4ebbda33-5948-49a7-a62c-942ed2c9a029

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: 0.3984

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: 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	0.0002	1	2.3596
2.628	0.0120	50	0.7902
2.4452	0.0240	100	0.6675
1.848	0.0360	150	0.6423
1.5846	0.0480	200	0.5910
1.4877	0.0600	250	0.5162
1.4091	0.0720	300	0.4774
1.3631	0.0839	350	0.4429
1.7897	0.0959	400	0.4148
1.2615	0.1079	450	0.4024
0.994	0.1199	500	0.3984

Framework versions

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