instructs

This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9313

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: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss
1.1326	0.5614	8	1.1244
1.0454	1.0702	16	1.0752
1.0377	1.6316	24	1.0369
0.9498	2.1404	32	1.0040
0.9241	2.7018	40	0.9807
0.8259	3.2105	48	0.9605
0.8531	3.7719	56	0.9540
0.8317	4.2807	64	0.9431
0.815	4.8421	72	0.9305
0.8022	5.3509	80	0.9313

Framework versions

• PEFT 0.14.0
• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0