metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: Bert_Stacked_model_100
results: []
datasets:
- pkavumba/balanced-copa
- 12ml/e-CARE
pipeline_tag: question-answering
Bert_Stacked_model_100
This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1094
- F1: 0.5669
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- 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 | F1 |
|---|---|---|---|---|
| 1.249 | 1.0 | 1576 | 1.1862 | 0.5172 |
| 1.1963 | 2.0 | 3152 | 1.1461 | 0.5407 |
| 1.1495 | 3.0 | 4728 | 1.1241 | 0.5570 |
| 1.1192 | 4.0 | 6304 | 1.1172 | 0.5634 |
| 1.1025 | 5.0 | 7880 | 1.1094 | 0.5669 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1