|
--- |
|
license: mit |
|
base_model: openai-community/gpt2 |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: '47185774_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. --> |
|
|
|
# 47185774_0 |
|
|
|
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5103 |
|
- Accuracy: 0.0000 |
|
|
|
## 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: 1.41e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 256 |
|
- total_eval_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 1.0647 | 1.67 | 25 | 0.9608 | 0.0001 | |
|
| 0.8454 | 3.33 | 50 | 0.7926 | 0.0001 | |
|
| 0.7865 | 5.0 | 75 | 0.7448 | 0.0001 | |
|
| 0.757 | 6.67 | 100 | 0.7207 | 0.0001 | |
|
| 0.7338 | 8.33 | 125 | 0.7058 | 0.0000 | |
|
| 0.721 | 10.0 | 150 | 0.6932 | 0.0000 | |
|
| 0.7216 | 11.67 | 175 | 0.6845 | 0.0000 | |
|
| 0.709 | 13.33 | 200 | 0.6766 | 0.0000 | |
|
| 0.6942 | 15.0 | 225 | 0.6694 | 0.0000 | |
|
| 0.6921 | 16.67 | 250 | 0.6633 | 0.0000 | |
|
| 0.6945 | 18.33 | 275 | 0.6582 | 0.0000 | |
|
| 0.6826 | 20.0 | 300 | 0.6524 | 0.0000 | |
|
| 0.6702 | 21.67 | 325 | 0.6475 | 0.0000 | |
|
| 0.6637 | 23.33 | 350 | 0.6428 | 0.0000 | |
|
| 0.6695 | 25.0 | 375 | 0.6384 | 0.0000 | |
|
| 0.6615 | 26.67 | 400 | 0.6334 | 0.0000 | |
|
| 0.6491 | 28.33 | 425 | 0.6299 | 0.0000 | |
|
| 0.6553 | 30.0 | 450 | 0.6254 | 0.0000 | |
|
| 0.6473 | 31.67 | 475 | 0.6216 | 0.0000 | |
|
| 0.6345 | 33.33 | 500 | 0.6183 | 0.0000 | |
|
| 0.6486 | 35.0 | 525 | 0.6145 | 0.0000 | |
|
| 0.6365 | 36.67 | 550 | 0.6109 | 0.0000 | |
|
| 0.6313 | 38.33 | 575 | 0.6079 | 0.0000 | |
|
| 0.636 | 40.0 | 600 | 0.6048 | 0.0000 | |
|
| 0.6268 | 41.67 | 625 | 0.6015 | 0.0000 | |
|
| 0.6274 | 43.33 | 650 | 0.5981 | 0.0000 | |
|
| 0.6135 | 45.0 | 675 | 0.5952 | 0.0000 | |
|
| 0.6219 | 46.67 | 700 | 0.5919 | 0.0000 | |
|
| 0.6166 | 48.33 | 725 | 0.5890 | 0.0000 | |
|
| 0.6136 | 50.0 | 750 | 0.5863 | 0.0000 | |
|
| 0.6053 | 51.67 | 775 | 0.5837 | 0.0000 | |
|
| 0.5999 | 53.33 | 800 | 0.5806 | 0.0000 | |
|
| 0.6141 | 55.0 | 825 | 0.5782 | 0.0000 | |
|
| 0.6058 | 56.67 | 850 | 0.5753 | 0.0000 | |
|
| 0.6026 | 58.33 | 875 | 0.5728 | 0.0000 | |
|
| 0.5949 | 60.0 | 900 | 0.5702 | 0.0000 | |
|
| 0.6007 | 61.67 | 925 | 0.5675 | 0.0000 | |
|
| 0.5927 | 63.33 | 950 | 0.5647 | 0.0000 | |
|
| 0.593 | 65.0 | 975 | 0.5625 | 0.0000 | |
|
| 0.5831 | 66.67 | 1000 | 0.5597 | 0.0000 | |
|
| 0.6008 | 68.33 | 1025 | 0.5574 | 0.0000 | |
|
| 0.5877 | 70.0 | 1050 | 0.5551 | 0.0000 | |
|
| 0.5847 | 71.67 | 1075 | 0.5524 | 0.0000 | |
|
| 0.5794 | 73.33 | 1100 | 0.5500 | 0.0000 | |
|
| 0.5952 | 75.0 | 1125 | 0.5474 | 0.0000 | |
|
| 0.5857 | 76.67 | 1150 | 0.5455 | 0.0000 | |
|
| 0.5787 | 78.33 | 1175 | 0.5433 | 0.0000 | |
|
| 0.5963 | 80.0 | 1200 | 0.5416 | 0.0000 | |
|
| 0.564 | 81.67 | 1225 | 0.5390 | 0.0000 | |
|
| 0.5691 | 83.33 | 1250 | 0.5368 | 0.0000 | |
|
| 0.5837 | 85.0 | 1275 | 0.5352 | 0.0000 | |
|
| 0.5668 | 86.67 | 1300 | 0.5333 | 0.0000 | |
|
| 0.5716 | 88.33 | 1325 | 0.5319 | 0.0000 | |
|
| 0.557 | 90.0 | 1350 | 0.5300 | 0.0000 | |
|
| 0.5539 | 91.67 | 1375 | 0.5286 | 0.0000 | |
|
| 0.5683 | 93.33 | 1400 | 0.5273 | 0.0000 | |
|
| 0.5671 | 95.0 | 1425 | 0.5255 | 0.0000 | |
|
| 0.5723 | 96.67 | 1450 | 0.5244 | 0.0000 | |
|
| 0.5627 | 98.33 | 1475 | 0.5229 | 0.0000 | |
|
| 0.5627 | 100.0 | 1500 | 0.5215 | 0.0000 | |
|
| 0.5606 | 101.67 | 1525 | 0.5205 | 0.0000 | |
|
| 0.5651 | 103.33 | 1550 | 0.5192 | 0.0000 | |
|
| 0.5703 | 105.0 | 1575 | 0.5184 | 0.0000 | |
|
| 0.5533 | 106.67 | 1600 | 0.5176 | 0.0000 | |
|
| 0.5627 | 108.33 | 1625 | 0.5165 | 0.0000 | |
|
| 0.5563 | 110.0 | 1650 | 0.5158 | 0.0000 | |
|
| 0.5526 | 111.67 | 1675 | 0.5151 | 0.0000 | |
|
| 0.5432 | 113.33 | 1700 | 0.5143 | 0.0000 | |
|
| 0.5224 | 115.0 | 1725 | 0.5136 | 0.0000 | |
|
| 0.5622 | 116.67 | 1750 | 0.5130 | 0.0000 | |
|
| 0.5494 | 118.33 | 1775 | 0.5125 | 0.0000 | |
|
| 0.554 | 120.0 | 1800 | 0.5121 | 0.0000 | |
|
| 0.5495 | 121.67 | 1825 | 0.5116 | 0.0000 | |
|
| 0.5458 | 123.33 | 1850 | 0.5113 | 0.0000 | |
|
| 0.552 | 125.0 | 1875 | 0.5110 | 0.0000 | |
|
| 0.5475 | 126.67 | 1900 | 0.5108 | 0.0000 | |
|
| 0.5493 | 128.33 | 1925 | 0.5105 | 0.0000 | |
|
| 0.5296 | 130.0 | 1950 | 0.5105 | 0.0000 | |
|
| 0.5562 | 131.67 | 1975 | 0.5104 | 0.0000 | |
|
| 0.561 | 133.33 | 2000 | 0.5103 | 0.0000 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
