b9b013cc-f1b6-41f9-9ba5-e3cd34cb1567

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: 1.4685

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: 0.000202
• 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	2.8470
3.7854	0.0084	50	1.6934
4.0803	0.0169	100	1.7288
3.8591	0.0253	150	1.6561
3.7396	0.0338	200	1.6160
3.5356	0.0422	250	1.5846
3.3379	0.0507	300	1.5483
3.1528	0.0591	350	1.5069
3.1429	0.0676	400	1.4790
3.061	0.0760	450	1.4701
3.0799	0.0844	500	1.4685

Framework versions

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