metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: distilbert_sa_GLUE_Experiment_logit_kd_pretrain_qnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QNLI
type: glue
config: qnli
split: validation
args: qnli
metrics:
- name: Accuracy
type: accuracy
value: 0.8735127219476478
distilbert_sa_GLUE_Experiment_logit_kd_pretrain_qnli
This model is a fine-tuned version of gokuls/distilbert_sa_pre-training-complete on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.2515
- Accuracy: 0.8735
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
- 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 |
---|---|---|---|---|
0.303 | 1.0 | 410 | 0.2569 | 0.8651 |
0.2557 | 2.0 | 820 | 0.2515 | 0.8735 |
0.2357 | 3.0 | 1230 | 0.2556 | 0.8828 |
0.2222 | 4.0 | 1640 | 0.2562 | 0.8847 |
0.2146 | 5.0 | 2050 | 0.2547 | 0.8869 |
0.2098 | 6.0 | 2460 | 0.2585 | 0.8803 |
0.2069 | 7.0 | 2870 | 0.2588 | 0.8849 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2