metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
model-index:
- name: rat-t5-qdmr-grounded-with-db
results: []
rat-t5-qdmr-grounded-with-db
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1317
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 |
|---|---|---|---|
| 0.7551 | 0.23 | 500 | 0.3197 |
| 0.3105 | 0.46 | 1000 | 0.2357 |
| 0.2423 | 0.69 | 1500 | 0.1971 |
| 0.2029 | 0.92 | 2000 | 0.1769 |
| 0.1575 | 1.16 | 2500 | 0.1655 |
| 0.1403 | 1.39 | 3000 | 0.1471 |
| 0.1318 | 1.62 | 3500 | 0.1415 |
| 0.1297 | 1.85 | 4000 | 0.1312 |
| 0.1143 | 2.08 | 4500 | 0.1317 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3