|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: gbharathi80/mt5-small-finetuned-amazon-en-es |
|
results: [] |
|
datasets: |
|
- amazon_reviews_multi |
|
language: |
|
- es |
|
- en |
|
metrics: |
|
- bleu |
|
- rouge |
|
pipeline_tag: summarization |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
# gbharathi80/mt5-small-finetuned-amazon-en-es |
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an amazon reviews dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 4.2325 |
|
- Validation Loss: 3.4452 |
|
- Epoch: 7 |
|
|
|
## Model description |
|
|
|
This is a fine-tuned version of the google/mt5-small model for translation tasks from English to Spanish for text summarization |
|
## Intended uses & limitations |
|
|
|
multi lingual text summarization. model trained using spanish and english revirwes |
|
## Training and evaluation data |
|
|
|
DatasetDict({ |
|
train: Dataset({ |
|
features: ['review_id', 'product_id', 'reviewer_id', 'stars', 'review_body', 'review_title', 'language', 'product_category'], |
|
num_rows: 200000 |
|
}) |
|
validation: Dataset({ |
|
features: ['review_id', 'product_id', 'reviewer_id', 'stars', 'review_body', 'review_title', 'language', 'product_category'], |
|
num_rows: 5000 |
|
}) |
|
test: Dataset({ |
|
features: ['review_id', 'product_id', 'reviewer_id', 'stars', 'review_body', 'review_title', 'language', 'product_category'], |
|
num_rows: 5000 |
|
}) |
|
}) |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 9672, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01} |
|
- training_precision: mixed_float16 |
|
|
|
### Training results |
|
|
|
| Train Loss | Validation Loss | Epoch | |
|
|:----------:|:---------------:|:-----:| |
|
| 10.7747 | 4.7510 | 0 | |
|
| 6.3001 | 4.0096 | 1 | |
|
| 5.4388 | 3.7376 | 2 | |
|
| 4.9710 | 3.6136 | 3 | |
|
| 4.6689 | 3.5349 | 4 | |
|
| 4.4622 | 3.4885 | 5 | |
|
| 4.3101 | 3.4537 | 6 | |
|
| 4.2325 | 3.4452 | 7 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.1 |
|
- TensorFlow 2.9.1 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |