metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model_index:
- name: distilbert-base-uncased-finetuned-cola
results:
- task:
name: Text Classification
type: text-classification
metric:
name: Matthews Correlation
type: matthews_correlation
value: 0.5
distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of distilbert-base-uncased on an unkown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1964
- Matthews Correlation: 0.5
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| No log | 1.0 | 8 | 1.3423 | 0.3333 |
| No log | 2.0 | 16 | 1.3086 | 0.5 |
| No log | 3.0 | 24 | 1.2516 | 0.5 |
| No log | 4.0 | 32 | 1.2170 | 0.5 |
| No log | 5.0 | 40 | 1.1964 | 0.5 |
Framework versions
- Transformers 4.9.2
- Pytorch 1.9.0+cu102
- Datasets 1.11.0
- Tokenizers 0.10.3