dhanishetty/phi-3-mini-QLoRA_Adapters-1

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: 0.4568

Platform - *** Trained on Local System ***

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: polynomial
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.9625	0.2022	100	0.9498
0.625	0.4044	200	0.6202
0.4719	0.6067	300	0.4961
0.4938	0.8089	400	0.4806
0.4594	1.0111	500	0.4738
0.4594	1.2133	600	0.4692
0.4625	1.4156	700	0.4658
0.45	1.6178	800	0.4635
0.5062	1.8200	900	0.4613
0.425	2.0222	1000	0.4600
0.4781	2.2245	1100	0.4588
0.4625	2.4267	1200	0.4580
0.4625	2.6289	1300	0.4571
0.4594	2.8311	1400	0.4568

Framework versions

• PEFT 0.11.2.dev0
• Transformers 4.42.3
• Pytorch 2.3.1+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1