metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.8578431372549019
- name: F1
type: f1
value: 0.9006849315068494
distilbert-base-uncased-finetuned-mrpc
This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5556
- Accuracy: 0.8578
- F1: 0.9007
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 | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 230 | 0.3937 | 0.8113 | 0.8670 |
| No log | 2.0 | 460 | 0.3660 | 0.8480 | 0.8967 |
| 0.4387 | 3.0 | 690 | 0.4298 | 0.8529 | 0.8973 |
| 0.4387 | 4.0 | 920 | 0.5573 | 0.8529 | 0.8990 |
| 0.1832 | 5.0 | 1150 | 0.5556 | 0.8578 | 0.9007 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1