metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: Greg-Sentiment-classifier
results: []
Greg-Sentiment-classifier
This model is a fine-tuned version of microsoft/MiniLM-L12-H384-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0161
- F1: 0.3222
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: 0.0005
- 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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.9805 | 1.0 | 499 | 1.0211 | 0.2347 |
| 1.0289 | 2.0 | 998 | 1.0175 | 0.2347 |
| 0.9924 | 3.0 | 1497 | 1.0189 | 0.2347 |
| 1.0319 | 4.0 | 1996 | 1.0165 | 0.3222 |
| 1.0351 | 5.0 | 2495 | 1.0179 | 0.3222 |
| 1.0339 | 6.0 | 2994 | 1.0172 | 0.3222 |
| 1.0039 | 7.0 | 3493 | 1.0163 | 0.3222 |
| 1.0299 | 8.0 | 3992 | 1.0164 | 0.3222 |
| 0.9914 | 9.0 | 4491 | 1.0168 | 0.3222 |
| 1.0038 | 10.0 | 4990 | 1.0162 | 0.3222 |
| 1.0399 | 11.0 | 5489 | 1.0161 | 0.3222 |
| 0.996 | 12.0 | 5988 | 1.0161 | 0.3222 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3