phi-3-mini-LoRA

This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6516

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.6795	0.3578	500	0.6740
0.6663	0.7156	1000	0.6629
0.6509	1.0733	1500	0.6576
0.6374	1.4311	2000	0.6553
0.6364	1.7889	2500	0.6528
0.6228	2.1467	3000	0.6526
0.6197	2.5045	3500	0.6519
0.6194	2.8623	4000	0.6516

Framework versions

• PEFT 0.11.1
• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1