openhermes-mistral-dpo-gptq

This model is a fine-tuned version of TheBloke/OpenHermes-2-Mistral-7B-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• training_steps: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.0056	10	nan
0.0	0.0112	20	nan
0.0	0.0169	30	nan
0.0	0.0225	40	nan
0.0	0.0281	50	nan

Framework versions

• PEFT 0.12.0
• Transformers 4.42.3
• Pytorch 2.0.1+cu117
• Datasets 2.20.0
• Tokenizers 0.19.1