metadata
library_name: transformers
language:
- en
base_model: Hartunka/distilbert_rand_100_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: distilbert_rand_100_v2_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.6936274509803921
- name: F1
type: f1
value: 0.7974068071312804
distilbert_rand_100_v2_mrpc
This model is a fine-tuned version of Hartunka/distilbert_rand_100_v2 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5903
- Accuracy: 0.6936
- F1: 0.7974
- Combined Score: 0.7455
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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6269 | 1.0 | 15 | 0.6202 | 0.6716 | 0.7752 | 0.7234 |
| 0.5818 | 2.0 | 30 | 0.5903 | 0.6936 | 0.7974 | 0.7455 |
| 0.5151 | 3.0 | 45 | 0.6081 | 0.6887 | 0.7928 | 0.7408 |
| 0.412 | 4.0 | 60 | 0.7463 | 0.6446 | 0.7259 | 0.6853 |
| 0.2566 | 5.0 | 75 | 1.0279 | 0.6373 | 0.7197 | 0.6785 |
| 0.1435 | 6.0 | 90 | 1.2920 | 0.6495 | 0.7327 | 0.6911 |
| 0.0905 | 7.0 | 105 | 1.4994 | 0.6324 | 0.7082 | 0.6703 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1