|
--- |
|
base_model: Musixmatch/umberto-commoncrawl-cased-v1 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: irony_sarcasm_ita |
|
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. --> |
|
|
|
# irony_sarcasm_ita |
|
|
|
This model is a fine-tuned version of [Musixmatch/umberto-commoncrawl-cased-v1](https://huggingface.co/Musixmatch/umberto-commoncrawl-cased-v1) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3359 |
|
- Accuracy: 0.8282 |
|
- F1: 0.4474 |
|
|
|
## 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 | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.5985 | 1.0 | 715 | 0.6131 | 0.7955 | 0.4459 | |
|
| 0.2312 | 2.0 | 1430 | 0.8496 | 0.8196 | 0.4403 | |
|
| 0.0632 | 3.0 | 2145 | 0.8931 | 0.8402 | 0.3988 | |
|
| 0.0464 | 4.0 | 2860 | 1.0947 | 0.8402 | 0.4332 | |
|
| 0.015 | 5.0 | 3575 | 1.3966 | 0.8041 | 0.4004 | |
|
| 0.0174 | 6.0 | 4290 | 1.3359 | 0.8282 | 0.4474 | |
|
| 0.0102 | 7.0 | 5005 | 1.3382 | 0.8299 | 0.3857 | |
|
| 0.0011 | 8.0 | 5720 | 1.4105 | 0.8213 | 0.4196 | |
|
| 0.0098 | 9.0 | 6435 | 1.4673 | 0.8213 | 0.4253 | |
|
| 0.0057 | 10.0 | 7150 | 1.4211 | 0.8333 | 0.4226 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.3.0+cu118 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
