|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: outputs |
|
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. --> |
|
|
|
# outputs |
|
|
|
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: 0.7371 |
|
- Rouge1: 8.8243 |
|
- Rouge2: 1.3093 |
|
- Rougel: 8.7971 |
|
- Rougelsum: 8.838 |
|
- Gen Len: 18.6465 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 0.8929 | 1.0 | 10995 | 0.8547 | 8.6675 | 1.2002 | 8.6197 | 8.6811 | 18.5008 | |
|
| 0.8248 | 2.0 | 21990 | 0.7847 | 8.8312 | 1.3639 | 8.8073 | 8.8448 | 18.4607 | |
|
| 0.7483 | 3.0 | 32985 | 0.7488 | 8.913 | 1.3639 | 8.8925 | 8.9096 | 18.9223 | |
|
| 0.6492 | 4.0 | 43980 | 0.7371 | 8.8243 | 1.3093 | 8.7971 | 8.838 | 18.6465 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|