<!-- 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_lgbt
This model is a fine-tuned version of gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5240
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 |
---|---|---|---|
72.2061 | 0.03 | 10 | 64.5518 |
30.2689 | 0.06 | 20 | 17.8618 |
8.8488 | 0.08 | 30 | 6.3771 |
3.4282 | 0.11 | 40 | 2.6682 |
1.6187 | 0.14 | 50 | 1.1887 |
0.9184 | 0.17 | 60 | 0.9858 |
1.0938 | 0.2 | 70 | 0.7108 |
0.7254 | 0.23 | 80 | 0.6445 |
0.5847 | 0.25 | 90 | 0.6457 |
0.7175 | 0.28 | 100 | 0.6043 |
0.5929 | 0.31 | 110 | 0.5937 |
0.5411 | 0.34 | 120 | 0.5871 |
0.5367 | 0.37 | 130 | 0.5809 |
0.6046 | 0.4 | 140 | 0.5761 |
0.5401 | 0.42 | 150 | 0.5660 |
0.6756 | 0.45 | 160 | 0.5609 |
0.5675 | 0.48 | 170 | 0.5586 |
0.5903 | 0.51 | 180 | 0.5584 |
0.5611 | 0.54 | 190 | 0.5530 |
0.5807 | 0.57 | 200 | 0.5526 |
0.538 | 0.59 | 210 | 0.5481 |
0.5831 | 0.62 | 220 | 0.5438 |
0.6179 | 0.65 | 230 | 0.5417 |
0.6591 | 0.68 | 240 | 0.5424 |
0.4662 | 0.71 | 250 | 0.5494 |
0.5973 | 0.74 | 260 | 0.5390 |
0.5606 | 0.76 | 270 | 0.5359 |
0.5623 | 0.79 | 280 | 0.5429 |
0.5374 | 0.82 | 290 | 0.5337 |
0.6014 | 0.85 | 300 | 0.5343 |
0.5345 | 0.88 | 310 | 0.5328 |
0.5215 | 0.91 | 320 | 0.5304 |
0.5398 | 0.93 | 330 | 0.5274 |
0.5192 | 0.96 | 340 | 0.5256 |
0.591 | 0.99 | 350 | 0.5252 |
0.5141 | 1.02 | 360 | 0.5301 |
0.4937 | 1.05 | 370 | 0.5254 |
0.4945 | 1.08 | 380 | 0.5225 |
0.4774 | 1.1 | 390 | 0.5252 |
0.4898 | 1.13 | 400 | 0.5278 |
0.4856 | 1.16 | 410 | 0.5240 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.13.3