Commit
•
56d2df5
1
Parent(s):
1d7bc72
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- f1
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: convnext-base-224_finetuned_on_unlabelled_IA_with_snorkel_labels
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# convnext-base-224_finetuned_on_unlabelled_IA_with_snorkel_labels
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [facebook/convnext-base-224](https://huggingface.co/facebook/convnext-base-224) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.3443
|
| 23 |
+
- Precision: 0.9864
|
| 24 |
+
- Recall: 0.9822
|
| 25 |
+
- F1: 0.9843
|
| 26 |
+
- Accuracy: 0.9884
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 5e-05
|
| 46 |
+
- train_batch_size: 16
|
| 47 |
+
- eval_batch_size: 16
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 10
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
- label_smoothing_factor: 0.2
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 58 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 59 |
+
| 0.3611 | 1.0 | 2021 | 0.3467 | 0.9843 | 0.9729 | 0.9784 | 0.9842 |
|
| 60 |
+
| 0.3524 | 2.0 | 4042 | 0.3453 | 0.9853 | 0.9790 | 0.9821 | 0.9868 |
|
| 61 |
+
| 0.3466 | 3.0 | 6063 | 0.3438 | 0.9854 | 0.9847 | 0.9851 | 0.9889 |
|
| 62 |
+
| 0.3433 | 4.0 | 8084 | 0.3434 | 0.9850 | 0.9808 | 0.9829 | 0.9873 |
|
| 63 |
+
| 0.3404 | 5.0 | 10105 | 0.3459 | 0.9853 | 0.9790 | 0.9821 | 0.9868 |
|
| 64 |
+
| 0.3384 | 6.0 | 12126 | 0.3453 | 0.9853 | 0.9790 | 0.9821 | 0.9868 |
|
| 65 |
+
| 0.3382 | 7.0 | 14147 | 0.3437 | 0.9864 | 0.9822 | 0.9843 | 0.9884 |
|
| 66 |
+
| 0.3358 | 8.0 | 16168 | 0.3441 | 0.9857 | 0.9829 | 0.9843 | 0.9884 |
|
| 67 |
+
| 0.3349 | 9.0 | 18189 | 0.3448 | 0.9857 | 0.9829 | 0.9843 | 0.9884 |
|
| 68 |
+
| 0.3325 | 10.0 | 20210 | 0.3443 | 0.9864 | 0.9822 | 0.9843 | 0.9884 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.22.2
|
| 74 |
+
- Pytorch 1.12.1+cu113
|
| 75 |
+
- Datasets 2.5.1
|
| 76 |
+
- Tokenizers 0.12.1
|