9871a2df-076d-41df-9855-adc30b892ead

This model is a fine-tuned version of NousResearch/Nous-Hermes-2-SOLAR-10.7B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3663

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: 0.000214
• train_batch_size: 4
• eval_batch_size: 4
• seed: 140
• 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	0.0004	1	0.9532
0.4759	0.0208	50	0.5046
0.5449	0.0416	100	0.5162
0.4928	0.0624	150	0.4712
0.4794	0.0832	200	0.4591
0.431	0.1040	250	0.4351
0.4421	0.1248	300	0.4267
0.3983	0.1456	350	0.3934
0.391	0.1664	400	0.3778
0.3407	0.1871	450	0.3683
0.4067	0.2079	500	0.3663

Framework versions

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