flant5-finetuning
This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0746
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.126 | 0.32 | 250 | 0.0827 |
0.0959 | 0.64 | 500 | 0.0801 |
0.0942 | 0.96 | 750 | 0.0788 |
0.0897 | 1.28 | 1000 | 0.0772 |
0.0883 | 1.61 | 1250 | 0.0769 |
0.0876 | 1.93 | 1500 | 0.0766 |
0.0858 | 2.25 | 1750 | 0.0762 |
0.0841 | 2.57 | 2000 | 0.0757 |
0.0835 | 2.89 | 2250 | 0.0753 |
0.0822 | 3.21 | 2500 | 0.0754 |
0.0818 | 3.53 | 2750 | 0.0751 |
0.0801 | 3.85 | 3000 | 0.0750 |
0.0807 | 4.17 | 3250 | 0.0749 |
0.0779 | 4.49 | 3500 | 0.0749 |
0.0796 | 4.82 | 3750 | 0.0748 |
0.0779 | 5.14 | 4000 | 0.0746 |
0.0773 | 5.46 | 4250 | 0.0748 |
0.0778 | 5.78 | 4500 | 0.0746 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 1