hbertv1-small-wt-48-emotion-emb-comp
This model is a fine-tuned version of gokuls/model_v1_complete_training_wt_init_48_small_emb_comp on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.4539
- Accuracy: 0.8805
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 |
---|---|---|---|---|
1.0539 | 1.0 | 250 | 0.5988 | 0.796 |
0.4694 | 2.0 | 500 | 0.4600 | 0.838 |
0.3032 | 3.0 | 750 | 0.4113 | 0.8535 |
0.2149 | 4.0 | 1000 | 0.4051 | 0.8705 |
0.1541 | 5.0 | 1250 | 0.4504 | 0.866 |
0.1072 | 6.0 | 1500 | 0.4539 | 0.8805 |
0.0714 | 7.0 | 1750 | 0.5262 | 0.8745 |
0.0489 | 8.0 | 2000 | 0.5990 | 0.8705 |
0.0326 | 9.0 | 2250 | 0.6372 | 0.875 |
0.0198 | 10.0 | 2500 | 0.6528 | 0.8725 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 10