CommitPredictor

This model is a fine-tuned version of microsoft/codebert-base-mlm on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8427
• Accuracy: 0.6409

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	292	2.2754	0.5767
2.5787	2.0	584	2.2006	0.5877
2.5787	3.0	876	2.0851	0.5953
2.2167	4.0	1168	2.0148	0.6142
2.2167	5.0	1460	1.9583	0.6144
2.064	6.0	1752	1.8846	0.6309
1.9626	7.0	2044	1.9399	0.6247
1.9626	8.0	2336	1.8423	0.6401
1.8671	9.0	2628	1.8065	0.6407
1.8671	10.0	2920	1.7582	0.6507
1.7957	11.0	3212	1.7978	0.6479
1.7226	12.0	3504	1.8058	0.6521
1.7226	13.0	3796	1.8427	0.6409

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu117
• Datasets 2.7.1
• Tokenizers 0.13.2