README.md

metadata

base_model: meta-llama/Llama-2-7b-chat-hf
library_name: peft
license: llama2
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: llama_2_alpaca_per_class_reflect
    results: []

llama_2_alpaca_per_class_reflect

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0753

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: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 20

Training results

Training Loss	Epoch	Step	Validation Loss
2.0231	0.7692	5	1.8074
1.2461	1.5385	10	1.3001
1.0347	2.3077	15	1.1189
1.0003	3.0769	20	1.0753

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1