phi-3-text2sql-modal

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: 0.7743

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: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	2.8715
1.3561	0.1072	500	0.8902
0.8557	0.2143	1000	0.8305
0.815	0.3215	1500	0.8092
0.7983	0.4287	2000	0.7938
0.7896	0.5358	2500	0.7866
0.7873	0.6430	3000	0.7800
0.7804	0.7502	3500	0.7764
0.7725	0.8574	4000	0.7749
0.7733	0.9645	4500	0.7743

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.19.1