metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
- generated_from_trainer
model-index:
- name: inquisitive-hawk-387
results: []
inquisitive-hawk-387
This model is a fine-tuned version of google-bert/bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1747
- Hamming Loss: 0.0614
- Zero One Loss: 0.3838
- Jaccard Score: 0.3282
- Hamming Loss Optimised: 0.0592
- Hamming Loss Threshold: 0.6752
- Zero One Loss Optimised: 0.3838
- Zero One Loss Threshold: 0.5124
- Jaccard Score Optimised: 0.3189
- Jaccard Score Threshold: 0.2932
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: 3.5002189804196904e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 2024
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Hamming Loss | Zero One Loss | Jaccard Score | Hamming Loss Optimised | Hamming Loss Threshold | Zero One Loss Optimised | Zero One Loss Threshold | Jaccard Score Optimised | Jaccard Score Threshold |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 100 | 0.2398 | 0.0735 | 0.6325 | 0.6113 | 0.069 | 0.3881 | 0.5687 | 0.3736 | 0.4701 | 0.2311 |
| No log | 2.0 | 200 | 0.1921 | 0.0629 | 0.49 | 0.4479 | 0.0611 | 0.5862 | 0.4550 | 0.4417 | 0.3590 | 0.3433 |
| No log | 3.0 | 300 | 0.1754 | 0.062 | 0.4712 | 0.4326 | 0.0611 | 0.5370 | 0.4350 | 0.3792 | 0.3368 | 0.2775 |
| No log | 4.0 | 400 | 0.1698 | 0.0602 | 0.4300 | 0.3786 | 0.0596 | 0.6756 | 0.4062 | 0.4274 | 0.3274 | 0.1997 |
| 0.1907 | 5.0 | 500 | 0.1686 | 0.0605 | 0.3888 | 0.3361 | 0.0579 | 0.6614 | 0.3838 | 0.4056 | 0.3134 | 0.3219 |
| 0.1907 | 6.0 | 600 | 0.1755 | 0.0619 | 0.38 | 0.3276 | 0.0606 | 0.6396 | 0.3762 | 0.4744 | 0.3093 | 0.3137 |
| 0.1907 | 7.0 | 700 | 0.1747 | 0.0609 | 0.3838 | 0.3318 | 0.0596 | 0.6388 | 0.3838 | 0.5031 | 0.3076 | 0.2883 |
| 0.1907 | 8.0 | 800 | 0.1747 | 0.0614 | 0.3838 | 0.3282 | 0.0592 | 0.6752 | 0.3838 | 0.5124 | 0.3189 | 0.2932 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0