metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: google/flan-t5-small
metrics:
- rouge
model-index:
- name: flan-t5-small-chat
results: []
flan-t5-small-chat
This model is a fine-tuned version of google/flan-t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4063
- Rouge1: 12.3084
- Rouge2: 4.6455
- Rougel: 12.1876
- Rougelsum: 12.1825
- Gen Len: 16.2885
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|---|
| 2.6252 | 1.0 | 2000 | 2.4694 | 12.2248 | 4.6103 | 12.1019 | 12.0965 | 15.146 |
| 2.5362 | 2.0 | 4000 | 2.4252 | 12.2682 | 4.7742 | 12.136 | 12.1353 | 15.9622 |
| 2.466 | 3.0 | 6000 | 2.4110 | 12.0624 | 4.4491 | 11.9607 | 11.954 | 16.2845 |
| 2.459 | 4.0 | 8000 | 2.4063 | 12.3084 | 4.6455 | 12.1876 | 12.1825 | 16.2885 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1