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_NKD_t1.0_g1.5
|
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_NKD_t1.0_g1.5
|
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: 2.9013
|
21 |
+
- Accuracy: 0.7933
|
22 |
+
- Brier Loss: 0.3080
|
23 |
+
- Nll: 1.8102
|
24 |
+
- F1 Micro: 0.7932
|
25 |
+
- F1 Macro: 0.7937
|
26 |
+
- Ece: 0.0719
|
27 |
+
- Aurc: 0.0635
|
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 | 6.0054 | 0.098 | 0.9327 | 9.3196 | 0.0980 | 0.0481 | 0.0462 | 0.8670 |
|
60 |
+
| 6.0141 | 2.0 | 500 | 5.4713 | 0.2195 | 0.8933 | 5.2235 | 0.2195 | 0.1452 | 0.1046 | 0.7129 |
|
61 |
+
| 6.0141 | 3.0 | 750 | 4.4006 | 0.4535 | 0.7034 | 3.0178 | 0.4535 | 0.4351 | 0.1373 | 0.3334 |
|
62 |
+
| 4.5079 | 4.0 | 1000 | 3.8431 | 0.59 | 0.5686 | 2.5843 | 0.59 | 0.5822 | 0.1309 | 0.2072 |
|
63 |
+
| 4.5079 | 5.0 | 1250 | 3.5315 | 0.6552 | 0.4864 | 2.4330 | 0.6552 | 0.6537 | 0.1048 | 0.1504 |
|
64 |
+
| 3.5028 | 6.0 | 1500 | 3.2850 | 0.707 | 0.4163 | 2.2375 | 0.707 | 0.7082 | 0.0790 | 0.1111 |
|
65 |
+
| 3.5028 | 7.0 | 1750 | 3.0974 | 0.7312 | 0.3721 | 2.0933 | 0.7312 | 0.7328 | 0.0452 | 0.0899 |
|
66 |
+
| 3.0599 | 8.0 | 2000 | 3.0385 | 0.7455 | 0.3561 | 2.0148 | 0.7455 | 0.7456 | 0.0432 | 0.0838 |
|
67 |
+
| 3.0599 | 9.0 | 2250 | 2.9978 | 0.7565 | 0.3432 | 1.9780 | 0.7565 | 0.7572 | 0.0437 | 0.0777 |
|
68 |
+
| 2.8562 | 10.0 | 2500 | 2.9853 | 0.7622 | 0.3397 | 1.9176 | 0.7622 | 0.7619 | 0.0495 | 0.0751 |
|
69 |
+
| 2.8562 | 11.0 | 2750 | 2.9803 | 0.7615 | 0.3385 | 1.9327 | 0.7615 | 0.7627 | 0.0547 | 0.0760 |
|
70 |
+
| 2.7414 | 12.0 | 3000 | 2.9711 | 0.7658 | 0.3322 | 1.9439 | 0.7658 | 0.7661 | 0.0495 | 0.0740 |
|
71 |
+
| 2.7414 | 13.0 | 3250 | 2.9618 | 0.771 | 0.3276 | 1.8599 | 0.771 | 0.7718 | 0.0548 | 0.0704 |
|
72 |
+
| 2.6658 | 14.0 | 3500 | 2.9534 | 0.7762 | 0.3252 | 1.8935 | 0.7762 | 0.7770 | 0.0581 | 0.0699 |
|
73 |
+
| 2.6658 | 15.0 | 3750 | 2.9568 | 0.776 | 0.3248 | 1.8836 | 0.776 | 0.7776 | 0.0588 | 0.0699 |
|
74 |
+
| 2.6197 | 16.0 | 4000 | 2.9196 | 0.7812 | 0.3169 | 1.8338 | 0.7812 | 0.7814 | 0.0601 | 0.0655 |
|
75 |
+
| 2.6197 | 17.0 | 4250 | 2.9267 | 0.7785 | 0.3202 | 1.8430 | 0.7785 | 0.7783 | 0.0647 | 0.0677 |
|
76 |
+
| 2.5794 | 18.0 | 4500 | 2.9189 | 0.779 | 0.3155 | 1.8279 | 0.779 | 0.7794 | 0.0631 | 0.0661 |
|
77 |
+
| 2.5794 | 19.0 | 4750 | 2.9324 | 0.7823 | 0.3177 | 1.8508 | 0.7823 | 0.7823 | 0.0665 | 0.0669 |
|
78 |
+
| 2.5553 | 20.0 | 5000 | 2.9192 | 0.7837 | 0.3146 | 1.8312 | 0.7837 | 0.7840 | 0.0641 | 0.0654 |
|
79 |
+
| 2.5553 | 21.0 | 5250 | 2.9160 | 0.7817 | 0.3140 | 1.8366 | 0.7817 | 0.7828 | 0.0682 | 0.0658 |
|
80 |
+
| 2.53 | 22.0 | 5500 | 2.9172 | 0.7837 | 0.3139 | 1.8138 | 0.7837 | 0.7842 | 0.0602 | 0.0652 |
|
81 |
+
| 2.53 | 23.0 | 5750 | 2.9132 | 0.7875 | 0.3134 | 1.8254 | 0.7875 | 0.7877 | 0.0656 | 0.0646 |
|
82 |
+
| 2.5127 | 24.0 | 6000 | 2.9108 | 0.7875 | 0.3132 | 1.8367 | 0.7875 | 0.7869 | 0.0669 | 0.0652 |
|
83 |
+
| 2.5127 | 25.0 | 6250 | 2.9272 | 0.7837 | 0.3139 | 1.8551 | 0.7837 | 0.7843 | 0.0632 | 0.0653 |
|
84 |
+
| 2.4979 | 26.0 | 6500 | 2.9157 | 0.7867 | 0.3128 | 1.8101 | 0.7868 | 0.7876 | 0.0655 | 0.0647 |
|
85 |
+
| 2.4979 | 27.0 | 6750 | 2.9031 | 0.785 | 0.3112 | 1.8089 | 0.785 | 0.7856 | 0.0688 | 0.0639 |
|
86 |
+
| 2.4814 | 28.0 | 7000 | 2.9094 | 0.7875 | 0.3110 | 1.8594 | 0.7875 | 0.7880 | 0.0677 | 0.0646 |
|
87 |
+
| 2.4814 | 29.0 | 7250 | 2.9110 | 0.7885 | 0.3116 | 1.8150 | 0.7885 | 0.7891 | 0.0696 | 0.0639 |
|
88 |
+
| 2.4741 | 30.0 | 7500 | 2.9039 | 0.7877 | 0.3091 | 1.8471 | 0.7877 | 0.7887 | 0.0694 | 0.0632 |
|
89 |
+
| 2.4741 | 31.0 | 7750 | 2.9029 | 0.7907 | 0.3087 | 1.7604 | 0.7907 | 0.7917 | 0.0691 | 0.0633 |
|
90 |
+
| 2.4626 | 32.0 | 8000 | 2.8983 | 0.7877 | 0.3094 | 1.8191 | 0.7877 | 0.7884 | 0.0677 | 0.0625 |
|
91 |
+
| 2.4626 | 33.0 | 8250 | 2.9024 | 0.7897 | 0.3088 | 1.8025 | 0.7897 | 0.7905 | 0.0720 | 0.0635 |
|
92 |
+
| 2.4558 | 34.0 | 8500 | 2.9055 | 0.792 | 0.3070 | 1.7869 | 0.792 | 0.7920 | 0.0667 | 0.0628 |
|
93 |
+
| 2.4558 | 35.0 | 8750 | 2.9055 | 0.788 | 0.3104 | 1.8349 | 0.788 | 0.7883 | 0.0733 | 0.0645 |
|
94 |
+
| 2.4481 | 36.0 | 9000 | 2.9061 | 0.7887 | 0.3078 | 1.7840 | 0.7887 | 0.7898 | 0.0676 | 0.0642 |
|
95 |
+
| 2.4481 | 37.0 | 9250 | 2.9086 | 0.7917 | 0.3102 | 1.7942 | 0.7917 | 0.7923 | 0.0716 | 0.0644 |
|
96 |
+
| 2.4422 | 38.0 | 9500 | 2.9067 | 0.7897 | 0.3084 | 1.7915 | 0.7897 | 0.7900 | 0.0704 | 0.0637 |
|
97 |
+
| 2.4422 | 39.0 | 9750 | 2.9080 | 0.7927 | 0.3092 | 1.7951 | 0.7927 | 0.7930 | 0.0709 | 0.0631 |
|
98 |
+
| 2.4386 | 40.0 | 10000 | 2.9064 | 0.7943 | 0.3084 | 1.8079 | 0.7943 | 0.7949 | 0.0734 | 0.0635 |
|
99 |
+
| 2.4386 | 41.0 | 10250 | 2.8990 | 0.792 | 0.3056 | 1.7918 | 0.792 | 0.7924 | 0.0699 | 0.0623 |
|
100 |
+
| 2.4312 | 42.0 | 10500 | 2.9057 | 0.7893 | 0.3090 | 1.7892 | 0.7893 | 0.7901 | 0.0735 | 0.0641 |
|
101 |
+
| 2.4312 | 43.0 | 10750 | 2.8998 | 0.7923 | 0.3079 | 1.7909 | 0.7923 | 0.7932 | 0.0707 | 0.0630 |
|
102 |
+
| 2.4294 | 44.0 | 11000 | 2.9108 | 0.7905 | 0.3090 | 1.8220 | 0.7905 | 0.7916 | 0.0773 | 0.0636 |
|
103 |
+
| 2.4294 | 45.0 | 11250 | 2.9030 | 0.7927 | 0.3086 | 1.8126 | 0.7927 | 0.7932 | 0.0710 | 0.0631 |
|
104 |
+
| 2.4282 | 46.0 | 11500 | 2.9033 | 0.7915 | 0.3077 | 1.8234 | 0.7915 | 0.7920 | 0.0712 | 0.0631 |
|
105 |
+
| 2.4282 | 47.0 | 11750 | 2.8975 | 0.7957 | 0.3063 | 1.8070 | 0.7957 | 0.7968 | 0.0702 | 0.0630 |
|
106 |
+
| 2.4246 | 48.0 | 12000 | 2.9049 | 0.7935 | 0.3085 | 1.8090 | 0.7935 | 0.7944 | 0.0722 | 0.0635 |
|
107 |
+
| 2.4246 | 49.0 | 12250 | 2.9020 | 0.792 | 0.3075 | 1.8233 | 0.792 | 0.7927 | 0.0700 | 0.0638 |
|
108 |
+
| 2.4227 | 50.0 | 12500 | 2.9013 | 0.7933 | 0.3080 | 1.8102 | 0.7932 | 0.7937 | 0.0719 | 0.0635 |
|
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:e4abe07566ea8f8cd4bfeeb49875f2599b008acbc678f7f87037f1378d0e26d6
|
3 |
+
size 94490186
|
test-logits.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ed33134b1c53dcc0a6a000d8eedf5f053e89b69c524069fe6cb2b189f7ab903
|
3 |
+
size 2337289
|
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 sha256:50bed8ac4234c043cd651619f6081b5f3d85bec8dc658d2cd053444f907d245e
|
3 |
+
size 4792
|
validation-logits.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e4d712481383eced1115c0610d3daa53f3aa4caa4b99943946c3026a06883b6
|
3 |
+
size 233580
|
validation-references.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9d6bda37454a6b9af2a9246dad3ac3aed3f946e7420dd22cdc88f6c0f94c4e0
|
3 |
+
size 326
|