codet5-small-ft-v10

This model is a fine-tuned version of Salesforce/codet5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6076
• Rouge1: 64.7797
• Rouge2: 49.8902
• Rougel: 62.433
• Rougelsum: 61.8109
• Gen Len: 12.9286

Model description

More information needed

FORMAT

[BUG] reader = ReaderFactory.newXmlReader( null) ; [CONTEXT] outputFile = output.getFile(); } Reader reader; try { if (inputEncoding != null) { if (parser.getType() == Parser.XML_TYPE) { } else { reader = ReaderFactory.newReader(inputFile, inputEncoding); } } else { reader = ReaderFactory.newPlatformReader(inputFile); }

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	19	1.9088	54.5113	41.9981	53.7739	53.7474	12.3286
No log	2.0	38	1.1442	66.1136	56.2675	65.0547	64.8304	12.4857
No log	3.0	57	0.6821	67.6198	52.8142	64.9905	64.3787	13.3429
No log	4.0	76	0.6076	64.7797	49.8902	62.433	61.8109	12.9286

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1