metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_rand_100_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_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: 0.696078431372549
- name: F1
type: f1
value: 0.7832167832167832
bert_base_rand_100_v2_mrpc
This model is a fine-tuned version of Hartunka/bert_base_rand_100_v2 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5916
- Accuracy: 0.6961
- F1: 0.7832
- Combined Score: 0.7396
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 |
|---|---|---|---|---|---|---|
| 0.6254 | 1.0 | 15 | 0.6040 | 0.6765 | 0.7898 | 0.7331 |
| 0.5783 | 2.0 | 30 | 0.5916 | 0.6961 | 0.7832 | 0.7396 |
| 0.5106 | 3.0 | 45 | 0.6093 | 0.7010 | 0.7918 | 0.7464 |
| 0.3753 | 4.0 | 60 | 0.7311 | 0.6642 | 0.7584 | 0.7113 |
| 0.2454 | 5.0 | 75 | 1.0231 | 0.6201 | 0.6906 | 0.6554 |
| 0.158 | 6.0 | 90 | 1.2619 | 0.6201 | 0.6918 | 0.6560 |
| 0.1077 | 7.0 | 105 | 1.3472 | 0.6544 | 0.7413 | 0.6978 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1