78aa7fb5-fa60-469f-bf6d-f333502c0485

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

• Loss: 1.2980

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: 0.000211
• train_batch_size: 4
• eval_batch_size: 4
• seed: 110
• 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	1.9224
3.3039	0.0082	50	1.7195
3.3779	0.0164	100	1.5542
3.3247	0.0246	150	1.5729
3.6928	0.0328	200	1.4884
3.1858	0.0410	250	1.4328
3.3135	0.0492	300	1.3692
3.0865	0.0574	350	1.3285
3.3587	0.0656	400	1.3077
3.0626	0.0738	450	1.2962
3.1303	0.0820	500	1.2980

Framework versions

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