bert_12_layer_model_v2_complete_training_new_wt_init_48
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6821
- Accuracy: 0.5170
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 |
|---|---|---|---|---|
| 6.4035 | 0.08 | 10000 | 6.3587 | 0.1308 |
| 6.171 | 0.16 | 20000 | 6.1316 | 0.1478 |
| 4.1594 | 0.25 | 30000 | 3.9287 | 0.3710 |
| 3.7683 | 0.33 | 40000 | 3.5265 | 0.4190 |
| 3.5679 | 0.41 | 50000 | 3.3359 | 0.4400 |
| 3.4509 | 0.49 | 60000 | 3.2192 | 0.4534 |
| 3.3501 | 0.57 | 70000 | 3.1324 | 0.4631 |
| 3.2776 | 0.66 | 80000 | 3.0619 | 0.4713 |
| 3.211 | 0.74 | 90000 | 3.0021 | 0.4779 |
| 3.1587 | 0.82 | 100000 | 2.9570 | 0.4836 |
| 3.1076 | 0.9 | 110000 | 2.9157 | 0.4883 |
| 3.0716 | 0.98 | 120000 | 2.8727 | 0.4931 |
| 3.0248 | 1.07 | 130000 | 2.8422 | 0.4969 |
| 2.9941 | 1.15 | 140000 | 2.8102 | 0.5009 |
| 2.9629 | 1.23 | 150000 | 2.7851 | 0.5041 |
| 2.9422 | 1.31 | 160000 | 2.7617 | 0.5065 |
| 2.9062 | 1.39 | 170000 | 2.7347 | 0.5102 |
| 2.8847 | 1.47 | 180000 | 2.7163 | 0.5126 |
| 2.8556 | 1.56 | 190000 | 2.6974 | 0.5148 |
| 2.8483 | 1.64 | 200000 | 2.6821 | 0.5170 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3