|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
base_model: Prasadrao/roberta-large-go-emotions |
|
model-index: |
|
- name: roberta-large-go-emotions_v2 |
|
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. --> |
|
|
|
# roberta-large-go-emotions_v2 |
|
|
|
This model is a fine-tuned version of [Prasadrao/roberta-large-go-emotions](https://huggingface.co./Prasadrao/roberta-large-go-emotions) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0952 |
|
- Accuracy: 0.4613 |
|
- Precision: 0.5326 |
|
- Recall: 0.5126 |
|
- F1: 0.5165 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| No log | 1.0 | 679 | 0.0844 | 0.4552 | 0.5190 | 0.5026 | 0.4984 | |
|
| 0.0647 | 2.0 | 1358 | 0.0866 | 0.4449 | 0.5308 | 0.5100 | 0.5063 | |
|
| 0.0647 | 3.0 | 2037 | 0.0898 | 0.4471 | 0.5261 | 0.5253 | 0.5166 | |
|
| 0.0473 | 4.0 | 2716 | 0.0952 | 0.4613 | 0.5326 | 0.5126 | 0.5165 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.1 |
|
|