metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: working
results: []
working
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1953
- Rouge1: 0.0416
- Rouge2: 0.0103
- Rougel: 0.0411
- Rougelsum: 0.0412
- Gen Len: 13.6933
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: 2e-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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 9.9902 | 1.0 | 938 | 3.5849 | 0.0198 | 0.0053 | 0.0196 | 0.0197 | 11.0792 |
| 4.5579 | 2.0 | 1876 | 3.2813 | 0.024 | 0.0067 | 0.0239 | 0.024 | 12.9491 |
| 4.2559 | 3.0 | 2814 | 3.2169 | 0.0396 | 0.0093 | 0.0391 | 0.0393 | 13.7149 |
| 4.1769 | 4.0 | 3752 | 3.1953 | 0.0416 | 0.0103 | 0.0411 | 0.0412 | 13.6933 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3