metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: google/bert_uncased_L-2_H-256_A-4
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_uncased_L-2_H-256_A-4_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.7332180634662328
bert_uncased_L-2_H-256_A-4_mnli
This model is a fine-tuned version of google/bert_uncased_L-2_H-256_A-4 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6492
- Accuracy: 0.7332
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 |
|---|---|---|---|---|
| 0.8512 | 1.0 | 1534 | 0.7602 | 0.6654 |
| 0.7432 | 2.0 | 3068 | 0.7031 | 0.6940 |
| 0.6912 | 3.0 | 4602 | 0.6761 | 0.7101 |
| 0.6524 | 4.0 | 6136 | 0.6655 | 0.7179 |
| 0.6224 | 5.0 | 7670 | 0.6699 | 0.7217 |
| 0.5935 | 6.0 | 9204 | 0.6757 | 0.7192 |
| 0.5689 | 7.0 | 10738 | 0.6650 | 0.7255 |
| 0.5458 | 8.0 | 12272 | 0.6831 | 0.7271 |
| 0.526 | 9.0 | 13806 | 0.6980 | 0.7222 |
| 0.5031 | 10.0 | 15340 | 0.7006 | 0.7258 |
| 0.4847 | 11.0 | 16874 | 0.7057 | 0.7250 |
| 0.4673 | 12.0 | 18408 | 0.7297 | 0.7264 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3