microsoft_CodeGPT-small-java_0_ft_clm

This model is a fine-tuned version of microsoft/CodeGPT-small-java on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1672
• Accuracy: 0.7708

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: 8e-05
• train_batch_size: 4
• eval_batch_size: 12
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 24
• optimizer: Use OptimizerNames.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: 0.02
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8842	0.7788	500	1.1934	0.7688
0.7557	1.5576	1000	1.1676	0.7693
0.7033	2.3364	1500	1.1631	0.7705
0.6624	3.1153	2000	1.1650	0.7707
0.6414	3.8941	2500	1.1646	0.7710
0.6187	4.6729	3000	1.1672	0.7708

Framework versions

• Transformers 4.53.0
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.2