metadata
license: apache-2.0
base_model: google/t5-v1_1-small
tags:
- generated_from_trainer
model-index:
- name: T5_1_mrqa_v1
results: []
T5_1_mrqa_v1
This model is a fine-tuned version of google/t5-v1_1-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7981
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: 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 |
|---|---|---|---|
| 10.3869 | 1.0 | 500 | 4.9828 |
| 6.7903 | 2.0 | 1000 | 3.4878 |
| 5.8096 | 3.0 | 1500 | 3.1873 |
| 5.2496 | 4.0 | 2000 | 3.0379 |
| 4.9384 | 5.0 | 2500 | 2.9406 |
| 4.6901 | 6.0 | 3000 | 2.8722 |
| 4.5321 | 7.0 | 3500 | 2.8254 |
| 4.4324 | 8.0 | 4000 | 2.8045 |
| 4.3835 | 9.0 | 4500 | 2.7981 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1