metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: distill_bert_classification
results: []
distill_bert_classification
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: 1.6024
- F1: 0.7168
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 388 | 0.5234 | 0.7637 |
| 0.5453 | 2.0 | 776 | 0.5314 | 0.7673 |
| 0.4146 | 3.0 | 1164 | 0.5694 | 0.7541 |
| 0.2822 | 4.0 | 1552 | 0.6709 | 0.7428 |
| 0.2822 | 5.0 | 1940 | 1.0074 | 0.7154 |
| 0.1729 | 6.0 | 2328 | 1.2874 | 0.7049 |
| 0.0885 | 7.0 | 2716 | 1.3463 | 0.7316 |
| 0.0656 | 8.0 | 3104 | 1.5599 | 0.7064 |
| 0.0656 | 9.0 | 3492 | 1.5743 | 0.7195 |
| 0.0426 | 10.0 | 3880 | 1.6024 | 0.7168 |
Framework versions
- Transformers 4.41.1
- Pytorch 1.13.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1