beingamit99
commited on
Commit
•
d8b6f45
1
Parent(s):
fa23060
Upload 8 files
Browse files- config.json +40 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +163 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "Label_1",
|
13 |
+
"1": "Label_2",
|
14 |
+
"2": "Label_3",
|
15 |
+
"3": "Label_4",
|
16 |
+
"4": "Label_5",
|
17 |
+
"5": "Label_6"
|
18 |
+
},
|
19 |
+
"image_size": 224,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"Label_1": 0,
|
24 |
+
"Label_2": 1,
|
25 |
+
"Label_3": 2,
|
26 |
+
"Label_4": 3,
|
27 |
+
"Label_5": 4,
|
28 |
+
"Label_6": 5
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-12,
|
31 |
+
"model_type": "vit",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_channels": 3,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"patch_size": 16,
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"qkv_bias": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.35.2"
|
40 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64333ad705b252db284237627eeab9561aaec17ef8329567d1238c8055a44518
|
3 |
+
size 343236280
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fb5ea0417f9e43001469a6c0876fec2c0c78ee15b5dd6dc83f943cb70f2fd80
|
3 |
+
size 686593466
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27b3f5da84362263ada750e9677e6134c3138b0a57517e2c0599b62de2913cf9
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34b719ba35aac37c0ef62bdc25992a7556e7066c7a53391b7acfaac4ca0f8385
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.06947986781597137,
|
3 |
+
"best_model_checkpoint": "Insurance_image_detection/checkpoint-4620",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4620,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.908475494178175,
|
14 |
+
"eval_loss": 0.49756574630737305,
|
15 |
+
"eval_runtime": 105.1312,
|
16 |
+
"eval_samples_per_second": 35.128,
|
17 |
+
"eval_steps_per_second": 4.395,
|
18 |
+
"step": 462
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.08,
|
22 |
+
"learning_rate": 9.01531728665208e-06,
|
23 |
+
"loss": 0.9489,
|
24 |
+
"step": 500
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"eval_accuracy": 0.9520714865962632,
|
29 |
+
"eval_loss": 0.26380735635757446,
|
30 |
+
"eval_runtime": 105.9363,
|
31 |
+
"eval_samples_per_second": 34.861,
|
32 |
+
"eval_steps_per_second": 4.361,
|
33 |
+
"step": 924
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 2.16,
|
37 |
+
"learning_rate": 7.921225382932167e-06,
|
38 |
+
"loss": 0.313,
|
39 |
+
"step": 1000
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 3.0,
|
43 |
+
"eval_accuracy": 0.9653398321148118,
|
44 |
+
"eval_loss": 0.1818619966506958,
|
45 |
+
"eval_runtime": 107.4735,
|
46 |
+
"eval_samples_per_second": 34.362,
|
47 |
+
"eval_steps_per_second": 4.299,
|
48 |
+
"step": 1386
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.25,
|
52 |
+
"learning_rate": 6.827133479212255e-06,
|
53 |
+
"loss": 0.1717,
|
54 |
+
"step": 1500
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 4.0,
|
58 |
+
"eval_accuracy": 0.9718386135932846,
|
59 |
+
"eval_loss": 0.14493609964847565,
|
60 |
+
"eval_runtime": 104.8947,
|
61 |
+
"eval_samples_per_second": 35.207,
|
62 |
+
"eval_steps_per_second": 4.404,
|
63 |
+
"step": 1848
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 4.33,
|
67 |
+
"learning_rate": 5.733041575492342e-06,
|
68 |
+
"loss": 0.1147,
|
69 |
+
"step": 2000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 5.0,
|
73 |
+
"eval_accuracy": 0.975088004332521,
|
74 |
+
"eval_loss": 0.12107384949922562,
|
75 |
+
"eval_runtime": 105.3855,
|
76 |
+
"eval_samples_per_second": 35.043,
|
77 |
+
"eval_steps_per_second": 4.384,
|
78 |
+
"step": 2310
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 5.41,
|
82 |
+
"learning_rate": 4.638949671772429e-06,
|
83 |
+
"loss": 0.0761,
|
84 |
+
"step": 2500
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"eval_accuracy": 0.9777958299485513,
|
89 |
+
"eval_loss": 0.10232008993625641,
|
90 |
+
"eval_runtime": 106.0442,
|
91 |
+
"eval_samples_per_second": 34.825,
|
92 |
+
"eval_steps_per_second": 4.357,
|
93 |
+
"step": 2772
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 6.49,
|
97 |
+
"learning_rate": 3.5448577680525163e-06,
|
98 |
+
"loss": 0.063,
|
99 |
+
"step": 3000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 7.0,
|
103 |
+
"eval_accuracy": 0.983211481180612,
|
104 |
+
"eval_loss": 0.08677352964878082,
|
105 |
+
"eval_runtime": 105.532,
|
106 |
+
"eval_samples_per_second": 34.994,
|
107 |
+
"eval_steps_per_second": 4.378,
|
108 |
+
"step": 3234
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 7.58,
|
112 |
+
"learning_rate": 2.450765864332604e-06,
|
113 |
+
"loss": 0.0468,
|
114 |
+
"step": 3500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 8.0,
|
118 |
+
"eval_accuracy": 0.9853777416734363,
|
119 |
+
"eval_loss": 0.08024903386831284,
|
120 |
+
"eval_runtime": 108.9827,
|
121 |
+
"eval_samples_per_second": 33.886,
|
122 |
+
"eval_steps_per_second": 4.239,
|
123 |
+
"step": 3696
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 8.66,
|
127 |
+
"learning_rate": 1.3566739606126916e-06,
|
128 |
+
"loss": 0.0397,
|
129 |
+
"step": 4000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 9.0,
|
133 |
+
"eval_accuracy": 0.9856485242350392,
|
134 |
+
"eval_loss": 0.07339881360530853,
|
135 |
+
"eval_runtime": 106.3452,
|
136 |
+
"eval_samples_per_second": 34.727,
|
137 |
+
"eval_steps_per_second": 4.344,
|
138 |
+
"step": 4158
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 9.74,
|
142 |
+
"learning_rate": 2.62582056892779e-07,
|
143 |
+
"loss": 0.0346,
|
144 |
+
"step": 4500
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 10.0,
|
148 |
+
"eval_accuracy": 0.9867316544814514,
|
149 |
+
"eval_loss": 0.06947986781597137,
|
150 |
+
"eval_runtime": 107.5358,
|
151 |
+
"eval_samples_per_second": 34.342,
|
152 |
+
"eval_steps_per_second": 4.296,
|
153 |
+
"step": 4620
|
154 |
+
}
|
155 |
+
],
|
156 |
+
"logging_steps": 500,
|
157 |
+
"max_steps": 4620,
|
158 |
+
"num_train_epochs": 10,
|
159 |
+
"save_steps": 500,
|
160 |
+
"total_flos": 1.144752709341266e+19,
|
161 |
+
"trial_name": null,
|
162 |
+
"trial_params": null
|
163 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:734e5209a48a43b24ee02b950c90e63f9535ed00aa0b9cc5a2f7094feba15585
|
3 |
+
size 4536
|