ultrafeedback-binarized-tulu-2-7b-dpo-full

This model is a fine-tuned version of allenai/tulu-2-7b on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

• Loss: 0.6636
• Rewards/chosen: 0.0407
• Rewards/rejected: -0.0326
• Rewards/accuracies: 0.6746
• Rewards/margins: 0.0733
• Logps/rejected: -317.3561
• Logps/chosen: -335.2600
• Logits/rejected: -1.2511
• Logits/chosen: -1.1780

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: 8
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• 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
0.6762	0.4184	100	0.6753	0.0546	0.0122	0.6627	0.0424	-312.8761	-333.8717	-1.2638	-1.1861
0.6604	0.8368	200	0.6640	0.0423	-0.0311	0.6706	0.0734	-317.2082	-335.1042	-1.2523	-1.1794

Framework versions

• Transformers 4.44.1
• Pytorch 2.1.2+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1