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: 0.8384

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: 8
• 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
1.4537	0.2052	100	1.2281
1.0408	0.4105	200	0.9405
0.915	0.6157	300	0.9088
0.9159	0.8209	400	0.8933
0.8925	1.0262	500	0.8809
0.8837	1.2314	600	0.8712
0.8753	1.4366	700	0.8604
0.8701	1.6419	800	0.8537
0.8755	1.8471	900	0.8498
0.8603	2.0523	1000	0.8460
0.8669	2.2576	1100	0.8434
0.8558	2.4628	1200	0.8410
0.8482	2.6680	1300	0.8395
0.844	2.8733	1400	0.8384

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1