metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: gokulsrinivasagan/bert_base_train_book_ent_15p_s_init
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_base_train_book_ent_15p_s_init_mnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MNLI
          type: glue
          args: mnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.3522172497965826

bert_base_train_book_ent_15p_s_init_mnli

This model is a fine-tuned version of gokulsrinivasagan/bert_base_train_book_ent_15p_s_init on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

Loss: 1.0971
Accuracy: 0.3522

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: 5e-05
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
1.1034	1.0	1534	1.1021	0.3182
1.1019	2.0	3068	1.0971	0.3545
1.1011	3.0	4602	1.0991	0.3274
1.1007	4.0	6136	1.0990	0.3545
1.1004	5.0	7670	1.0988	0.3534
1.1	6.0	9204	1.0991	0.3182
1.0997	7.0	10738	1.1003	0.3182

Framework versions

Transformers 4.51.2
Pytorch 2.6.0+cu126
Datasets 3.5.0
Tokenizers 0.21.1