bert_12_layer_model_v2_complete_training_new_emb_compress_48
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.8914
- Accuracy: 0.2945
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 |
|---|---|---|---|---|
| 7.111 | 0.08 | 10000 | 7.0878 | 0.0852 |
| 6.6847 | 0.16 | 20000 | 6.6790 | 0.1094 |
| 6.5375 | 0.25 | 30000 | 6.5342 | 0.1189 |
| 6.4521 | 0.33 | 40000 | 6.4410 | 0.1272 |
| 6.3795 | 0.41 | 50000 | 6.3764 | 0.1316 |
| 6.3315 | 0.49 | 60000 | 6.3245 | 0.1354 |
| 6.2877 | 0.57 | 70000 | 6.2828 | 0.1382 |
| 6.2569 | 0.66 | 80000 | 6.2511 | 0.1409 |
| 6.2242 | 0.74 | 90000 | 6.2219 | 0.1422 |
| 6.1972 | 0.82 | 100000 | 6.1979 | 0.1434 |
| 6.1799 | 0.9 | 110000 | 6.1787 | 0.1445 |
| 6.162 | 0.98 | 120000 | 6.1568 | 0.1458 |
| 6.1324 | 1.07 | 130000 | 6.1354 | 0.1469 |
| 6.1067 | 1.15 | 140000 | 6.1014 | 0.1475 |
| 6.0558 | 1.23 | 150000 | 6.0465 | 0.1493 |
| 5.9739 | 1.31 | 160000 | 5.9502 | 0.1561 |
| 5.8932 | 1.39 | 170000 | 5.8741 | 0.1683 |
| 5.7488 | 1.47 | 180000 | 5.7045 | 0.2000 |
| 5.5336 | 1.56 | 190000 | 5.4830 | 0.2298 |
| 5.3678 | 1.64 | 200000 | 5.2979 | 0.2504 |
| 5.1831 | 1.72 | 210000 | 5.1048 | 0.2714 |
| 4.9486 | 1.8 | 220000 | 4.8914 | 0.2945 |
Framework versions
- Transformers 4.30.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3