SeonghuJeon/task-7-phi-3-medium-4k-instruct

train_2025-04-09-16-08

This model is a fine-tuned version of microsoft/Phi-3-medium-4k-instruct on the demo_data dataset. It achieves the following results on the evaluation set:

• Loss: 0.5246
• Num Input Tokens Seen: 1419568

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-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.4879	2.2424	20	0.5867	356000
0.4577	4.4848	40	0.5385	712336
0.5001	6.7273	60	0.5248	1061472
0.5027	8.9697	80	0.5246	1419568

Framework versions

• PEFT 0.15.0
• Transformers 4.51.0
• Pytorch 2.1.0+cu118
• Datasets 3.4.1
• Tokenizers 0.21.0