metadata
library_name: transformers
language:
- en
base_model: Hartunka/distilbert_rand_100_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: distilbert_rand_100_v1_qnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QNLI
type: glue
args: qnli
metrics:
- name: Accuracy
type: accuracy
value: 0.6258466044298004
distilbert_rand_100_v1_qnli
This model is a fine-tuned version of Hartunka/distilbert_rand_100_v1 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6362
- Accuracy: 0.6258
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 |
|---|---|---|---|---|
| 0.6638 | 1.0 | 410 | 0.6415 | 0.6268 |
| 0.6237 | 2.0 | 820 | 0.6362 | 0.6258 |
| 0.5559 | 3.0 | 1230 | 0.6767 | 0.6189 |
| 0.4491 | 4.0 | 1640 | 0.7469 | 0.6313 |
| 0.3288 | 5.0 | 2050 | 0.8629 | 0.6193 |
| 0.2354 | 6.0 | 2460 | 1.1685 | 0.6125 |
| 0.1733 | 7.0 | 2870 | 1.4222 | 0.6141 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1