|
--- |
|
base_model: MilaNLProc/feel-it-italian-emotion |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: multilabel_emotion_classification_finetuned_multimodal |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# multilabel_emotion_classification_finetuned_multimodal |
|
|
|
This model is a fine-tuned version of [MilaNLProc/feel-it-italian-emotion](https://huggingface.co/MilaNLProc/feel-it-italian-emotion) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3025 |
|
- F1: 0.2543 |
|
- Roc Auc: 0.5733 |
|
- Accuracy: 0.2464 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
|
| No log | 1.0 | 35 | 0.4602 | 0.2394 | 0.5743 | 0.1884 | |
|
| No log | 2.0 | 70 | 0.3852 | 0.0 | 0.5 | 0.1087 | |
|
| No log | 3.0 | 105 | 0.3511 | 0.0 | 0.5 | 0.1087 | |
|
| No log | 4.0 | 140 | 0.3328 | 0.0 | 0.5 | 0.1087 | |
|
| No log | 5.0 | 175 | 0.3221 | 0.0 | 0.5 | 0.1087 | |
|
| No log | 6.0 | 210 | 0.3154 | 0.0136 | 0.5034 | 0.1159 | |
|
| No log | 7.0 | 245 | 0.3103 | 0.0789 | 0.5205 | 0.1449 | |
|
| No log | 8.0 | 280 | 0.3064 | 0.1274 | 0.5338 | 0.1739 | |
|
| No log | 9.0 | 315 | 0.3036 | 0.2442 | 0.5699 | 0.2391 | |
|
| No log | 10.0 | 350 | 0.3025 | 0.2543 | 0.5733 | 0.2464 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 1.11.0 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
