<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
HBERTv1_48_L8_H256_A4_massive
This model is a fine-tuned version of gokuls/HBERTv1_48_L8_H256_A4 on the massive dataset. It achieves the following results on the evaluation set:
- Loss: 0.8150
- Accuracy: 0.8249
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 33
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.4219 | 1.0 | 180 | 2.6196 | 0.3271 |
| 2.1509 | 2.0 | 360 | 1.6609 | 0.5391 |
| 1.4651 | 3.0 | 540 | 1.2692 | 0.6729 |
| 1.0854 | 4.0 | 720 | 1.0301 | 0.7324 |
| 0.8432 | 5.0 | 900 | 0.9082 | 0.7644 |
| 0.6907 | 6.0 | 1080 | 0.8722 | 0.7693 |
| 0.5661 | 7.0 | 1260 | 0.8526 | 0.7885 |
| 0.4712 | 8.0 | 1440 | 0.8450 | 0.8087 |
| 0.4047 | 9.0 | 1620 | 0.8018 | 0.8077 |
| 0.3505 | 10.0 | 1800 | 0.8219 | 0.8136 |
| 0.3046 | 11.0 | 1980 | 0.8110 | 0.8210 |
| 0.2649 | 12.0 | 2160 | 0.7957 | 0.8200 |
| 0.2341 | 13.0 | 2340 | 0.8053 | 0.8219 |
| 0.2046 | 14.0 | 2520 | 0.8194 | 0.8229 |
| 0.189 | 15.0 | 2700 | 0.8150 | 0.8249 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.0
