Phi-3-mini-128k-instruct-advisegpt-v0.3

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

• Loss: 1.6513

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: 2e-05
• train_batch_size: 14
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 30
• total_train_batch_size: 420
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.838	0.9633	14	1.7877
1.5618	1.9954	29	1.6674
1.4944	2.8899	42	1.6513

Framework versions

• PEFT 0.10.0
• Transformers 4.40.2
• Pytorch 2.2.0
• Datasets 2.19.1
• Tokenizers 0.19.1