Hugging Face's logo

alem-147
/
poison-distill

Image Classification
Transformers
TensorBoard
Safetensors
mobilenet_v2
Generated from Trainer
Model card Files Metrics Community
alem-147 commited on
Commit
10978cd
·
verified ·
1 Parent(s): f09e68d

End of training

Browse files
Files changed (2) hide show
  1. README.md +53 -23
  2. logs/events.out.tfevents.1733186863.e54e41aa74d9.2851.5 +3 -0
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: -42.4617
20
- - Accuracy: 0.6165
21
 
22
  ## Model description
23
 
@@ -42,33 +42,63 @@ The following hyperparameters were used during training:
42
  - seed: 42
43
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: linear
45
- - num_epochs: 20
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | -1.7321 | 1.0 | 130 | -17.9718 | 0.4135 |
53
- | -10.3826 | 2.0 | 260 | -21.0786 | 0.4286 |
54
- | -15.9561 | 3.0 | 390 | -30.7402 | 0.3609 |
55
- | -20.4105 | 4.0 | 520 | -8.7054 | 0.6090 |
56
- | -23.6697 | 5.0 | 650 | -41.1276 | 0.5263 |
57
- | -28.1385 | 6.0 | 780 | -53.7167 | 0.4135 |
58
- | -30.4932 | 7.0 | 910 | -54.0164 | 0.3609 |
59
- | -33.5563 | 8.0 | 1040 | -49.4077 | 0.3233 |
60
- | -36.6955 | 9.0 | 1170 | -38.3125 | 0.5489 |
61
- | -38.8208 | 10.0 | 1300 | -42.4497 | 0.6842 |
62
- | -40.791 | 11.0 | 1430 | -37.1019 | 0.5789 |
63
- | -43.1559 | 12.0 | 1560 | -38.0363 | 0.3759 |
64
- | -45.1497 | 13.0 | 1690 | -81.5224 | 0.3609 |
65
- | -46.5745 | 14.0 | 1820 | -105.4418 | 0.3609 |
66
- | -47.6707 | 15.0 | 1950 | -70.0515 | 0.5639 |
67
- | -48.1727 | 16.0 | 2080 | -38.0205 | 0.3233 |
68
- | -50.192 | 17.0 | 2210 | -87.6547 | 0.5113 |
69
- | -50.2229 | 18.0 | 2340 | -103.3304 | 0.5263 |
70
- | -50.7076 | 19.0 | 2470 | -45.6348 | 0.5414 |
71
- | -51.8644 | 20.0 | 2600 | -37.3647 | 0.5940 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: -113.4181
20
+ - Accuracy: 0.6917
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 50
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | -0.7533 | 1.0 | 130 | -7.9549 | 0.5263 |
53
+ | -8.2193 | 2.0 | 260 | -15.5418 | 0.4662 |
54
+ | -14.3197 | 3.0 | 390 | -32.2167 | 0.4737 |
55
+ | -18.5547 | 4.0 | 520 | -18.9202 | 0.5489 |
56
+ | -22.6905 | 5.0 | 650 | -55.1682 | 0.4361 |
57
+ | -27.5336 | 6.0 | 780 | -32.4679 | 0.3459 |
58
+ | -29.5975 | 7.0 | 910 | -48.1715 | 0.3985 |
59
+ | -34.1837 | 8.0 | 1040 | -67.7293 | 0.6165 |
60
+ | -37.6123 | 9.0 | 1170 | -52.1341 | 0.4662 |
61
+ | -40.7694 | 10.0 | 1300 | -49.0945 | 0.6767 |
62
+ | -43.3691 | 11.0 | 1430 | -37.0478 | 0.5489 |
63
+ | -47.6433 | 12.0 | 1560 | -73.0523 | 0.4511 |
64
+ | -51.0141 | 13.0 | 1690 | -110.8840 | 0.4812 |
65
+ | -54.6 | 14.0 | 1820 | -81.2219 | 0.3308 |
66
+ | -57.2133 | 15.0 | 1950 | -80.8684 | 0.5113 |
67
+ | -58.3442 | 16.0 | 2080 | -66.5341 | 0.4060 |
68
+ | -64.7089 | 17.0 | 2210 | -75.7059 | 0.5564 |
69
+ | -64.26 | 18.0 | 2340 | -77.7801 | 0.5263 |
70
+ | -67.8509 | 19.0 | 2470 | -61.1841 | 0.6316 |
71
+ | -71.9371 | 20.0 | 2600 | -118.1544 | 0.5038 |
72
+ | -75.9672 | 21.0 | 2730 | -179.2044 | 0.4812 |
73
+ | -78.0096 | 22.0 | 2860 | -129.4854 | 0.4436 |
74
+ | -80.3581 | 23.0 | 2990 | -100.0687 | 0.4286 |
75
+ | -84.623 | 24.0 | 3120 | -82.5292 | 0.3835 |
76
+ | -86.5363 | 25.0 | 3250 | -84.6636 | 0.4211 |
77
+ | -90.8566 | 26.0 | 3380 | -96.3337 | 0.5489 |
78
+ | -92.2054 | 27.0 | 3510 | -110.3293 | 0.4737 |
79
+ | -97.6982 | 28.0 | 3640 | -195.6973 | 0.4135 |
80
+ | -95.8944 | 29.0 | 3770 | -101.9933 | 0.3609 |
81
+ | -99.491 | 30.0 | 3900 | -99.8199 | 0.6541 |
82
+ | -103.0877 | 31.0 | 4030 | -94.2175 | 0.6767 |
83
+ | -102.7123 | 32.0 | 4160 | -98.6300 | 0.4887 |
84
+ | -105.2087 | 33.0 | 4290 | -152.7768 | 0.4962 |
85
+ | -105.3795 | 34.0 | 4420 | -198.8245 | 0.5263 |
86
+ | -108.9734 | 35.0 | 4550 | -105.7644 | 0.4286 |
87
+ | -111.1308 | 36.0 | 4680 | -121.4677 | 0.4962 |
88
+ | -115.0085 | 37.0 | 4810 | -75.3733 | 0.3083 |
89
+ | -114.714 | 38.0 | 4940 | -115.4598 | 0.6617 |
90
+ | -117.5734 | 39.0 | 5070 | -108.3964 | 0.4135 |
91
+ | -115.1971 | 40.0 | 5200 | -123.7679 | 0.3835 |
92
+ | -117.5617 | 41.0 | 5330 | -69.2224 | 0.2932 |
93
+ | -118.2803 | 42.0 | 5460 | -104.5906 | 0.6541 |
94
+ | -119.6297 | 43.0 | 5590 | -187.3416 | 0.5188 |
95
+ | -121.6325 | 44.0 | 5720 | -221.8878 | 0.5113 |
96
+ | -120.9663 | 45.0 | 5850 | -176.6644 | 0.3759 |
97
+ | -122.3583 | 46.0 | 5980 | -142.5218 | 0.4361 |
98
+ | -126.6614 | 47.0 | 6110 | -271.1018 | 0.4962 |
99
+ | -122.1615 | 48.0 | 6240 | -240.8323 | 0.3985 |
100
+ | -125.4207 | 49.0 | 6370 | -103.5760 | 0.6466 |
101
+ | -127.0661 | 50.0 | 6500 | -113.2718 | 0.6842 |
102
 
103
 
104
  ### Framework versions
logs/events.out.tfevents.1733186863.e54e41aa74d9.2851.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39539f1d1946d7bfdbf6c7fd18711304e5e2fa69aa0c6b93abdaf06812b75960
3
+ size 411