|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: lr_3e-05_batch_4_epoch_5_model |
|
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. --> |
|
|
|
# lr_3e-05_batch_4_epoch_5_model |
|
|
|
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: 3.3894 |
|
- Rouge-1: 23.1328 |
|
- Rouge-2: 8.2792 |
|
- Rouge-l: 20.6918 |
|
- Gen Len: 17.5857 |
|
|
|
## 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: 3e-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: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge-1 | Rouge-2 | Rouge-l | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:-------:| |
|
| 4.3664 | 1.0 | 2714 | 3.6755 | 20.4397 | 7.1141 | 18.5425 | 15.2485 | |
|
| 4.045 | 2.0 | 5428 | 3.5179 | 21.7301 | 7.5448 | 19.5604 | 17.0885 | |
|
| 3.9873 | 3.0 | 8142 | 3.4348 | 22.7243 | 8.0561 | 20.314 | 17.2721 | |
|
| 3.8907 | 4.0 | 10856 | 3.4019 | 22.9219 | 8.1905 | 20.5067 | 17.4083 | |
|
| 3.7785 | 5.0 | 13570 | 3.3894 | 23.1328 | 8.2792 | 20.6918 | 17.5857 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.1.0 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
