8b14f083-7b4e-4c1b-9d19-abeb2cb24bdf

This model is a fine-tuned version of NousResearch/Yarn-Mistral-7b-64k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0104

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: 0.000205
• train_batch_size: 4
• eval_batch_size: 4
• seed: 50
• 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	0.0002	1	0.2526
0.0253	0.0085	50	0.0273
0.0327	0.0170	100	0.0598
0.0118	0.0256	150	0.0549
0.0385	0.0341	200	0.0201
0.0032	0.0426	250	0.0173
0.0022	0.0511	300	0.0129
0.0012	0.0596	350	0.0162
0.0001	0.0681	400	0.0110
0.0014	0.0767	450	0.0108
0.0002	0.0852	500	0.0104

Framework versions

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