metadata
base_model: google-t5/t5-small
library_name: peft
license: apache-2.0
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: model
results: []
model
This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3571
- Rouge1: 0.1552
- Rouge2: 0.0673
- Rougel: 0.1307
- Rougelsum: 0.1308
- Gen Len: 18.9893
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 352 | 2.4060 | 0.1516 | 0.0638 | 0.1275 | 0.1276 | 18.9893 |
| 2.6991 | 2.0 | 704 | 2.3757 | 0.1545 | 0.0664 | 0.13 | 0.1301 | 18.9893 |
| 2.6372 | 3.0 | 1056 | 2.3621 | 0.1556 | 0.0676 | 0.131 | 0.131 | 18.9893 |
| 2.6372 | 4.0 | 1408 | 2.3571 | 0.1552 | 0.0673 | 0.1307 | 0.1308 | 18.9893 |
Framework versions
- PEFT 0.11.1
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1