3b9dd9df-231d-4f0c-8f91-5dcc06b68653

This model is a fine-tuned version of NousResearch/Yarn-Mistral-7b-128k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1631

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: 0.000202
• 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	0.0000	1	0.8839
0.9047	0.0015	50	0.5682
0.6338	0.0029	100	0.3447
0.5013	0.0044	150	0.3267
0.4989	0.0058	200	0.2529
0.4974	0.0073	250	0.2563
0.3723	0.0087	300	0.2179
0.3841	0.0102	350	0.1948
0.3314	0.0117	400	0.1745
0.357	0.0131	450	0.1640
0.3247	0.0146	500	0.1631

Framework versions

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