Hugging Face's logo

mountaincreek12
/
swin-tiny-patch4-window7-224-finetuned-sealv1

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mountaincreek12 commited on
Commit
5dce8b7
•
1 Parent(s): 01debff

Training in progress, epoch 0

Browse files
Files changed (7) hide show
  1. all_results.json +8 -0
  2. model.safetensors +1 -1
  3. runs/Mar03_00-48-41_pytorch-1-10-gpu-py-ml-g4dn-xlarge-bd81d1f288c5d63d0571c57fb0b0/events.out.tfevents.1709441808.pytorch-1-10-gpu-py-ml-g4dn-xlarge-bd81d1f288c5d63d0571c57fb0b0.2065.2 +3 -0
  4. runs/Mar03_16-51-33_pytorch-1-10-gpu-py-ml-g4dn-xlarge-bd81d1f288c5d63d0571c57fb0b0/events.out.tfevents.1709484721.pytorch-1-10-gpu-py-ml-g4dn-xlarge-bd81d1f288c5d63d0571c57fb0b0.2936.0 +3 -0
  5. train_results.json +8 -0
  6. trainer_state.json +218 -0
  7. training_args.bin +2 -2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.49,
3
+ "total_flos": 4.447730655960883e+17,
4
+ "train_loss": 0.31461275049618315,
5
+ "train_runtime": 310.8231,
6
+ "train_samples_per_second": 60.645,
7
+ "train_steps_per_second": 0.45
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f25918ae082e92bcaacdf53b7b93e9182aa1583a10243573d8b9df369f933db
3
  size 110348984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ead9576f47b40a3f2ce065ae77d6e1638a034f05b3718294ef4c2cb78b17a6
3
  size 110348984
runs/Mar03_00-48-41_pytorch-1-10-gpu-py-ml-g4dn-xlarge-bd81d1f288c5d63d0571c57fb0b0/events.out.tfevents.1709441808.pytorch-1-10-gpu-py-ml-g4dn-xlarge-bd81d1f288c5d63d0571c57fb0b0.2065.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5fd2e08c6019422bbffb068aebc69fe471d9ca98fac501f859d917b9b4c935
3
+ size 1703
runs/Mar03_16-51-33_pytorch-1-10-gpu-py-ml-g4dn-xlarge-bd81d1f288c5d63d0571c57fb0b0/events.out.tfevents.1709484721.pytorch-1-10-gpu-py-ml-g4dn-xlarge-bd81d1f288c5d63d0571c57fb0b0.2936.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ed06b95ac1e5024964f75027c2139328c1f35e1cb03a71d1e12ea0c4bbab32
3
+ size 5657
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.49,
3
+ "total_flos": 4.447730655960883e+17,
4
+ "train_loss": 0.31461275049618315,
5
+ "train_runtime": 310.8231,
6
+ "train_samples_per_second": 60.645,
7
+ "train_steps_per_second": 0.45
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.921760391198044,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-sealv1/checkpoint-118",
4
+ "epoch": 9.491525423728813,
5
+ "eval_steps": 500,
6
+ "global_step": 140,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.68,
13
+ "grad_norm": 8.243694305419922,
14
+ "learning_rate": 3.571428571428572e-05,
15
+ "loss": 1.1068,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.95,
20
+ "eval_accuracy": 0.706601466992665,
21
+ "eval_loss": 0.6517727375030518,
22
+ "eval_runtime": 2.518,
23
+ "eval_samples_per_second": 162.428,
24
+ "eval_steps_per_second": 5.163,
25
+ "step": 14
26
+ },
27
+ {
28
+ "epoch": 1.36,
29
+ "grad_norm": 11.443496704101562,
30
+ "learning_rate": 4.761904761904762e-05,
31
+ "loss": 0.4912,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 1.97,
36
+ "eval_accuracy": 0.843520782396088,
37
+ "eval_loss": 0.46679040789604187,
38
+ "eval_runtime": 2.5032,
39
+ "eval_samples_per_second": 163.39,
40
+ "eval_steps_per_second": 5.193,
41
+ "step": 29
42
+ },
43
+ {
44
+ "epoch": 2.03,
45
+ "grad_norm": 9.79934024810791,
46
+ "learning_rate": 4.3650793650793655e-05,
47
+ "loss": 0.3366,
48
+ "step": 30
49
+ },
50
+ {
51
+ "epoch": 2.71,
52
+ "grad_norm": 8.352068901062012,
53
+ "learning_rate": 3.968253968253968e-05,
54
+ "loss": 0.2749,
55
+ "step": 40
56
+ },
57
+ {
58
+ "epoch": 2.98,
59
+ "eval_accuracy": 0.8704156479217604,
60
+ "eval_loss": 0.41268301010131836,
61
+ "eval_runtime": 2.4728,
62
+ "eval_samples_per_second": 165.399,
63
+ "eval_steps_per_second": 5.257,
64
+ "step": 44
65
+ },
66
+ {
67
+ "epoch": 3.39,
68
+ "grad_norm": 7.004426002502441,
69
+ "learning_rate": 3.571428571428572e-05,
70
+ "loss": 0.3189,
71
+ "step": 50
72
+ },
73
+ {
74
+ "epoch": 4.0,
75
+ "eval_accuracy": 0.8875305623471883,
76
+ "eval_loss": 0.36258456110954285,
77
+ "eval_runtime": 2.4887,
78
+ "eval_samples_per_second": 164.344,
79
+ "eval_steps_per_second": 5.224,
80
+ "step": 59
81
+ },
82
+ {
83
+ "epoch": 4.07,
84
+ "grad_norm": 4.621389865875244,
85
+ "learning_rate": 3.1746031746031745e-05,
86
+ "loss": 0.2412,
87
+ "step": 60
88
+ },
89
+ {
90
+ "epoch": 4.75,
91
+ "grad_norm": 6.152388572692871,
92
+ "learning_rate": 2.777777777777778e-05,
93
+ "loss": 0.2226,
94
+ "step": 70
95
+ },
96
+ {
97
+ "epoch": 4.95,
98
+ "eval_accuracy": 0.9046454767726161,
99
+ "eval_loss": 0.26376911997795105,
100
+ "eval_runtime": 2.4808,
101
+ "eval_samples_per_second": 164.864,
102
+ "eval_steps_per_second": 5.24,
103
+ "step": 73
104
+ },
105
+ {
106
+ "epoch": 5.42,
107
+ "grad_norm": 6.929192066192627,
108
+ "learning_rate": 2.380952380952381e-05,
109
+ "loss": 0.2394,
110
+ "step": 80
111
+ },
112
+ {
113
+ "epoch": 5.97,
114
+ "eval_accuracy": 0.8801955990220048,
115
+ "eval_loss": 0.358397513628006,
116
+ "eval_runtime": 2.4802,
117
+ "eval_samples_per_second": 164.908,
118
+ "eval_steps_per_second": 5.242,
119
+ "step": 88
120
+ },
121
+ {
122
+ "epoch": 6.1,
123
+ "grad_norm": 6.410078525543213,
124
+ "learning_rate": 1.984126984126984e-05,
125
+ "loss": 0.2156,
126
+ "step": 90
127
+ },
128
+ {
129
+ "epoch": 6.78,
130
+ "grad_norm": 6.870254039764404,
131
+ "learning_rate": 1.5873015873015872e-05,
132
+ "loss": 0.2241,
133
+ "step": 100
134
+ },
135
+ {
136
+ "epoch": 6.98,
137
+ "eval_accuracy": 0.9046454767726161,
138
+ "eval_loss": 0.2820737659931183,
139
+ "eval_runtime": 2.4944,
140
+ "eval_samples_per_second": 163.967,
141
+ "eval_steps_per_second": 5.212,
142
+ "step": 103
143
+ },
144
+ {
145
+ "epoch": 7.46,
146
+ "grad_norm": 20.99500274658203,
147
+ "learning_rate": 1.1904761904761905e-05,
148
+ "loss": 0.1815,
149
+ "step": 110
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "eval_accuracy": 0.921760391198044,
154
+ "eval_loss": 0.21383894979953766,
155
+ "eval_runtime": 2.4781,
156
+ "eval_samples_per_second": 165.045,
157
+ "eval_steps_per_second": 5.246,
158
+ "step": 118
159
+ },
160
+ {
161
+ "epoch": 8.14,
162
+ "grad_norm": 10.073310852050781,
163
+ "learning_rate": 7.936507936507936e-06,
164
+ "loss": 0.1715,
165
+ "step": 120
166
+ },
167
+ {
168
+ "epoch": 8.81,
169
+ "grad_norm": 5.79032564163208,
170
+ "learning_rate": 3.968253968253968e-06,
171
+ "loss": 0.1862,
172
+ "step": 130
173
+ },
174
+ {
175
+ "epoch": 8.95,
176
+ "eval_accuracy": 0.9046454767726161,
177
+ "eval_loss": 0.27377307415008545,
178
+ "eval_runtime": 2.4752,
179
+ "eval_samples_per_second": 165.24,
180
+ "eval_steps_per_second": 5.252,
181
+ "step": 132
182
+ },
183
+ {
184
+ "epoch": 9.49,
185
+ "grad_norm": 9.280794143676758,
186
+ "learning_rate": 0.0,
187
+ "loss": 0.1942,
188
+ "step": 140
189
+ },
190
+ {
191
+ "epoch": 9.49,
192
+ "eval_accuracy": 0.9119804400977995,
193
+ "eval_loss": 0.25534436106681824,
194
+ "eval_runtime": 2.4962,
195
+ "eval_samples_per_second": 163.851,
196
+ "eval_steps_per_second": 5.208,
197
+ "step": 140
198
+ },
199
+ {
200
+ "epoch": 9.49,
201
+ "step": 140,
202
+ "total_flos": 4.447730655960883e+17,
203
+ "train_loss": 0.31461275049618315,
204
+ "train_runtime": 310.8231,
205
+ "train_samples_per_second": 60.645,
206
+ "train_steps_per_second": 0.45
207
+ }
208
+ ],
209
+ "logging_steps": 10,
210
+ "max_steps": 140,
211
+ "num_input_tokens_seen": 0,
212
+ "num_train_epochs": 10,
213
+ "save_steps": 500,
214
+ "total_flos": 4.447730655960883e+17,
215
+ "train_batch_size": 32,
216
+ "trial_name": null,
217
+ "trial_params": null
218
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a065b5a9c697301f9196b81778dc35cabfa642e1bbd867b18285b0e492652c68
3
- size 4527
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf8abcd5888b7243e90f61a501300c854cc329c324dbdfa48e3f57edf0477edf
3
+ size 4539