metadata
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
model-index:
- name: peft-finetune-flan-t5-mc-question-generation
results: []
peft-finetune-flan-t5-mc-question-generation
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: 1.2240
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.3143 | 0.13 | 100 | 1.7677 |
1.8538 | 0.25 | 200 | 1.4179 |
1.5767 | 0.38 | 300 | 1.3186 |
1.4908 | 0.51 | 400 | 1.2879 |
1.4503 | 0.64 | 500 | 1.2700 |
1.4281 | 0.76 | 600 | 1.2578 |
1.406 | 0.89 | 700 | 1.2489 |
1.4052 | 1.02 | 800 | 1.2415 |
1.3974 | 1.15 | 900 | 1.2387 |
1.3889 | 1.27 | 1000 | 1.2334 |
1.3811 | 1.4 | 1100 | 1.2303 |
1.3808 | 1.53 | 1200 | 1.2266 |
1.3782 | 1.65 | 1300 | 1.2265 |
1.376 | 1.78 | 1400 | 1.2248 |
1.3734 | 1.91 | 1500 | 1.2240 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3