distilroberta-base-finetuned-lora-mrpc
This model is a fine-tuned version of distilroberta-base on the glue dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.8456
- F1: 0.8912
- trainable model parameters: 887042
- all model parameters: 83006980
- percentage of trainable model parameters: 1.07%
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-04
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- weight_decay: 0.01
- rank: 16
- lora_alpha: 32
- lora_dropout: 0.05
- num_epochs: 4
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Dataset used to train rambodazimi/distilroberta-base-finetuned-LoRA-MRPC
Evaluation results
- Accuracy on glueself-reported0.846
- F1 on glueself-reported0.891