metadata
library_name: transformers
license: apache-2.0
base_model: Mat17892/t5small_enfr_opus
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: t5small_enfr_opus
results: []
t5small_enfr_opus
This model is a fine-tuned version of Mat17892/t5small_enfr_opus on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3217
- Bleu: 7.3648
- Gen Len: 17.5145
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.542 | 1.0 | 6355 | 1.3460 | 7.1462 | 17.5281 |
| 1.5196 | 2.0 | 12710 | 1.3419 | 7.2241 | 17.5219 |
| 1.5005 | 3.0 | 19065 | 1.3346 | 7.3005 | 17.5137 |
| 1.5083 | 4.0 | 25420 | 1.3298 | 7.3326 | 17.5174 |
| 1.4999 | 5.0 | 31775 | 1.3269 | 7.3337 | 17.5214 |
| 1.4906 | 6.0 | 38130 | 1.3237 | 7.3359 | 17.5185 |
| 1.4944 | 7.0 | 44485 | 1.3223 | 7.3664 | 17.5161 |
| 1.5018 | 8.0 | 50840 | 1.3217 | 7.3648 | 17.5145 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3