metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda_100_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_lda_100_v1_wnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE WNLI
type: glue
args: wnli
metrics:
- name: Accuracy
type: accuracy
value: 0.5633802816901409
bert_base_lda_100_v1_wnli
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_100_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6905
- Accuracy: 0.5634
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 |
|---|---|---|---|---|
| 0.8315 | 1.0 | 3 | 0.8521 | 0.4366 |
| 0.7469 | 2.0 | 6 | 0.6964 | 0.5634 |
| 0.7109 | 3.0 | 9 | 0.7104 | 0.4648 |
| 0.707 | 4.0 | 12 | 0.6995 | 0.4930 |
| 0.7035 | 5.0 | 15 | 0.6905 | 0.5634 |
| 0.6961 | 6.0 | 18 | 0.7092 | 0.4648 |
| 0.6981 | 7.0 | 21 | 0.6949 | 0.5211 |
| 0.692 | 8.0 | 24 | 0.7024 | 0.3944 |
| 0.6974 | 9.0 | 27 | 0.7059 | 0.4085 |
| 0.685 | 10.0 | 30 | 0.6992 | 0.4789 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3