metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_rand_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_rand_5_v1_wnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE WNLI
type: glue
args: wnli
metrics:
- name: Accuracy
type: accuracy
value: 0.5352112676056338
bert_base_rand_5_v1_wnli
This model is a fine-tuned version of Hartunka/bert_base_rand_5_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.7008
- Accuracy: 0.5352
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 |
|---|---|---|---|---|
| 0.7385 | 1.0 | 3 | 0.7008 | 0.5352 |
| 0.6977 | 2.0 | 6 | 0.7294 | 0.4225 |
| 0.6963 | 3.0 | 9 | 0.7183 | 0.5211 |
| 0.699 | 4.0 | 12 | 0.7429 | 0.2817 |
| 0.6899 | 5.0 | 15 | 0.7939 | 0.2676 |
| 0.6944 | 6.0 | 18 | 0.8157 | 0.2113 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1