Model save
Browse files
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: facebook/convnextv2-base-22k-224
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- f1
|
10 |
+
- precision
|
11 |
+
- recall
|
12 |
+
model-index:
|
13 |
+
- name: convnextv2-base-22k-224-finetuned-tekno24-highdata-90
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# convnextv2-base-22k-224-finetuned-tekno24-highdata-90
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on an unknown dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 1.0280
|
25 |
+
- Accuracy: 0.6129
|
26 |
+
- F1: 0.6087
|
27 |
+
- Precision: 0.6161
|
28 |
+
- Recall: 0.6129
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 5e-05
|
48 |
+
- train_batch_size: 16
|
49 |
+
- eval_batch_size: 16
|
50 |
+
- seed: 42
|
51 |
+
- gradient_accumulation_steps: 4
|
52 |
+
- total_train_batch_size: 64
|
53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
+
- lr_scheduler_type: linear
|
55 |
+
- lr_scheduler_warmup_ratio: 0.1
|
56 |
+
- num_epochs: 30
|
57 |
+
- mixed_precision_training: Native AMP
|
58 |
+
|
59 |
+
### Training results
|
60 |
+
|
61 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
62 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
63 |
+
| 1.3277 | 0.9908 | 81 | 1.2870 | 0.4147 | 0.3280 | 0.3714 | 0.4147 |
|
64 |
+
| 1.2024 | 1.9939 | 163 | 1.0890 | 0.4747 | 0.3907 | 0.4944 | 0.4747 |
|
65 |
+
| 1.2067 | 2.9969 | 245 | 1.0601 | 0.5438 | 0.4965 | 0.5084 | 0.5438 |
|
66 |
+
| 1.206 | 4.0 | 327 | 1.0143 | 0.5392 | 0.5159 | 0.5180 | 0.5392 |
|
67 |
+
| 1.1049 | 4.9908 | 408 | 0.9688 | 0.5760 | 0.5451 | 0.5467 | 0.5760 |
|
68 |
+
| 1.0931 | 5.9939 | 490 | 1.0351 | 0.5622 | 0.5562 | 0.5939 | 0.5622 |
|
69 |
+
| 1.0752 | 6.9969 | 572 | 0.9370 | 0.5899 | 0.5592 | 0.5730 | 0.5899 |
|
70 |
+
| 1.03 | 8.0 | 654 | 0.9417 | 0.5760 | 0.5510 | 0.5414 | 0.5760 |
|
71 |
+
| 0.988 | 8.9908 | 735 | 0.8942 | 0.5991 | 0.5772 | 0.5819 | 0.5991 |
|
72 |
+
| 0.9692 | 9.9939 | 817 | 0.9091 | 0.6083 | 0.5937 | 0.5981 | 0.6083 |
|
73 |
+
| 0.9896 | 10.9969 | 899 | 0.8690 | 0.6037 | 0.5905 | 0.5937 | 0.6037 |
|
74 |
+
| 0.9479 | 12.0 | 981 | 0.8705 | 0.6406 | 0.6268 | 0.6307 | 0.6406 |
|
75 |
+
| 0.898 | 12.9908 | 1062 | 0.8569 | 0.6498 | 0.6440 | 0.6465 | 0.6498 |
|
76 |
+
| 0.9101 | 13.9939 | 1144 | 0.8736 | 0.6129 | 0.6091 | 0.6179 | 0.6129 |
|
77 |
+
| 0.8431 | 14.9969 | 1226 | 0.8684 | 0.6452 | 0.6419 | 0.6447 | 0.6452 |
|
78 |
+
| 0.8187 | 16.0 | 1308 | 0.9032 | 0.6221 | 0.6199 | 0.6207 | 0.6221 |
|
79 |
+
| 0.7614 | 16.9908 | 1389 | 0.9013 | 0.6359 | 0.6305 | 0.6434 | 0.6359 |
|
80 |
+
| 0.725 | 17.9939 | 1471 | 0.9702 | 0.5991 | 0.5975 | 0.6072 | 0.5991 |
|
81 |
+
| 0.6938 | 18.9969 | 1553 | 0.9598 | 0.6728 | 0.6660 | 0.6840 | 0.6728 |
|
82 |
+
| 0.6761 | 20.0 | 1635 | 0.9886 | 0.6083 | 0.6112 | 0.6242 | 0.6083 |
|
83 |
+
| 0.5865 | 20.9908 | 1716 | 0.9367 | 0.6498 | 0.6428 | 0.6432 | 0.6498 |
|
84 |
+
| 0.5857 | 21.9939 | 1798 | 0.9694 | 0.6313 | 0.6322 | 0.6331 | 0.6313 |
|
85 |
+
| 0.556 | 22.9969 | 1880 | 1.0212 | 0.6359 | 0.6296 | 0.6574 | 0.6359 |
|
86 |
+
| 0.4871 | 24.0 | 1962 | 1.0328 | 0.5945 | 0.5879 | 0.5951 | 0.5945 |
|
87 |
+
| 0.5254 | 24.9908 | 2043 | 1.0132 | 0.5945 | 0.5917 | 0.5968 | 0.5945 |
|
88 |
+
| 0.5054 | 25.9939 | 2125 | 1.0385 | 0.5945 | 0.5944 | 0.5988 | 0.5945 |
|
89 |
+
| 0.4706 | 26.9969 | 2207 | 1.0626 | 0.6037 | 0.5983 | 0.6100 | 0.6037 |
|
90 |
+
| 0.418 | 28.0 | 2289 | 1.0531 | 0.5806 | 0.5774 | 0.5830 | 0.5806 |
|
91 |
+
| 0.455 | 28.9908 | 2370 | 1.0340 | 0.6083 | 0.6039 | 0.6151 | 0.6083 |
|
92 |
+
| 0.4414 | 29.7248 | 2430 | 1.0280 | 0.6129 | 0.6087 | 0.6161 | 0.6129 |
|
93 |
+
|
94 |
+
|
95 |
+
### Framework versions
|
96 |
+
|
97 |
+
- Transformers 4.44.2
|
98 |
+
- Pytorch 2.4.0+cu121
|
99 |
+
- Datasets 2.21.0
|
100 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 350833648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ee2f776470709eaa4651be429bac5e47577f1e0b3e7d52e3b80709ab2f303f0
|
3 |
size 350833648
|
runs/Sep05_12-48-05_b998cf4c28a2/events.out.tfevents.1725540494.b998cf4c28a2.3248.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f83a2f17a79e9a6aab0a6d43966ee3ffe59a44bb60077926780e89df9b3369de
|
3 |
+
size 71040
|