9940c5d2-8e79-4b67-83eb-f072290d21e7

This model is a fine-tuned version of VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6874

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: 0.000209
• train_batch_size: 4
• eval_batch_size: 4
• seed: 90
• 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	2.4392
1.2534	0.0119	50	0.9771
0.6972	0.0237	100	0.8934
0.6788	0.0356	150	0.8343
0.6146	0.0475	200	0.8104
0.5039	0.0593	250	0.7584
0.4956	0.0712	300	0.7242
0.7137	0.0831	350	0.7085
0.5914	0.0949	400	0.6943
0.4236	0.1068	450	0.6880
0.5821	0.1187	500	0.6874

Framework versions

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