metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: glue-mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.8553921568627451
- name: F1
type: f1
value: 0.8998302207130731
- task:
type: natural-language-inference
name: Natural Language Inference
dataset:
name: glue
type: glue
config: mrpc
split: test
metrics:
- name: Accuracy
type: accuracy
value: 0.8226086956521739
verified: true
- name: Precision
type: precision
value: 0.8372093023255814
verified: true
- name: Recall
type: recall
value: 0.9102005231037489
verified: true
- name: AUC
type: auc
value: 0.8902771786185113
verified: true
- name: F1
type: f1
value: 0.8721804511278195
verified: true
- name: loss
type: loss
value: 0.4117553234100342
verified: true
glue-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: 0.3654
- Accuracy: 0.8554
- F1: 0.8998
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 | 0.4039 | 0.8039 | 0.8611 |
| No log | 2.0 | 460 | 0.3654 | 0.8554 | 0.8998 |
| 0.4368 | 3.0 | 690 | 0.4146 | 0.8407 | 0.8885 |
| 0.4368 | 4.0 | 920 | 0.5756 | 0.8456 | 0.8941 |
| 0.1744 | 5.0 | 1150 | 0.5523 | 0.8456 | 0.8916 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.3.2
- Tokenizers 0.11.6