<!-- 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-no_ear-loto_jews
This model is a fine-tuned version of gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5270
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 |
---|---|---|---|
72.9514 | 0.03 | 10 | 65.3603 |
32.1127 | 0.06 | 20 | 18.4547 |
8.2152 | 0.08 | 30 | 6.7267 |
3.4911 | 0.11 | 40 | 2.9798 |
1.6339 | 0.14 | 50 | 1.2141 |
0.8984 | 0.17 | 60 | 0.9466 |
0.8166 | 0.2 | 70 | 0.7656 |
0.6533 | 0.23 | 80 | 0.6374 |
0.6208 | 0.25 | 90 | 0.6106 |
0.6942 | 0.28 | 100 | 0.5941 |
0.6241 | 0.31 | 110 | 0.5825 |
0.736 | 0.34 | 120 | 0.5790 |
0.5359 | 0.37 | 130 | 0.5745 |
0.6451 | 0.4 | 140 | 0.5694 |
0.5871 | 0.42 | 150 | 0.5625 |
0.6146 | 0.45 | 160 | 0.5635 |
0.5091 | 0.48 | 170 | 0.5578 |
0.5911 | 0.51 | 180 | 0.5580 |
0.5398 | 0.54 | 190 | 0.5528 |
0.6379 | 0.57 | 200 | 0.5484 |
0.5205 | 0.59 | 210 | 0.5481 |
0.5752 | 0.62 | 220 | 0.5448 |
0.6035 | 0.65 | 230 | 0.5419 |
0.5582 | 0.68 | 240 | 0.5417 |
0.5331 | 0.71 | 250 | 0.5407 |
0.5062 | 0.74 | 260 | 0.5398 |
0.562 | 0.76 | 270 | 0.5375 |
0.5845 | 0.79 | 280 | 0.5332 |
0.4904 | 0.82 | 290 | 0.5317 |
0.596 | 0.85 | 300 | 0.5303 |
0.5976 | 0.88 | 310 | 0.5298 |
0.5614 | 0.91 | 320 | 0.5284 |
0.6057 | 0.93 | 330 | 0.5287 |
0.4378 | 0.96 | 340 | 0.5290 |
0.6069 | 0.99 | 350 | 0.5267 |
0.4918 | 1.02 | 360 | 0.5291 |
0.5506 | 1.05 | 370 | 0.5315 |
0.4013 | 1.08 | 380 | 0.5270 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.13.3