metadata
base_model: MilaNLProc/feel-it-italian-emotion
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: feel_it_finetuned_pro_emit_correlations
results: []
feel_it_finetuned_pro_emit_correlations
This model is a fine-tuned version of MilaNLProc/feel-it-italian-emotion on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3170
- F1: 0.4564
- Roc Auc: 0.6868
- Accuracy: 0.3162
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 |
|---|---|---|---|---|---|---|
| 0.309 | 1.0 | 1037 | 0.2952 | 0.1169 | 0.5394 | 0.2079 |
| 0.2586 | 2.0 | 2074 | 0.2731 | 0.2947 | 0.6109 | 0.2766 |
| 0.2142 | 3.0 | 3111 | 0.2721 | 0.4023 | 0.6552 | 0.3024 |
| 0.1829 | 4.0 | 4148 | 0.2731 | 0.4274 | 0.6637 | 0.3076 |
| 0.1564 | 5.0 | 5185 | 0.2862 | 0.4288 | 0.6700 | 0.3110 |
| 0.1341 | 6.0 | 6222 | 0.3004 | 0.4502 | 0.6826 | 0.3024 |
| 0.1187 | 7.0 | 7259 | 0.3126 | 0.4548 | 0.6892 | 0.3230 |
| 0.1024 | 8.0 | 8296 | 0.3170 | 0.4564 | 0.6868 | 0.3162 |
| 0.0939 | 9.0 | 9333 | 0.3280 | 0.4516 | 0.6874 | 0.3110 |
| 0.0864 | 10.0 | 10370 | 0.3316 | 0.4501 | 0.6873 | 0.3076 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1