tulu2-7b-cost-UF-UI-HHRLHF-5e-6

This model is a fine-tuned version of allenai/tulu-2-7b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8630
• Rewards/chosen: -4.9803
• Rewards/rejected: -5.7374
• Rewards/accuracies: 0.5905
• Rewards/margins: 0.7571
• Rewards/margins Max: 5.4488
• Rewards/margins Min: -2.7483
• Rewards/margins Std: 2.6664
• Logps/rejected: -892.1482
• Logps/chosen: -835.0510
• Logits/rejected: 1.2553
• Logits/chosen: 1.0857

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-06
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Rewards/margins Max	Rewards/margins Min	Rewards/margins Std	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.0556	1.0	3974	0.8630	-4.9803	-5.7374	0.5905	0.7571	5.4488	-2.7483	2.6664	-892.1482	-835.0510	1.2553	1.0857

Framework versions

• PEFT 0.7.1
• Transformers 4.39.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2