|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt2-kl_01_04-hs_cn-loto_women |
|
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-kl_01_04-hs_cn-loto_women |
|
|
|
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5255 |
|
|
|
## 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: 4 |
|
- seed: 21 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 72.3926 | 0.03 | 10 | 64.4148 | |
|
| 30.9965 | 0.06 | 20 | 18.3281 | |
|
| 9.3508 | 0.08 | 30 | 6.8328 | |
|
| 3.4241 | 0.11 | 40 | 2.8584 | |
|
| 1.6453 | 0.14 | 50 | 1.2170 | |
|
| 1.2959 | 0.17 | 60 | 0.9385 | |
|
| 0.8158 | 0.2 | 70 | 0.7754 | |
|
| 0.6544 | 0.23 | 80 | 0.7423 | |
|
| 0.6712 | 0.25 | 90 | 0.7252 | |
|
| 0.699 | 0.28 | 100 | 0.6105 | |
|
| 0.6505 | 0.31 | 110 | 0.5996 | |
|
| 0.5894 | 0.34 | 120 | 0.6120 | |
|
| 0.6332 | 0.37 | 130 | 0.5771 | |
|
| 0.5938 | 0.4 | 140 | 0.5713 | |
|
| 0.6967 | 0.42 | 150 | 0.5658 | |
|
| 0.5814 | 0.45 | 160 | 0.5639 | |
|
| 0.6871 | 0.48 | 170 | 0.5620 | |
|
| 0.7062 | 0.51 | 180 | 0.5577 | |
|
| 0.6324 | 0.54 | 190 | 0.5526 | |
|
| 0.5662 | 0.57 | 200 | 0.5551 | |
|
| 0.5518 | 0.59 | 210 | 0.5488 | |
|
| 0.6076 | 0.62 | 220 | 0.5491 | |
|
| 0.5995 | 0.65 | 230 | 0.5428 | |
|
| 0.5814 | 0.68 | 240 | 0.5438 | |
|
| 0.5011 | 0.71 | 250 | 0.5429 | |
|
| 0.5419 | 0.74 | 260 | 0.5419 | |
|
| 0.5354 | 0.76 | 270 | 0.5392 | |
|
| 0.6176 | 0.79 | 280 | 0.5355 | |
|
| 0.5353 | 0.82 | 290 | 0.5367 | |
|
| 0.6365 | 0.85 | 300 | 0.5312 | |
|
| 0.6529 | 0.88 | 310 | 0.5319 | |
|
| 0.5899 | 0.91 | 320 | 0.5277 | |
|
| 0.5617 | 0.93 | 330 | 0.5263 | |
|
| 0.6409 | 0.96 | 340 | 0.5250 | |
|
| 0.6277 | 0.99 | 350 | 0.5218 | |
|
| 0.5406 | 1.02 | 360 | 0.5229 | |
|
| 0.4896 | 1.05 | 370 | 0.5267 | |
|
| 0.4776 | 1.08 | 380 | 0.5255 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
