convnextv2-tiny-22k-384-finetuned-spiderTraining100-1000
This model is a fine-tuned version of facebook/convnextv2-tiny-22k-384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3472
- Accuracy: 0.9017
- Precision: 0.9020
- Recall: 0.9010
- F1: 0.9008
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: 16
- eval_batch_size: 16
- seed: 42
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.1428 | 1.0 | 1249 | 0.8161 | 0.7863 | 0.7938 | 0.7848 | 0.7815 |
| 0.8248 | 2.0 | 2499 | 0.5184 | 0.8583 | 0.8616 | 0.8569 | 0.8568 |
| 0.7002 | 3.0 | 3749 | 0.4145 | 0.8816 | 0.8836 | 0.8803 | 0.8805 |
| 0.5284 | 4.0 | 4999 | 0.3724 | 0.8953 | 0.8966 | 0.8942 | 0.8943 |
| 0.4511 | 5.0 | 6245 | 0.3472 | 0.9017 | 0.9020 | 0.9010 | 0.9008 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3