metadata
license: apache-2.0
base_model: google/flan-t5-small
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: flan-t5-small
results: []
flan-t5-small
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: 2.8602
- Bleu: 2.1166
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 12.1197 | 1.0 | 50 | 5.2384 | 0.3407 |
| 5.2507 | 2.0 | 100 | 3.9968 | 0.7662 |
| 4.0611 | 3.0 | 150 | 3.5896 | 1.0135 |
| 3.6339 | 4.0 | 200 | 3.3513 | 1.6069 |
| 3.3393 | 5.0 | 250 | 3.1621 | 1.9097 |
| 3.0968 | 6.0 | 300 | 3.0131 | 2.0856 |
| 2.9193 | 7.0 | 350 | 2.9345 | 2.1837 |
| 2.8098 | 8.0 | 400 | 2.8925 | 2.1651 |
| 2.7505 | 9.0 | 450 | 2.8672 | 2.0322 |
| 2.7153 | 10.0 | 500 | 2.8602 | 2.1166 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2