Mistral-7B-v0.1_Emotion

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the generator dataset.

Model description

Article: https://medium.com/@frankmorales_91352/fine-tuning-mistral-7b-instruct-v0-1-88b27a194248

Intended uses & limitations

More information needed

Training and evaluation data

Evaluation: https://github.com/frank-morales2020/MLxDL/blob/main/FineTunning_Testing_For_EmotionQADataset.ipynb

The following hyperparameters were used during training: learning_rate: 0.0002 train_batch_size: 3 eval_batch_size: 8 seed: 42 gradient_accumulation_steps: 2 total_train_batch_size: 6 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 lr_scheduler_type: constant lr_scheduler_warmup_ratio: 0.03

num_epochs: 40

Accuracy (Eval dataset and predict) for a sample of 2000: TBD%

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 3
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 6
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 40

Training results

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1