metadata
license: cc-by-sa-4.0
base_model: aiknowyou/it-emotion-analyzer
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: it-emotion-analyzer_finetuned_pro_multilbel_emit
results: []
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: 0.2714
- F1: 0.4804
- Roc Auc: 0.6939
- Accuracy: 0.3110
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 |
|---|---|---|---|---|---|---|
| 0.2712 | 1.0 | 1037 | 0.2740 | 0.3755 | 0.6250 | 0.2680 |
| 0.2238 | 2.0 | 2074 | 0.2703 | 0.4161 | 0.6504 | 0.2749 |
| 0.1743 | 3.0 | 3111 | 0.2714 | 0.4804 | 0.6939 | 0.3110 |
| 0.143 | 4.0 | 4148 | 0.2838 | 0.4632 | 0.6811 | 0.2887 |
| 0.1089 | 5.0 | 5185 | 0.2971 | 0.4756 | 0.6897 | 0.3041 |
| 0.0874 | 6.0 | 6222 | 0.3242 | 0.4718 | 0.6965 | 0.2887 |
| 0.0726 | 7.0 | 7259 | 0.3414 | 0.4798 | 0.7003 | 0.3076 |
| 0.0565 | 8.0 | 8296 | 0.3538 | 0.4690 | 0.6897 | 0.2973 |
| 0.0501 | 9.0 | 9333 | 0.3712 | 0.4696 | 0.6959 | 0.2938 |
| 0.0426 | 10.0 | 10370 | 0.3692 | 0.4702 | 0.6922 | 0.2904 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1