metadata
library_name: transformers
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: my_summary_model
results: []
my_summary_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: 2.7034
- Rouge1: 0.145
- Rouge2: 0.05
- Rougel: 0.1188
- Rougelsum: 0.1187
- Gen Len: 20.0
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|---|---|---|---|
| 3.4617 | 1.0 | 62 | 3.0013 | 0.1262 | 0.0332 | 0.104 | 0.104 | 20.0 |
| 3.0289 | 2.0 | 124 | 2.7830 | 0.1375 | 0.045 | 0.112 | 0.1123 | 20.0 |
| 2.9931 | 3.0 | 186 | 2.7208 | 0.1439 | 0.0491 | 0.1174 | 0.1171 | 20.0 |
| 2.9153 | 4.0 | 248 | 2.7034 | 0.145 | 0.05 | 0.1188 | 0.1187 | 20.0 |
Framework versions
- Transformers 4.55.0
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4