4237ed73-fec6-4af5-ab02-4631757aed8d

This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3686

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: 0.000204
• train_batch_size: 4
• eval_batch_size: 4
• seed: 40
• 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	0.0004	1	0.6069
0.4463	0.0214	50	0.4172
0.3423	0.0429	100	0.4017
0.3084	0.0643	150	0.3910
0.3035	0.0857	200	0.3854
0.3659	0.1072	250	0.3821
0.361	0.1286	300	0.3750
0.3716	0.1500	350	0.3722
0.3733	0.1715	400	0.3701
0.3344	0.1929	450	0.3675
0.3574	0.2143	500	0.3686

Framework versions

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