metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: google-t5/t5-small
metrics:
- rouge
model-index:
- name: summarization_fine_tune_peft
results: []
summarization_fine_tune_peft
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: 3.7075
- Rouge1: 0.1357
- Rouge2: 0.045
- Rougel: 0.1149
- Rougelsum: 0.1149
- 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: 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 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 62 | 4.7640 | 0.1417 | 0.0501 | 0.1206 | 0.1207 | 19.0 |
| No log | 2.0 | 124 | 4.1242 | 0.1408 | 0.0486 | 0.1194 | 0.1193 | 19.0 |
| No log | 3.0 | 186 | 3.8060 | 0.136 | 0.0462 | 0.1155 | 0.1155 | 19.0 |
| No log | 4.0 | 248 | 3.7075 | 0.1357 | 0.045 | 0.1149 | 0.1149 | 19.0 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2