---
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
- generated_from_trainer
model-index:
- name: calm-toad-592
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# calm-toad-592

This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2100
- Hamming Loss: 0.0635
- Zero One Loss: 0.37
- Jaccard Score: 0.3135
- Hamming Loss Optimised: 0.0596
- Hamming Loss Threshold: 0.7821
- Zero One Loss Optimised: 0.3688
- Zero One Loss Threshold: 0.5845
- Jaccard Score Optimised: 0.3081
- Jaccard Score Threshold: 0.4331

## 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: 2.8076328160265536e-05
- train_batch_size: 4
- eval_batch_size: 4
- 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: 7

### 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 |
|:-------------:|:-----:|:----:|:---------------:|:------------:|:-------------:|:-------------:|:----------------------:|:----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|
| 0.2771        | 1.0   | 800  | 0.1783          | 0.0614       | 0.4938        | 0.4535        | 0.0606                 | 0.4706                 | 0.4275                  | 0.3518                  | 0.3479                  | 0.2844                  |
| 0.1522        | 2.0   | 1600 | 0.1701          | 0.0585       | 0.38          | 0.3341        | 0.0579                 | 0.5975                 | 0.3738                  | 0.4904                  | 0.3057                  | 0.3508                  |
| 0.1174        | 3.0   | 2400 | 0.1704          | 0.0616       | 0.405         | 0.3534        | 0.058                  | 0.7566                 | 0.3862                  | 0.3655                  | 0.3061                  | 0.2510                  |
| 0.0897        | 4.0   | 3200 | 0.1823          | 0.0599       | 0.3738        | 0.3224        | 0.0581                 | 0.7112                 | 0.3688                  | 0.4400                  | 0.3068                  | 0.3538                  |
| 0.0637        | 5.0   | 4000 | 0.1978          | 0.062        | 0.365         | 0.3132        | 0.0595                 | 0.6567                 | 0.3612                  | 0.4636                  | 0.3008                  | 0.2970                  |
| 0.0486        | 6.0   | 4800 | 0.2055          | 0.0615       | 0.3625        | 0.3054        | 0.0595                 | 0.6736                 | 0.3638                  | 0.5862                  | 0.3029                  | 0.3143                  |
| 0.038         | 7.0   | 5600 | 0.2100          | 0.0635       | 0.37          | 0.3135        | 0.0596                 | 0.7821                 | 0.3688                  | 0.5845                  | 0.3081                  | 0.4331                  |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0