metadata

library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_tiny_lda_100_v1_rte
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE RTE
          type: glue
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.48736462093862815

bert_tiny_lda_100_v1_rte

This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_100_v1 on the GLUE RTE dataset. It achieves the following results on the evaluation set:

Loss: 0.6925
Accuracy: 0.4874

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
0.7159	1.0	10	0.7091	0.4729
0.6926	2.0	20	0.6925	0.4874
0.6814	3.0	30	0.6944	0.5199
0.6663	4.0	40	0.6978	0.5271
0.6472	5.0	50	0.7425	0.5415
0.6276	6.0	60	0.7315	0.5451
0.5534	7.0	70	0.8165	0.5018

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3