metadata
license: apache-2.0
base_model: facebook/convnextv2-atto-1k-224
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: 10-convnextv2-atto-1k-224-finetuned-spiderTraining20-500
results: []
10-convnextv2-atto-1k-224-finetuned-spiderTraining20-500
This model is a fine-tuned version of facebook/convnextv2-atto-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4791
- Accuracy: 0.8408
- Precision: 0.8390
- Recall: 0.8394
- F1: 0.8383
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: 5e-05
- train_batch_size: 25
- eval_batch_size: 25
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 100
- 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 |
|---|---|---|---|---|---|---|---|
| 1.8923 | 1.0 | 80 | 1.6643 | 0.4955 | 0.5096 | 0.4901 | 0.4754 |
| 1.0142 | 2.0 | 160 | 0.8840 | 0.7347 | 0.7512 | 0.7309 | 0.7279 |
| 0.8541 | 3.0 | 240 | 0.7184 | 0.7638 | 0.7659 | 0.7570 | 0.7554 |
| 0.7463 | 4.0 | 320 | 0.6199 | 0.8058 | 0.8057 | 0.8044 | 0.8005 |
| 0.6316 | 5.0 | 400 | 0.5719 | 0.8308 | 0.8344 | 0.8283 | 0.8277 |
| 0.576 | 6.0 | 480 | 0.5260 | 0.8258 | 0.8251 | 0.8211 | 0.8216 |
| 0.5158 | 7.0 | 560 | 0.5165 | 0.8428 | 0.8413 | 0.8397 | 0.8386 |
| 0.4545 | 8.0 | 640 | 0.4952 | 0.8428 | 0.8427 | 0.8400 | 0.8405 |
| 0.4602 | 9.0 | 720 | 0.4858 | 0.8418 | 0.8386 | 0.8388 | 0.8378 |
| 0.4606 | 10.0 | 800 | 0.4791 | 0.8408 | 0.8390 | 0.8394 | 0.8383 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3