hbertv1-mini-wt-48-emotion
This model is a fine-tuned version of gokuls/model_v1_complete_training_wt_init_48_mini on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.2561
- Accuracy: 0.908
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 |
---|---|---|---|---|
1.0852 | 1.0 | 250 | 0.5567 | 0.8195 |
0.4522 | 2.0 | 500 | 0.3409 | 0.8775 |
0.3152 | 3.0 | 750 | 0.3007 | 0.8885 |
0.2646 | 4.0 | 1000 | 0.2999 | 0.9045 |
0.23 | 5.0 | 1250 | 0.2842 | 0.8945 |
0.205 | 6.0 | 1500 | 0.2658 | 0.9035 |
0.1871 | 7.0 | 1750 | 0.2674 | 0.902 |
0.1623 | 8.0 | 2000 | 0.2561 | 0.908 |
0.1488 | 9.0 | 2250 | 0.2529 | 0.9075 |
0.1379 | 10.0 | 2500 | 0.2523 | 0.908 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 3