metadata
library_name: peft
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
model-index:
- name: fine_tune
results: []
fine_tune
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3085
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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.7293 | 1.0 | 30 | 4.6146 |
| 3.3709 | 2.0 | 60 | 2.0158 |
| 1.382 | 3.0 | 90 | 0.7932 |
| 0.8337 | 4.0 | 120 | 0.5675 |
| 0.6557 | 5.0 | 150 | 0.4715 |
| 0.5561 | 6.0 | 180 | 0.4106 |
| 0.5042 | 7.0 | 210 | 0.3627 |
| 0.4905 | 8.0 | 240 | 0.3346 |
| 0.4602 | 9.0 | 270 | 0.3145 |
| 0.39 | 10.0 | 300 | 0.3085 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0