<!-- 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_women
This model is a fine-tuned version of gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5473
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 |
---|---|---|---|
72.3557 | 0.03 | 10 | 64.4036 |
30.9725 | 0.06 | 20 | 18.3129 |
9.4309 | 0.08 | 30 | 6.6428 |
3.7579 | 0.11 | 40 | 2.9526 |
1.6919 | 0.14 | 50 | 1.2236 |
1.09 | 0.17 | 60 | 0.8718 |
0.8348 | 0.2 | 70 | 0.7829 |
0.6574 | 0.23 | 80 | 0.6525 |
0.6218 | 0.25 | 90 | 0.6155 |
0.6654 | 0.28 | 100 | 0.6041 |
0.6137 | 0.31 | 110 | 0.5944 |
0.5564 | 0.34 | 120 | 0.5821 |
0.5956 | 0.37 | 130 | 0.5755 |
0.5782 | 0.4 | 140 | 0.5706 |
0.6667 | 0.42 | 150 | 0.5674 |
0.5486 | 0.45 | 160 | 0.5663 |
0.6661 | 0.48 | 170 | 0.5636 |
0.6784 | 0.51 | 180 | 0.5622 |
0.6032 | 0.54 | 190 | 0.5580 |
0.5356 | 0.57 | 200 | 0.5538 |
0.5262 | 0.59 | 210 | 0.5511 |
0.5859 | 0.62 | 220 | 0.5503 |
0.5721 | 0.65 | 230 | 0.5459 |
0.5463 | 0.68 | 240 | 0.5513 |
0.4686 | 0.71 | 250 | 0.5461 |
0.5127 | 0.74 | 260 | 0.5473 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.11.0+cu113
- Datasets 2.11.0
- Tokenizers 0.13.3