metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda_5
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_lda_5_rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.5270758122743683
bert_base_lda_5_rte
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_5 on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6935
- Accuracy: 0.5271
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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2915 | 1.0 | 10 | 1.0912 | 0.5271 |
| 0.8449 | 2.0 | 20 | 0.7609 | 0.5271 |
| 0.7309 | 3.0 | 30 | 0.7081 | 0.4729 |
| 0.698 | 4.0 | 40 | 0.6935 | 0.5271 |
| 0.699 | 5.0 | 50 | 0.7013 | 0.5271 |
| 0.7093 | 6.0 | 60 | 0.7016 | 0.4729 |
| 0.696 | 7.0 | 70 | 0.6949 | 0.4729 |
| 0.6942 | 8.0 | 80 | 0.6974 | 0.4729 |
| 0.6946 | 9.0 | 90 | 0.6966 | 0.4729 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3