phi-2-sft-lora-ultrachat

This model is a fine-tuned version of microsoft/phi-2 on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

• Loss: 1.2043

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: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.2257	1.0	3996	1.2098
1.1658	2.0	7993	1.2050
1.2092	3.0	11988	1.2043

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.1.2+cu118
• Datasets 2.14.6
• Tokenizers 0.15.2