metadata
license: apache-2.0
base_model: t5-large
tags:
- generated_from_trainer
model-index:
- name: rat-t5-large-qdmr-grounded-with-db-v2
results: []
rat-t5-large-qdmr-grounded-with-db-v2
This model is a fine-tuned version of t5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0994
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 |
|---|---|---|---|
| 0.5239 | 0.23 | 500 | 0.2421 |
| 0.2233 | 0.46 | 1000 | 0.1800 |
| 0.1734 | 0.69 | 1500 | 0.1397 |
| 0.1466 | 0.92 | 2000 | 0.1268 |
| 0.1092 | 1.16 | 2500 | 0.1153 |
| 0.094 | 1.39 | 3000 | 0.1078 |
| 0.0933 | 1.62 | 3500 | 0.1035 |
| 0.0947 | 1.85 | 4000 | 0.0924 |
| 0.0799 | 2.08 | 4500 | 0.0994 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3