Phi-3-mini-4k-instruct-mbti

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: 0.6615
• Accuracy: 0.6220

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7155	0.1977	500	0.7196	0.5898
0.6873	0.3955	1000	0.6776	0.5931
0.6841	0.5932	1500	0.6620	0.6058
0.6746	0.7909	2000	0.6615	0.6220
0.6655	0.9886	2500	0.6647	0.6133
0.6092	1.1864	3000	0.6873	0.5716
0.5661	1.3841	3500	0.7262	0.6092
0.5565	1.5818	4000	0.6938	0.6185
0.5308	1.7795	4500	0.7100	0.6060
0.5236	1.9773	5000	0.7046	0.6127

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1