metadata
base_model: distilbert-base-uncased
library_name: peft
license: apache-2.0
metrics:
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-ICU-Readmission-classification_test2_DistilBERT
results: []
distilbert-base-uncased-ICU-Readmission-classification_test2_DistilBERT
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: 0.6973
- F1: 0.5333
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|
| 0.7109 | 1.0 | 125 | 0.6959 | 0.4396 |
| 0.668 | 2.0 | 250 | 0.6841 | 0.5192 |
| 0.6016 | 3.0 | 375 | 0.6925 | 0.5098 |
| 0.5938 | 4.0 | 500 | 0.6892 | 0.5472 |
| 0.5625 | 5.0 | 625 | 0.6994 | 0.5000 |
| 0.6445 | 6.0 | 750 | 0.6970 | 0.5049 |
| 0.6602 | 7.0 | 875 | 0.6961 | 0.5333 |
| 0.6328 | 8.0 | 1000 | 0.6953 | 0.5333 |
| 0.625 | 9.0 | 1125 | 0.6975 | 0.5333 |
| 0.6406 | 10.0 | 1250 | 0.6973 | 0.5333 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1