metadata

library_name: transformers
tags:
  - generated_from_trainer
datasets:
  - gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-5
metrics:
  - accuracy
model-index:
  - name: distilbert_lda_5_v1
    results:
      - task:
          name: Masked Language Modeling
          type: fill-mask
        dataset:
          name: gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-5
          type: gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-5
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5803243487596768

distilbert_lda_5_v1

This model is a fine-tuned version of on the gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-5 dataset. It achieves the following results on the evaluation set:

Loss: 3.6788
Accuracy: 0.5803

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: 0.0001
train_batch_size: 96
eval_batch_size: 96
seed: 10
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10000
num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
7.6763	4.1982	10000	7.6034	0.1522
6.8215	8.3963	20000	6.3711	0.2653
4.1639	12.5945	30000	4.0536	0.5321
3.88	16.7926	40000	3.7792	0.5683
3.7563	20.9908	50000	3.6849	0.5794

Framework versions

Transformers 4.46.1
Pytorch 2.2.0+cu121
Datasets 3.1.0
Tokenizers 0.20.1