End of training
Browse files- README.md +4 -2
- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +169 -0
README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-huge-patch14-224-in21k
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- imagefolder
|
@@ -14,7 +16,7 @@ model-index:
|
|
14 |
name: Image Classification
|
15 |
type: image-classification
|
16 |
dataset:
|
17 |
-
name:
|
18 |
type: imagefolder
|
19 |
config: default
|
20 |
split: train
|
@@ -30,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
# fashion-images-pack-types-vit-huge-patch14-224-in21k
|
32 |
|
33 |
-
This model is a fine-tuned version of [google/vit-huge-patch14-224-in21k](https://huggingface.co/google/vit-huge-patch14-224-in21k) on the
|
34 |
It achieves the following results on the evaluation set:
|
35 |
- Loss: 0.0436
|
36 |
- Accuracy: 0.9890
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-huge-patch14-224-in21k
|
4 |
tags:
|
5 |
+
- image-classification
|
6 |
+
- vision
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- imagefolder
|
|
|
16 |
name: Image Classification
|
17 |
type: image-classification
|
18 |
dataset:
|
19 |
+
name: touchtech/fashion-images-pack-types
|
20 |
type: imagefolder
|
21 |
config: default
|
22 |
split: train
|
|
|
32 |
|
33 |
# fashion-images-pack-types-vit-huge-patch14-224-in21k
|
34 |
|
35 |
+
This model is a fine-tuned version of [google/vit-huge-patch14-224-in21k](https://huggingface.co/google/vit-huge-patch14-224-in21k) on the touchtech/fashion-images-pack-types dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
- Loss: 0.0436
|
38 |
- Accuracy: 0.9890
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.989010989010989,
|
4 |
+
"eval_loss": 0.043642520904541016,
|
5 |
+
"eval_runtime": 190.3854,
|
6 |
+
"eval_samples_per_second": 12.427,
|
7 |
+
"eval_steps_per_second": 1.555,
|
8 |
+
"train_loss": 0.16767553475136404,
|
9 |
+
"train_runtime": 9223.4668,
|
10 |
+
"train_samples_per_second": 7.267,
|
11 |
+
"train_steps_per_second": 0.909
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.989010989010989,
|
4 |
+
"eval_loss": 0.043642520904541016,
|
5 |
+
"eval_runtime": 190.3854,
|
6 |
+
"eval_samples_per_second": 12.427,
|
7 |
+
"eval_steps_per_second": 1.555
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.16767553475136404,
|
4 |
+
"train_runtime": 9223.4668,
|
5 |
+
"train_samples_per_second": 7.267,
|
6 |
+
"train_steps_per_second": 0.909
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.043642520904541016,
|
3 |
+
"best_model_checkpoint": "/workspace/training_output/pack-types-vit-huge-patch14-224-in21k/checkpoint-8380",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8380,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.3,
|
13 |
+
"learning_rate": 1.8806682577565632e-05,
|
14 |
+
"loss": 0.7754,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.6,
|
19 |
+
"learning_rate": 1.7613365155131266e-05,
|
20 |
+
"loss": 0.3257,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.89,
|
25 |
+
"learning_rate": 1.6420047732696897e-05,
|
26 |
+
"loss": 0.2292,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 1.0,
|
31 |
+
"eval_accuracy": 0.9754860524091293,
|
32 |
+
"eval_loss": 0.12931108474731445,
|
33 |
+
"eval_runtime": 199.7614,
|
34 |
+
"eval_samples_per_second": 11.844,
|
35 |
+
"eval_steps_per_second": 1.482,
|
36 |
+
"step": 1676
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 1.19,
|
40 |
+
"learning_rate": 1.5226730310262532e-05,
|
41 |
+
"loss": 0.1825,
|
42 |
+
"step": 2000
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.49,
|
46 |
+
"learning_rate": 1.4033412887828164e-05,
|
47 |
+
"loss": 0.1507,
|
48 |
+
"step": 2500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.79,
|
52 |
+
"learning_rate": 1.2840095465393797e-05,
|
53 |
+
"loss": 0.1376,
|
54 |
+
"step": 3000
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 2.0,
|
58 |
+
"eval_accuracy": 0.9826711749788672,
|
59 |
+
"eval_loss": 0.07693611830472946,
|
60 |
+
"eval_runtime": 199.5492,
|
61 |
+
"eval_samples_per_second": 11.857,
|
62 |
+
"eval_steps_per_second": 1.483,
|
63 |
+
"step": 3352
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.09,
|
67 |
+
"learning_rate": 1.1646778042959427e-05,
|
68 |
+
"loss": 0.1307,
|
69 |
+
"step": 3500
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.39,
|
73 |
+
"learning_rate": 1.045346062052506e-05,
|
74 |
+
"loss": 0.1099,
|
75 |
+
"step": 4000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.68,
|
79 |
+
"learning_rate": 9.260143198090693e-06,
|
80 |
+
"loss": 0.1186,
|
81 |
+
"step": 4500
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.98,
|
85 |
+
"learning_rate": 8.066825775656326e-06,
|
86 |
+
"loss": 0.1122,
|
87 |
+
"step": 5000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 3.0,
|
91 |
+
"eval_accuracy": 0.985207100591716,
|
92 |
+
"eval_loss": 0.056492872536182404,
|
93 |
+
"eval_runtime": 201.7734,
|
94 |
+
"eval_samples_per_second": 11.726,
|
95 |
+
"eval_steps_per_second": 1.467,
|
96 |
+
"step": 5028
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 3.28,
|
100 |
+
"learning_rate": 6.873508353221957e-06,
|
101 |
+
"loss": 0.0818,
|
102 |
+
"step": 5500
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 3.58,
|
106 |
+
"learning_rate": 5.68019093078759e-06,
|
107 |
+
"loss": 0.0971,
|
108 |
+
"step": 6000
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 3.88,
|
112 |
+
"learning_rate": 4.486873508353222e-06,
|
113 |
+
"loss": 0.0759,
|
114 |
+
"step": 6500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 4.0,
|
118 |
+
"eval_accuracy": 0.9873203719357565,
|
119 |
+
"eval_loss": 0.05010140314698219,
|
120 |
+
"eval_runtime": 199.0051,
|
121 |
+
"eval_samples_per_second": 11.889,
|
122 |
+
"eval_steps_per_second": 1.487,
|
123 |
+
"step": 6704
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 4.18,
|
127 |
+
"learning_rate": 3.293556085918855e-06,
|
128 |
+
"loss": 0.0833,
|
129 |
+
"step": 7000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 4.47,
|
133 |
+
"learning_rate": 2.100238663484487e-06,
|
134 |
+
"loss": 0.073,
|
135 |
+
"step": 7500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 4.77,
|
139 |
+
"learning_rate": 9.069212410501194e-07,
|
140 |
+
"loss": 0.0678,
|
141 |
+
"step": 8000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 5.0,
|
145 |
+
"eval_accuracy": 0.989010989010989,
|
146 |
+
"eval_loss": 0.043642520904541016,
|
147 |
+
"eval_runtime": 202.3495,
|
148 |
+
"eval_samples_per_second": 11.693,
|
149 |
+
"eval_steps_per_second": 1.463,
|
150 |
+
"step": 8380
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 5.0,
|
154 |
+
"step": 8380,
|
155 |
+
"total_flos": 3.818394112407598e+19,
|
156 |
+
"train_loss": 0.16767553475136404,
|
157 |
+
"train_runtime": 9223.4668,
|
158 |
+
"train_samples_per_second": 7.267,
|
159 |
+
"train_steps_per_second": 0.909
|
160 |
+
}
|
161 |
+
],
|
162 |
+
"logging_steps": 500,
|
163 |
+
"max_steps": 8380,
|
164 |
+
"num_train_epochs": 5,
|
165 |
+
"save_steps": 500,
|
166 |
+
"total_flos": 3.818394112407598e+19,
|
167 |
+
"trial_name": null,
|
168 |
+
"trial_params": null
|
169 |
+
}
|