tulu2-13b-cost-tulumix-1e-6

This model is a fine-tuned version of allenai/tulu-2-13b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6891
• Rewards/chosen: 0.0068
• Rewards/rejected: -0.0036
• Rewards/accuracies: 0.5570
• Rewards/margins: 0.0103
• Rewards/margins Max: 0.1265
• Rewards/margins Min: -0.1089
• Rewards/margins Std: 0.0783
• Logps/rejected: -316.0208
• Logps/chosen: -324.2853
• Logits/rejected: -0.9127
• Logits/chosen: -1.0350

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: 1e-06
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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
0.6183	1.0	3174	0.6891	0.0068	-0.0036	0.5570	0.0103	0.1265	-0.1089	0.0783	-316.0208	-324.2853	-0.9127	-1.0350

Framework versions

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