metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: jim-crow-test2323
results: []
jim-crow-test2323
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0984
- Accuracy: 0.9720
- Precision: 0.9340
- Recall: 0.9706
- F1: 0.9519
- Macro Precision: 0.9610
- Macro Recall: 0.9716
- Macro F1: 0.9661
- Tn: 248
- Fp: 7
- Fn: 3
- Tp: 99
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: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Macro Precision | Macro Recall | Macro F1 | Tn | Fp | Fn | Tp |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0677 | 1.0 | 90 | 0.1643 | 0.9524 | 0.8899 | 0.9510 | 0.9194 | 0.9349 | 0.9520 | 0.9428 | 243 | 12 | 5 | 97 |
| 0.1282 | 2.0 | 180 | 0.0984 | 0.9720 | 0.9340 | 0.9706 | 0.9519 | 0.9610 | 0.9716 | 0.9661 | 248 | 7 | 3 | 99 |
| 0.0683 | 3.0 | 270 | 0.1819 | 0.9720 | 0.9694 | 0.9314 | 0.95 | 0.9712 | 0.9598 | 0.9653 | 252 | 3 | 7 | 95 |
| 0.0226 | 4.0 | 360 | 0.1095 | 0.9692 | 0.9174 | 0.9804 | 0.9479 | 0.9547 | 0.9725 | 0.9630 | 246 | 9 | 2 | 100 |
| 0.0219 | 5.0 | 450 | 0.1491 | 0.9720 | 0.9423 | 0.9608 | 0.9515 | 0.9632 | 0.9686 | 0.9659 | 249 | 6 | 4 | 98 |
Framework versions
- Transformers 5.7.0
- Pytorch 2.11.0+cu130
- Datasets 4.8.5
- Tokenizers 0.22.2