metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: t5-base-lora-1.77M-snli
results: []
t5-base-lora-1.77M-snli
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7467
- Accuracy: 0.7375
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4536 | 1.0 | 8584 | 0.3747 | 0.8610 |
| 0.434 | 2.0 | 17168 | 0.3531 | 0.8695 |
| 0.4218 | 3.0 | 25752 | 0.3478 | 0.8713 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0