CodePhi-St10

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5030

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: 5e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use paged_adamw_32bit 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: 10
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.847	1.0	60	0.6064
0.7418	2.0	120	0.5886
0.7207	3.0	180	0.5663
0.7391	4.0	240	0.5463
0.6526	5.0	300	0.5302
0.723	6.0	360	0.5176
0.6411	7.0	420	0.5095
0.6282	8.0	480	0.5050
0.6591	9.0	540	0.5033
0.6123	10.0	600	0.5030

Framework versions

• PEFT 0.12.0
• Transformers 4.49.0
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0