short_first_noditransitive_seed-21_1e-3
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2431
- Accuracy: 0.3984
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: 21
- 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 |
|---|---|---|---|---|
| 6.0253 | 0.9998 | 1495 | 4.4449 | 0.2906 |
| 4.4052 | 1.9997 | 2990 | 3.9709 | 0.3283 |
| 3.8026 | 2.9995 | 4485 | 3.7021 | 0.3508 |
| 3.6311 | 4.0 | 5981 | 3.5405 | 0.3663 |
| 3.3988 | 4.9998 | 7476 | 3.4488 | 0.3754 |
| 3.3258 | 5.9997 | 8971 | 3.3869 | 0.3813 |
| 3.2111 | 6.9995 | 10466 | 3.3492 | 0.3853 |
| 3.1739 | 8.0 | 11962 | 3.3202 | 0.3880 |
| 3.1055 | 8.9998 | 13457 | 3.3006 | 0.3908 |
| 3.0878 | 9.9997 | 14952 | 3.2869 | 0.3924 |
| 3.0406 | 10.9995 | 16447 | 3.2781 | 0.3933 |
| 3.028 | 12.0 | 17943 | 3.2703 | 0.3942 |
| 2.9963 | 12.9998 | 19438 | 3.2665 | 0.3952 |
| 2.9881 | 13.9997 | 20933 | 3.2563 | 0.3961 |
| 2.9648 | 14.9995 | 22428 | 3.2558 | 0.3969 |
| 2.962 | 16.0 | 23924 | 3.2547 | 0.3972 |
| 2.944 | 16.9998 | 25419 | 3.2509 | 0.3975 |
| 2.9403 | 17.9997 | 26914 | 3.2480 | 0.3977 |
| 2.93 | 18.9995 | 28409 | 3.2484 | 0.3976 |
| 2.9284 | 19.9967 | 29900 | 3.2431 | 0.3984 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.20.0
- Downloads last month
- 2