You can deploy this model and start earning money today!

clee9/
opt125m-lora-pruned-wanda-2-4

Name: opt125m-lora-pruned-wanda-2-4
Availability: InStock

Views

No views yet

opt125m-lora-pruned-wanda-2-4

This model is a fine-tuned version of saresri/pruned_opt on an unknown dataset.

More information needed

More information needed

More information needed

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

Evaluation Results (Validation): {'rouge1': 0.2943, 'rouge2': 0.0737, 'rougeL': 0.1923, 'rougeLsum': 0.2062}

Evaluation Results (Test): {'rouge1': 0.1739, 'rouge2': 0.088, 'rougeL': 0.144, 'rougeLsum': 0.1451}