metadata
license: apache-2.0
base_model: t5-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: t5-large-snli
results: []
t5-large-snli
This model is a fine-tuned version of t5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2087
- Accuracy: 0.809
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0943 | 1.0 | 4292 | 0.0741 | 0.9229 |
| 0.082 | 2.0 | 8584 | 0.0722 | 0.9265 |
| 0.0767 | 3.0 | 12876 | 0.0717 | 0.9280 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0