T5_mrqa_fast_learner
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: 0.8387
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9917 | 1.0 | 500 | 0.7513 |
| 0.7799 | 2.0 | 1000 | 0.7524 |
| 0.6705 | 3.0 | 1500 | 0.7539 |
| 0.5894 | 4.0 | 2000 | 0.7659 |
| 0.5239 | 5.0 | 2500 | 0.7906 |
| 0.4808 | 6.0 | 3000 | 0.8057 |
| 0.4391 | 7.0 | 3500 | 0.8203 |
| 0.4156 | 8.0 | 4000 | 0.8283 |
| 0.3974 | 9.0 | 4500 | 0.8387 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for enriquesaou/T5_mrqa_fast_learner
Base model
google/flan-t5-small