long_first_noditransitive_seed-63_1e-3
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3951
- Accuracy: 0.3910
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: 0.001
- train_batch_size: 32
- eval_batch_size: 64
- seed: 63
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 32000
- num_epochs: 20.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.1563 | 0.9998 | 1495 | 4.6420 | 0.2734 |
| 4.5977 | 1.9997 | 2990 | 4.1513 | 0.3160 |
| 3.9713 | 2.9995 | 4485 | 3.8892 | 0.3388 |
| 3.794 | 4.0 | 5981 | 3.7233 | 0.3545 |
| 3.5571 | 4.9998 | 7476 | 3.6262 | 0.3647 |
| 3.4789 | 5.9997 | 8971 | 3.5550 | 0.3721 |
| 3.3581 | 6.9995 | 10466 | 3.5133 | 0.3765 |
| 3.32 | 8.0 | 11962 | 3.4808 | 0.3798 |
| 3.2472 | 8.9998 | 13457 | 3.4632 | 0.3821 |
| 3.2254 | 9.9997 | 14952 | 3.4465 | 0.3844 |
| 3.1781 | 10.9995 | 16447 | 3.4334 | 0.3856 |
| 3.1641 | 12.0 | 17943 | 3.4277 | 0.3866 |
| 3.1302 | 12.9998 | 19438 | 3.4188 | 0.3878 |
| 3.1207 | 13.9997 | 20933 | 3.4113 | 0.3891 |
| 3.0967 | 14.9995 | 22428 | 3.4120 | 0.3891 |
| 3.0926 | 16.0 | 23924 | 3.4058 | 0.3896 |
| 3.0738 | 16.9998 | 25419 | 3.4029 | 0.3899 |
| 3.071 | 17.9997 | 26914 | 3.4020 | 0.3903 |
| 3.0584 | 18.9995 | 28409 | 3.3985 | 0.3909 |
| 3.0574 | 19.9967 | 29900 | 3.3951 | 0.3910 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.20.0
- Downloads last month
- 6