full-transformer-4
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8633
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: 4
- 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 |
---|---|---|---|
4.2293 | 0.03 | 76319 | 4.1958 |
4.0241 | 0.03 | 152638 | 4.0255 |
3.9167 | 0.03 | 228957 | 3.9510 |
3.8423 | 0.03 | 305276 | 3.9094 |
3.79 | 0.03 | 381595 | 3.8845 |
3.7451 | 0.03 | 457914 | 3.8687 |
3.7143 | 0.03 | 534233 | 3.8576 |
3.6846 | 0.03 | 610552 | 3.8510 |
3.6544 | 0.03 | 686871 | 3.8464 |
3.6297 | 1.03 | 763190 | 3.8441 |
3.6212 | 0.03 | 839510 | 3.8373 |
3.5951 | 1.03 | 915830 | 3.8372 |
3.5801 | 0.03 | 992150 | 3.8371 |
3.5587 | 1.03 | 1068470 | 3.8380 |
3.541 | 0.03 | 1144790 | 3.8388 |
3.5279 | 0.03 | 1221110 | 3.8406 |
3.5065 | 0.03 | 1297430 | 3.8408 |
3.4926 | 1.03 | 1373750 | 3.8426 |
3.4816 | 0.03 | 1450070 | 3.8444 |
3.4687 | 1.03 | 1526390 | 3.8461 |
3.4613 | 0.03 | 1602710 | 3.8466 |
3.4541 | 1.03 | 1679030 | 3.8492 |
3.4461 | 0.03 | 1755350 | 3.8516 |
3.4383 | 1.03 | 1831670 | 3.8521 |
3.4247 | 0.03 | 1907990 | 3.8537 |
3.4145 | 1.03 | 1984310 | 3.8540 |
3.4033 | 0.03 | 2060630 | 3.8561 |
3.3879 | 0.03 | 2136950 | 3.8585 |
3.3817 | 1.03 | 2213270 | 3.8583 |
3.3676 | 0.03 | 2289590 | 3.8602 |
3.357 | 1.03 | 2365910 | 3.8611 |
3.3479 | 0.03 | 2442230 | 3.8625 |
3.3342 | 0.03 | 2518550 | 3.8638 |
3.3243 | 0.03 | 2594870 | 3.8639 |
3.3153 | 0.03 | 2671190 | 3.8642 |
3.3042 | 1.03 | 2747510 | 3.8649 |
3.3014 | 0.03 | 2823830 | 3.8649 |
3.2975 | 0.03 | 2900150 | 3.8650 |
3.2925 | 0.03 | 2976470 | 3.8643 |
3.2897 | 0.02 | 3052726 | 3.8633 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 1