d97b3b84-37a6-46e0-ac36-cc86bb102c86

This model is a fine-tuned version of lmsys/vicuna-7b-v1.5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9172

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: 0.000211
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0008	1	1.1151
1.0884	0.0400	50	1.0024
1.0354	0.0799	100	0.9806
1.0402	0.1199	150	0.9756
1.0123	0.1599	200	0.9476
1.0209	0.1998	250	0.9486
0.9919	0.2398	300	0.9261
0.9827	0.2798	350	0.9207
0.9826	0.3197	400	0.9138
0.9848	0.3597	450	0.9121
0.9083	0.3997	500	0.9172

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1