Saving best model to hub
Browse files- README.md +116 -0
- config.json +76 -0
- pytorch_model.bin +3 -0
- test-logits.npz +3 -0
- test-references.npz +3 -0
- training_args.bin +3 -0
- validation-logits.npz +3 -0
- validation-references.npz +3 -0
README.md
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/resnet-50
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t1.0_a1.0
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t1.0_a1.0
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.7844
|
21 |
+
- Accuracy: 0.742
|
22 |
+
- Brier Loss: 0.4405
|
23 |
+
- Nll: 2.8680
|
24 |
+
- F1 Micro: 0.7420
|
25 |
+
- F1 Macro: 0.7411
|
26 |
+
- Ece: 0.1946
|
27 |
+
- Aurc: 0.1002
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 0.0001
|
47 |
+
- train_batch_size: 64
|
48 |
+
- eval_batch_size: 64
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- num_epochs: 50
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc |
|
58 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:|
|
59 |
+
| No log | 1.0 | 250 | 2.7345 | 0.153 | 0.9327 | 8.3371 | 0.153 | 0.1246 | 0.0866 | 0.7933 |
|
60 |
+
| 2.6983 | 2.0 | 500 | 2.4500 | 0.4213 | 0.8816 | 4.7062 | 0.4213 | 0.3924 | 0.3073 | 0.4444 |
|
61 |
+
| 2.6983 | 3.0 | 750 | 1.7959 | 0.5012 | 0.7003 | 3.3576 | 0.5012 | 0.4758 | 0.1869 | 0.3051 |
|
62 |
+
| 1.7341 | 4.0 | 1000 | 1.3637 | 0.5985 | 0.5511 | 2.8818 | 0.5985 | 0.5868 | 0.1005 | 0.1935 |
|
63 |
+
| 1.7341 | 5.0 | 1250 | 1.1978 | 0.6498 | 0.4862 | 2.7546 | 0.6498 | 0.6471 | 0.0826 | 0.1500 |
|
64 |
+
| 1.0818 | 6.0 | 1500 | 1.0812 | 0.6853 | 0.4364 | 2.6325 | 0.6853 | 0.6845 | 0.0522 | 0.1217 |
|
65 |
+
| 1.0818 | 7.0 | 1750 | 1.0276 | 0.7013 | 0.4149 | 2.5542 | 0.7013 | 0.7003 | 0.0397 | 0.1108 |
|
66 |
+
| 0.7498 | 8.0 | 2000 | 0.9724 | 0.7133 | 0.3944 | 2.4773 | 0.7133 | 0.7129 | 0.0505 | 0.1040 |
|
67 |
+
| 0.7498 | 9.0 | 2250 | 0.9777 | 0.7248 | 0.3924 | 2.4916 | 0.7248 | 0.7242 | 0.0628 | 0.0992 |
|
68 |
+
| 0.5034 | 10.0 | 2500 | 1.0027 | 0.724 | 0.3976 | 2.4974 | 0.724 | 0.7250 | 0.0751 | 0.1032 |
|
69 |
+
| 0.5034 | 11.0 | 2750 | 0.9979 | 0.729 | 0.3913 | 2.5344 | 0.729 | 0.7295 | 0.0805 | 0.0988 |
|
70 |
+
| 0.3237 | 12.0 | 3000 | 1.0553 | 0.7192 | 0.4075 | 2.6242 | 0.7192 | 0.7193 | 0.0963 | 0.1072 |
|
71 |
+
| 0.3237 | 13.0 | 3250 | 1.1162 | 0.7175 | 0.4139 | 2.6543 | 0.7175 | 0.7185 | 0.1295 | 0.1093 |
|
72 |
+
| 0.2023 | 14.0 | 3500 | 1.1259 | 0.725 | 0.4140 | 2.6758 | 0.7250 | 0.7246 | 0.1237 | 0.1055 |
|
73 |
+
| 0.2023 | 15.0 | 3750 | 1.2728 | 0.7115 | 0.4381 | 2.8308 | 0.7115 | 0.7147 | 0.1464 | 0.1168 |
|
74 |
+
| 0.1264 | 16.0 | 4000 | 1.2664 | 0.7222 | 0.4296 | 2.8434 | 0.7223 | 0.7236 | 0.1523 | 0.1107 |
|
75 |
+
| 0.1264 | 17.0 | 4250 | 1.2620 | 0.724 | 0.4252 | 2.7990 | 0.724 | 0.7252 | 0.1563 | 0.1066 |
|
76 |
+
| 0.0802 | 18.0 | 4500 | 1.3362 | 0.727 | 0.4293 | 2.8642 | 0.7270 | 0.7267 | 0.1653 | 0.1090 |
|
77 |
+
| 0.0802 | 19.0 | 4750 | 1.3608 | 0.7302 | 0.4288 | 2.7893 | 0.7302 | 0.7318 | 0.1637 | 0.1059 |
|
78 |
+
| 0.0553 | 20.0 | 5000 | 1.3757 | 0.7308 | 0.4303 | 2.8861 | 0.7308 | 0.7300 | 0.1670 | 0.1073 |
|
79 |
+
| 0.0553 | 21.0 | 5250 | 1.4947 | 0.7295 | 0.4420 | 2.8306 | 0.7295 | 0.7300 | 0.1770 | 0.1128 |
|
80 |
+
| 0.0329 | 22.0 | 5500 | 1.5338 | 0.7265 | 0.4416 | 2.8729 | 0.7265 | 0.7273 | 0.1808 | 0.1097 |
|
81 |
+
| 0.0329 | 23.0 | 5750 | 1.5127 | 0.7355 | 0.4362 | 2.8574 | 0.7355 | 0.7366 | 0.1774 | 0.1045 |
|
82 |
+
| 0.0258 | 24.0 | 6000 | 1.5189 | 0.7352 | 0.4360 | 2.8435 | 0.7353 | 0.7344 | 0.1784 | 0.1030 |
|
83 |
+
| 0.0258 | 25.0 | 6250 | 1.5802 | 0.7362 | 0.4404 | 2.8399 | 0.7362 | 0.7362 | 0.1847 | 0.1013 |
|
84 |
+
| 0.0193 | 26.0 | 6500 | 1.5869 | 0.737 | 0.4378 | 2.8237 | 0.737 | 0.7362 | 0.1846 | 0.1022 |
|
85 |
+
| 0.0193 | 27.0 | 6750 | 1.6160 | 0.7365 | 0.4373 | 2.7928 | 0.7365 | 0.7360 | 0.1864 | 0.1049 |
|
86 |
+
| 0.014 | 28.0 | 7000 | 1.6775 | 0.7372 | 0.4426 | 2.9236 | 0.7372 | 0.7373 | 0.1909 | 0.1039 |
|
87 |
+
| 0.014 | 29.0 | 7250 | 1.6391 | 0.736 | 0.4370 | 2.8717 | 0.736 | 0.7358 | 0.1905 | 0.0999 |
|
88 |
+
| 0.0132 | 30.0 | 7500 | 1.6804 | 0.7355 | 0.4434 | 2.8397 | 0.7355 | 0.7360 | 0.1903 | 0.1067 |
|
89 |
+
| 0.0132 | 31.0 | 7750 | 1.6809 | 0.738 | 0.4386 | 2.8853 | 0.738 | 0.7387 | 0.1920 | 0.1015 |
|
90 |
+
| 0.0121 | 32.0 | 8000 | 1.6953 | 0.734 | 0.4443 | 2.8451 | 0.734 | 0.7342 | 0.1961 | 0.1013 |
|
91 |
+
| 0.0121 | 33.0 | 8250 | 1.7184 | 0.7425 | 0.4344 | 2.8180 | 0.7425 | 0.7423 | 0.1910 | 0.1014 |
|
92 |
+
| 0.0098 | 34.0 | 8500 | 1.7151 | 0.735 | 0.4445 | 2.8532 | 0.735 | 0.7337 | 0.1952 | 0.1000 |
|
93 |
+
| 0.0098 | 35.0 | 8750 | 1.7781 | 0.7338 | 0.4484 | 2.8133 | 0.7338 | 0.7351 | 0.1999 | 0.1052 |
|
94 |
+
| 0.0086 | 36.0 | 9000 | 1.7540 | 0.7372 | 0.4443 | 2.8388 | 0.7372 | 0.7388 | 0.1954 | 0.1039 |
|
95 |
+
| 0.0086 | 37.0 | 9250 | 1.7744 | 0.738 | 0.4474 | 2.8600 | 0.738 | 0.7390 | 0.1953 | 0.1057 |
|
96 |
+
| 0.0079 | 38.0 | 9500 | 1.7446 | 0.7368 | 0.4417 | 2.8485 | 0.7367 | 0.7374 | 0.1972 | 0.1016 |
|
97 |
+
| 0.0079 | 39.0 | 9750 | 1.7700 | 0.739 | 0.4398 | 2.8826 | 0.739 | 0.7395 | 0.1970 | 0.1023 |
|
98 |
+
| 0.0076 | 40.0 | 10000 | 1.7896 | 0.7368 | 0.4442 | 2.8449 | 0.7367 | 0.7376 | 0.1988 | 0.1033 |
|
99 |
+
| 0.0076 | 41.0 | 10250 | 1.7435 | 0.7402 | 0.4387 | 2.8390 | 0.7402 | 0.7405 | 0.1926 | 0.1031 |
|
100 |
+
| 0.0074 | 42.0 | 10500 | 1.7837 | 0.7338 | 0.4470 | 2.8191 | 0.7338 | 0.7339 | 0.2018 | 0.1035 |
|
101 |
+
| 0.0074 | 43.0 | 10750 | 1.8015 | 0.7392 | 0.4427 | 2.8093 | 0.7392 | 0.7401 | 0.1981 | 0.1017 |
|
102 |
+
| 0.0061 | 44.0 | 11000 | 1.8155 | 0.739 | 0.4449 | 2.8333 | 0.739 | 0.7406 | 0.1983 | 0.1022 |
|
103 |
+
| 0.0061 | 45.0 | 11250 | 1.7958 | 0.7392 | 0.4426 | 2.8161 | 0.7392 | 0.7385 | 0.1963 | 0.1039 |
|
104 |
+
| 0.0059 | 46.0 | 11500 | 1.8089 | 0.7422 | 0.4411 | 2.8174 | 0.7422 | 0.7422 | 0.1955 | 0.1011 |
|
105 |
+
| 0.0059 | 47.0 | 11750 | 1.8125 | 0.743 | 0.4386 | 2.8184 | 0.743 | 0.7435 | 0.1939 | 0.1012 |
|
106 |
+
| 0.0053 | 48.0 | 12000 | 1.8004 | 0.7372 | 0.4432 | 2.8413 | 0.7372 | 0.7371 | 0.1995 | 0.1023 |
|
107 |
+
| 0.0053 | 49.0 | 12250 | 1.8075 | 0.7405 | 0.4392 | 2.8569 | 0.7405 | 0.7397 | 0.1962 | 0.1015 |
|
108 |
+
| 0.0055 | 50.0 | 12500 | 1.7844 | 0.742 | 0.4405 | 2.8680 | 0.7420 | 0.7411 | 0.1946 | 0.1002 |
|
109 |
+
|
110 |
+
|
111 |
+
### Framework versions
|
112 |
+
|
113 |
+
- Transformers 4.33.3
|
114 |
+
- Pytorch 2.2.0.dev20231002
|
115 |
+
- Datasets 2.7.1
|
116 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/resnet-50",
|
3 |
+
"architectures": [
|
4 |
+
"ResNetForImageClassification"
|
5 |
+
],
|
6 |
+
"depths": [
|
7 |
+
3,
|
8 |
+
4,
|
9 |
+
6,
|
10 |
+
3
|
11 |
+
],
|
12 |
+
"downsample_in_first_stage": false,
|
13 |
+
"embedding_size": 64,
|
14 |
+
"hidden_act": "relu",
|
15 |
+
"hidden_sizes": [
|
16 |
+
256,
|
17 |
+
512,
|
18 |
+
1024,
|
19 |
+
2048
|
20 |
+
],
|
21 |
+
"id2label": {
|
22 |
+
"0": "letter",
|
23 |
+
"1": "form",
|
24 |
+
"2": "email",
|
25 |
+
"3": "handwritten",
|
26 |
+
"4": "advertisement",
|
27 |
+
"5": "scientific_report",
|
28 |
+
"6": "scientific_publication",
|
29 |
+
"7": "specification",
|
30 |
+
"8": "file_folder",
|
31 |
+
"9": "news_article",
|
32 |
+
"10": "budget",
|
33 |
+
"11": "invoice",
|
34 |
+
"12": "presentation",
|
35 |
+
"13": "questionnaire",
|
36 |
+
"14": "resume",
|
37 |
+
"15": "memo"
|
38 |
+
},
|
39 |
+
"label2id": {
|
40 |
+
"advertisement": 4,
|
41 |
+
"budget": 10,
|
42 |
+
"email": 2,
|
43 |
+
"file_folder": 8,
|
44 |
+
"form": 1,
|
45 |
+
"handwritten": 3,
|
46 |
+
"invoice": 11,
|
47 |
+
"letter": 0,
|
48 |
+
"memo": 15,
|
49 |
+
"news_article": 9,
|
50 |
+
"presentation": 12,
|
51 |
+
"questionnaire": 13,
|
52 |
+
"resume": 14,
|
53 |
+
"scientific_publication": 6,
|
54 |
+
"scientific_report": 5,
|
55 |
+
"specification": 7
|
56 |
+
},
|
57 |
+
"layer_type": "bottleneck",
|
58 |
+
"model_type": "resnet",
|
59 |
+
"num_channels": 3,
|
60 |
+
"out_features": [
|
61 |
+
"stage4"
|
62 |
+
],
|
63 |
+
"out_indices": [
|
64 |
+
4
|
65 |
+
],
|
66 |
+
"problem_type": "single_label_classification",
|
67 |
+
"stage_names": [
|
68 |
+
"stem",
|
69 |
+
"stage1",
|
70 |
+
"stage2",
|
71 |
+
"stage3",
|
72 |
+
"stage4"
|
73 |
+
],
|
74 |
+
"torch_dtype": "float32",
|
75 |
+
"transformers_version": "4.33.3"
|
76 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:858173da12758d9fddfd82ff8dcda7c1a6d1692401c1775d6906e31735108cef
|
3 |
+
size 94490186
|
test-logits.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5105db6c67e70ae2f353616a7f94e96249204c670f37dbaa90024b76cd54105
|
3 |
+
size 2349389
|
test-references.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e7ff7e9109ab12165bc737f7df3f352e97c091a42dbf5ba5121e717df12a42a
|
3 |
+
size 34462
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc1dcbfe76216d892493e4ddcc74da11ae8fce3d51f14d4c6f4d26351cb219ce
|
3 |
+
size 4792
|
validation-logits.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7ac61a4aa3e32748d2d9c89d8c46d738da73a2f7b2c7070a6fa6949ce5fb66f
|
3 |
+
size 234448
|
validation-references.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9d6bda37454a6b9af2a9246dad3ac3aed3f946e7420dd22cdc88f6c0f94c4e0
|
3 |
+
size 326
|