Hyponatremia_L3_100steps_1e6rate_01beta_DPO

This model is a fine-tuned version of tsavage68/Hyponatremia_L3_450steps_1e7rate_SFT on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Rewards/chosen: 0.9749
• Rewards/rejected: -9.2781
• Rewards/accuracies: 1.0
• Rewards/margins: 10.2530
• Logps/rejected: -132.2077
• Logps/chosen: -12.9677
• Logits/rejected: -1.0433
• Logits/chosen: -0.9670

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: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.0005	0.2667	50	0.0003	0.8841	-7.2237	1.0	8.1078	-111.6638	-13.8759	-1.0293	-0.9511
0.0	0.5333	100	0.0000	0.9749	-9.2781	1.0	10.2530	-132.2077	-12.9677	-1.0433	-0.9670

Framework versions

• Transformers 4.42.3
• Pytorch 2.0.0+cu117
• Datasets 2.20.0
• Tokenizers 0.19.1