metadata
license: apache-2.0
base_model: google/flan-t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: flan-t5-small-test
results: []
flan-t5-small-test
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5080
- Rouge1: 6.8809
- Rouge2: 4.1822
- Rougel: 6.5856
- Rougelsum: 6.6317
- 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: 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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 100 | 0.6844 | 7.3626 | 4.67 | 7.1942 | 7.194 | 19.0 |
No log | 2.0 | 200 | 0.5658 | 6.7434 | 3.9578 | 6.4129 | 6.4381 | 19.0 |
No log | 3.0 | 300 | 0.5290 | 6.8062 | 4.081 | 6.5137 | 6.5406 | 19.0 |
No log | 4.0 | 400 | 0.5126 | 6.8813 | 4.164 | 6.5904 | 6.6226 | 19.0 |
0.7919 | 5.0 | 500 | 0.5080 | 6.8809 | 4.1822 | 6.5856 | 6.6317 | 19.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1