metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: t5-small-rte
results: []
t5-small-rte
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6873
- Accuracy: 0.5740
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 156 | 0.6926 | 0.4946 |
| No log | 2.0 | 312 | 0.6890 | 0.5487 |
| No log | 3.0 | 468 | 0.6887 | 0.5415 |
| 0.6967 | 4.0 | 624 | 0.6873 | 0.5740 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2