Hugging Face's logo

ElMad
/
dapper-ape-848

PEFT
Safetensors
Generated from Trainer
Model card Files Community
dapper-ape-848 / README.md
ElMad's picture
ElMad
stackoverflow_tag_classification/initial_run/roberta-base/dapper-ape-848
b600b3c verified
preview code
|
raw
history blame contribute delete
4.82 kB
metadata
library_name: peft
license: mit
base_model: FacebookAI/roberta-base
tags:
  - generated_from_trainer
model-index:
  - name: dapper-ape-848
    results: []

dapper-ape-848

This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5164
  • Hamming Loss: 0.1123
  • Zero One Loss: 1.0
  • Jaccard Score: 1.0
  • Hamming Loss Optimised: 0.1123
  • Hamming Loss Threshold: 0.5944
  • Zero One Loss Optimised: 0.8712
  • Zero One Loss Threshold: 0.4290
  • Jaccard Score Optimised: 0.8190
  • Jaccard Score Threshold: 0.4039

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: 8.506034831608646e-06
  • 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: 11

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 0.7056 0.567 1.0 0.8855 0.1123 0.5944 1.0 0.9000 0.8878 0.2889
No log 2.0 200 0.7020 0.4813 1.0 0.8993 0.1123 0.5944 1.0 0.9000 0.8878 0.2889
No log 3.0 300 0.6961 0.4363 1.0 0.9071 0.1123 0.5944 1.0 0.9000 0.8878 0.2889
No log 4.0 400 0.6856 0.4355 1.0 0.907 0.1123 0.5944 1.0 0.9000 0.8878 0.2889
0.6963 5.0 500 0.6619 0.2924 0.9912 0.9281 0.1123 0.5944 1.0 0.9000 0.8878 0.2889
0.6963 6.0 600 0.6033 0.1124 1.0 1.0 0.1123 0.5944 1.0 0.9000 0.8540 0.4530
0.6963 7.0 700 0.5635 0.1123 1.0 1.0 0.1123 0.5944 1.0 0.9000 0.8212 0.4305
0.6963 8.0 800 0.5386 0.1123 1.0 1.0 0.1123 0.5944 1.0 0.9000 0.8135 0.4232
0.6963 9.0 900 0.5250 0.1123 1.0 1.0 0.1123 0.5944 0.895 0.4370 0.8192 0.4047
0.5852 10.0 1000 0.5184 0.1123 1.0 1.0 0.1123 0.5944 0.88 0.4306 0.8163 0.4115
0.5852 11.0 1100 0.5164 0.1123 1.0 1.0 0.1123 0.5944 0.8712 0.4290 0.8190 0.4039

Framework versions

  • PEFT 0.13.2
  • Transformers 4.47.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.21.0