|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
base_model: google/mt5-large |
|
model-index: |
|
- name: mt5_emotion_multi |
|
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. --> |
|
|
|
# mt5_emotion_multi |
|
|
|
This model is a fine-tuned version of [google/mt5-large](https://huggingface.co/google/mt5-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3993 |
|
- Accuracy: 0.901 |
|
- Precision: 0.9037 |
|
- Recall: 0.901 |
|
- F1: 0.9008 |
|
|
|
## 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: 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 | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| No log | 0.4 | 50 | 1.6030 | 0.405 | 0.2816 | 0.405 | 0.3089 | |
|
| No log | 0.8 | 100 | 1.3838 | 0.5 | 0.5244 | 0.5 | 0.3826 | |
|
| 1.5266 | 1.2 | 150 | 1.1754 | 0.535 | 0.6592 | 0.535 | 0.4998 | |
|
| 1.5266 | 1.6 | 200 | 1.0208 | 0.645 | 0.7211 | 0.645 | 0.6155 | |
|
| 0.7436 | 2.0 | 250 | 0.7959 | 0.735 | 0.8247 | 0.735 | 0.7121 | |
|
| 0.7436 | 2.4 | 300 | 0.6869 | 0.79 | 0.8289 | 0.79 | 0.7871 | |
|
| 0.7436 | 2.8 | 350 | 0.6828 | 0.805 | 0.8335 | 0.805 | 0.7983 | |
|
| 0.2185 | 3.2 | 400 | 1.0537 | 0.75 | 0.8211 | 0.75 | 0.7343 | |
|
| 0.2185 | 3.6 | 450 | 0.5383 | 0.85 | 0.8587 | 0.85 | 0.8474 | |
|
| 0.1285 | 4.0 | 500 | 0.9033 | 0.795 | 0.8512 | 0.795 | 0.7851 | |
|
| 0.1285 | 4.4 | 550 | 1.1142 | 0.755 | 0.8272 | 0.755 | 0.7371 | |
|
| 0.1285 | 4.8 | 600 | 1.0917 | 0.77 | 0.8302 | 0.77 | 0.7640 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
