hbertv2-emotion_48_emb_compress
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.5104
- Accuracy: 0.8572
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 |
---|---|---|---|---|
1.5945 | 1.0 | 250 | 1.4950 | 0.478 |
1.352 | 2.0 | 500 | 1.1901 | 0.5595 |
1.0712 | 3.0 | 750 | 0.9287 | 0.651 |
0.8129 | 4.0 | 1000 | 0.7898 | 0.6955 |
0.6574 | 5.0 | 1250 | 0.7526 | 0.7335 |
0.5577 | 6.0 | 1500 | 0.6192 | 0.813 |
0.4418 | 7.0 | 1750 | 0.5638 | 0.8425 |
0.3931 | 8.0 | 2000 | 0.5432 | 0.8395 |
0.3536 | 9.0 | 2250 | 0.4958 | 0.8495 |
0.3184 | 10.0 | 2500 | 0.5104 | 0.851 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 7