ft-microsoft-phi-2

This model is a fine-tuned version of microsoft/phi-2 on the g-ronimo/riddles_evolved dataset. It achieves the following results on the evaluation set:

• Loss: 1.5572

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: 2
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.708	0.5	7	1.7003
1.6852	1.0	14	1.6505
1.5539	1.49	21	1.6054
1.5387	1.99	28	1.5572

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.1.2
• Datasets 2.15.0
• Tokenizers 0.15.2