|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: mt5-small-task1-dataset1 |
|
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-small-task1-dataset1 |
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6887 |
|
- Accuracy: 0.618 |
|
|
|
## 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: 5.6e-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: 12 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 10.3747 | 1.0 | 250 | 1.8894 | 0.19 | |
|
| 2.1263 | 2.0 | 500 | 1.3543 | 0.2 | |
|
| 1.5986 | 3.0 | 750 | 1.2566 | 0.2 | |
|
| 1.43 | 4.0 | 1000 | 1.0943 | 0.374 | |
|
| 1.2409 | 5.0 | 1250 | 0.9063 | 0.506 | |
|
| 1.0295 | 6.0 | 1500 | 0.8092 | 0.552 | |
|
| 0.9365 | 7.0 | 1750 | 0.7702 | 0.552 | |
|
| 0.9121 | 8.0 | 2000 | 0.7411 | 0.59 | |
|
| 0.8275 | 9.0 | 2250 | 0.7289 | 0.588 | |
|
| 0.8063 | 10.0 | 2500 | 0.6968 | 0.61 | |
|
| 0.7903 | 11.0 | 2750 | 0.6868 | 0.616 | |
|
| 0.7674 | 12.0 | 3000 | 0.6887 | 0.618 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
