|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt2-kl_01_04-hs_cn-loto_muslim |
|
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_muslim |
|
|
|
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: 0.5380 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 73.5693 | 0.03 | 10 | 65.1086 | |
|
| 31.2617 | 0.06 | 20 | 18.3949 | |
|
| 12.0113 | 0.08 | 30 | 7.2956 | |
|
| 3.702 | 0.11 | 40 | 2.9472 | |
|
| 1.8413 | 0.14 | 50 | 1.2727 | |
|
| 1.3358 | 0.17 | 60 | 0.9255 | |
|
| 0.8787 | 0.2 | 70 | 0.7903 | |
|
| 0.7065 | 0.23 | 80 | 0.7346 | |
|
| 0.6537 | 0.25 | 90 | 0.6680 | |
|
| 0.8109 | 0.28 | 100 | 0.6131 | |
|
| 0.6697 | 0.31 | 110 | 0.5983 | |
|
| 0.6555 | 0.34 | 120 | 0.5935 | |
|
| 0.6505 | 0.37 | 130 | 0.5838 | |
|
| 0.684 | 0.4 | 140 | 0.5768 | |
|
| 0.6723 | 0.42 | 150 | 0.5736 | |
|
| 0.687 | 0.45 | 160 | 0.5709 | |
|
| 0.6504 | 0.48 | 170 | 0.5710 | |
|
| 0.711 | 0.51 | 180 | 0.5685 | |
|
| 0.7001 | 0.54 | 190 | 0.5695 | |
|
| 0.5758 | 0.57 | 200 | 0.5651 | |
|
| 0.6491 | 0.59 | 210 | 0.5652 | |
|
| 0.6248 | 0.62 | 220 | 0.5617 | |
|
| 0.579 | 0.65 | 230 | 0.5515 | |
|
| 0.5784 | 0.68 | 240 | 0.5500 | |
|
| 0.5178 | 0.71 | 250 | 0.5550 | |
|
| 0.6129 | 0.74 | 260 | 0.5530 | |
|
| 0.5729 | 0.76 | 270 | 0.5467 | |
|
| 0.5687 | 0.79 | 280 | 0.5429 | |
|
| 0.6217 | 0.82 | 290 | 0.5413 | |
|
| 0.5902 | 0.85 | 300 | 0.5402 | |
|
| 0.6314 | 0.88 | 310 | 0.5362 | |
|
| 0.5481 | 0.91 | 320 | 0.5354 | |
|
| 0.6007 | 0.93 | 330 | 0.5333 | |
|
| 0.5496 | 0.96 | 340 | 0.5326 | |
|
| 0.6287 | 0.99 | 350 | 0.5329 | |
|
| 0.5383 | 1.02 | 360 | 0.5366 | |
|
| 0.5227 | 1.05 | 370 | 0.5380 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
