metadata
library_name: transformers
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: summarization_model
results: []
summarization_model
This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8757
- Rouge1: 0.394
- Rouge2: 0.166
- Rougel: 0.3264
- Rougelsum: 0.3263
- Gen Len: 16.3055
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
- 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 | 389 | 1.9453 | 0.3776 | 0.1556 | 0.3135 | 0.3136 | 15.9023 |
| 2.2585 | 2.0 | 778 | 1.8995 | 0.3864 | 0.1602 | 0.3209 | 0.321 | 16.1286 |
| 2.1003 | 3.0 | 1167 | 1.8807 | 0.3926 | 0.1654 | 0.3256 | 0.3256 | 16.1897 |
| 2.064 | 4.0 | 1556 | 1.8757 | 0.394 | 0.166 | 0.3264 | 0.3263 | 16.3055 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1