mergeLlama-7b-Instruct-hf-quantized-peft

This model is a fine-tuned version of meta-llama/CodeLlama-7b-Instruct-hf on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 6.2568

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
10.74	0.0122	20	7.4566
6.6528	0.0243	40	6.6315
6.4141	0.0365	60	6.4041
6.2451	0.0487	80	6.3026
6.1832	0.0608	100	6.2568

Framework versions

• PEFT 0.10.1.dev0
• Transformers 4.41.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1