Phi-3-mini-4k-instruct-mbti-2

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: 0.6372
• Accuracy: 0.6461
• F1: 0.7150

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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.7097	0.1582	2000	0.6888	0.6080	0.7463
0.6833	0.3164	4000	0.6675	0.5969	0.6512
0.6713	0.4745	6000	0.6596	0.6138	0.6748
0.6592	0.6327	8000	0.6540	0.6389	0.7222
0.6498	0.7909	10000	0.6456	0.5914	0.5887
0.6362	0.9491	12000	0.6372	0.6461	0.7150

Framework versions

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