metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: jrtec-distilroberta-base-mrpc-glue-omar-espejel
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.8774509803921569
- name: F1
type: f1
value: 0.9137931034482758
jrtec-distilroberta-base-mrpc-glue-omar-espejel
This model is a fine-tuned version of distilroberta-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.0468
- Accuracy: 0.8775
- F1: 0.9138
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2883 | 1.09 | 500 | 1.0351 | 0.8333 | 0.8790 |
| 0.3128 | 2.18 | 1000 | 0.7217 | 0.8407 | 0.8812 |
| 0.1607 | 3.27 | 1500 | 0.9991 | 0.8480 | 0.8946 |
| 0.1 | 4.36 | 2000 | 1.0454 | 0.8456 | 0.8869 |
| 0.051 | 5.45 | 2500 | 1.0003 | 0.8824 | 0.9184 |
| 0.037 | 6.54 | 3000 | 1.1195 | 0.8456 | 0.8948 |
| 0.028 | 7.63 | 3500 | 1.0448 | 0.8725 | 0.9091 |
| 0.0189 | 8.71 | 4000 | 1.0478 | 0.8725 | 0.9107 |
| 0.0099 | 9.8 | 4500 | 1.0468 | 0.8775 | 0.9138 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1