metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: tl-ceb-model
results: []
tl-ceb-model
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5272
- Bleu: 2.9334
- Gen Len: 18.2954
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: 0.001
- 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.9668 | 1.0 | 6516 | 0.8034 | 2.2949 | 18.3327 |
| 0.8082 | 2.0 | 13032 | 0.6691 | 2.6324 | 18.3182 |
| 0.7297 | 3.0 | 19548 | 0.5954 | 2.7526 | 18.2929 |
| 0.6745 | 4.0 | 26064 | 0.5474 | 2.886 | 18.308 |
| 0.6319 | 5.0 | 32580 | 0.5272 | 2.9334 | 18.2954 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0