ostapbodnar/Phi3-mini-4k-instruct-UA-adapter

phi-3-mini-QLoRA

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: 0.4826

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• 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: 0.1
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
0.8441	0.2930	1000	0.6059
0.5806	0.5859	2000	0.5601
0.5509	0.8789	3000	0.5371
0.5293	1.1718	4000	0.5231
0.5187	1.4648	5000	0.5121
0.5066	1.7577	6000	0.5041
0.501	2.0507	7000	0.4988
0.4904	2.3436	8000	0.4938
0.4889	2.6366	9000	0.4903
0.4871	2.9295	10000	0.4871
0.4823	3.2225	11000	0.4852
0.4759	3.5155	12000	0.4837
0.4756	3.8084	13000	0.4826

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1