Phi-3.5-mini-instruct-qlora

This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8242

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: 0
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
1.6254	0.3333	10	1.2928
1.0852	0.6667	20	0.9771
0.8786	1.0	30	0.8939
0.7889	1.3333	40	0.8575
0.7281	1.6667	50	0.8336
0.6876	2.0	60	0.8175
0.6217	2.3333	70	0.8238
0.6066	2.6667	80	0.8274
0.614	3.0	90	0.8193
0.5568	3.3333	100	0.8235
0.5435	3.6667	110	0.8242
0.5699	4.0	120	0.8242

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.4.0
• Datasets 3.0.2
• Tokenizers 0.20.0