<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
flan-t5-base-SQuAD-qa-ep10
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: 0.2700
- F1: 94.1644
- Exact Match: 87.5665
- Gen Len: 5.1122
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: 2e-05
- train_batch_size: 72
- eval_batch_size: 144
- seed: 1799
- 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 | F1 | Exact Match | Gen Len |
|---|---|---|---|---|---|---|
| 0.3178 | 0.76 | 200 | 0.2700 | 94.1644 | 87.5665 | 5.1122 |
| 0.283 | 1.52 | 400 | 0.2723 | 94.0528 | 87.6633 | 5.1132 |
| 0.2713 | 2.28 | 600 | 0.2749 | 94.1271 | 87.76 | 5.1364 |
| 0.2652 | 3.04 | 800 | 0.2723 | 94.113 | 87.76 | 5.0822 |
| 0.2467 | 3.8 | 1000 | 0.2717 | 93.8718 | 87.4214 | 5.0571 |
| 0.2448 | 4.56 | 1200 | 0.2759 | 93.8637 | 87.5181 | 5.1089 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
