<!-- 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. -->
hbertv2-emotion_48
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.3617
- Accuracy: 0.8955
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 |
|---|---|---|---|---|
| 1.3078 | 1.0 | 250 | 1.0127 | 0.613 |
| 0.6832 | 2.0 | 500 | 0.5913 | 0.81 |
| 0.4602 | 3.0 | 750 | 0.4422 | 0.876 |
| 0.3479 | 4.0 | 1000 | 0.5042 | 0.8575 |
| 0.2844 | 5.0 | 1250 | 0.3738 | 0.8825 |
| 0.2439 | 6.0 | 1500 | 0.3575 | 0.886 |
| 0.2029 | 7.0 | 1750 | 0.3617 | 0.8955 |
| 0.1675 | 8.0 | 2000 | 0.3826 | 0.887 |
| 0.1387 | 9.0 | 2250 | 0.3930 | 0.8875 |
| 0.1134 | 10.0 | 2500 | 0.4199 | 0.894 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
