nash_dpo_doff_no_golden_iter_2

This model is a fine-tuned version of YYYYYYibo/nash_dpo_doff_no_golden_iter_1 on the updated and the original datasets. It achieves the following results on the evaluation set:

• Loss: 0.6264
• Rewards/chosen: -0.0931
• Rewards/rejected: -0.2641
• Rewards/accuracies: 0.6300
• Rewards/margins: 0.1709
• Logps/rejected: -296.8029
• Logps/chosen: -301.2086
• Logits/rejected: -2.4038
• Logits/chosen: -2.4983

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: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 8
• 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
0.5862	0.67	100	0.6264	-0.0931	-0.2641	0.6300	0.1709	-296.8029	-301.2086	-2.4038	-2.4983

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2