metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: reviews_sum
results: []
reviews_sum
This model is a fine-tuned version of google/mt5-small on an reviews dataset. It achieves the following results on the evaluation set:
- Loss: 2.0004
- Rouge1: 0.0606
- Rouge2: 0.0075
- Rougel: 0.0615
- Rougelsum: 0.0611
- Gen Len: 19.0
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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 395 | 2.2625 | 0.0346 | 0.0069 | 0.035 | 0.0352 | 18.9778 |
| 3.319 | 2.0 | 790 | 2.1100 | 0.0419 | 0.0093 | 0.0428 | 0.0426 | 19.0 |
| 2.2853 | 3.0 | 1185 | 2.0675 | 0.047 | 0.0061 | 0.0483 | 0.0481 | 19.0 |
| 2.0122 | 4.0 | 1580 | 2.0005 | 0.0584 | 0.0095 | 0.0601 | 0.0599 | 19.0 |
| 2.0122 | 5.0 | 1975 | 2.0004 | 0.0606 | 0.0075 | 0.0615 | 0.0611 | 19.0 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0
- Datasets 2.14.6
- Tokenizers 0.14.1