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: 0.0508
- Accuracy: 0.9858
- Precision: 0.9892
- Recall: 0.9865
- F1: 0.9878
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|---|
| 0.1997 | 1.0 | 281 | 0.2264 | 0.9281 | 0.9395 | 0.8869 | 0.9045 |
| 0.17 | 2.0 | 563 | 0.1382 | 0.9565 | 0.8540 | 0.8266 | 0.8381 |
| 0.21 | 3.0 | 845 | 0.1404 | 0.9583 | 0.9747 | 0.9064 | 0.9349 |
| 0.1976 | 4.0 | 1127 | 0.0987 | 0.9689 | 0.9716 | 0.8917 | 0.9128 |
| 0.178 | 5.0 | 1408 | 0.1219 | 0.9636 | 0.9393 | 0.9600 | 0.9472 |
| 0.0659 | 6.0 | 1690 | 0.0804 | 0.9813 | 0.9815 | 0.9801 | 0.9807 |
| 0.0917 | 7.0 | 1972 | 0.1062 | 0.9734 | 0.9765 | 0.9676 | 0.9716 |
| 0.108 | 8.0 | 2254 | 0.0568 | 0.9849 | 0.9868 | 0.9794 | 0.9828 |
| 0.1151 | 9.0 | 2535 | 0.0508 | 0.9858 | 0.9876 | 0.9863 | 0.9869 |
| 0.049 | 9.97 | 2810 | 0.0508 | 0.9858 | 0.9892 | 0.9865 | 0.9878 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3