it-emotion-analyzer_finetuned_pro_multilbel_emit
This model is a fine-tuned version of aiknowyou/it-emotion-analyzer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3116
- F1: 0.5269
- Roc Auc: 0.7253
- Accuracy: 0.3643
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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 | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.2723 | 1.0 | 1037 | 0.2654 | 0.3992 | 0.6370 | 0.2801 |
| 0.2241 | 2.0 | 2074 | 0.2465 | 0.4387 | 0.6603 | 0.2973 |
| 0.1774 | 3.0 | 3111 | 0.2547 | 0.5066 | 0.7051 | 0.3608 |
| 0.1435 | 4.0 | 4148 | 0.2627 | 0.4834 | 0.6933 | 0.3333 |
| 0.1111 | 5.0 | 5185 | 0.2850 | 0.4992 | 0.7052 | 0.3540 |
| 0.0873 | 6.0 | 6222 | 0.3010 | 0.5112 | 0.7177 | 0.3505 |
| 0.0699 | 7.0 | 7259 | 0.3116 | 0.5269 | 0.7253 | 0.3643 |
| 0.054 | 8.0 | 8296 | 0.3288 | 0.5223 | 0.7246 | 0.3625 |
| 0.05 | 9.0 | 9333 | 0.3405 | 0.5149 | 0.7223 | 0.3608 |
| 0.0416 | 10.0 | 10370 | 0.3437 | 0.5196 | 0.7268 | 0.3591 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 1