aashraychegu commited on
Commit
7044d59
·
verified ·
1 Parent(s): f7a6bab

End of training

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. README.md +86 -0
  3. config.json +7 -8
  4. model.safetensors +3 -0
  5. training_args.bin +0 -0
.gitattributes CHANGED
@@ -1 +1,2 @@
1
  pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
 
 
1
  pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
2
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: glacier_segmentation_transformer
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # glacier_segmentation_transformer
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.0282
18
+ - Mean Iou: 0.9476
19
+ - Mean Accuracy: 0.9713
20
+ - Overall Accuracy: 0.9770
21
+ - Per Category Iou: [0.9615266525679848, 0.9111778317508353, 0.9702425642603907]
22
+ - Per Category Accuracy: [0.982983320714055, 0.9432032649898906, 0.987791939813118]
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.00012
42
+ - train_batch_size: 400
43
+ - eval_batch_size: 32
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 25
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------------------------------------------------:|:------------------------------------------------------------:|
54
+ | 0.0828 | 1.0 | 352 | 0.0592 | 0.9208 | 0.9565 | 0.9653 | [0.9469681453924418, 0.8581945798277895, 0.9570958935975151] | [0.9804346868205148, 0.9098953383424603, 0.979223227765012] |
55
+ | 0.0653 | 2.0 | 704 | 0.0545 | 0.9243 | 0.9585 | 0.9668 | [0.9491763751018332, 0.8652493086329979, 0.9583893801723153] | [0.9756058281282557, 0.9177942565930071, 0.9822091134529419] |
56
+ | 0.0615 | 3.0 | 1056 | 0.0520 | 0.9245 | 0.9576 | 0.9673 | [0.9488521139512287, 0.8629337582590615, 0.9615905436256834] | [0.9798485904989809, 0.9082150871992817, 0.9846862114785438] |
57
+ | 0.0568 | 4.0 | 1408 | 0.0497 | 0.9266 | 0.9586 | 0.9682 | [0.949606783690876, 0.8679034925410897, 0.962356135274943] | [0.9740655396584907, 0.9135029366787574, 0.9881750267882855] |
58
+ | 0.0553 | 5.0 | 1760 | 0.0448 | 0.9317 | 0.9624 | 0.9703 | [0.9518683104854363, 0.8791552266868088, 0.9640612798278586] | [0.9766581269222775, 0.9247480628978334, 0.9858310012185293] |
59
+ | 0.0531 | 6.0 | 2112 | 0.0440 | 0.9324 | 0.9633 | 0.9704 | [0.9519743922792153, 0.8820510654279622, 0.9633058622325834] | [0.978891790566398, 0.9277520457319947, 0.9833093882099169] |
60
+ | 0.0516 | 7.0 | 2464 | 0.0415 | 0.9342 | 0.9635 | 0.9713 | [0.9529858938673607, 0.8844842403407042, 0.9650597333255734] | [0.9767157615257003, 0.9266858712956193, 0.9871889860088424] |
61
+ | 0.0496 | 8.0 | 2816 | 0.0406 | 0.9359 | 0.9648 | 0.9719 | [0.9555651950006734, 0.8876507922287321, 0.964435754608489] | [0.9797262558665514, 0.9292800603938921, 0.9853461182114515] |
62
+ | 0.0493 | 9.0 | 3168 | 0.0393 | 0.9365 | 0.9648 | 0.9724 | [0.9556626924479936, 0.8881594759577742, 0.9657764420138888] | [0.9795360289173738, 0.927896526148365, 0.9869706285329666] |
63
+ | 0.0463 | 10.0 | 3520 | 0.0391 | 0.9371 | 0.9657 | 0.9724 | [0.9536840950074162, 0.8916567818261698, 0.9658607405632947] | [0.9765900676045612, 0.9343429939730185, 0.9862598369089146] |
64
+ | 0.046 | 11.0 | 3872 | 0.0379 | 0.9383 | 0.9669 | 0.9729 | [0.9544427772914603, 0.8947383943199397, 0.965840875611707] | [0.9764990841923821, 0.938799387304811, 0.9853293009539879] |
65
+ | 0.0452 | 12.0 | 4224 | 0.0358 | 0.9402 | 0.9671 | 0.9739 | [0.958365142157537, 0.8951548166027431, 0.9670090163868024] | [0.9826695002020712, 0.9327967021491497, 0.985958578753622] |
66
+ | 0.0452 | 13.0 | 4576 | 0.0353 | 0.9421 | 0.9697 | 0.9742 | [0.9566153552692265, 0.9041663510518988, 0.9654341965129734] | [0.9781511412717715, 0.947970829250211, 0.9829622282166149] |
67
+ | 0.0433 | 14.0 | 4928 | 0.0352 | 0.9405 | 0.9668 | 0.9742 | [0.9595360452886308, 0.8947929690736943, 0.9672666207041147] | [0.9845407781679891, 0.9292349314756656, 0.9867658421113708] |
68
+ | 0.0431 | 15.0 | 5280 | 0.0332 | 0.9429 | 0.9683 | 0.9751 | [0.9590021679605092, 0.9009428341327679, 0.9686646519537535] | [0.9808890258011358, 0.9357498662877368, 0.9883632103243261] |
69
+ | 0.0416 | 16.0 | 5632 | 0.0327 | 0.9434 | 0.9688 | 0.9753 | [0.9597417369530555, 0.901854332222541, 0.9686551773513613] | [0.9831348612466031, 0.9360674756485265, 0.9871674788190165] |
70
+ | 0.0414 | 17.0 | 5984 | 0.0319 | 0.9442 | 0.9695 | 0.9755 | [0.9600470959530699, 0.9043351787260081, 0.9681169153162615] | [0.982250790235736, 0.9399363046395433, 0.9864601258953718] |
71
+ | 0.0404 | 18.0 | 6336 | 0.0316 | 0.9446 | 0.9701 | 0.9755 | [0.9589776803135457, 0.9068715131060119, 0.9679329085470226] | [0.9802443827939673, 0.9437927758334433, 0.9862343091520727] |
72
+ | 0.0398 | 19.0 | 6688 | 0.0314 | 0.9446 | 0.9699 | 0.9757 | [0.9588814103780426, 0.905637545251067, 0.9692458875824727] | [0.98042751220199, 0.9420745529130178, 0.987227866073119] |
73
+ | 0.0386 | 20.0 | 7040 | 0.0303 | 0.9455 | 0.9698 | 0.9762 | [0.9601095729129755, 0.9062431533997868, 0.9700239091770606] | [0.9816721896884353, 0.9390483599830692, 0.9887402730113751] |
74
+ | 0.0389 | 21.0 | 7392 | 0.0293 | 0.9467 | 0.9709 | 0.9766 | [0.9608462864680724, 0.9092665750526754, 0.9699517538184947] | [0.9825323474452577, 0.9427535729381092, 0.9874417479885407] |
75
+ | 0.0381 | 22.0 | 7744 | 0.0289 | 0.9470 | 0.9711 | 0.9767 | [0.9613365594140901, 0.9099925770562975, 0.969649897217598] | [0.9831566934116577, 0.9431333306388411, 0.9870399712829142] |
76
+ | 0.0376 | 23.0 | 8096 | 0.0286 | 0.9473 | 0.9713 | 0.9769 | [0.9609977973725258, 0.9109702591251677, 0.970032992637466] | [0.9821836494233457, 0.9442533383545785, 0.98751595129339] |
77
+ | 0.0375 | 24.0 | 8448 | 0.0283 | 0.9472 | 0.9709 | 0.9769 | [0.9616875865568749, 0.9094524903163835, 0.9705179691807947] | [0.9833220629090078, 0.940861432490088, 0.9883972648331962] |
78
+ | 0.0363 | 25.0 | 8800 | 0.0282 | 0.9476 | 0.9713 | 0.9770 | [0.9615266525679848, 0.9111778317508353, 0.9702425642603907] | [0.982983320714055, 0.9432032649898906, 0.987791939813118] |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.45.1
84
+ - Pytorch 2.4.1+cu121
85
+ - Datasets 3.0.1
86
+ - Tokenizers 0.20.0
config.json CHANGED
@@ -1,16 +1,15 @@
1
  {
2
- "_name_or_path": "C:\\Users\\aashr\\Desktop\\research\\glaciers\\glacformer",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
6
  "attention_probs_dropout_prob": 0.0,
7
  "classifier_dropout_prob": 0.1,
8
- "decoder_hidden_size": 768,
9
  "depths": [
10
- 2,
11
- 3,
12
  4,
13
- 3
 
14
  ],
15
  "drop_path_rate": 0.1,
16
  "hidden_act": "gelu",
@@ -18,7 +17,7 @@
18
  "hidden_sizes": [
19
  64,
20
  128,
21
- 320,
22
  512
23
  ],
24
  "id2label": {
@@ -43,7 +42,7 @@
43
  "num_attention_heads": [
44
  1,
45
  2,
46
- 5,
47
  8
48
  ],
49
  "num_channels": 3,
@@ -69,5 +68,5 @@
69
  2
70
  ],
71
  "torch_dtype": "float32",
72
- "transformers_version": "4.33.3"
73
  }
 
1
  {
 
2
  "architectures": [
3
  "SegformerForSemanticSegmentation"
4
  ],
5
  "attention_probs_dropout_prob": 0.0,
6
  "classifier_dropout_prob": 0.1,
7
+ "decoder_hidden_size": 896,
8
  "depths": [
9
+ 6,
 
10
  4,
11
+ 3,
12
+ 2
13
  ],
14
  "drop_path_rate": 0.1,
15
  "hidden_act": "gelu",
 
17
  "hidden_sizes": [
18
  64,
19
  128,
20
+ 384,
21
  512
22
  ],
23
  "id2label": {
 
42
  "num_attention_heads": [
43
  1,
44
  2,
45
+ 6,
46
  8
47
  ],
48
  "num_channels": 3,
 
68
  2
69
  ],
70
  "torch_dtype": "float32",
71
+ "transformers_version": "4.45.1"
72
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b08bcfda208ddf0153a0b982996fc4eae21ae42b26394cac092ebf8fac9fb09d
3
+ size 94992836
training_args.bin ADDED
Binary file (5.37 kB). View file