|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: emotional-distilbert |
|
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. --> |
|
|
|
# emotional-distilbert |
|
|
|
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.2137 |
|
- Accuracy: 0.4310 |
|
- F1: 0.4257 |
|
- Precision: 0.4466 |
|
- Recall: 0.4310 |
|
|
|
## 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 | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 2.7164 | 1.0 | 276 | 2.6348 | 0.2840 | 0.2368 | 0.4033 | 0.2840 | |
|
| 1.3322 | 2.0 | 552 | 2.0566 | 0.4183 | 0.4064 | 0.4338 | 0.4183 | |
|
| 0.5727 | 3.0 | 828 | 1.9395 | 0.4029 | 0.3975 | 0.4292 | 0.4029 | |
|
| 0.2102 | 4.0 | 1104 | 1.9605 | 0.4156 | 0.4115 | 0.4400 | 0.4156 | |
|
| 0.0697 | 5.0 | 1380 | 2.0963 | 0.4365 | 0.4205 | 0.4438 | 0.4365 | |
|
| 0.0261 | 6.0 | 1656 | 2.2137 | 0.4310 | 0.4257 | 0.4466 | 0.4310 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
