.4041 | 27.8193 | 0.1369 | |
|
|
| 3.2071 | 3.0864 | 5500 | 3.2885 | 0.4080 | 26.8024 | 0.1442 | |
|
|
| 3.2002 | 3.3670 | 6000 | 3.2594 | 0.4117 | 26.0335 | 0.1477 | |
|
|
| 3.1778 | 3.6476 | 6500 | 3.2319 | 0.4142 | 25.3278 | 0.1436 | |
|
|
| 3.1523 | 3.9282 | 7000 | 3.2091 | 0.4167 | 24.7565 | 0.1462 | |
|
|
| 3.0842 | 4.2088 | 7500 | 3.1917 | 0.4185 | 24.3289 | 0.1434 | |
|
|
| 3.0465 | 4.4893 | 8000 | 3.1789 | 0.4201 | 24.0197 | 0.1460 | |
|
|
| 3.0563 | 4.7699 | 8500 | 3.1666 | 0.4218 | 23.7262 | 0.1462 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.3.2 |
|
|
- Tokenizers 0.21.0 |
|
|
|
