Commit
•
0fec038
1
Parent(s):
b8e0428
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
-
- image-classification
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: convnext_manuscript_iiif
|
| 8 |
results: []
|
|
@@ -13,7 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# convnext_manuscript_iiif
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [facebook/convnext-base-224-22k](https://huggingface.co/facebook/convnext-base-224-22k) on the
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -38,9 +42,45 @@ The following hyperparameters were used during training:
|
|
| 38 |
- seed: 1337
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
-
- num_epochs:
|
| 42 |
- mixed_precision_training: Native AMP
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- Transformers 4.18.0.dev0
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- f1
|
| 7 |
model-index:
|
| 8 |
- name: convnext_manuscript_iiif
|
| 9 |
results: []
|
|
|
|
| 14 |
|
| 15 |
# convnext_manuscript_iiif
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [facebook/convnext-base-224-22k](https://huggingface.co/facebook/convnext-base-224-22k) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 7.5595
|
| 20 |
+
- F1: 0.0041
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 42 |
- seed: 1337
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 30.0
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 52 |
+
| 6.5753 | 1.0 | 2038 | 6.4121 | 0.0016 |
|
| 53 |
+
| 5.9865 | 2.0 | 4076 | 5.9466 | 0.0021 |
|
| 54 |
+
| 5.6521 | 3.0 | 6114 | 5.7645 | 0.0029 |
|
| 55 |
+
| 5.3123 | 4.0 | 8152 | 5.6890 | 0.0033 |
|
| 56 |
+
| 5.0337 | 5.0 | 10190 | 5.6692 | 0.0034 |
|
| 57 |
+
| 4.743 | 6.0 | 12228 | 5.5856 | 0.0037 |
|
| 58 |
+
| 4.4387 | 7.0 | 14266 | 5.5969 | 0.0042 |
|
| 59 |
+
| 4.1422 | 8.0 | 16304 | 5.6711 | 0.0043 |
|
| 60 |
+
| 3.8372 | 9.0 | 18342 | 5.6761 | 0.0044 |
|
| 61 |
+
| 3.5244 | 10.0 | 20380 | 5.8469 | 0.0042 |
|
| 62 |
+
| 3.2321 | 11.0 | 22418 | 5.8774 | 0.0045 |
|
| 63 |
+
| 2.9004 | 12.0 | 24456 | 6.1186 | 0.0047 |
|
| 64 |
+
| 2.5937 | 13.0 | 26494 | 6.2398 | 0.0046 |
|
| 65 |
+
| 2.2983 | 14.0 | 28532 | 6.3732 | 0.0049 |
|
| 66 |
+
| 2.0611 | 15.0 | 30570 | 6.5024 | 0.0045 |
|
| 67 |
+
| 1.8153 | 16.0 | 32608 | 6.6585 | 0.0047 |
|
| 68 |
+
| 1.6075 | 17.0 | 34646 | 6.8333 | 0.0043 |
|
| 69 |
+
| 1.4342 | 18.0 | 36684 | 6.9529 | 0.0044 |
|
| 70 |
+
| 1.2614 | 19.0 | 38722 | 7.1129 | 0.0046 |
|
| 71 |
+
| 1.1463 | 20.0 | 40760 | 7.1977 | 0.0039 |
|
| 72 |
+
| 1.0387 | 21.0 | 42798 | 7.2700 | 0.0044 |
|
| 73 |
+
| 0.9635 | 22.0 | 44836 | 7.3375 | 0.0040 |
|
| 74 |
+
| 0.8872 | 23.0 | 46874 | 7.4003 | 0.0039 |
|
| 75 |
+
| 0.8156 | 24.0 | 48912 | 7.4884 | 0.0039 |
|
| 76 |
+
| 0.7544 | 25.0 | 50950 | 7.4764 | 0.0039 |
|
| 77 |
+
| 0.6893 | 26.0 | 52988 | 7.5153 | 0.0042 |
|
| 78 |
+
| 0.6767 | 27.0 | 55026 | 7.5427 | 0.0043 |
|
| 79 |
+
| 0.6098 | 28.0 | 57064 | 7.5547 | 0.0042 |
|
| 80 |
+
| 0.5871 | 29.0 | 59102 | 7.5533 | 0.0041 |
|
| 81 |
+
| 0.5696 | 30.0 | 61140 | 7.5595 | 0.0041 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
### Framework versions
|
| 85 |
|
| 86 |
- Transformers 4.18.0.dev0
|