metadata
license: apache-2.0
base_model: t5-large
tags:
- generated_from_trainer
model-index:
- name: rat-t5-large-qdmr-grounded-with-db
results: []
rat-t5-large-qdmr-grounded-with-db
This model is a fine-tuned version of t5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0996
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: 1
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 20000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5125 | 0.23 | 500 | 0.2132 |
| 0.2009 | 0.46 | 1000 | 0.1563 |
| 0.1616 | 0.69 | 1500 | 0.1306 |
| 0.1328 | 0.92 | 2000 | 0.1157 |
| 0.1024 | 1.16 | 2500 | 0.1075 |
| 0.0891 | 1.39 | 3000 | 0.0979 |
| 0.0866 | 1.62 | 3500 | 0.0996 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3