metadata
library_name: peft
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
model-index:
- name: Summarization
results: []
datasets:
- abisee/cnn_dailymail
language:
- en
metrics:
- rouge
- bleu
Summarization
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1039
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.362 | 0.2229 | 500 | 1.4059 |
| 1.3409 | 0.4458 | 1000 | 1.1536 |
| 1.1552 | 0.6687 | 1500 | 1.1228 |
| 1.1308 | 0.8916 | 2000 | 1.1134 |
| 1.1192 | 1.1141 | 2500 | 1.1088 |
| 1.1165 | 1.3370 | 3000 | 1.1061 |
| 1.1147 | 1.5599 | 3500 | 1.1046 |
| 1.1151 | 1.7828 | 4000 | 1.1039 |
Framework versions
- PEFT 0.14.0
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0