metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: google/bert_uncased_L-4_H-256_A-4
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_uncased_L-4_H-256_A-4_rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.631768953068592
bert_uncased_L-4_H-256_A-4_rte
This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6545
- Accuracy: 0.6318
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 |
|---|---|---|---|---|
| 0.6982 | 1.0 | 10 | 0.6899 | 0.5451 |
| 0.6864 | 2.0 | 20 | 0.6845 | 0.5523 |
| 0.6733 | 3.0 | 30 | 0.6737 | 0.5884 |
| 0.6495 | 4.0 | 40 | 0.6554 | 0.5884 |
| 0.61 | 5.0 | 50 | 0.6573 | 0.6101 |
| 0.5697 | 6.0 | 60 | 0.6545 | 0.6318 |
| 0.5279 | 7.0 | 70 | 0.6648 | 0.6354 |
| 0.4859 | 8.0 | 80 | 0.6778 | 0.6173 |
| 0.4524 | 9.0 | 90 | 0.6933 | 0.6137 |
| 0.4126 | 10.0 | 100 | 0.6992 | 0.6245 |
| 0.386 | 11.0 | 110 | 0.7181 | 0.6426 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3