library_name, base_model, tags, datasets, model-index

library_name	base_model	tags	datasets	model-index
transformers	W-61/llama-3-8b-base-sft-ultrachat-8xh200	alignment-handbook ipo generated_from_trainer	HuggingFaceH4/ultrafeedback_binarized	name results llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128-20260428-004616

llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128-20260428-004616

This model is a fine-tuned version of W-61/llama-3-8b-base-sft-ultrachat-8xh200 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

• Loss: 2313.8057
• Rewards/chosen: -0.0439
• Rewards/rejected: -0.0689
• Rewards/accuracies: 0.6800
• Rewards/margins: 0.0250
• Logps/rejected: -8.1847
• Logps/chosen: -5.5025
• Logits/rejected: -0.2777
• Logits/chosen: -0.2620

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: 5e-07
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• total_eval_batch_size: 16
• 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	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
19275.1328	0.4188	200	2417.4961	-0.0134	-0.0217	0.6560	0.0083	-3.4695	-2.4551	-0.6300	-0.6352
18486.2438	0.8377	400	2313.8057	-0.0439	-0.0689	0.6800	0.0250	-8.1847	-5.5025	-0.2777	-0.2620

Framework versions

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