metadata
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: squeezebert-mnli-headless-finetuned-mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.8823529411764706
- name: F1
type: f1
value: 0.9136690647482014
squeezebert-mnli-headless-finetuned-mrpc
This model is a fine-tuned version of squeezebert/squeezebert-mnli-headless on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3142
- Accuracy: 0.8824
- F1: 0.9137
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: 32
- eval_batch_size: 32
- seed: 73
- 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 | 115 | 0.4461 | 0.8162 | 0.8705 |
| No log | 2.0 | 230 | 0.3844 | 0.8407 | 0.8866 |
| No log | 3.0 | 345 | 0.3181 | 0.8848 | 0.9156 |
| No log | 4.0 | 460 | 0.3159 | 0.8775 | 0.9091 |
| 0.3723 | 5.0 | 575 | 0.3142 | 0.8824 | 0.9137 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3