Phi-3.5-baseline

This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.7926

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.7641	1.5238	500	0.7926

Framework versions

• PEFT 0.13.2
• Transformers 4.45.2
• Pytorch 2.2.2+cu118
• Datasets 3.0.1
• Tokenizers 0.20.1