metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: multi-label-class-classification-on-github-issues
results: []
multi-label-class-classification-on-github-issues
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3836
- Micro f1: 0.4888
- Macro f1: 0.0304
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: 3e-05
- train_batch_size: 512
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Micro f1 | Macro f1 |
|---|---|---|---|---|---|
| No log | 1.0 | 4 | 0.6376 | 0.1870 | 0.0280 |
| No log | 2.0 | 8 | 0.5847 | 0.1961 | 0.0154 |
| No log | 3.0 | 12 | 0.5465 | 0.1967 | 0.0146 |
| No log | 4.0 | 16 | 0.5148 | 0.1982 | 0.0146 |
| No log | 5.0 | 20 | 0.4878 | 0.2915 | 0.0187 |
| No log | 6.0 | 24 | 0.4653 | 0.4655 | 0.0301 |
| No log | 7.0 | 28 | 0.4465 | 0.4862 | 0.0305 |
| No log | 8.0 | 32 | 0.4310 | 0.4884 | 0.0305 |
| No log | 9.0 | 36 | 0.4179 | 0.4894 | 0.0305 |
| No log | 10.0 | 40 | 0.4072 | 0.4894 | 0.0305 |
| No log | 11.0 | 44 | 0.3986 | 0.4893 | 0.0305 |
| No log | 12.0 | 48 | 0.3921 | 0.4893 | 0.0305 |
| No log | 13.0 | 52 | 0.3875 | 0.4888 | 0.0304 |
| No log | 14.0 | 56 | 0.3847 | 0.4888 | 0.0304 |
| No log | 15.0 | 60 | 0.3836 | 0.4888 | 0.0304 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2