codet5p-770m-2

This model is a fine-tuned version of Salesforce/codet5p-770m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1083

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.5059	0.9971	85	0.1362
0.1474	1.9941	170	0.1209
0.1352	2.9912	255	0.1157
0.1259	4.0	341	0.1132
0.1224	4.9971	426	0.1105
0.117	5.9941	511	0.1096
0.1128	6.9912	596	0.1087
0.1084	8.0	682	0.1072
0.1065	8.9971	767	0.1075
0.1077	9.9941	852	0.1071
0.1013	10.9912	937	0.1074
0.0981	12.0	1023	0.1073
0.098	12.9971	1108	0.1078
0.097	13.9941	1193	0.1082
0.0952	14.9560	1275	0.1083

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1