phi-3-mini-LoRA-MEDQA-Extended-V2

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: 0.6515

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• 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
0.7812	0.2205	100	0.6948
0.6796	0.4410	200	0.6695
0.6687	0.6615	300	0.6632
0.662	0.8820	400	0.6599
0.6603	1.1025	500	0.6579
0.6587	1.3230	600	0.6568
0.6539	1.5436	700	0.6553
0.6552	1.7641	800	0.6540
0.6542	1.9846	900	0.6537
0.6501	2.2051	1000	0.6526
0.6523	2.4256	1100	0.6521
0.6527	2.6461	1200	0.6517
0.6502	2.8666	1300	0.6515

Framework versions

• PEFT 0.12.0
• Transformers 4.43.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1