metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt5-small-News
results: []
mt5-small-News
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4331
- Rouge1: 6.6074
- Rouge2: 0.8
- Rougel: 6.5487
- Rougelsum: 6.6233
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: 5.6e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 5.7796 | 1.0 | 625 | 2.7282 | 4.0839 | 0.8785 | 4.0421 | 4.0758 |
| 3.4978 | 2.0 | 1250 | 2.6171 | 6.6481 | 0.9067 | 6.6002 | 6.6437 |
| 3.2419 | 3.0 | 1875 | 2.5208 | 6.6661 | 0.64 | 6.5897 | 6.6246 |
| 3.1063 | 4.0 | 2500 | 2.4918 | 7.2246 | 1.0467 | 7.1758 | 7.1947 |
| 3.0177 | 5.0 | 3125 | 2.4535 | 6.8523 | 1.0 | 6.8009 | 6.8923 |
| 2.9537 | 6.0 | 3750 | 2.4452 | 6.459 | 0.8667 | 6.4208 | 6.481 |
| 2.9156 | 7.0 | 4375 | 2.4373 | 6.5019 | 0.8 | 6.4421 | 6.5094 |
| 2.8914 | 8.0 | 5000 | 2.4331 | 6.6074 | 0.8 | 6.5487 | 6.6233 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2