|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: EN_mt5-small_15_spider |
|
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. --> |
|
|
|
# EN_mt5-small_15_spider |
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3864 |
|
- Rouge2 Precision: 0.4111 |
|
- Rouge2 Recall: 0.2576 |
|
- Rouge2 Fmeasure: 0.2936 |
|
|
|
## 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: 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: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure | |
|
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:| |
|
| No log | 1.0 | 438 | 3.8361 | 0.0002 | 0.0006 | 0.0002 | |
|
| 16.5932 | 2.0 | 876 | 1.5381 | 0.0031 | 0.0011 | 0.0016 | |
|
| 2.0998 | 3.0 | 1314 | 0.7401 | 0.0941 | 0.0521 | 0.0571 | |
|
| 1.1309 | 4.0 | 1752 | 0.4827 | 0.2672 | 0.1628 | 0.1794 | |
|
| 0.5166 | 5.0 | 2190 | 0.4313 | 0.3065 | 0.192 | 0.212 | |
|
| 0.3883 | 6.0 | 2628 | 0.4112 | 0.3388 | 0.2187 | 0.2415 | |
|
| 0.3299 | 7.0 | 3066 | 0.3975 | 0.376 | 0.2326 | 0.262 | |
|
| 0.293 | 8.0 | 3504 | 0.3896 | 0.3758 | 0.245 | 0.271 | |
|
| 0.293 | 9.0 | 3942 | 0.3914 | 0.3954 | 0.2501 | 0.2837 | |
|
| 0.2687 | 10.0 | 4380 | 0.3863 | 0.3947 | 0.2529 | 0.285 | |
|
| 0.2537 | 11.0 | 4818 | 0.3877 | 0.3959 | 0.2539 | 0.2861 | |
|
| 0.2431 | 12.0 | 5256 | 0.3860 | 0.4098 | 0.2544 | 0.2908 | |
|
| 0.2331 | 13.0 | 5694 | 0.3872 | 0.4031 | 0.2559 | 0.2906 | |
|
| 0.23 | 14.0 | 6132 | 0.3862 | 0.4082 | 0.2575 | 0.2928 | |
|
| 0.225 | 15.0 | 6570 | 0.3864 | 0.4111 | 0.2576 | 0.2936 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.7.dev0 |
|
- Tokenizers 0.13.3 |
|
|
