|
---
|
|
library_name: peft
|
|
license: apache-2.0
|
|
base_model: google-bert/bert-base-cased
|
|
tags:
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: marvelous-pug-454
|
|
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. --> |
|
|
|
# marvelous-pug-454 |
|
|
|
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: 0.4049 |
|
- Hamming Loss: 0.1123 |
|
- Zero One Loss: 1.0 |
|
- Jaccard Score: 1.0 |
|
- Hamming Loss Optimised: 0.1034 |
|
- Hamming Loss Threshold: 0.4079 |
|
- Zero One Loss Optimised: 0.7662 |
|
- Zero One Loss Threshold: 0.3351 |
|
- Jaccard Score Optimised: 0.7625 |
|
- Jaccard Score Threshold: 0.3149 |
|
|
|
## 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: 3.691774561796012e-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: 10 |
|
|
|
### 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 | 0.6553 | 0.3676 | 1.0 | 0.9280 | 0.1123 | 0.6566 | 0.95 | 0.5576 | 0.8863 | 0.2993 | |
|
| No log | 2.0 | 200 | 0.5073 | 0.1205 | 0.94 | 0.9381 | 0.1123 | 0.6530 | 0.8175 | 0.4434 | 0.7941 | 0.4421 | |
|
| No log | 3.0 | 300 | 0.4412 | 0.1121 | 0.9988 | 0.9988 | 0.1123 | 0.5944 | 0.7675 | 0.3659 | 0.7621 | 0.3681 | |
|
| No log | 4.0 | 400 | 0.4228 | 0.1123 | 1.0 | 1.0 | 0.109 | 0.4184 | 0.7675 | 0.3485 | 0.7631 | 0.3402 | |
|
| 0.5269 | 5.0 | 500 | 0.4151 | 0.1123 | 1.0 | 1.0 | 0.1123 | 0.5944 | 0.7675 | 0.3646 | 0.7990 | 0.2948 | |
|
| 0.5269 | 6.0 | 600 | 0.4109 | 0.1123 | 1.0 | 1.0 | 0.1051 | 0.4182 | 0.7662 | 0.3532 | 0.7631 | 0.3362 | |
|
| 0.5269 | 7.0 | 700 | 0.4084 | 0.1123 | 1.0 | 1.0 | 0.1046 | 0.4138 | 0.7662 | 0.3368 | 0.7638 | 0.3453 | |
|
| 0.5269 | 8.0 | 800 | 0.4059 | 0.1123 | 1.0 | 1.0 | 0.1031 | 0.4037 | 0.7662 | 0.3314 | 0.7612 | 0.3225 | |
|
| 0.5269 | 9.0 | 900 | 0.4051 | 0.1123 | 1.0 | 1.0 | 0.1032 | 0.4075 | 0.7662 | 0.3350 | 0.7619 | 0.3209 | |
|
| 0.4202 | 10.0 | 1000 | 0.4049 | 0.1123 | 1.0 | 1.0 | 0.1034 | 0.4079 | 0.7662 | 0.3351 | 0.7625 | 0.3149 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.2 |
|
- Transformers 4.47.0 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.21.0 |
