metadata

library_name: transformers
tags:
  - generated_from_trainer
datasets:
  - gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-100
metrics:
  - accuracy
model-index:
  - name: bert_base_lda_100_v1
    results:
      - task:
          name: Masked Language Modeling
          type: fill-mask
        dataset:
          name: gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-100
          type: gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-100
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.42346160366163754

bert_base_lda_100_v1

This model is a fine-tuned version of on the gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-100 dataset. It achieves the following results on the evaluation set:

Loss: 6.9999
Accuracy: 0.4235

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
10.4589	4.1982	10000	10.2935	0.1510
9.6043	8.3963	20000	9.6179	0.1525
9.48	12.5945	30000	9.5449	0.1561
8.9658	16.7926	40000	8.8322	0.2303
7.2614	20.9908	50000	7.0173	0.4201

Framework versions

Transformers 4.46.1
Pytorch 2.2.0+cu121
Datasets 3.1.0
Tokenizers 0.20.1