0174a28c-3979-4d41-8c08-4e4949362bad

This model is a fine-tuned version of NousResearch/CodeLlama-13b-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2942

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: 0.000203
• train_batch_size: 4
• eval_batch_size: 4
• seed: 30
• 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	2.7153
3.5349	0.0004	50	1.6396
2.6529	0.0008	100	1.6510
3.0371	0.0013	150	1.4133
2.8876	0.0017	200	1.4252
2.6179	0.0021	250	1.3522
2.2612	0.0025	300	1.3425
2.6005	0.0030	350	1.3104
3.125	0.0034	400	1.3096
2.6446	0.0038	450	1.2991
2.645	0.0042	500	1.2942

Framework versions

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