|
--- |
|
base_model: cardiffnlp/twitter-roberta-base-irony |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: Twroberta-baseB_5epoch |
|
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. --> |
|
|
|
# Twroberta-baseB_5epoch |
|
|
|
This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-irony](https://huggingface.co/cardiffnlp/twitter-roberta-base-irony) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1414 |
|
- Accuracy: 0.7971 |
|
- Precision: 0.2686 |
|
- Recall: 0.3395 |
|
- F1: 0.2984 |
|
|
|
## 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: 5e-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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| No log | 1.0 | 217 | 0.1259 | 0.8571 | 0.0 | 0.0 | 0.0 | |
|
| No log | 2.0 | 434 | 0.1252 | 0.8579 | 0.3690 | 0.0185 | 0.0351 | |
|
| 0.1645 | 3.0 | 651 | 0.1203 | 0.8414 | 0.2958 | 0.2066 | 0.2431 | |
|
| 0.1645 | 4.0 | 868 | 0.1383 | 0.7686 | 0.2221 | 0.3616 | 0.2751 | |
|
| 0.0952 | 5.0 | 1085 | 0.1414 | 0.7971 | 0.2686 | 0.3395 | 0.2984 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
