88ce2cca-a246-4ce2-be63-3cd4de0f6163

This model is a fine-tuned version of Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2240

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: 0.000212
• train_batch_size: 4
• eval_batch_size: 4
• seed: 120
• 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	0.0006	1	1.7007
0.6347	0.0307	50	1.0054
0.5141	0.0613	100	0.7634
0.44	0.0920	150	0.5680
0.4269	0.1226	200	0.4901
0.4478	0.1533	250	0.3961
0.3999	0.1839	300	0.3428
0.3468	0.2146	350	0.2793
0.3078	0.2452	400	0.2378
0.2993	0.2759	450	0.2281
0.2835	0.3066	500	0.2240

Framework versions

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