opt350m-lora-billsum-1
This model is a fine-tuned version of facebook/opt-350m on an unknown dataset.
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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
- lr_scheduler_warmup_steps: 1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Evaluation Results (Validation): {'rouge1': 0.3226, 'rouge2': 0.1138, 'rougeL': 0.2143, 'rougeLsum': 0.2374}
Evaluation Results (Test): {'rouge1': 0.4778, 'rouge2': 0.2811, 'rougeL': 0.3785, 'rougeLsum': 0.3992}
Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.21.0
- Downloads last month
- 6
Model tree for clee9/opt350m-lora-billsum-1
Base model
facebook/opt-350m