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: 0.3785
- Micro f1: 0.5031
- Macro f1: 0.0317
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 | 0.6548 | 0.2035 | 0.0412 |
| No log | 2.0 | 8 | 0.5953 | 0.2747 | 0.0395 |
| No log | 3.0 | 12 | 0.5509 | 0.3474 | 0.0376 |
| No log | 4.0 | 16 | 0.5159 | 0.4098 | 0.0375 |
| No log | 5.0 | 20 | 0.4859 | 0.4842 | 0.0362 |
| No log | 6.0 | 24 | 0.4625 | 0.4875 | 0.0315 |
| No log | 7.0 | 28 | 0.4434 | 0.4893 | 0.0315 |
| No log | 8.0 | 32 | 0.4268 | 0.4906 | 0.0315 |
| No log | 9.0 | 36 | 0.4134 | 0.4920 | 0.0306 |
| No log | 10.0 | 40 | 0.4027 | 0.4943 | 0.0308 |
| No log | 11.0 | 44 | 0.3939 | 0.4952 | 0.0309 |
| No log | 12.0 | 48 | 0.3872 | 0.4986 | 0.0312 |
| No log | 13.0 | 52 | 0.3824 | 0.5025 | 0.0316 |
| No log | 14.0 | 56 | 0.3796 | 0.5033 | 0.0317 |
| No log | 15.0 | 60 | 0.3785 | 0.5031 | 0.0317 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2