bert_12_layer_model_v1_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: 2.6168
- Accuracy: 0.5281
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 |
|---|---|---|---|---|
| 6.4172 | 0.08 | 10000 | 6.3664 | 0.1317 |
| 6.1014 | 0.16 | 20000 | 6.0532 | 0.1497 |
| 5.8255 | 0.25 | 30000 | 5.7466 | 0.1656 |
| 5.0543 | 0.33 | 40000 | 4.7539 | 0.2752 |
| 4.1669 | 0.41 | 50000 | 3.8568 | 0.3739 |
| 3.7259 | 0.49 | 60000 | 3.4751 | 0.4215 |
| 3.4547 | 0.57 | 70000 | 3.2615 | 0.4469 |
| 3.2968 | 0.66 | 80000 | 3.1250 | 0.4638 |
| 3.1805 | 0.74 | 90000 | 3.0246 | 0.4760 |
| 3.0963 | 0.82 | 100000 | 2.9491 | 0.4858 |
| 3.0238 | 0.9 | 110000 | 2.8874 | 0.4933 |
| 2.9729 | 0.98 | 120000 | 2.8317 | 0.5003 |
| 2.9156 | 1.07 | 130000 | 2.7824 | 0.5063 |
| 2.8784 | 1.15 | 140000 | 2.7434 | 0.5111 |
| 2.8333 | 1.23 | 150000 | 2.7081 | 0.5164 |
| 2.8043 | 1.31 | 160000 | 2.6730 | 0.5205 |
| 2.7646 | 1.39 | 170000 | 2.6436 | 0.5248 |
| 2.7403 | 1.47 | 180000 | 2.6168 | 0.5281 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3