mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_2ep

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.5932
• eval_runtime: 4.0164
• eval_samples_per_second: 49.796
• eval_steps_per_second: 6.224
• epoch: 1.9968
• step: 156

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: 2
• eval_batch_size: 8
• seed: 0
• gradient_accumulation_steps: 32
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Framework versions

• PEFT 0.9.0
• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.17.1
• Tokenizers 0.19.1