Edit model card

codebert-base-finetuned-code-ner

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

  • Loss: 0.3522
  • Precision: 0.6297
  • Recall: 0.6417
  • F1: 0.6356
  • Accuracy: 0.9185

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: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 191 0.4601 0.4861 0.4578 0.4715 0.8853
No log 2.0 382 0.3989 0.5806 0.5243 0.5510 0.8996
0.5081 3.0 573 0.3547 0.5723 0.6017 0.5866 0.9059
0.5081 4.0 764 0.3507 0.6161 0.6115 0.6138 0.9135
0.5081 5.0 955 0.3412 0.6299 0.6252 0.6276 0.9161
0.2299 6.0 1146 0.3418 0.6162 0.6465 0.6310 0.9175
0.2299 7.0 1337 0.3497 0.6288 0.6287 0.6287 0.9175
0.1618 8.0 1528 0.3474 0.6340 0.6397 0.6368 0.9189
0.1618 9.0 1719 0.3501 0.6262 0.6432 0.6346 0.9179
0.1618 10.0 1910 0.3522 0.6297 0.6417 0.6356 0.9185

Framework versions

  • Transformers 4.23.1
  • Pytorch 1.12.1+cu113
  • Datasets 2.6.1
  • Tokenizers 0.13.1
Downloads last month
9
Safetensors
Model size
124M params
Tensor type
I64
·
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.