<!-- 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_migrants
This model is a fine-tuned version of gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5187
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 |
---|---|---|---|
72.7055 | 0.03 | 10 | 64.5599 |
31.1168 | 0.06 | 20 | 18.0645 |
7.9718 | 0.08 | 30 | 6.4249 |
3.593 | 0.11 | 40 | 2.8392 |
1.5931 | 0.14 | 50 | 1.1970 |
0.9132 | 0.17 | 60 | 0.8438 |
0.9833 | 0.2 | 70 | 0.7343 |
0.7158 | 0.23 | 80 | 0.6462 |
0.6371 | 0.25 | 90 | 0.6704 |
0.5655 | 0.28 | 100 | 0.6012 |
0.6755 | 0.31 | 110 | 0.5922 |
0.6232 | 0.34 | 120 | 0.5784 |
0.5715 | 0.37 | 130 | 0.5718 |
0.5352 | 0.4 | 140 | 0.5650 |
0.5183 | 0.42 | 150 | 0.5605 |
0.6424 | 0.45 | 160 | 0.5563 |
0.586 | 0.48 | 170 | 0.5515 |
0.58 | 0.51 | 180 | 0.5454 |
0.5932 | 0.54 | 190 | 0.5439 |
0.5204 | 0.57 | 200 | 0.5377 |
0.5654 | 0.59 | 210 | 0.5359 |
0.5129 | 0.62 | 220 | 0.5366 |
0.5451 | 0.65 | 230 | 0.5330 |
0.5637 | 0.68 | 240 | 0.5316 |
0.6052 | 0.71 | 250 | 0.5326 |
0.5741 | 0.74 | 260 | 0.5286 |
0.5437 | 0.76 | 270 | 0.5247 |
0.531 | 0.79 | 280 | 0.5262 |
0.566 | 0.82 | 290 | 0.5228 |
0.6128 | 0.85 | 300 | 0.5197 |
0.6034 | 0.88 | 310 | 0.5173 |
0.5983 | 0.91 | 320 | 0.5211 |
0.5023 | 0.93 | 330 | 0.5212 |
0.5662 | 0.96 | 340 | 0.5187 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.13.3