zkdeng's picture
Model save
5a46cf7 verified
metadata
license: apache-2.0
base_model: zkdeng/10-convnextv2-base-22k-384-finetuned-spiderTraining1000-1000
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: 10-finetuned-ausSpiders2000
    results: []

10-finetuned-ausSpiders2000

This model is a fine-tuned version of zkdeng/10-convnextv2-base-22k-384-finetuned-spiderTraining1000-1000 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0184
  • Accuracy: 0.9929
  • Precision: 0.9955
  • Recall: 0.9910
  • F1: 0.9932

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: 0.0005
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
0.2684 1.0 141 0.1271 0.9503 0.9350 0.9199 0.9198
0.1698 2.0 282 0.1668 0.9485 0.9229 0.9195 0.9123
0.1538 3.0 423 0.0906 0.9645 0.9764 0.9365 0.9523
0.153 4.0 564 0.0860 0.9707 0.9685 0.9451 0.9525
0.0699 5.0 705 0.0528 0.9813 0.9830 0.9728 0.9776
0.1107 6.0 846 0.0460 0.9831 0.9832 0.9879 0.9855
0.0647 7.0 987 0.0319 0.9849 0.9905 0.9765 0.9829
0.0461 8.0 1128 0.0350 0.9840 0.9866 0.9710 0.9776
0.0371 9.0 1269 0.0198 0.9920 0.9952 0.9903 0.9927
0.0496 10.0 1410 0.0184 0.9929 0.9955 0.9910 0.9932

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.13.3