metadata
base_model: kghanlon/distilbert-base-uncased-finetuned-MP-unannotated-half-frozen-v1
tags:
- generated_from_trainer
metrics:
- accuracy
- recall
- f1
model-index:
- name: >-
distilbert-base-uncased-finetuned-MP-unannotated-half-frozen-v1-FULL_CLASSES-v1_un_frozen
results: []
distilbert-base-uncased-finetuned-MP-unannotated-half-frozen-v1-FULL_CLASSES-v1_un_frozen
This model is a fine-tuned version of kghanlon/distilbert-base-uncased-finetuned-MP-unannotated-half-frozen-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2635
- Accuracy: 0.5909
- Recall: 0.5909
- F1: 0.5861
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: 5e-05
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 |
|---|---|---|---|---|---|---|
| 1.7051 | 1.0 | 15490 | 1.6329 | 0.5557 | 0.5557 | 0.5381 |
| 1.3579 | 2.0 | 30980 | 1.5647 | 0.5771 | 0.5771 | 0.5650 |
| 1.0119 | 3.0 | 46470 | 1.6397 | 0.5900 | 0.5900 | 0.5821 |
| 0.5922 | 4.0 | 61960 | 1.9336 | 0.5922 | 0.5922 | 0.5855 |
| 0.3721 | 5.0 | 77450 | 2.2635 | 0.5909 | 0.5909 | 0.5861 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0