Upload folder using huggingface_hub
Browse files- README.md +41 -0
- checkpoint-1362/config.json +60 -0
- checkpoint-1362/model.safetensors +3 -0
- checkpoint-1362/optimizer.pt +3 -0
- checkpoint-1362/rng_state.pth +3 -0
- checkpoint-1362/scheduler.pt +3 -0
- checkpoint-1362/trainer_state.json +474 -0
- checkpoint-1362/training_args.bin +3 -0
- config.json +60 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Sep09_07-07-31_r-guntramg-autotrain-advanced-0urwwzga-023be-hzenw/events.out.tfevents.1725865652.r-guntramg-autotrain-advanced-0urwwzga-023be-hzenw.146.0 +2 -2
- runs/Sep09_07-07-31_r-guntramg-autotrain-advanced-0urwwzga-023be-hzenw/events.out.tfevents.1725865926.r-guntramg-autotrain-advanced-0urwwzga-023be-hzenw.146.1 +3 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- image-classification
|
6 |
+
base_model: facebook/convnextv2-tiny-1k-224
|
7 |
+
widget:
|
8 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
9 |
+
example_title: Tiger
|
10 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
|
11 |
+
example_title: Teapot
|
12 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
|
13 |
+
example_title: Palace
|
14 |
+
---
|
15 |
+
|
16 |
+
# Model Trained Using AutoTrain
|
17 |
+
|
18 |
+
- Problem type: Image Classification
|
19 |
+
|
20 |
+
## Validation Metrics
|
21 |
+
loss: 0.16949759423732758
|
22 |
+
|
23 |
+
f1_macro: 0.921808528788731
|
24 |
+
|
25 |
+
f1_micro: 0.9431880860452289
|
26 |
+
|
27 |
+
f1_weighted: 0.9428034220405396
|
28 |
+
|
29 |
+
precision_macro: 0.9255554286892043
|
30 |
+
|
31 |
+
precision_micro: 0.9431880860452289
|
32 |
+
|
33 |
+
precision_weighted: 0.9438687873791154
|
34 |
+
|
35 |
+
recall_macro: 0.9204182136037321
|
36 |
+
|
37 |
+
recall_micro: 0.9431880860452289
|
38 |
+
|
39 |
+
recall_weighted: 0.9431880860452289
|
40 |
+
|
41 |
+
accuracy: 0.9431880860452289
|
checkpoint-1362/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/convnextv2-tiny-1k-224",
|
3 |
+
"_num_labels": 6,
|
4 |
+
"architectures": [
|
5 |
+
"ConvNextV2ForImageClassification"
|
6 |
+
],
|
7 |
+
"depths": [
|
8 |
+
3,
|
9 |
+
3,
|
10 |
+
9,
|
11 |
+
3
|
12 |
+
],
|
13 |
+
"drop_path_rate": 0.0,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_sizes": [
|
16 |
+
96,
|
17 |
+
192,
|
18 |
+
384,
|
19 |
+
768
|
20 |
+
],
|
21 |
+
"id2label": {
|
22 |
+
"0": "food",
|
23 |
+
"1": "guru",
|
24 |
+
"2": "inside",
|
25 |
+
"3": "menu",
|
26 |
+
"4": "outside",
|
27 |
+
"5": "people"
|
28 |
+
},
|
29 |
+
"image_size": 224,
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"label2id": {
|
32 |
+
"food": 0,
|
33 |
+
"guru": 1,
|
34 |
+
"inside": 2,
|
35 |
+
"menu": 3,
|
36 |
+
"outside": 4,
|
37 |
+
"people": 5
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-12,
|
40 |
+
"model_type": "convnextv2",
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_stages": 4,
|
43 |
+
"out_features": [
|
44 |
+
"stage4"
|
45 |
+
],
|
46 |
+
"out_indices": [
|
47 |
+
4
|
48 |
+
],
|
49 |
+
"patch_size": 4,
|
50 |
+
"problem_type": "single_label_classification",
|
51 |
+
"stage_names": [
|
52 |
+
"stem",
|
53 |
+
"stage1",
|
54 |
+
"stage2",
|
55 |
+
"stage3",
|
56 |
+
"stage4"
|
57 |
+
],
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.44.2"
|
60 |
+
}
|
checkpoint-1362/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b55f95c1428e59cf3640f1e3cb9d2220a75927999ff2726b711867cf0dd0840
|
3 |
+
size 111508128
|
checkpoint-1362/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b89a07adc0120cdfe1056e00f0d6728c2878cf4d0d0f13856530f90757f1958
|
3 |
+
size 223137210
|
checkpoint-1362/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b910f9f2ade40112f0012587429df6360865ee6b8ef9a0b101faac17a6498bcc
|
3 |
+
size 14244
|
checkpoint-1362/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acf7c1213ec83c65808f9dc4a225d73d14cb2ec4df8eaeab3a4c93c4bb3a3918
|
3 |
+
size 1064
|
checkpoint-1362/trainer_state.json
ADDED
@@ -0,0 +1,474 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.16949759423732758,
|
3 |
+
"best_model_checkpoint": "autotrain-sh8gw-ccble/checkpoint-1362",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1362,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05506607929515418,
|
13 |
+
"grad_norm": 14.598111152648926,
|
14 |
+
"learning_rate": 8.02919708029197e-06,
|
15 |
+
"loss": 1.8556,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.11013215859030837,
|
20 |
+
"grad_norm": 20.4303035736084,
|
21 |
+
"learning_rate": 1.715328467153285e-05,
|
22 |
+
"loss": 1.6556,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.16519823788546256,
|
27 |
+
"grad_norm": 29.148277282714844,
|
28 |
+
"learning_rate": 2.6277372262773724e-05,
|
29 |
+
"loss": 1.3584,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.22026431718061673,
|
34 |
+
"grad_norm": 16.219594955444336,
|
35 |
+
"learning_rate": 3.5401459854014604e-05,
|
36 |
+
"loss": 1.09,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2753303964757709,
|
41 |
+
"grad_norm": 31.08094596862793,
|
42 |
+
"learning_rate": 4.452554744525548e-05,
|
43 |
+
"loss": 0.8176,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3303964757709251,
|
48 |
+
"grad_norm": 58.6417236328125,
|
49 |
+
"learning_rate": 4.963265306122449e-05,
|
50 |
+
"loss": 0.6597,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.3854625550660793,
|
55 |
+
"grad_norm": 11.836067199707031,
|
56 |
+
"learning_rate": 4.8612244897959186e-05,
|
57 |
+
"loss": 0.5218,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.44052863436123346,
|
62 |
+
"grad_norm": 91.57707977294922,
|
63 |
+
"learning_rate": 4.759183673469388e-05,
|
64 |
+
"loss": 0.414,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.4955947136563877,
|
69 |
+
"grad_norm": 2.3629424571990967,
|
70 |
+
"learning_rate": 4.6571428571428575e-05,
|
71 |
+
"loss": 0.3714,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.5506607929515418,
|
76 |
+
"grad_norm": 129.56517028808594,
|
77 |
+
"learning_rate": 4.555102040816327e-05,
|
78 |
+
"loss": 0.3493,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6057268722466961,
|
83 |
+
"grad_norm": 48.04598617553711,
|
84 |
+
"learning_rate": 4.4571428571428574e-05,
|
85 |
+
"loss": 0.3769,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.6607929515418502,
|
90 |
+
"grad_norm": 47.53449249267578,
|
91 |
+
"learning_rate": 4.355102040816327e-05,
|
92 |
+
"loss": 0.477,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.7158590308370044,
|
97 |
+
"grad_norm": 17.811521530151367,
|
98 |
+
"learning_rate": 4.253061224489796e-05,
|
99 |
+
"loss": 0.4341,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.7709251101321586,
|
104 |
+
"grad_norm": 8.362146377563477,
|
105 |
+
"learning_rate": 4.151020408163265e-05,
|
106 |
+
"loss": 0.2695,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.8259911894273128,
|
111 |
+
"grad_norm": 24.986268997192383,
|
112 |
+
"learning_rate": 4.048979591836735e-05,
|
113 |
+
"loss": 0.502,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.8810572687224669,
|
118 |
+
"grad_norm": 28.8356876373291,
|
119 |
+
"learning_rate": 3.9469387755102045e-05,
|
120 |
+
"loss": 0.3231,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.9361233480176211,
|
125 |
+
"grad_norm": 37.625213623046875,
|
126 |
+
"learning_rate": 3.844897959183674e-05,
|
127 |
+
"loss": 0.2708,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.9911894273127754,
|
132 |
+
"grad_norm": 22.338773727416992,
|
133 |
+
"learning_rate": 3.742857142857143e-05,
|
134 |
+
"loss": 0.31,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.0,
|
139 |
+
"eval_accuracy": 0.919746276889134,
|
140 |
+
"eval_f1_macro": 0.8922845489450274,
|
141 |
+
"eval_f1_micro": 0.919746276889134,
|
142 |
+
"eval_f1_weighted": 0.9218831391092777,
|
143 |
+
"eval_loss": 0.23288899660110474,
|
144 |
+
"eval_precision_macro": 0.8940334696888717,
|
145 |
+
"eval_precision_micro": 0.919746276889134,
|
146 |
+
"eval_precision_weighted": 0.9267204134675875,
|
147 |
+
"eval_recall_macro": 0.8948346000728363,
|
148 |
+
"eval_recall_micro": 0.919746276889134,
|
149 |
+
"eval_recall_weighted": 0.919746276889134,
|
150 |
+
"eval_runtime": 21.1514,
|
151 |
+
"eval_samples_per_second": 171.431,
|
152 |
+
"eval_steps_per_second": 10.732,
|
153 |
+
"step": 454
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 1.0462555066079295,
|
157 |
+
"grad_norm": 7.589050769805908,
|
158 |
+
"learning_rate": 3.640816326530612e-05,
|
159 |
+
"loss": 0.4484,
|
160 |
+
"step": 475
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 1.1013215859030836,
|
164 |
+
"grad_norm": 3.8066580295562744,
|
165 |
+
"learning_rate": 3.538775510204082e-05,
|
166 |
+
"loss": 0.332,
|
167 |
+
"step": 500
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 1.1563876651982379,
|
171 |
+
"grad_norm": 1.0897353887557983,
|
172 |
+
"learning_rate": 3.436734693877551e-05,
|
173 |
+
"loss": 0.2705,
|
174 |
+
"step": 525
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.2114537444933922,
|
178 |
+
"grad_norm": 43.75095748901367,
|
179 |
+
"learning_rate": 3.3346938775510205e-05,
|
180 |
+
"loss": 0.2558,
|
181 |
+
"step": 550
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 1.2665198237885462,
|
185 |
+
"grad_norm": 3.1810498237609863,
|
186 |
+
"learning_rate": 3.236734693877551e-05,
|
187 |
+
"loss": 0.3549,
|
188 |
+
"step": 575
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.3215859030837005,
|
192 |
+
"grad_norm": 0.1776355355978012,
|
193 |
+
"learning_rate": 3.1346938775510204e-05,
|
194 |
+
"loss": 0.2123,
|
195 |
+
"step": 600
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.3766519823788546,
|
199 |
+
"grad_norm": 41.68134689331055,
|
200 |
+
"learning_rate": 3.0326530612244898e-05,
|
201 |
+
"loss": 0.3495,
|
202 |
+
"step": 625
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.4317180616740088,
|
206 |
+
"grad_norm": 15.639876365661621,
|
207 |
+
"learning_rate": 2.9306122448979596e-05,
|
208 |
+
"loss": 0.4163,
|
209 |
+
"step": 650
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.4867841409691631,
|
213 |
+
"grad_norm": 45.413299560546875,
|
214 |
+
"learning_rate": 2.8285714285714287e-05,
|
215 |
+
"loss": 0.3474,
|
216 |
+
"step": 675
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.5418502202643172,
|
220 |
+
"grad_norm": 18.598854064941406,
|
221 |
+
"learning_rate": 2.726530612244898e-05,
|
222 |
+
"loss": 0.38,
|
223 |
+
"step": 700
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 1.5969162995594712,
|
227 |
+
"grad_norm": 2.7749788761138916,
|
228 |
+
"learning_rate": 2.6244897959183672e-05,
|
229 |
+
"loss": 0.4032,
|
230 |
+
"step": 725
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.6519823788546255,
|
234 |
+
"grad_norm": 12.994845390319824,
|
235 |
+
"learning_rate": 2.522448979591837e-05,
|
236 |
+
"loss": 0.3246,
|
237 |
+
"step": 750
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.7070484581497798,
|
241 |
+
"grad_norm": 34.15009307861328,
|
242 |
+
"learning_rate": 2.420408163265306e-05,
|
243 |
+
"loss": 0.2937,
|
244 |
+
"step": 775
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.7621145374449338,
|
248 |
+
"grad_norm": 2.871756076812744,
|
249 |
+
"learning_rate": 2.3183673469387755e-05,
|
250 |
+
"loss": 0.2008,
|
251 |
+
"step": 800
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.8171806167400881,
|
255 |
+
"grad_norm": 1.7972595691680908,
|
256 |
+
"learning_rate": 2.216326530612245e-05,
|
257 |
+
"loss": 0.4188,
|
258 |
+
"step": 825
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.8722466960352424,
|
262 |
+
"grad_norm": 15.454833984375,
|
263 |
+
"learning_rate": 2.1142857142857144e-05,
|
264 |
+
"loss": 0.2821,
|
265 |
+
"step": 850
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.9273127753303965,
|
269 |
+
"grad_norm": 0.6686480641365051,
|
270 |
+
"learning_rate": 2.012244897959184e-05,
|
271 |
+
"loss": 0.3706,
|
272 |
+
"step": 875
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.9823788546255505,
|
276 |
+
"grad_norm": 13.417647361755371,
|
277 |
+
"learning_rate": 1.910204081632653e-05,
|
278 |
+
"loss": 0.3225,
|
279 |
+
"step": 900
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 2.0,
|
283 |
+
"eval_accuracy": 0.9236072807501379,
|
284 |
+
"eval_f1_macro": 0.8981028824019618,
|
285 |
+
"eval_f1_micro": 0.9236072807501379,
|
286 |
+
"eval_f1_weighted": 0.92638105205174,
|
287 |
+
"eval_loss": 0.1980753093957901,
|
288 |
+
"eval_precision_macro": 0.9066084517869921,
|
289 |
+
"eval_precision_micro": 0.9236072807501379,
|
290 |
+
"eval_precision_weighted": 0.9360810250439844,
|
291 |
+
"eval_recall_macro": 0.9009909368364234,
|
292 |
+
"eval_recall_micro": 0.9236072807501379,
|
293 |
+
"eval_recall_weighted": 0.9236072807501379,
|
294 |
+
"eval_runtime": 21.1211,
|
295 |
+
"eval_samples_per_second": 171.677,
|
296 |
+
"eval_steps_per_second": 10.748,
|
297 |
+
"step": 908
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 2.037444933920705,
|
301 |
+
"grad_norm": 28.311424255371094,
|
302 |
+
"learning_rate": 1.8081632653061227e-05,
|
303 |
+
"loss": 0.3026,
|
304 |
+
"step": 925
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 2.092511013215859,
|
308 |
+
"grad_norm": 38.7237548828125,
|
309 |
+
"learning_rate": 1.706122448979592e-05,
|
310 |
+
"loss": 0.2717,
|
311 |
+
"step": 950
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 2.147577092511013,
|
315 |
+
"grad_norm": 59.18606948852539,
|
316 |
+
"learning_rate": 1.6040816326530613e-05,
|
317 |
+
"loss": 0.2559,
|
318 |
+
"step": 975
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 2.202643171806167,
|
322 |
+
"grad_norm": 76.78392791748047,
|
323 |
+
"learning_rate": 1.5020408163265307e-05,
|
324 |
+
"loss": 0.3441,
|
325 |
+
"step": 1000
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 2.2577092511013217,
|
329 |
+
"grad_norm": 0.5000678896903992,
|
330 |
+
"learning_rate": 1.4000000000000001e-05,
|
331 |
+
"loss": 0.3059,
|
332 |
+
"step": 1025
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 2.3127753303964758,
|
336 |
+
"grad_norm": 46.82283401489258,
|
337 |
+
"learning_rate": 1.2979591836734694e-05,
|
338 |
+
"loss": 0.2467,
|
339 |
+
"step": 1050
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 2.36784140969163,
|
343 |
+
"grad_norm": 0.16057251393795013,
|
344 |
+
"learning_rate": 1.1959183673469389e-05,
|
345 |
+
"loss": 0.3052,
|
346 |
+
"step": 1075
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 2.4229074889867843,
|
350 |
+
"grad_norm": 3.6819064617156982,
|
351 |
+
"learning_rate": 1.0938775510204081e-05,
|
352 |
+
"loss": 0.2848,
|
353 |
+
"step": 1100
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 2.4779735682819384,
|
357 |
+
"grad_norm": 3.26033878326416,
|
358 |
+
"learning_rate": 9.918367346938776e-06,
|
359 |
+
"loss": 0.2358,
|
360 |
+
"step": 1125
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 2.5330396475770924,
|
364 |
+
"grad_norm": 3.413316488265991,
|
365 |
+
"learning_rate": 8.89795918367347e-06,
|
366 |
+
"loss": 0.287,
|
367 |
+
"step": 1150
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 2.5881057268722465,
|
371 |
+
"grad_norm": 34.6589469909668,
|
372 |
+
"learning_rate": 7.877551020408164e-06,
|
373 |
+
"loss": 0.1574,
|
374 |
+
"step": 1175
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.643171806167401,
|
378 |
+
"grad_norm": 17.196468353271484,
|
379 |
+
"learning_rate": 6.857142857142858e-06,
|
380 |
+
"loss": 0.2718,
|
381 |
+
"step": 1200
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 2.698237885462555,
|
385 |
+
"grad_norm": 5.279835224151611,
|
386 |
+
"learning_rate": 5.8367346938775515e-06,
|
387 |
+
"loss": 0.27,
|
388 |
+
"step": 1225
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 2.753303964757709,
|
392 |
+
"grad_norm": 11.918065071105957,
|
393 |
+
"learning_rate": 4.816326530612245e-06,
|
394 |
+
"loss": 0.1459,
|
395 |
+
"step": 1250
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 2.8083700440528636,
|
399 |
+
"grad_norm": 0.6315783858299255,
|
400 |
+
"learning_rate": 3.7959183673469385e-06,
|
401 |
+
"loss": 0.203,
|
402 |
+
"step": 1275
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.8634361233480177,
|
406 |
+
"grad_norm": 6.937969207763672,
|
407 |
+
"learning_rate": 2.775510204081633e-06,
|
408 |
+
"loss": 0.2701,
|
409 |
+
"step": 1300
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 2.9185022026431717,
|
413 |
+
"grad_norm": 19.936586380004883,
|
414 |
+
"learning_rate": 1.7551020408163264e-06,
|
415 |
+
"loss": 0.1779,
|
416 |
+
"step": 1325
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.9735682819383262,
|
420 |
+
"grad_norm": 14.280041694641113,
|
421 |
+
"learning_rate": 7.346938775510204e-07,
|
422 |
+
"loss": 0.3115,
|
423 |
+
"step": 1350
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 3.0,
|
427 |
+
"eval_accuracy": 0.9431880860452289,
|
428 |
+
"eval_f1_macro": 0.921808528788731,
|
429 |
+
"eval_f1_micro": 0.9431880860452289,
|
430 |
+
"eval_f1_weighted": 0.9428034220405396,
|
431 |
+
"eval_loss": 0.16949759423732758,
|
432 |
+
"eval_precision_macro": 0.9255554286892043,
|
433 |
+
"eval_precision_micro": 0.9431880860452289,
|
434 |
+
"eval_precision_weighted": 0.9438687873791154,
|
435 |
+
"eval_recall_macro": 0.9204182136037321,
|
436 |
+
"eval_recall_micro": 0.9431880860452289,
|
437 |
+
"eval_recall_weighted": 0.9431880860452289,
|
438 |
+
"eval_runtime": 21.1051,
|
439 |
+
"eval_samples_per_second": 171.807,
|
440 |
+
"eval_steps_per_second": 10.756,
|
441 |
+
"step": 1362
|
442 |
+
}
|
443 |
+
],
|
444 |
+
"logging_steps": 25,
|
445 |
+
"max_steps": 1362,
|
446 |
+
"num_input_tokens_seen": 0,
|
447 |
+
"num_train_epochs": 3,
|
448 |
+
"save_steps": 500,
|
449 |
+
"stateful_callbacks": {
|
450 |
+
"EarlyStoppingCallback": {
|
451 |
+
"args": {
|
452 |
+
"early_stopping_patience": 5,
|
453 |
+
"early_stopping_threshold": 0.01
|
454 |
+
},
|
455 |
+
"attributes": {
|
456 |
+
"early_stopping_patience_counter": 0
|
457 |
+
}
|
458 |
+
},
|
459 |
+
"TrainerControl": {
|
460 |
+
"args": {
|
461 |
+
"should_epoch_stop": false,
|
462 |
+
"should_evaluate": false,
|
463 |
+
"should_log": false,
|
464 |
+
"should_save": true,
|
465 |
+
"should_training_stop": true
|
466 |
+
},
|
467 |
+
"attributes": {}
|
468 |
+
}
|
469 |
+
},
|
470 |
+
"total_flos": 2.7382422149074944e+17,
|
471 |
+
"train_batch_size": 8,
|
472 |
+
"trial_name": null,
|
473 |
+
"trial_params": null
|
474 |
+
}
|
checkpoint-1362/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:331a759e290cfd2072297a364af4deb936dcc91d1da5da5c639855e231148fb3
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/convnextv2-tiny-1k-224",
|
3 |
+
"_num_labels": 6,
|
4 |
+
"architectures": [
|
5 |
+
"ConvNextV2ForImageClassification"
|
6 |
+
],
|
7 |
+
"depths": [
|
8 |
+
3,
|
9 |
+
3,
|
10 |
+
9,
|
11 |
+
3
|
12 |
+
],
|
13 |
+
"drop_path_rate": 0.0,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_sizes": [
|
16 |
+
96,
|
17 |
+
192,
|
18 |
+
384,
|
19 |
+
768
|
20 |
+
],
|
21 |
+
"id2label": {
|
22 |
+
"0": "food",
|
23 |
+
"1": "guru",
|
24 |
+
"2": "inside",
|
25 |
+
"3": "menu",
|
26 |
+
"4": "outside",
|
27 |
+
"5": "people"
|
28 |
+
},
|
29 |
+
"image_size": 224,
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"label2id": {
|
32 |
+
"food": 0,
|
33 |
+
"guru": 1,
|
34 |
+
"inside": 2,
|
35 |
+
"menu": 3,
|
36 |
+
"outside": 4,
|
37 |
+
"people": 5
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-12,
|
40 |
+
"model_type": "convnextv2",
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_stages": 4,
|
43 |
+
"out_features": [
|
44 |
+
"stage4"
|
45 |
+
],
|
46 |
+
"out_indices": [
|
47 |
+
4
|
48 |
+
],
|
49 |
+
"patch_size": 4,
|
50 |
+
"problem_type": "single_label_classification",
|
51 |
+
"stage_names": [
|
52 |
+
"stem",
|
53 |
+
"stage1",
|
54 |
+
"stage2",
|
55 |
+
"stage3",
|
56 |
+
"stage4"
|
57 |
+
],
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.44.2"
|
60 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b55f95c1428e59cf3640f1e3cb9d2220a75927999ff2726b711867cf0dd0840
|
3 |
+
size 111508128
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_pct": 0.875,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.485,
|
8 |
+
0.456,
|
9 |
+
0.406
|
10 |
+
],
|
11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.229,
|
14 |
+
0.224,
|
15 |
+
0.225
|
16 |
+
],
|
17 |
+
"resample": 3,
|
18 |
+
"rescale_factor": 0.00392156862745098,
|
19 |
+
"size": {
|
20 |
+
"shortest_edge": 224
|
21 |
+
}
|
22 |
+
}
|
runs/Sep09_07-07-31_r-guntramg-autotrain-advanced-0urwwzga-023be-hzenw/events.out.tfevents.1725865652.r-guntramg-autotrain-advanced-0urwwzga-023be-hzenw.146.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d69aa2317a1ee1deafd51cdfb773d8171f15bd1dd7f251479a1485cdecdc27b
|
3 |
+
size 19466
|
runs/Sep09_07-07-31_r-guntramg-autotrain-advanced-0urwwzga-023be-hzenw/events.out.tfevents.1725865926.r-guntramg-autotrain-advanced-0urwwzga-023be-hzenw.146.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:825d950fdd11f97a90bd448a811126af633b93d67313c2ba64ea7d7f455d62e5
|
3 |
+
size 921
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:331a759e290cfd2072297a364af4deb936dcc91d1da5da5c639855e231148fb3
|
3 |
+
size 5240
|
training_params.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-sh8gw-ccble/autotrain-data",
|
3 |
+
"model": "facebook/convnextv2-tiny-1k-224",
|
4 |
+
"username": "GuntramG",
|
5 |
+
"lr": 5e-05,
|
6 |
+
"epochs": 3,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"logging_steps": -1,
|
18 |
+
"project_name": "autotrain-sh8gw-ccble",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": "fp16",
|
21 |
+
"save_total_limit": 1,
|
22 |
+
"push_to_hub": true,
|
23 |
+
"eval_strategy": "epoch",
|
24 |
+
"image_column": "autotrain_image",
|
25 |
+
"target_column": "autotrain_label",
|
26 |
+
"log": "tensorboard",
|
27 |
+
"early_stopping_patience": 5,
|
28 |
+
"early_stopping_threshold": 0.01
|
29 |
+
}
|