metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: mobilebert_sa_GLUE_Experiment_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
config: mnli
split: validation_matched
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.6110659072416599
mobilebert_sa_GLUE_Experiment_mnli
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.8609
- Accuracy: 0.6111
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: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9907 | 1.0 | 3068 | 0.9408 | 0.5485 |
| 0.9094 | 2.0 | 6136 | 0.9065 | 0.5819 |
| 0.8828 | 3.0 | 9204 | 0.8969 | 0.5874 |
| 0.8627 | 4.0 | 12272 | 0.8821 | 0.5967 |
| 0.8429 | 5.0 | 15340 | 0.8743 | 0.6003 |
| 0.8207 | 6.0 | 18408 | 0.8663 | 0.6077 |
| 0.7989 | 7.0 | 21476 | 0.8665 | 0.6100 |
| 0.7789 | 8.0 | 24544 | 0.8751 | 0.6096 |
| 0.7603 | 9.0 | 27612 | 0.8620 | 0.6139 |
| 0.7425 | 10.0 | 30680 | 0.8813 | 0.6095 |
| 0.7238 | 11.0 | 33748 | 0.8913 | 0.6142 |
| 0.7063 | 12.0 | 36816 | 0.9026 | 0.6056 |
| 0.6891 | 13.0 | 39884 | 0.9267 | 0.5976 |
| 0.6721 | 14.0 | 42952 | 0.9072 | 0.6105 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2