|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt2-kl_01_04-hs_cn-loto_migrants |
|
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_migrants |
|
|
|
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: 0.5142 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 72.7331 | 0.03 | 10 | 64.5524 | |
|
| 31.1386 | 0.06 | 20 | 18.0676 | |
|
| 8.0161 | 0.08 | 30 | 6.4050 | |
|
| 3.3753 | 0.11 | 40 | 2.7106 | |
|
| 1.601 | 0.14 | 50 | 1.1822 | |
|
| 0.9923 | 0.17 | 60 | 0.8619 | |
|
| 1.0632 | 0.2 | 70 | 0.8305 | |
|
| 0.7501 | 0.23 | 80 | 0.6396 | |
|
| 0.6715 | 0.25 | 90 | 0.6099 | |
|
| 0.5965 | 0.28 | 100 | 0.6137 | |
|
| 0.711 | 0.31 | 110 | 0.5942 | |
|
| 0.6546 | 0.34 | 120 | 0.5745 | |
|
| 0.6075 | 0.37 | 130 | 0.5696 | |
|
| 0.5607 | 0.4 | 140 | 0.5633 | |
|
| 0.5469 | 0.42 | 150 | 0.5569 | |
|
| 0.6887 | 0.45 | 160 | 0.5543 | |
|
| 0.6184 | 0.48 | 170 | 0.5495 | |
|
| 0.596 | 0.51 | 180 | 0.5474 | |
|
| 0.6104 | 0.54 | 190 | 0.5442 | |
|
| 0.5553 | 0.57 | 200 | 0.5388 | |
|
| 0.5714 | 0.59 | 210 | 0.5346 | |
|
| 0.534 | 0.62 | 220 | 0.5356 | |
|
| 0.5739 | 0.65 | 230 | 0.5326 | |
|
| 0.5873 | 0.68 | 240 | 0.5298 | |
|
| 0.619 | 0.71 | 250 | 0.5312 | |
|
| 0.6038 | 0.74 | 260 | 0.5282 | |
|
| 0.6058 | 0.76 | 270 | 0.5241 | |
|
| 0.5508 | 0.79 | 280 | 0.5252 | |
|
| 0.5919 | 0.82 | 290 | 0.5233 | |
|
| 0.6513 | 0.85 | 300 | 0.5206 | |
|
| 0.6376 | 0.88 | 310 | 0.5178 | |
|
| 0.6252 | 0.91 | 320 | 0.5181 | |
|
| 0.5341 | 0.93 | 330 | 0.5160 | |
|
| 0.5913 | 0.96 | 340 | 0.5139 | |
|
| 0.6227 | 0.99 | 350 | 0.5143 | |
|
| 0.4582 | 1.02 | 360 | 0.5140 | |
|
| 0.5281 | 1.05 | 370 | 0.5142 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
