lora_phi-1_5

This model is a fine-tuned version of microsoft/phi-1_5 on the databricks/databricks-dolly-15k dataset. It achieves the following results on the evaluation set:

• Loss: 2.3998

Model description

This is a fine-tuned version of the microsoft/phi-1_5 model using Parameter Efficient Fine Tuning (PEFT) with Low Rank Adaptation (LoRA) on Intel(R) Data Center GPU Max 1100 and Intel(R) Xeon(R) Platinum 8480+ CPU . This model can be used for various text generation tasks including chatbots, content creation, and other NLP applications.

Training Hardware

This model was trained using: GPU:

• Intel(R) Data Center GPU Max 1100
• CPU: Intel(R) Xeon(R) Platinum 8480+

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.05
• training_steps: 593

Training results

Training Loss	Epoch	Step	Validation Loss
2.7756	0.8065	100	2.5791
2.558	1.6129	200	2.4656
2.4521	2.4194	300	2.4294
2.4589	3.2258	400	2.4103
2.4248	4.0323	500	2.3998

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.1.0.post0+cxx11.abi
• Datasets 2.19.1
• Tokenizers 0.19.1