Mistral-7B-v0.1_cola_relu_distillation_ignore_02

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6546
• Accuracy: {'accuracy': 0.6728971962616822}
• Matthews Correlation: -0.0184

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 32
• seed: 2
• distributed_type: multi-GPU
• num_devices: 6
• total_train_batch_size: 96
• total_eval_batch_size: 192
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Matthews Correlation
0.8988	0.12	10	0.7592	{'accuracy': 0.47171620325982744}	-0.0379
0.6785	0.25	20	0.6739	{'accuracy': 0.6653883029721956}	-0.0162

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0