Hugging Face's logo

JuudasMooses
/
detr

Object Detection
Transformers
TensorBoard
Safetensors
detr
Generated from Trainer
Model card Files
xet
 Metrics Community
JuudasMooses commited on
Commit
5af4851
·
verified ·
1 Parent(s): 3114210

End of training

Browse files
Files changed (5) hide show
  1. README.md +7 -66
  2. model.safetensors +1 -1
  3. runs/Apr25_20-31-04_943210d522d2/events.out.tfevents.1714077065.943210d522d2.184.0 +3 -0
  4. runs/Apr25_20-32-27_943210d522d2/events.out.tfevents.1714077149.943210d522d2.184.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 5.6048
19
 
20
  ## Model description
21
 
@@ -35,7 +35,7 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.001
38
- - train_batch_size: 16
39
  - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -45,70 +45,11 @@ The following hyperparameters were used during training:
45
 
46
  ### Training results
47
 
48
- | Training Loss | Epoch | Step | Validation Loss |
49
- |:-------------:|:-----:|:----:|:---------------:|
50
- | 4.4599 | 0.016 | 10 | 2.8936 |
51
- | 3.3016 | 0.032 | 20 | 6.6479 |
52
- | 5.2065 | 0.048 | 30 | 6.2123 |
53
- | 3.5324 | 0.064 | 40 | 6.4983 |
54
- | 3.2202 | 0.08 | 50 | 5.9336 |
55
- | 2.7929 | 0.096 | 60 | 6.3128 |
56
- | 2.7633 | 0.112 | 70 | 5.5931 |
57
- | 2.8813 | 0.128 | 80 | 6.3179 |
58
- | 2.8933 | 0.144 | 90 | 5.8585 |
59
- | 2.679 | 0.16 | 100 | 6.0404 |
60
- | 2.6873 | 0.176 | 110 | 5.8601 |
61
- | 2.6229 | 0.192 | 120 | 5.8184 |
62
- | 2.4642 | 0.208 | 130 | 5.8825 |
63
- | 2.55 | 0.224 | 140 | 5.5856 |
64
- | 2.8452 | 0.24 | 150 | 7.0418 |
65
- | 2.9801 | 0.256 | 160 | 6.7697 |
66
- | 2.6145 | 0.272 | 170 | 5.8766 |
67
- | 2.4697 | 0.288 | 180 | 5.5391 |
68
- | 2.5697 | 0.304 | 190 | 5.8266 |
69
- | 2.6082 | 0.32 | 200 | 5.9582 |
70
- | 2.5206 | 0.336 | 210 | 6.5178 |
71
- | 2.5752 | 0.352 | 220 | 5.6517 |
72
- | 2.5935 | 0.368 | 230 | 5.6123 |
73
- | 2.5473 | 0.384 | 240 | 5.7041 |
74
- | 2.3811 | 0.4 | 250 | 5.7744 |
75
- | 2.3651 | 0.416 | 260 | 5.6436 |
76
- | 2.4254 | 0.432 | 270 | 6.8432 |
77
- | 2.4753 | 0.448 | 280 | 5.7462 |
78
- | 2.5104 | 0.464 | 290 | 5.6794 |
79
- | 2.765 | 0.48 | 300 | 8.6370 |
80
- | 2.6003 | 0.496 | 310 | 5.6606 |
81
- | 2.5401 | 0.512 | 320 | 5.6641 |
82
- | 2.3749 | 0.528 | 330 | 6.1166 |
83
- | 2.4125 | 0.544 | 340 | 5.5938 |
84
- | 2.3311 | 0.56 | 350 | 5.9182 |
85
- | 2.3081 | 0.576 | 360 | 7.1080 |
86
- | 2.3663 | 0.592 | 370 | 5.8343 |
87
- | 2.4314 | 0.608 | 380 | 5.5815 |
88
- | 2.2678 | 0.624 | 390 | 5.6065 |
89
- | 2.2555 | 0.64 | 400 | 5.5740 |
90
- | 2.2658 | 0.656 | 410 | 5.8555 |
91
- | 2.1868 | 0.672 | 420 | 5.5262 |
92
- | 2.2358 | 0.688 | 430 | 5.7307 |
93
- | 2.3013 | 0.704 | 440 | 5.6189 |
94
- | 2.236 | 0.72 | 450 | 5.7384 |
95
- | 2.3447 | 0.736 | 460 | 5.5739 |
96
- | 2.4224 | 0.752 | 470 | 5.7780 |
97
- | 2.2245 | 0.768 | 480 | 5.4866 |
98
- | 2.0615 | 0.784 | 490 | 5.8015 |
99
- | 2.2247 | 0.8 | 500 | 5.6490 |
100
- | 2.2072 | 0.816 | 510 | 5.6494 |
101
- | 2.154 | 0.832 | 520 | 5.6202 |
102
- | 2.1415 | 0.848 | 530 | 5.6474 |
103
- | 2.1173 | 0.864 | 540 | 5.6269 |
104
- | 2.1209 | 0.88 | 550 | 5.6553 |
105
- | 2.215 | 0.896 | 560 | 5.8474 |
106
- | 2.1895 | 0.912 | 570 | 5.6095 |
107
- | 2.141 | 0.928 | 580 | 5.6234 |
108
- | 2.1979 | 0.944 | 590 | 5.5694 |
109
- | 2.1458 | 0.96 | 600 | 5.6973 |
110
- | 2.0407 | 0.976 | 610 | 5.5849 |
111
- | 2.1269 | 0.992 | 620 | 5.6048 |
112
 
113
 
114
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 5.6795
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.001
38
+ - train_batch_size: 32
39
  - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:------:|:----:|:---------------:|
50
+ | 2.9973 | 0.3195 | 100 | 3.0595 |
51
+ | 2.5938 | 0.6390 | 200 | 5.8527 |
52
+ | 2.0334 | 0.9585 | 300 | 5.6795 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:277a4b558f7a73e397c2f095657694c56af34bb500d280c91d8614256f14da65
3
  size 166506812
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea733b181c1c0891657f085b56c76ebe0916d249ff603eaaa38719c884675c6b
3
  size 166506812
runs/Apr25_20-31-04_943210d522d2/events.out.tfevents.1714077065.943210d522d2.184.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f304c591ccba489aa34fa77b33c8373719f7d714998dc30ba9c139c8ae1675ce
3
+ size 7482
runs/Apr25_20-32-27_943210d522d2/events.out.tfevents.1714077149.943210d522d2.184.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be817058cfc25e965c3193fdf225a99d622a1297f0241092d6db4b71c750ce59
3
+ size 9273
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95b1d48bd89f8d4f14af6a3056aa55bb139e5349907f78e59008e9a1c6fa0d2c
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cac1b3adcb6df02d383ebb97e7861b4be98eb6a601838b0d99f880ac0d3065
3
  size 4920