full-lstm-2
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9716
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: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 3052726
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.7917 | 0.03 | 76319 | 4.7567 |
4.5064 | 1.03 | 152638 | 4.4756 |
4.3631 | 0.03 | 228957 | 4.3407 |
4.2711 | 1.03 | 305276 | 4.2578 |
4.2077 | 0.03 | 381595 | 4.2014 |
4.157 | 1.03 | 457914 | 4.1600 |
4.1224 | 0.03 | 534233 | 4.1296 |
4.0928 | 0.03 | 610552 | 4.1052 |
4.0627 | 1.03 | 686871 | 4.0866 |
4.0409 | 0.03 | 763190 | 4.0706 |
4.0209 | 1.03 | 839509 | 4.0576 |
4.0041 | 0.03 | 915828 | 4.0470 |
3.9838 | 0.03 | 992147 | 4.0377 |
3.9707 | 0.03 | 1068467 | 4.0283 |
3.96 | 1.03 | 1144787 | 4.0217 |
3.9578 | 0.03 | 1221107 | 4.0144 |
3.9374 | 1.03 | 1297427 | 4.0091 |
3.9288 | 0.03 | 1373747 | 4.0045 |
3.9178 | 1.03 | 1450067 | 4.0008 |
3.9111 | 0.03 | 1526387 | 3.9972 |
3.9123 | 1.03 | 1602707 | 3.9945 |
3.9072 | 0.03 | 1679027 | 3.9921 |
3.9062 | 1.03 | 1755347 | 3.9889 |
3.9022 | 0.03 | 1831667 | 3.9870 |
3.8944 | 0.03 | 1907987 | 3.9850 |
3.8882 | 1.03 | 1984307 | 3.9836 |
3.883 | 0.03 | 2060627 | 3.9817 |
3.8755 | 1.03 | 2136947 | 3.9808 |
3.8735 | 0.03 | 2213267 | 3.9796 |
3.8684 | 1.03 | 2289587 | 3.9782 |
3.86 | 0.03 | 2365907 | 3.9773 |
3.8611 | 1.03 | 2442227 | 3.9764 |
3.8488 | 0.03 | 2518547 | 3.9757 |
3.8468 | 1.03 | 2594867 | 3.9747 |
3.8413 | 0.03 | 2671187 | 3.9741 |
3.8399 | 0.03 | 2747507 | 3.9734 |
3.845 | 1.03 | 2823827 | 3.9730 |
3.8433 | 0.03 | 2900147 | 3.9724 |
3.8469 | 1.03 | 2976467 | 3.9720 |
3.8461 | 0.02 | 3052726 | 3.9716 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 28