|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: EN_mt5-small_10_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_10_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: 0.4350 |
|
- Rouge2 Precision: 0.3068 |
|
- Rouge2 Recall: 0.202 |
|
- Rouge2 Fmeasure: 0.2177 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure | |
|
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:| |
|
| No log | 1.0 | 438 | 4.5527 | 0.0024 | 0.001 | 0.0014 | |
|
| 17.6146 | 2.0 | 876 | 1.6584 | 0.0 | 0.0 | 0.0 | |
|
| 2.53 | 3.0 | 1314 | 1.5698 | 0.0 | 0.0 | 0.0 | |
|
| 1.9045 | 4.0 | 1752 | 1.3153 | 0.0206 | 0.0074 | 0.0106 | |
|
| 1.5088 | 5.0 | 2190 | 0.6748 | 0.1009 | 0.056 | 0.0623 | |
|
| 0.8005 | 6.0 | 2628 | 0.5124 | 0.2301 | 0.1513 | 0.1593 | |
|
| 0.5297 | 7.0 | 3066 | 0.4683 | 0.2899 | 0.1903 | 0.2021 | |
|
| 0.4507 | 8.0 | 3504 | 0.4464 | 0.2966 | 0.2016 | 0.2129 | |
|
| 0.4507 | 9.0 | 3942 | 0.4385 | 0.3125 | 0.2065 | 0.2224 | |
|
| 0.4161 | 10.0 | 4380 | 0.4350 | 0.3068 | 0.202 | 0.2177 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.7.dev0 |
|
- Tokenizers 0.13.3 |
|
|
