Phi-4-mini-instruct_sft_sg_values_resp_split

This model is a fine-tuned version of microsoft/Phi-4-mini-instruct on the sft_sg_values_res_split dataset. It achieves the following results on the evaluation set:

• Loss: 2.3214

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: 1e-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
4.3698	0.1710	250	4.1731
3.5096	0.3419	500	3.1497
2.6213	0.5129	750	2.5736
2.4305	0.6839	1000	2.3980
2.3653	0.8548	1250	2.3345

Framework versions

• PEFT 0.15.2
• Transformers 4.51.1
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.1