<!-- 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-small-wt-frz-48-Massive-intent-emb-comp
This model is a fine-tuned version of gokuls/model_v1_complete_training_wt_init_48_small_emb_comp_frz on the massive dataset. It achieves the following results on the evaluation set:
- Loss: 0.6512
- Accuracy: 0.8382
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 |
|---|---|---|---|---|
| 2.3044 | 1.0 | 180 | 1.1025 | 0.7167 |
| 0.8662 | 2.0 | 360 | 0.7731 | 0.7934 |
| 0.5469 | 3.0 | 540 | 0.6981 | 0.8224 |
| 0.357 | 4.0 | 720 | 0.6512 | 0.8382 |
| 0.228 | 5.0 | 900 | 0.6980 | 0.8254 |
| 0.1435 | 6.0 | 1080 | 0.7169 | 0.8278 |
| 0.0863 | 7.0 | 1260 | 0.7441 | 0.8323 |
| 0.0534 | 8.0 | 1440 | 0.7516 | 0.8382 |
| 0.0334 | 9.0 | 1620 | 0.8162 | 0.8357 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.1
- Tokenizers 0.13.3
