<!-- 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-emotion-emb-comp
This model is a fine-tuned version of gokuls/model_v1_complete_training_wt_init_48_small_emb_comp_frz on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.4013
- Accuracy: 0.887
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1127 | 1.0 | 250 | 0.6028 | 0.798 |
| 0.4399 | 2.0 | 500 | 0.4066 | 0.855 |
| 0.2726 | 3.0 | 750 | 0.3762 | 0.866 |
| 0.1907 | 4.0 | 1000 | 0.3649 | 0.876 |
| 0.1412 | 5.0 | 1250 | 0.4169 | 0.8755 |
| 0.1065 | 6.0 | 1500 | 0.4013 | 0.887 |
| 0.0761 | 7.0 | 1750 | 0.4679 | 0.884 |
| 0.0548 | 8.0 | 2000 | 0.5221 | 0.8775 |
| 0.0379 | 9.0 | 2250 | 0.5458 | 0.8835 |
| 0.0233 | 10.0 | 2500 | 0.5586 | 0.8805 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.1
- Tokenizers 0.13.3
