Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/convnext-base-384-22k-1k
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
model-index:
|
| 9 |
+
- name: convnext-base-384-22k-1k-Kontur-competition-1.3K
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# convnext-base-384-22k-1k-Kontur-competition-1.3K
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/convnext-base-384-22k-1k](https://huggingface.co/facebook/convnext-base-384-22k-1k) on the imagefolder dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0003
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 32
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 128
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 15
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| No log | 0.95 | 9 | 0.5273 |
|
| 55 |
+
| 0.6611 | 2.0 | 19 | 0.1518 |
|
| 56 |
+
| 0.2686 | 2.95 | 28 | 0.0266 |
|
| 57 |
+
| 0.0899 | 4.0 | 38 | 0.0066 |
|
| 58 |
+
| 0.0379 | 4.95 | 47 | 0.0025 |
|
| 59 |
+
| 0.0202 | 6.0 | 57 | 0.0020 |
|
| 60 |
+
| 0.0048 | 6.95 | 66 | 0.0010 |
|
| 61 |
+
| 0.0056 | 8.0 | 76 | 0.0011 |
|
| 62 |
+
| 0.0011 | 8.95 | 85 | 0.0005 |
|
| 63 |
+
| 0.0017 | 10.0 | 95 | 0.0014 |
|
| 64 |
+
| 0.0076 | 10.95 | 104 | 0.0004 |
|
| 65 |
+
| 0.0018 | 12.0 | 114 | 0.0003 |
|
| 66 |
+
| 0.0027 | 12.95 | 123 | 0.0003 |
|
| 67 |
+
| 0.0008 | 14.0 | 133 | 0.0003 |
|
| 68 |
+
| 0.0008 | 14.21 | 135 | 0.0003 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.39.3
|
| 74 |
+
- Pytorch 2.1.2
|
| 75 |
+
- Datasets 2.18.0
|
| 76 |
+
- Tokenizers 0.15.2
|