|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: mt5-small-task1-dataset2 |
|
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-dataset2 |
|
|
|
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: 0.3880 |
|
- Accuracy: 0.182 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 4.3254 | 1.0 | 250 | 0.7650 | 0.0 | |
|
| 0.9928 | 2.0 | 500 | 0.6343 | 0.034 | |
|
| 0.725 | 3.0 | 750 | 0.5447 | 0.114 | |
|
| 0.6197 | 4.0 | 1000 | 0.5004 | 0.106 | |
|
| 0.566 | 5.0 | 1250 | 0.4723 | 0.106 | |
|
| 0.5267 | 6.0 | 1500 | 0.4457 | 0.128 | |
|
| 0.4978 | 7.0 | 1750 | 0.4222 | 0.144 | |
|
| 0.4803 | 8.0 | 2000 | 0.4103 | 0.156 | |
|
| 0.4683 | 9.0 | 2250 | 0.3969 | 0.172 | |
|
| 0.4583 | 10.0 | 2500 | 0.3931 | 0.178 | |
|
| 0.4526 | 11.0 | 2750 | 0.3901 | 0.18 | |
|
| 0.4438 | 12.0 | 3000 | 0.3880 | 0.182 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
