bert_12_layer_model_v2_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: 3.5669
- Accuracy: 0.4078
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 |
|---|---|---|---|---|
| 6.5761 | 0.08 | 10000 | 6.5400 | 0.1270 |
| 6.3285 | 0.16 | 20000 | 6.3050 | 0.1411 |
| 6.2279 | 0.25 | 30000 | 6.2128 | 0.1449 |
| 6.1754 | 0.33 | 40000 | 6.1535 | 0.1478 |
| 6.1291 | 0.41 | 50000 | 6.1181 | 0.1488 |
| 6.1008 | 0.49 | 60000 | 6.0846 | 0.1495 |
| 6.0716 | 0.57 | 70000 | 6.0609 | 0.1504 |
| 5.9041 | 0.66 | 80000 | 5.8688 | 0.1577 |
| 5.7999 | 0.74 | 90000 | 5.7595 | 0.1691 |
| 5.6997 | 0.82 | 100000 | 5.6469 | 0.1828 |
| 5.6002 | 0.9 | 110000 | 5.5358 | 0.1963 |
| 5.4372 | 0.98 | 120000 | 5.3113 | 0.2253 |
| 5.0465 | 1.07 | 130000 | 4.8765 | 0.2743 |
| 4.7373 | 1.15 | 140000 | 4.5536 | 0.3095 |
| 4.3779 | 1.23 | 150000 | 4.2078 | 0.3417 |
| 4.1299 | 1.31 | 160000 | 3.9910 | 0.3630 |
| 3.9585 | 1.39 | 170000 | 3.8347 | 0.3798 |
| 3.8423 | 1.47 | 180000 | 3.7274 | 0.3911 |
| 3.7403 | 1.56 | 190000 | 3.6422 | 0.3996 |
| 3.6767 | 1.64 | 200000 | 3.5669 | 0.4078 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3