README.md

metadata

license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - HuggingFaceH4/deita-10k-v0-sft
model-index:
  - name: llama3-8b-instruct-wo-kqa_golden-iter-sft-step1
    results: []

llama3-8b-instruct-wo-kqa_golden-iter-sft-step1

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set:

• Loss: 0.4835

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.6774	1.0	11	0.5812
0.3859	2.0	22	0.4977
0.2871	3.0	33	0.4835

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2