bert_12_layer_model_v1_complete_training_new_48
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9912
- Accuracy: 0.4898
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: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.5749 | 0.08 | 10000 | 6.5381 | 0.1270 |
| 6.333 | 0.16 | 20000 | 6.3097 | 0.1410 |
| 6.2341 | 0.25 | 30000 | 6.2179 | 0.1450 |
| 6.1803 | 0.33 | 40000 | 6.1586 | 0.1478 |
| 6.0775 | 0.41 | 50000 | 6.0471 | 0.1520 |
| 5.8957 | 0.49 | 60000 | 5.8458 | 0.1655 |
| 5.7655 | 0.57 | 70000 | 5.7040 | 0.1846 |
| 5.6281 | 0.66 | 80000 | 5.5480 | 0.2026 |
| 5.1797 | 0.74 | 90000 | 5.0004 | 0.2661 |
| 4.7518 | 0.82 | 100000 | 4.5751 | 0.3097 |
| 4.3368 | 0.9 | 110000 | 4.1455 | 0.3518 |
| 3.9513 | 0.98 | 120000 | 3.7659 | 0.3964 |
| 3.682 | 1.07 | 130000 | 3.5328 | 0.4248 |
| 3.5114 | 1.15 | 140000 | 3.3715 | 0.4441 |
| 3.3789 | 1.23 | 150000 | 3.2500 | 0.4591 |
| 3.2776 | 1.31 | 160000 | 3.1468 | 0.4709 |
| 3.204 | 1.39 | 170000 | 3.0899 | 0.4784 |
| 3.1051 | 1.47 | 180000 | 2.9912 | 0.4898 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3