metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-base-uncased-classification-flat
results: []
bert-base-uncased-classification-flat
This model is a fine-tuned version of irfanamal/bert-base-uncased-finetuned-amazonreviews on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4951
- Accuracy: 0.4957
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: 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 | Accuracy |
|---|---|---|---|---|
| 3.7227 | 1.0 | 1250 | 3.3098 | 0.3826 |
| 2.6109 | 2.0 | 2500 | 2.7897 | 0.4568 |
| 2.2396 | 3.0 | 3750 | 2.5943 | 0.4809 |
| 1.9093 | 4.0 | 5000 | 2.5155 | 0.4937 |
| 1.7949 | 5.0 | 6250 | 2.4951 | 0.4957 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3