gokulsrinivasagan's picture
End of training
ed21618 verified
|
raw
history blame
2.27 kB
metadata
library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/distilbert_lda_50_v1
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: distilbert_lda_50_v1_sst2
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE SST2
          type: glue
          args: sst2
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5091743119266054

distilbert_lda_50_v1_sst2

This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_50_v1 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6954
  • Accuracy: 0.5092

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: 0.001
  • train_batch_size: 256
  • eval_batch_size: 256
  • seed: 10
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.7089 1.0 264 0.6971 0.5092
0.6871 2.0 528 0.6957 0.5092
0.6867 3.0 792 0.6989 0.5092
0.6868 4.0 1056 0.6954 0.5092
0.6867 5.0 1320 0.6973 0.5092
0.6866 6.0 1584 0.6989 0.5092
0.6862 7.0 1848 0.6970 0.5092
0.6866 8.0 2112 0.6971 0.5092
0.6867 9.0 2376 0.6970 0.5092

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.2.1+cu118
  • Datasets 2.17.0
  • Tokenizers 0.20.3