model_v1_complete_training_wt_init_48_mini
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0264
- Accuracy: 0.4705
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 |
|---|---|---|---|---|
| 5.9396 | 0.25 | 30000 | 5.8819 | 0.1521 |
| 4.3744 | 0.49 | 60000 | 4.1662 | 0.3331 |
| 3.901 | 0.74 | 90000 | 3.6945 | 0.3869 |
| 3.719 | 0.98 | 120000 | 3.5061 | 0.4091 |
| 3.6055 | 1.23 | 150000 | 3.3960 | 0.4227 |
| 3.5327 | 1.47 | 180000 | 3.3195 | 0.4324 |
| 3.4776 | 1.72 | 210000 | 3.2639 | 0.4396 |
| 3.4304 | 1.97 | 240000 | 3.2153 | 0.4458 |
| 3.3846 | 2.21 | 270000 | 3.1775 | 0.4506 |
| 3.3467 | 2.46 | 300000 | 3.1462 | 0.4547 |
| 3.3217 | 2.7 | 330000 | 3.1217 | 0.4581 |
| 3.2998 | 2.95 | 360000 | 3.0995 | 0.4609 |
| 3.2792 | 3.2 | 390000 | 3.0830 | 0.4632 |
| 3.2767 | 3.44 | 420000 | 3.0674 | 0.4653 |
| 3.2565 | 3.69 | 450000 | 3.0556 | 0.4668 |
| 3.2503 | 3.93 | 480000 | 3.0452 | 0.4680 |
| 3.2373 | 4.18 | 510000 | 3.0383 | 0.4690 |
| 3.2267 | 4.42 | 540000 | 3.0327 | 0.4696 |
| 3.2303 | 4.67 | 570000 | 3.0287 | 0.4703 |
| 3.2264 | 4.92 | 600000 | 3.0264 | 0.4705 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 3