llama-3-8b-base-sft-hh-helpful-8xh200/README.md

library_name, base_model, tags, datasets, model-index

library_name	base_model	tags	datasets	model-index
transformers	meta-llama/Meta-Llama-3-8B	alignment-handbook generated_from_trainer	Anthropic/hh-rlhf	name results llama-3-8b-base-sft-hh-helpful-8xh200-20260410-133758

llama-3-8b-base-sft-hh-helpful-8xh200-20260410-133758

This model is a fine-tuned version of /scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B on the Anthropic/hh-rlhf dataset. It achieves the following results on the evaluation set:

• Loss: 1.3882

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: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 128
• total_eval_batch_size: 128
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.3924	0.7692	100	1.3882

Framework versions

• Transformers 4.51.0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.21.4