update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: convnextv2-base-22k-224-finetuned-critique-100k
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# convnextv2-base-22k-224-finetuned-critique-100k
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1320
|
| 20 |
+
- Accuracy: 0.9479
|
| 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: 5
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 0.6277 | 0.07 | 50 | 0.5987 | 0.6767 |
|
| 55 |
+
| 0.5459 | 0.14 | 100 | 0.5187 | 0.7401 |
|
| 56 |
+
| 0.4397 | 0.21 | 150 | 0.4448 | 0.7768 |
|
| 57 |
+
| 0.4197 | 0.28 | 200 | 0.3686 | 0.8401 |
|
| 58 |
+
| 0.3397 | 0.36 | 250 | 0.3153 | 0.8664 |
|
| 59 |
+
| 0.3345 | 0.43 | 300 | 0.3071 | 0.8701 |
|
| 60 |
+
| 0.3177 | 0.5 | 350 | 0.2576 | 0.8938 |
|
| 61 |
+
| 0.3182 | 0.57 | 400 | 0.2546 | 0.8926 |
|
| 62 |
+
| 0.2596 | 0.64 | 450 | 0.2320 | 0.9004 |
|
| 63 |
+
| 0.2563 | 0.71 | 500 | 0.2205 | 0.9082 |
|
| 64 |
+
| 0.2543 | 0.78 | 550 | 0.2142 | 0.9147 |
|
| 65 |
+
| 0.2768 | 0.85 | 600 | 0.2136 | 0.9132 |
|
| 66 |
+
| 0.2486 | 0.92 | 650 | 0.2052 | 0.9175 |
|
| 67 |
+
| 0.2504 | 1.0 | 700 | 0.2314 | 0.9058 |
|
| 68 |
+
| 0.2437 | 1.07 | 750 | 0.1943 | 0.9235 |
|
| 69 |
+
| 0.212 | 1.14 | 800 | 0.2019 | 0.9183 |
|
| 70 |
+
| 0.1891 | 1.21 | 850 | 0.1845 | 0.9254 |
|
| 71 |
+
| 0.2105 | 1.28 | 900 | 0.1834 | 0.9288 |
|
| 72 |
+
| 0.2285 | 1.35 | 950 | 0.1994 | 0.9206 |
|
| 73 |
+
| 0.2214 | 1.42 | 1000 | 0.1804 | 0.9251 |
|
| 74 |
+
| 0.1848 | 1.49 | 1050 | 0.1975 | 0.9196 |
|
| 75 |
+
| 0.191 | 1.56 | 1100 | 0.1795 | 0.9269 |
|
| 76 |
+
| 0.1794 | 1.64 | 1150 | 0.1606 | 0.9358 |
|
| 77 |
+
| 0.2084 | 1.71 | 1200 | 0.1807 | 0.9293 |
|
| 78 |
+
| 0.199 | 1.78 | 1250 | 0.1697 | 0.9307 |
|
| 79 |
+
| 0.1874 | 1.85 | 1300 | 0.1650 | 0.9372 |
|
| 80 |
+
| 0.1681 | 1.92 | 1350 | 0.1515 | 0.939 |
|
| 81 |
+
| 0.1696 | 1.99 | 1400 | 0.1473 | 0.9416 |
|
| 82 |
+
| 0.1651 | 2.06 | 1450 | 0.1489 | 0.9428 |
|
| 83 |
+
| 0.1627 | 2.13 | 1500 | 0.1529 | 0.9395 |
|
| 84 |
+
| 0.1754 | 2.2 | 1550 | 0.1540 | 0.9379 |
|
| 85 |
+
| 0.1302 | 2.28 | 1600 | 0.1579 | 0.939 |
|
| 86 |
+
| 0.1643 | 2.35 | 1650 | 0.1518 | 0.9401 |
|
| 87 |
+
| 0.1938 | 2.42 | 1700 | 0.1479 | 0.941 |
|
| 88 |
+
| 0.1441 | 2.49 | 1750 | 0.1451 | 0.9436 |
|
| 89 |
+
| 0.1478 | 2.56 | 1800 | 0.1324 | 0.9472 |
|
| 90 |
+
| 0.1275 | 2.63 | 1850 | 0.1340 | 0.9466 |
|
| 91 |
+
| 0.1582 | 2.7 | 1900 | 0.1501 | 0.9391 |
|
| 92 |
+
| 0.1472 | 2.77 | 1950 | 0.1354 | 0.9451 |
|
| 93 |
+
| 0.1522 | 2.84 | 2000 | 0.1309 | 0.9479 |
|
| 94 |
+
| 0.1593 | 2.92 | 2050 | 0.1433 | 0.9452 |
|
| 95 |
+
| 0.1541 | 2.99 | 2100 | 0.1381 | 0.9466 |
|
| 96 |
+
| 0.1297 | 3.06 | 2150 | 0.1320 | 0.9479 |
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
### Framework versions
|
| 100 |
+
|
| 101 |
+
- Transformers 4.30.2
|
| 102 |
+
- Pytorch 1.13.1
|
| 103 |
+
- Datasets 2.13.1
|
| 104 |
+
- Tokenizers 0.13.3
|