jonaszhu6666
commited on
Commit
•
ffb5571
1
Parent(s):
df1eca2
Upload folder using huggingface_hub
Browse files- checkpoint-1450/config.json +46 -0
- checkpoint-1450/model.safetensors +3 -0
- checkpoint-1450/optimizer.pt +3 -0
- checkpoint-1450/preprocessor_config.json +22 -0
- checkpoint-1450/rng_state.pth +3 -0
- checkpoint-1450/scheduler.pt +3 -0
- checkpoint-1450/trainer_state.json +497 -0
- checkpoint-1450/training_args.bin +3 -0
- config.json +46 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- training_args.bin +3 -0
checkpoint-1450/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Bridge",
|
13 |
+
"1": "Child",
|
14 |
+
"2": "Cobra",
|
15 |
+
"3": "Downward-Dog",
|
16 |
+
"4": "Pigeon",
|
17 |
+
"5": "Standing-Mountain",
|
18 |
+
"6": "Tree",
|
19 |
+
"7": "Triangle",
|
20 |
+
"8": "Warrior"
|
21 |
+
},
|
22 |
+
"image_size": 224,
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"Bridge": 0,
|
27 |
+
"Child": 1,
|
28 |
+
"Cobra": 2,
|
29 |
+
"Downward-Dog": 3,
|
30 |
+
"Pigeon": 4,
|
31 |
+
"Standing-Mountain": 5,
|
32 |
+
"Tree": 6,
|
33 |
+
"Triangle": 7,
|
34 |
+
"Warrior": 8
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"model_type": "vit",
|
38 |
+
"num_attention_heads": 12,
|
39 |
+
"num_channels": 3,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"patch_size": 16,
|
42 |
+
"problem_type": "single_label_classification",
|
43 |
+
"qkv_bias": true,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.42.3"
|
46 |
+
}
|
checkpoint-1450/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a156f76db08cbad8caa9be8fe1bfd43847a4cff43e9996a234c6d91440490554
|
3 |
+
size 343245508
|
checkpoint-1450/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef698fbfc5286fb13e99dc78f2093853a69b48e4d9e4a98307839a397f90f5bd
|
3 |
+
size 686611461
|
checkpoint-1450/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 |
+
}
|
checkpoint-1450/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9660f69c06b6c23443a37d8fc2332393dfe0d2ea573ee4199aba36699f2307dc
|
3 |
+
size 14575
|
checkpoint-1450/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:509713abc1e5b951bdcdfebd13cac3dd7e309ec8b9d6a97c0703b585660be1bc
|
3 |
+
size 627
|
checkpoint-1450/trainer_state.json
ADDED
@@ -0,0 +1,497 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.555110216140747,
|
3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k/checkpoint-1450",
|
4 |
+
"epoch": 50.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1450,
|
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": 0.14214463840399003,
|
14 |
+
"eval_loss": 2.1949472427368164,
|
15 |
+
"eval_runtime": 16.6682,
|
16 |
+
"eval_samples_per_second": 72.173,
|
17 |
+
"eval_steps_per_second": 2.28,
|
18 |
+
"step": 29
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.16874480465502908,
|
23 |
+
"eval_loss": 2.186838388442993,
|
24 |
+
"eval_runtime": 16.7522,
|
25 |
+
"eval_samples_per_second": 71.811,
|
26 |
+
"eval_steps_per_second": 2.268,
|
27 |
+
"step": 58
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_accuracy": 0.18952618453865336,
|
32 |
+
"eval_loss": 2.1766607761383057,
|
33 |
+
"eval_runtime": 16.8234,
|
34 |
+
"eval_samples_per_second": 71.508,
|
35 |
+
"eval_steps_per_second": 2.259,
|
36 |
+
"step": 87
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_accuracy": 0.2144638403990025,
|
41 |
+
"eval_loss": 2.165771722793579,
|
42 |
+
"eval_runtime": 16.9209,
|
43 |
+
"eval_samples_per_second": 71.096,
|
44 |
+
"eval_steps_per_second": 2.246,
|
45 |
+
"step": 116
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 5.0,
|
49 |
+
"eval_accuracy": 0.2427265170407315,
|
50 |
+
"eval_loss": 2.153604030609131,
|
51 |
+
"eval_runtime": 16.8242,
|
52 |
+
"eval_samples_per_second": 71.504,
|
53 |
+
"eval_steps_per_second": 2.259,
|
54 |
+
"step": 145
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 6.0,
|
58 |
+
"eval_accuracy": 0.2809642560266002,
|
59 |
+
"eval_loss": 2.1398112773895264,
|
60 |
+
"eval_runtime": 16.8785,
|
61 |
+
"eval_samples_per_second": 71.274,
|
62 |
+
"eval_steps_per_second": 2.251,
|
63 |
+
"step": 174
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 7.0,
|
67 |
+
"eval_accuracy": 0.31504571903574397,
|
68 |
+
"eval_loss": 2.1249942779541016,
|
69 |
+
"eval_runtime": 16.7869,
|
70 |
+
"eval_samples_per_second": 71.663,
|
71 |
+
"eval_steps_per_second": 2.264,
|
72 |
+
"step": 203
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 8.0,
|
76 |
+
"eval_accuracy": 0.3516209476309227,
|
77 |
+
"eval_loss": 2.1092069149017334,
|
78 |
+
"eval_runtime": 16.6708,
|
79 |
+
"eval_samples_per_second": 72.162,
|
80 |
+
"eval_steps_per_second": 2.279,
|
81 |
+
"step": 232
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 9.0,
|
85 |
+
"eval_accuracy": 0.3865336658354115,
|
86 |
+
"eval_loss": 2.0922772884368896,
|
87 |
+
"eval_runtime": 16.7596,
|
88 |
+
"eval_samples_per_second": 71.78,
|
89 |
+
"eval_steps_per_second": 2.267,
|
90 |
+
"step": 261
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 10.0,
|
94 |
+
"eval_accuracy": 0.4172901080631754,
|
95 |
+
"eval_loss": 2.0741829872131348,
|
96 |
+
"eval_runtime": 17.2756,
|
97 |
+
"eval_samples_per_second": 69.636,
|
98 |
+
"eval_steps_per_second": 2.2,
|
99 |
+
"step": 290
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 11.0,
|
103 |
+
"eval_accuracy": 0.45054031587697424,
|
104 |
+
"eval_loss": 2.0549581050872803,
|
105 |
+
"eval_runtime": 16.8587,
|
106 |
+
"eval_samples_per_second": 71.358,
|
107 |
+
"eval_steps_per_second": 2.254,
|
108 |
+
"step": 319
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 12.0,
|
112 |
+
"eval_accuracy": 0.4746467165419784,
|
113 |
+
"eval_loss": 2.0356059074401855,
|
114 |
+
"eval_runtime": 16.8686,
|
115 |
+
"eval_samples_per_second": 71.316,
|
116 |
+
"eval_steps_per_second": 2.253,
|
117 |
+
"step": 348
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 13.0,
|
121 |
+
"eval_accuracy": 0.5103906899418121,
|
122 |
+
"eval_loss": 2.0160348415374756,
|
123 |
+
"eval_runtime": 16.8138,
|
124 |
+
"eval_samples_per_second": 71.548,
|
125 |
+
"eval_steps_per_second": 2.26,
|
126 |
+
"step": 377
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 14.0,
|
130 |
+
"eval_accuracy": 0.5278470490440565,
|
131 |
+
"eval_loss": 1.996354341506958,
|
132 |
+
"eval_runtime": 16.8252,
|
133 |
+
"eval_samples_per_second": 71.5,
|
134 |
+
"eval_steps_per_second": 2.259,
|
135 |
+
"step": 406
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 15.0,
|
139 |
+
"eval_accuracy": 0.5411471321695761,
|
140 |
+
"eval_loss": 1.9763015508651733,
|
141 |
+
"eval_runtime": 16.7531,
|
142 |
+
"eval_samples_per_second": 71.808,
|
143 |
+
"eval_steps_per_second": 2.268,
|
144 |
+
"step": 435
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 16.0,
|
148 |
+
"eval_accuracy": 0.5627597672485453,
|
149 |
+
"eval_loss": 1.9563554525375366,
|
150 |
+
"eval_runtime": 16.7782,
|
151 |
+
"eval_samples_per_second": 71.7,
|
152 |
+
"eval_steps_per_second": 2.265,
|
153 |
+
"step": 464
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 17.0,
|
157 |
+
"eval_accuracy": 0.5935162094763092,
|
158 |
+
"eval_loss": 1.9363466501235962,
|
159 |
+
"eval_runtime": 16.8283,
|
160 |
+
"eval_samples_per_second": 71.487,
|
161 |
+
"eval_steps_per_second": 2.258,
|
162 |
+
"step": 493
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 17.24137931034483,
|
166 |
+
"grad_norm": 1.170919418334961,
|
167 |
+
"learning_rate": 1.3571428571428572e-06,
|
168 |
+
"loss": 2.0616,
|
169 |
+
"step": 500
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 18.0,
|
173 |
+
"eval_accuracy": 0.6059850374064838,
|
174 |
+
"eval_loss": 1.9157662391662598,
|
175 |
+
"eval_runtime": 16.8442,
|
176 |
+
"eval_samples_per_second": 71.419,
|
177 |
+
"eval_steps_per_second": 2.256,
|
178 |
+
"step": 522
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 19.0,
|
182 |
+
"eval_accuracy": 0.6184538653366584,
|
183 |
+
"eval_loss": 1.8954347372055054,
|
184 |
+
"eval_runtime": 16.8002,
|
185 |
+
"eval_samples_per_second": 71.606,
|
186 |
+
"eval_steps_per_second": 2.262,
|
187 |
+
"step": 551
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 20.0,
|
191 |
+
"eval_accuracy": 0.6275976724854531,
|
192 |
+
"eval_loss": 1.87549889087677,
|
193 |
+
"eval_runtime": 16.9097,
|
194 |
+
"eval_samples_per_second": 71.143,
|
195 |
+
"eval_steps_per_second": 2.247,
|
196 |
+
"step": 580
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 21.0,
|
200 |
+
"eval_accuracy": 0.6433915211970075,
|
201 |
+
"eval_loss": 1.856285572052002,
|
202 |
+
"eval_runtime": 16.8322,
|
203 |
+
"eval_samples_per_second": 71.47,
|
204 |
+
"eval_steps_per_second": 2.258,
|
205 |
+
"step": 609
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 22.0,
|
209 |
+
"eval_accuracy": 0.6525353283458022,
|
210 |
+
"eval_loss": 1.8366234302520752,
|
211 |
+
"eval_runtime": 16.8751,
|
212 |
+
"eval_samples_per_second": 71.289,
|
213 |
+
"eval_steps_per_second": 2.252,
|
214 |
+
"step": 638
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 23.0,
|
218 |
+
"eval_accuracy": 0.6600166251039069,
|
219 |
+
"eval_loss": 1.8174903392791748,
|
220 |
+
"eval_runtime": 16.8399,
|
221 |
+
"eval_samples_per_second": 71.437,
|
222 |
+
"eval_steps_per_second": 2.257,
|
223 |
+
"step": 667
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 24.0,
|
227 |
+
"eval_accuracy": 0.6699916874480466,
|
228 |
+
"eval_loss": 1.799251914024353,
|
229 |
+
"eval_runtime": 16.95,
|
230 |
+
"eval_samples_per_second": 70.973,
|
231 |
+
"eval_steps_per_second": 2.242,
|
232 |
+
"step": 696
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 25.0,
|
236 |
+
"eval_accuracy": 0.684123025768911,
|
237 |
+
"eval_loss": 1.7816163301467896,
|
238 |
+
"eval_runtime": 17.3768,
|
239 |
+
"eval_samples_per_second": 69.23,
|
240 |
+
"eval_steps_per_second": 2.187,
|
241 |
+
"step": 725
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 26.0,
|
245 |
+
"eval_accuracy": 0.6965918536990856,
|
246 |
+
"eval_loss": 1.7638013362884521,
|
247 |
+
"eval_runtime": 16.8626,
|
248 |
+
"eval_samples_per_second": 71.341,
|
249 |
+
"eval_steps_per_second": 2.254,
|
250 |
+
"step": 754
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 27.0,
|
254 |
+
"eval_accuracy": 0.6982543640897756,
|
255 |
+
"eval_loss": 1.7467155456542969,
|
256 |
+
"eval_runtime": 16.6815,
|
257 |
+
"eval_samples_per_second": 72.116,
|
258 |
+
"eval_steps_per_second": 2.278,
|
259 |
+
"step": 783
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 28.0,
|
263 |
+
"eval_accuracy": 0.7024106400665004,
|
264 |
+
"eval_loss": 1.730850100517273,
|
265 |
+
"eval_runtime": 16.731,
|
266 |
+
"eval_samples_per_second": 71.902,
|
267 |
+
"eval_steps_per_second": 2.271,
|
268 |
+
"step": 812
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 29.0,
|
272 |
+
"eval_accuracy": 0.7090606816292602,
|
273 |
+
"eval_loss": 1.714859127998352,
|
274 |
+
"eval_runtime": 16.8823,
|
275 |
+
"eval_samples_per_second": 71.258,
|
276 |
+
"eval_steps_per_second": 2.251,
|
277 |
+
"step": 841
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 30.0,
|
281 |
+
"eval_accuracy": 0.7182044887780549,
|
282 |
+
"eval_loss": 1.6998004913330078,
|
283 |
+
"eval_runtime": 16.9754,
|
284 |
+
"eval_samples_per_second": 70.867,
|
285 |
+
"eval_steps_per_second": 2.239,
|
286 |
+
"step": 870
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 31.0,
|
290 |
+
"eval_accuracy": 0.7240232751454697,
|
291 |
+
"eval_loss": 1.6857184171676636,
|
292 |
+
"eval_runtime": 16.864,
|
293 |
+
"eval_samples_per_second": 71.335,
|
294 |
+
"eval_steps_per_second": 2.253,
|
295 |
+
"step": 899
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 32.0,
|
299 |
+
"eval_accuracy": 0.7339983374896093,
|
300 |
+
"eval_loss": 1.6722785234451294,
|
301 |
+
"eval_runtime": 17.0525,
|
302 |
+
"eval_samples_per_second": 70.547,
|
303 |
+
"eval_steps_per_second": 2.228,
|
304 |
+
"step": 928
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 33.0,
|
308 |
+
"eval_accuracy": 0.7348295926849543,
|
309 |
+
"eval_loss": 1.6595127582550049,
|
310 |
+
"eval_runtime": 17.129,
|
311 |
+
"eval_samples_per_second": 70.232,
|
312 |
+
"eval_steps_per_second": 2.218,
|
313 |
+
"step": 957
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 34.0,
|
317 |
+
"eval_accuracy": 0.7389858686616791,
|
318 |
+
"eval_loss": 1.6473374366760254,
|
319 |
+
"eval_runtime": 16.9347,
|
320 |
+
"eval_samples_per_second": 71.037,
|
321 |
+
"eval_steps_per_second": 2.244,
|
322 |
+
"step": 986
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 34.48275862068966,
|
326 |
+
"grad_norm": 1.199028491973877,
|
327 |
+
"learning_rate": 6.428571428571429e-07,
|
328 |
+
"loss": 1.7089,
|
329 |
+
"step": 1000
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 35.0,
|
333 |
+
"eval_accuracy": 0.741479634247714,
|
334 |
+
"eval_loss": 1.6358741521835327,
|
335 |
+
"eval_runtime": 16.7459,
|
336 |
+
"eval_samples_per_second": 71.839,
|
337 |
+
"eval_steps_per_second": 2.269,
|
338 |
+
"step": 1015
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 36.0,
|
342 |
+
"eval_accuracy": 0.744804655029094,
|
343 |
+
"eval_loss": 1.6255922317504883,
|
344 |
+
"eval_runtime": 16.7298,
|
345 |
+
"eval_samples_per_second": 71.907,
|
346 |
+
"eval_steps_per_second": 2.271,
|
347 |
+
"step": 1044
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 37.0,
|
351 |
+
"eval_accuracy": 0.7506234413965087,
|
352 |
+
"eval_loss": 1.6154671907424927,
|
353 |
+
"eval_runtime": 16.6855,
|
354 |
+
"eval_samples_per_second": 72.098,
|
355 |
+
"eval_steps_per_second": 2.277,
|
356 |
+
"step": 1073
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 38.0,
|
360 |
+
"eval_accuracy": 0.7522859517871987,
|
361 |
+
"eval_loss": 1.6062015295028687,
|
362 |
+
"eval_runtime": 16.7723,
|
363 |
+
"eval_samples_per_second": 71.725,
|
364 |
+
"eval_steps_per_second": 2.266,
|
365 |
+
"step": 1102
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 39.0,
|
369 |
+
"eval_accuracy": 0.7531172069825436,
|
370 |
+
"eval_loss": 1.5981698036193848,
|
371 |
+
"eval_runtime": 16.7879,
|
372 |
+
"eval_samples_per_second": 71.659,
|
373 |
+
"eval_steps_per_second": 2.264,
|
374 |
+
"step": 1131
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 40.0,
|
378 |
+
"eval_accuracy": 0.7564422277639236,
|
379 |
+
"eval_loss": 1.5905556678771973,
|
380 |
+
"eval_runtime": 16.7358,
|
381 |
+
"eval_samples_per_second": 71.882,
|
382 |
+
"eval_steps_per_second": 2.271,
|
383 |
+
"step": 1160
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 41.0,
|
387 |
+
"eval_accuracy": 0.7581047381546134,
|
388 |
+
"eval_loss": 1.5838948488235474,
|
389 |
+
"eval_runtime": 16.7294,
|
390 |
+
"eval_samples_per_second": 71.909,
|
391 |
+
"eval_steps_per_second": 2.271,
|
392 |
+
"step": 1189
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 42.0,
|
396 |
+
"eval_accuracy": 0.7622610141313383,
|
397 |
+
"eval_loss": 1.5777734518051147,
|
398 |
+
"eval_runtime": 16.7829,
|
399 |
+
"eval_samples_per_second": 71.68,
|
400 |
+
"eval_steps_per_second": 2.264,
|
401 |
+
"step": 1218
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 43.0,
|
405 |
+
"eval_accuracy": 0.7605985037406484,
|
406 |
+
"eval_loss": 1.5723505020141602,
|
407 |
+
"eval_runtime": 16.8898,
|
408 |
+
"eval_samples_per_second": 71.226,
|
409 |
+
"eval_steps_per_second": 2.25,
|
410 |
+
"step": 1247
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 44.0,
|
414 |
+
"eval_accuracy": 0.7622610141313383,
|
415 |
+
"eval_loss": 1.5677645206451416,
|
416 |
+
"eval_runtime": 16.9782,
|
417 |
+
"eval_samples_per_second": 70.856,
|
418 |
+
"eval_steps_per_second": 2.238,
|
419 |
+
"step": 1276
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 45.0,
|
423 |
+
"eval_accuracy": 0.7630922693266833,
|
424 |
+
"eval_loss": 1.5637906789779663,
|
425 |
+
"eval_runtime": 16.962,
|
426 |
+
"eval_samples_per_second": 70.923,
|
427 |
+
"eval_steps_per_second": 2.24,
|
428 |
+
"step": 1305
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 46.0,
|
432 |
+
"eval_accuracy": 0.7672485453034081,
|
433 |
+
"eval_loss": 1.560693383216858,
|
434 |
+
"eval_runtime": 16.8368,
|
435 |
+
"eval_samples_per_second": 71.451,
|
436 |
+
"eval_steps_per_second": 2.257,
|
437 |
+
"step": 1334
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 47.0,
|
441 |
+
"eval_accuracy": 0.7672485453034081,
|
442 |
+
"eval_loss": 1.558199405670166,
|
443 |
+
"eval_runtime": 16.8053,
|
444 |
+
"eval_samples_per_second": 71.585,
|
445 |
+
"eval_steps_per_second": 2.261,
|
446 |
+
"step": 1363
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 48.0,
|
450 |
+
"eval_accuracy": 0.7689110556940981,
|
451 |
+
"eval_loss": 1.5564790964126587,
|
452 |
+
"eval_runtime": 16.8812,
|
453 |
+
"eval_samples_per_second": 71.263,
|
454 |
+
"eval_steps_per_second": 2.251,
|
455 |
+
"step": 1392
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 49.0,
|
459 |
+
"eval_accuracy": 0.7689110556940981,
|
460 |
+
"eval_loss": 1.5554701089859009,
|
461 |
+
"eval_runtime": 16.7556,
|
462 |
+
"eval_samples_per_second": 71.797,
|
463 |
+
"eval_steps_per_second": 2.268,
|
464 |
+
"step": 1421
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 50.0,
|
468 |
+
"eval_accuracy": 0.7689110556940981,
|
469 |
+
"eval_loss": 1.555110216140747,
|
470 |
+
"eval_runtime": 16.8736,
|
471 |
+
"eval_samples_per_second": 71.295,
|
472 |
+
"eval_steps_per_second": 2.252,
|
473 |
+
"step": 1450
|
474 |
+
}
|
475 |
+
],
|
476 |
+
"logging_steps": 500,
|
477 |
+
"max_steps": 1450,
|
478 |
+
"num_input_tokens_seen": 0,
|
479 |
+
"num_train_epochs": 50,
|
480 |
+
"save_steps": 500,
|
481 |
+
"stateful_callbacks": {
|
482 |
+
"TrainerControl": {
|
483 |
+
"args": {
|
484 |
+
"should_epoch_stop": false,
|
485 |
+
"should_evaluate": false,
|
486 |
+
"should_log": false,
|
487 |
+
"should_save": true,
|
488 |
+
"should_training_stop": true
|
489 |
+
},
|
490 |
+
"attributes": {}
|
491 |
+
}
|
492 |
+
},
|
493 |
+
"total_flos": 6.98634115081943e+18,
|
494 |
+
"train_batch_size": 64,
|
495 |
+
"trial_name": null,
|
496 |
+
"trial_params": null
|
497 |
+
}
|
checkpoint-1450/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91555a243d19d8c99f25042374350800d7a87e58e3e327fdcf67c44ce4c333fd
|
3 |
+
size 4603
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Bridge",
|
13 |
+
"1": "Child",
|
14 |
+
"2": "Cobra",
|
15 |
+
"3": "Downward-Dog",
|
16 |
+
"4": "Pigeon",
|
17 |
+
"5": "Standing-Mountain",
|
18 |
+
"6": "Tree",
|
19 |
+
"7": "Triangle",
|
20 |
+
"8": "Warrior"
|
21 |
+
},
|
22 |
+
"image_size": 224,
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"Bridge": 0,
|
27 |
+
"Child": 1,
|
28 |
+
"Cobra": 2,
|
29 |
+
"Downward-Dog": 3,
|
30 |
+
"Pigeon": 4,
|
31 |
+
"Standing-Mountain": 5,
|
32 |
+
"Tree": 6,
|
33 |
+
"Triangle": 7,
|
34 |
+
"Warrior": 8
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"model_type": "vit",
|
38 |
+
"num_attention_heads": 12,
|
39 |
+
"num_channels": 3,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"patch_size": 16,
|
42 |
+
"problem_type": "single_label_classification",
|
43 |
+
"qkv_bias": true,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.42.3"
|
46 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a156f76db08cbad8caa9be8fe1bfd43847a4cff43e9996a234c6d91440490554
|
3 |
+
size 343245508
|
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 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91555a243d19d8c99f25042374350800d7a87e58e3e327fdcf67c44ce4c333fd
|
3 |
+
size 4603
|