metadata
base_model: nferruz/ProtGPT2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 5e05_output_dir_clean_df_10-100_noX_100_50_epoch_cluster
results: []
widget:
- text: <|endoftext|>
5e05_output_dir_clean_df_10-100_noX_100_50_epoch_cluster
This model is a fine-tuned version of nferruz/ProtGPT2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4181
- Accuracy: 0.5481
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 148 | 5.1495 | 0.2912 |
No log | 2.0 | 296 | 4.6761 | 0.3383 |
No log | 3.0 | 444 | 4.3827 | 0.3712 |
4.9816 | 4.0 | 592 | 4.1762 | 0.3960 |
4.9816 | 5.0 | 740 | 4.0295 | 0.4136 |
4.9816 | 6.0 | 888 | 3.9151 | 0.4276 |
3.9068 | 7.0 | 1036 | 3.8298 | 0.4400 |
3.9068 | 8.0 | 1184 | 3.7551 | 0.4500 |
3.9068 | 9.0 | 1332 | 3.6968 | 0.4586 |
3.9068 | 10.0 | 1480 | 3.6389 | 0.4668 |
3.3777 | 11.0 | 1628 | 3.5960 | 0.4743 |
3.3777 | 12.0 | 1776 | 3.5560 | 0.4803 |
3.3777 | 13.0 | 1924 | 3.5380 | 0.4868 |
3.0075 | 14.0 | 2072 | 3.4846 | 0.4914 |
3.0075 | 15.0 | 2220 | 3.4658 | 0.4969 |
3.0075 | 16.0 | 2368 | 3.4555 | 0.5010 |
2.7329 | 17.0 | 2516 | 3.4300 | 0.5053 |
2.7329 | 18.0 | 2664 | 3.4208 | 0.5080 |
2.7329 | 19.0 | 2812 | 3.4250 | 0.5121 |
2.7329 | 20.0 | 2960 | 3.3964 | 0.5147 |
2.5153 | 21.0 | 3108 | 3.3893 | 0.5181 |
2.5153 | 22.0 | 3256 | 3.3914 | 0.5204 |
2.5153 | 23.0 | 3404 | 3.3819 | 0.5229 |
2.336 | 24.0 | 3552 | 3.3786 | 0.5247 |
2.336 | 25.0 | 3700 | 3.3749 | 0.5267 |
2.336 | 26.0 | 3848 | 3.3774 | 0.5287 |
2.336 | 27.0 | 3996 | 3.3700 | 0.5303 |
2.1918 | 28.0 | 4144 | 3.3722 | 0.5321 |
2.1918 | 29.0 | 4292 | 3.3729 | 0.5340 |
2.1918 | 30.0 | 4440 | 3.3896 | 0.5350 |
2.0717 | 31.0 | 4588 | 3.3776 | 0.5367 |
2.0717 | 32.0 | 4736 | 3.3842 | 0.5385 |
2.0717 | 33.0 | 4884 | 3.3820 | 0.5399 |
1.9814 | 34.0 | 5032 | 3.3933 | 0.5404 |
1.9814 | 35.0 | 5180 | 3.3861 | 0.5411 |
1.9814 | 36.0 | 5328 | 3.3878 | 0.5425 |
1.9814 | 37.0 | 5476 | 3.3903 | 0.5431 |
1.9049 | 38.0 | 5624 | 3.3848 | 0.5440 |
1.9049 | 39.0 | 5772 | 3.3965 | 0.5447 |
1.9049 | 40.0 | 5920 | 3.4033 | 0.5453 |
1.8441 | 41.0 | 6068 | 3.4074 | 0.5456 |
1.8441 | 42.0 | 6216 | 3.4046 | 0.5462 |
1.8441 | 43.0 | 6364 | 3.4120 | 0.5467 |
1.804 | 44.0 | 6512 | 3.4044 | 0.5467 |
1.804 | 45.0 | 6660 | 3.4125 | 0.5472 |
1.804 | 46.0 | 6808 | 3.4115 | 0.5477 |
1.804 | 47.0 | 6956 | 3.4070 | 0.5477 |
1.7744 | 48.0 | 7104 | 3.4203 | 0.5478 |
1.7744 | 49.0 | 7252 | 3.4174 | 0.5479 |
1.7744 | 50.0 | 7400 | 3.4181 | 0.5481 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0