|
|
--- |
|
|
base_model: cardiffnlp/twitter-roberta-base-irony |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
model-index: |
|
|
- name: Twroberta-baseB_15epoch |
|
|
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_15epoch |
|
|
|
|
|
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: 0.1971 |
|
|
- Accuracy: 0.7686 |
|
|
- Precision: 0.2328 |
|
|
- Recall: 0.3210 |
|
|
- F1: 0.2693 |
|
|
|
|
|
## 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: 15 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
|
| No log | 1.0 | 217 | 0.1248 | 0.8571 | 0.0 | 0.0 | 0.0 | |
|
|
| No log | 2.0 | 434 | 0.1250 | 0.8679 | 0.5258 | 0.0701 | 0.1237 | |
|
|
| 0.1617 | 3.0 | 651 | 0.1225 | 0.825 | 0.2771 | 0.2657 | 0.2712 | |
|
|
| 0.1617 | 4.0 | 868 | 0.1325 | 0.8079 | 0.3164 | 0.2583 | 0.2554 | |
|
|
| 0.0885 | 5.0 | 1085 | 0.1553 | 0.7707 | 0.2169 | 0.2694 | 0.2391 | |
|
|
| 0.0885 | 6.0 | 1302 | 0.1680 | 0.7507 | 0.2112 | 0.3358 | 0.2592 | |
|
|
| 0.0392 | 7.0 | 1519 | 0.2129 | 0.7093 | 0.1936 | 0.3875 | 0.2575 | |
|
|
| 0.0392 | 8.0 | 1736 | 0.1717 | 0.7764 | 0.2316 | 0.2841 | 0.2528 | |
|
|
| 0.0392 | 9.0 | 1953 | 0.1915 | 0.7507 | 0.2287 | 0.3321 | 0.2671 | |
|
|
| 0.0178 | 10.0 | 2170 | 0.1987 | 0.7586 | 0.2294 | 0.3653 | 0.2809 | |
|
|
| 0.0178 | 11.0 | 2387 | 0.1923 | 0.7564 | 0.2287 | 0.3358 | 0.2710 | |
|
|
| 0.0108 | 12.0 | 2604 | 0.1925 | 0.7586 | 0.2317 | 0.3358 | 0.2729 | |
|
|
| 0.0108 | 13.0 | 2821 | 0.1965 | 0.775 | 0.2356 | 0.3284 | 0.2743 | |
|
|
| 0.0078 | 14.0 | 3038 | 0.1964 | 0.7621 | 0.2326 | 0.3284 | 0.2712 | |
|
|
| 0.0078 | 15.0 | 3255 | 0.1971 | 0.7686 | 0.2328 | 0.3210 | 0.2693 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.41.2 |
|
|
- Pytorch 2.3.0+cu121 |
|
|
- Datasets 2.19.2 |
|
|
- Tokenizers 0.19.1 |
|
|
|
