Hugging Face's logo

JOECHAN890
/
beitv2-base-beans

Image Classification
Transformers
Safetensors
timm
timm_wrapper
Generated from Trainer
Model card Files
xet
Community
JOECHAN890 commited on
Commit
e4247d9
·
verified ·
1 Parent(s): 3447bc2

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. README.md +12 -64
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -3,8 +3,6 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: timm/beitv2_base_patch16_224.in1k_ft_in22k
5
  tags:
6
- - image-classification
7
- - vision
8
  - timm
9
  - generated_from_trainer
10
  metrics:
@@ -19,10 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # beitv2-base-beans
21
 
22
- This model is a fine-tuned version of [timm/beitv2_base_patch16_224.in1k_ft_in22k](https://huggingface.co/timm/beitv2_base_patch16_224.in1k_ft_in22k) on the AI-Lab-Makerere/beans dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.0003
25
- - Accuracy: 1.0
 
26
 
27
  ## Model description
28
 
@@ -41,73 +40,22 @@ More information needed
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
- - learning_rate: 2e-05
45
- - train_batch_size: 8
46
- - eval_batch_size: 8
47
  - seed: 1337
48
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
- - lr_scheduler_type: linear
50
- - num_epochs: 50.0
 
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
- | 0.0435 | 1.0 | 130 | 0.1193 | 0.9624 |
57
- | 0.1536 | 2.0 | 260 | 0.0023 | 1.0 |
58
- | 0.183 | 3.0 | 390 | 0.0015 | 1.0 |
59
- | 0.2256 | 4.0 | 520 | 0.0386 | 0.9850 |
60
- | 0.0555 | 5.0 | 650 | 0.0340 | 0.9850 |
61
- | 0.0713 | 6.0 | 780 | 0.0728 | 0.9925 |
62
- | 0.0082 | 7.0 | 910 | 0.0411 | 0.9925 |
63
- | 0.0085 | 8.0 | 1040 | 0.1002 | 0.9850 |
64
- | 0.0733 | 9.0 | 1170 | 0.0004 | 1.0 |
65
- | 0.0215 | 10.0 | 1300 | 0.0003 | 1.0 |
66
- | 0.0501 | 11.0 | 1430 | 0.0634 | 0.9774 |
67
- | 0.0338 | 12.0 | 1560 | 0.0248 | 0.9925 |
68
- | 0.0045 | 13.0 | 1690 | 0.0939 | 0.9850 |
69
- | 0.0013 | 14.0 | 1820 | 0.0373 | 0.9850 |
70
- | 0.0002 | 15.0 | 1950 | 0.0515 | 0.9925 |
71
- | 0.0074 | 16.0 | 2080 | 0.0017 | 1.0 |
72
- | 0.0005 | 17.0 | 2210 | 0.0588 | 0.9925 |
73
- | 0.0046 | 18.0 | 2340 | 0.0715 | 0.9850 |
74
- | 0.0618 | 19.0 | 2470 | 0.0003 | 1.0 |
75
- | 0.0007 | 20.0 | 2600 | 0.0697 | 0.9850 |
76
- | 0.0001 | 21.0 | 2730 | 0.1105 | 0.9774 |
77
- | 0.0214 | 22.0 | 2860 | 0.0930 | 0.9850 |
78
- | 0.0004 | 23.0 | 2990 | 0.0272 | 0.9925 |
79
- | 0.1619 | 24.0 | 3120 | 0.0024 | 1.0 |
80
- | 0.0015 | 25.0 | 3250 | 0.0003 | 1.0 |
81
- | 0.0148 | 26.0 | 3380 | 0.1312 | 0.9774 |
82
- | 0.0482 | 27.0 | 3510 | 0.0873 | 0.9850 |
83
- | 0.0001 | 28.0 | 3640 | 0.0721 | 0.9850 |
84
- | 0.0954 | 29.0 | 3770 | 0.0143 | 0.9925 |
85
- | 0.1373 | 30.0 | 3900 | 0.0449 | 0.9925 |
86
- | 0.0076 | 31.0 | 4030 | 0.0435 | 0.9925 |
87
- | 0.0028 | 32.0 | 4160 | 0.0101 | 0.9925 |
88
- | 0.0001 | 33.0 | 4290 | 0.0414 | 0.9850 |
89
- | 0.001 | 34.0 | 4420 | 0.0017 | 1.0 |
90
- | 0.0055 | 35.0 | 4550 | 0.0733 | 0.9925 |
91
- | 0.1471 | 36.0 | 4680 | 0.1221 | 0.9774 |
92
- | 0.0484 | 37.0 | 4810 | 0.1473 | 0.9850 |
93
- | 0.0014 | 38.0 | 4940 | 0.0748 | 0.9925 |
94
- | 0.1825 | 39.0 | 5070 | 0.1072 | 0.9850 |
95
- | 0.0 | 40.0 | 5200 | 0.0687 | 0.9925 |
96
- | 0.0081 | 41.0 | 5330 | 0.1147 | 0.9850 |
97
- | 0.0557 | 42.0 | 5460 | 0.0630 | 0.9850 |
98
- | 0.0 | 43.0 | 5590 | 0.0162 | 0.9925 |
99
- | 0.0 | 44.0 | 5720 | 0.0463 | 0.9925 |
100
- | 0.0197 | 45.0 | 5850 | 0.0757 | 0.9850 |
101
- | 0.1442 | 46.0 | 5980 | 0.0941 | 0.9850 |
102
- | 0.0019 | 47.0 | 6110 | 0.0760 | 0.9850 |
103
- | 0.0001 | 48.0 | 6240 | 0.0885 | 0.9850 |
104
- | 0.0854 | 49.0 | 6370 | 0.0788 | 0.9850 |
105
- | 0.0005 | 50.0 | 6500 | 0.0707 | 0.9850 |
106
 
107
 
108
  ### Framework versions
109
 
110
- - Transformers 4.54.1
111
  - Pytorch 2.7.1+cu126
112
  - Datasets 4.0.0
113
- - Tokenizers 0.21.4
 
3
  license: apache-2.0
4
  base_model: timm/beitv2_base_patch16_224.in1k_ft_in22k
5
  tags:
 
 
6
  - timm
7
  - generated_from_trainer
8
  metrics:
 
17
 
18
  # beitv2-base-beans
19
 
20
+ This model is a fine-tuned version of [timm/beitv2_base_patch16_224.in1k_ft_in22k](https://huggingface.co/timm/beitv2_base_patch16_224.in1k_ft_in22k) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Accuracy: 0.9232
23
+ - Loss: 0.3161
24
+ - Num Input Tokens Seen: 0
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 7.8125e-05
44
+ - train_batch_size: 160
45
+ - eval_batch_size: 160
46
  - seed: 1337
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_steps: 20360
50
+ - num_epochs: 100.0
51
 
52
  ### Training results
53
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
57
 
58
+ - Transformers 4.57.0.dev0
59
  - Pytorch 2.7.1+cu126
60
  - Datasets 4.0.0
61
+ - Tokenizers 0.22.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20a2521a0ba0401c479014afc86b8f08bcf85f6c7470f67fdb7580c196229778
3
  size 343189472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0ed1391d64681ee76552fa4f17cd43f9eed97a0fec7c7e2f1f25d1ef7da323
3
  size 343189472
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d65bd1e532de54c525c8dc470d48e597ef9231abb57cefdf7c4751949982bb4a
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3897e1f33ed58cd1f2cde2efe2aaeeacc7204b7519c5a4b54be65956979ff680
3
  size 5777