metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
base_model: bert-base-uncased
model-index:
- name: finetuning-sentiment-model-5000-samples
results: []
finetuning-sentiment-model-5000-samples
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0701
- Accuracy: 0.758
- F1: 0.7580
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: 16
- eval_batch_size: 16
- 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 | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 313 | 1.0216 | 0.744 | 0.744 |
| 0.2263 | 2.0 | 626 | 1.0701 | 0.758 | 0.7580 |
| 0.2263 | 3.0 | 939 | 1.3097 | 0.723 | 0.723 |
| 0.1273 | 4.0 | 1252 | 1.4377 | 0.743 | 0.743 |
| 0.051 | 5.0 | 1565 | 1.4884 | 0.739 | 0.739 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1