phi-1_5-lora-tuned-sft-dolly

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

• Loss: 2.4000

Model description

More information needed

Intended uses & limitations

More information needed

Hardware

Trained model on Intel Max 1550 GPU

Training and evaluation data

databricks/databricks-dolly-15k

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
2.7868	0.8065	100	2.5808
2.547	1.6129	200	2.4670
2.4664	2.4194	300	2.4305
2.4586	3.2258	400	2.4108
2.4204	4.0323	500	2.4000

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