Edit model card

codet5-small-ft-v10.1

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: 0.2959
  • Rouge1: 81.3062
  • Rouge2: 75.041
  • Rougel: 81.6284
  • Rougelsum: 81.0728
  • Gen Len: 13.9857

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: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 19 1.8175 54.4184 41.9095 54.2713 53.6157 12.8857
No log 2.0 38 0.8332 69.024 55.6554 66.6238 66.2558 13.2286
No log 3.0 57 0.5293 64.9854 48.4359 62.4491 61.9973 12.8857
No log 4.0 76 0.4513 70.6432 59.744 69.8409 69.4408 14.3
No log 5.0 95 0.3845 73.7268 64.6645 73.4703 72.9311 14.3571
No log 6.0 114 0.3549 75.2727 66.4769 75.1021 74.6361 14.4571
No log 7.0 133 0.3199 78.5225 72.2594 78.8828 78.3729 13.9
No log 8.0 152 0.3053 79.2229 72.7468 79.6079 79.1507 14.2429
No log 9.0 171 0.2998 80.4535 73.8457 80.587 80.1368 14.1571
No log 10.0 190 0.2959 81.3062 75.041 81.6284 81.0728 13.9857

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1
Downloads last month
5
Safetensors
Model size
60.5M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ayeshgk/codet5-small-ft-v10.1

Finetuned
(47)
this model