mt5_small-silver-standard-lora
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.9282
- Rouge1: 17.173
- Rouge2: 5.1482
- Rougel: 16.6617
- Rougelsum: 16.7675
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 54.2369 | 1.0 | 149 | 5.1842 | 6.182 | 1.2295 | 5.9424 | 5.8969 |
| 23.4568 | 2.0 | 298 | 4.0397 | 15.3558 | 4.4153 | 14.839 | 14.9532 |
| 20.8425 | 3.0 | 447 | 3.9282 | 17.173 | 5.1482 | 16.6617 | 16.7675 |
Framework versions
- PEFT 0.18.1
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2
- Downloads last month
- 157
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Firmansyah-Ibrahim/mt5_small-silver-standard-lora
Base model
google/mt5-small