metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: gokulsrinivasagan/tinybert_train_book_ent_15p
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tinybert_train_book_ent_15p_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.7018917819365338
tinybert_train_book_ent_15p_mnli
This model is a fine-tuned version of gokulsrinivasagan/tinybert_train_book_ent_15p on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.7105
- Accuracy: 0.7019
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 |
|---|---|---|---|---|
| 0.9734 | 1.0 | 1534 | 0.8839 | 0.5948 |
| 0.8336 | 2.0 | 3068 | 0.7823 | 0.6555 |
| 0.7502 | 3.0 | 4602 | 0.7526 | 0.6718 |
| 0.6949 | 4.0 | 6136 | 0.7428 | 0.6831 |
| 0.6482 | 5.0 | 7670 | 0.7338 | 0.6931 |
| 0.6063 | 6.0 | 9204 | 0.7623 | 0.6976 |
| 0.5649 | 7.0 | 10738 | 0.7467 | 0.7031 |
| 0.5287 | 8.0 | 12272 | 0.7779 | 0.6937 |
| 0.4907 | 9.0 | 13806 | 0.8163 | 0.7008 |
| 0.4577 | 10.0 | 15340 | 0.8233 | 0.7008 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3