kam414/pre-train-mistral-v2

train_2024-02-01-10-50-39

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the wiki_demo dataset. It achieves the following results on the evaluation set:

• Loss: 2.3668

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 20.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• PEFT 0.8.1
• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1