Hugging Face's logo

kiru1998
/
classification_right_false_data

TensorBoard
Safetensors
Model card Files Metrics Community
kiru1998 commited on
Commit
26a9e4f
•
1 Parent(s): 531c459

version1

Browse files
Files changed (22) hide show
  1. data2right.ipynb +0 -0
  2. swin-tiny-patch4-window7-224-finetuned-kiru/all_results.json +12 -0
  3. swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/config.json +61 -0
  4. swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/model.safetensors +3 -0
  5. swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/optimizer.pt +3 -0
  6. swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/preprocessor_config.json +22 -0
  7. swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/rng_state.pth +3 -0
  8. swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/scheduler.pt +3 -0
  9. swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/trainer_state.json +979 -0
  10. swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/training_args.bin +3 -0
  11. swin-tiny-patch4-window7-224-finetuned-kiru/config.json +61 -0
  12. swin-tiny-patch4-window7-224-finetuned-kiru/eval_results.json +8 -0
  13. swin-tiny-patch4-window7-224-finetuned-kiru/model.safetensors +3 -0
  14. swin-tiny-patch4-window7-224-finetuned-kiru/preprocessor_config.json +22 -0
  15. swin-tiny-patch4-window7-224-finetuned-kiru/runs/Nov10_17-13-00_DESKTOP-0P1K3MU/events.out.tfevents.1699603993.DESKTOP-0P1K3MU.11396.0 +3 -0
  16. swin-tiny-patch4-window7-224-finetuned-kiru/runs/Nov10_17-36-22_DESKTOP-0P1K3MU/events.out.tfevents.1699605389.DESKTOP-0P1K3MU.18804.0 +3 -0
  17. swin-tiny-patch4-window7-224-finetuned-kiru/runs/Nov10_17-37-34_DESKTOP-0P1K3MU/events.out.tfevents.1699605454.DESKTOP-0P1K3MU.22564.0 +3 -0
  18. swin-tiny-patch4-window7-224-finetuned-kiru/runs/Nov10_17-37-34_DESKTOP-0P1K3MU/events.out.tfevents.1699606603.DESKTOP-0P1K3MU.22564.1 +3 -0
  19. swin-tiny-patch4-window7-224-finetuned-kiru/runs/Nov10_18-01-44_DESKTOP-0P1K3MU/events.out.tfevents.1699606911.DESKTOP-0P1K3MU.22564.2 +3 -0
  20. swin-tiny-patch4-window7-224-finetuned-kiru/train_results.json +7 -0
  21. swin-tiny-patch4-window7-224-finetuned-kiru/trainer_state.json +988 -0
  22. swin-tiny-patch4-window7-224-finetuned-kiru/training_args.bin +3 -0
data2right.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
swin-tiny-patch4-window7-224-finetuned-kiru/all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_accuracy": 0.9333333333333333,
4
+ "eval_loss": 0.252092570066452,
5
+ "eval_runtime": 3.0916,
6
+ "eval_samples_per_second": 53.37,
7
+ "eval_steps_per_second": 1.941,
8
+ "train_loss": 0.11401470561822255,
9
+ "train_runtime": 1213.3224,
10
+ "train_samples_per_second": 31.484,
11
+ "train_steps_per_second": 0.247
12
+ }
swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
3
+ "architectures": [
4
+ "SwinForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "depths": [
8
+ 2,
9
+ 2,
10
+ 6,
11
+ 2
12
+ ],
13
+ "drop_path_rate": 0.1,
14
+ "embed_dim": 96,
15
+ "encoder_stride": 32,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.0,
18
+ "hidden_size": 768,
19
+ "id2label": {
20
+ "0": "true",
21
+ "1": "false"
22
+ },
23
+ "image_size": 224,
24
+ "initializer_range": 0.02,
25
+ "label2id": {
26
+ "false": 1,
27
+ "true": 0
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "mlp_ratio": 4.0,
31
+ "model_type": "swin",
32
+ "num_channels": 3,
33
+ "num_heads": [
34
+ 3,
35
+ 6,
36
+ 12,
37
+ 24
38
+ ],
39
+ "num_layers": 4,
40
+ "out_features": [
41
+ "stage4"
42
+ ],
43
+ "out_indices": [
44
+ 4
45
+ ],
46
+ "patch_size": 4,
47
+ "path_norm": true,
48
+ "problem_type": "single_label_classification",
49
+ "qkv_bias": true,
50
+ "stage_names": [
51
+ "stem",
52
+ "stage1",
53
+ "stage2",
54
+ "stage3",
55
+ "stage4"
56
+ ],
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.35.0",
59
+ "use_absolute_embeddings": false,
60
+ "window_size": 7
61
+ }
swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af174a905e9bcc74c02f5b90704257a4051c1ec2bd4b09562ecc4dd5795e34d
3
+ size 110342832
swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3eb437ba5f328818c229d347dd52adb6be350c1b83d515fe05f9c1eb4bd62c
3
+ size 220350149
swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.485,
7
+ 0.456,
8
+ 0.406
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.229,
13
+ 0.224,
14
+ 0.225
15
+ ],
16
+ "resample": 3,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0febe9bcdac8c774ff5ec8acec7818f18349b71f0ce36cd20afa2456528e78
3
+ size 14575
swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b279ae653e8586f53131748fd3b342caabfcbf09c7c49daafd3ae2bb0679b7
3
+ size 627
swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,979 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9393939393939394,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-kiru\\checkpoint-63",
4
+ "epoch": 100.0,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
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": 0.2,
14
+ "eval_loss": 0.9137158989906311,
15
+ "eval_runtime": 2.4017,
16
+ "eval_samples_per_second": 68.703,
17
+ "eval_steps_per_second": 2.498,
18
+ "step": 3
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.41818181818181815,
23
+ "eval_loss": 0.7433991432189941,
24
+ "eval_runtime": 2.3854,
25
+ "eval_samples_per_second": 69.171,
26
+ "eval_steps_per_second": 2.515,
27
+ "step": 6
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.7757575757575758,
32
+ "eval_loss": 0.558496356010437,
33
+ "eval_runtime": 2.91,
34
+ "eval_samples_per_second": 56.702,
35
+ "eval_steps_per_second": 2.062,
36
+ "step": 9
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.7757575757575758,
41
+ "eval_loss": 0.4807980954647064,
42
+ "eval_runtime": 2.7225,
43
+ "eval_samples_per_second": 60.606,
44
+ "eval_steps_per_second": 2.204,
45
+ "step": 12
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_accuracy": 0.7757575757575758,
50
+ "eval_loss": 0.44610753655433655,
51
+ "eval_runtime": 2.8794,
52
+ "eval_samples_per_second": 57.303,
53
+ "eval_steps_per_second": 2.084,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 6.0,
58
+ "eval_accuracy": 0.8,
59
+ "eval_loss": 0.41230690479278564,
60
+ "eval_runtime": 2.7147,
61
+ "eval_samples_per_second": 60.781,
62
+ "eval_steps_per_second": 2.21,
63
+ "step": 18
64
+ },
65
+ {
66
+ "epoch": 7.0,
67
+ "eval_accuracy": 0.8545454545454545,
68
+ "eval_loss": 0.4499864876270294,
69
+ "eval_runtime": 2.9708,
70
+ "eval_samples_per_second": 55.54,
71
+ "eval_steps_per_second": 2.02,
72
+ "step": 21
73
+ },
74
+ {
75
+ "epoch": 8.0,
76
+ "eval_accuracy": 0.7636363636363637,
77
+ "eval_loss": 0.4703312814235687,
78
+ "eval_runtime": 2.7665,
79
+ "eval_samples_per_second": 59.642,
80
+ "eval_steps_per_second": 2.169,
81
+ "step": 24
82
+ },
83
+ {
84
+ "epoch": 9.0,
85
+ "eval_accuracy": 0.8,
86
+ "eval_loss": 0.41265082359313965,
87
+ "eval_runtime": 2.7687,
88
+ "eval_samples_per_second": 59.595,
89
+ "eval_steps_per_second": 2.167,
90
+ "step": 27
91
+ },
92
+ {
93
+ "epoch": 10.0,
94
+ "learning_rate": 5e-05,
95
+ "loss": 0.5353,
96
+ "step": 30
97
+ },
98
+ {
99
+ "epoch": 10.0,
100
+ "eval_accuracy": 0.8787878787878788,
101
+ "eval_loss": 0.3097422420978546,
102
+ "eval_runtime": 2.932,
103
+ "eval_samples_per_second": 56.276,
104
+ "eval_steps_per_second": 2.046,
105
+ "step": 30
106
+ },
107
+ {
108
+ "epoch": 11.0,
109
+ "eval_accuracy": 0.7696969696969697,
110
+ "eval_loss": 0.45016413927078247,
111
+ "eval_runtime": 2.8763,
112
+ "eval_samples_per_second": 57.366,
113
+ "eval_steps_per_second": 2.086,
114
+ "step": 33
115
+ },
116
+ {
117
+ "epoch": 12.0,
118
+ "eval_accuracy": 0.8121212121212121,
119
+ "eval_loss": 0.3948935270309448,
120
+ "eval_runtime": 2.4262,
121
+ "eval_samples_per_second": 68.008,
122
+ "eval_steps_per_second": 2.473,
123
+ "step": 36
124
+ },
125
+ {
126
+ "epoch": 13.0,
127
+ "eval_accuracy": 0.8727272727272727,
128
+ "eval_loss": 0.2976933419704437,
129
+ "eval_runtime": 2.9565,
130
+ "eval_samples_per_second": 55.809,
131
+ "eval_steps_per_second": 2.029,
132
+ "step": 39
133
+ },
134
+ {
135
+ "epoch": 14.0,
136
+ "eval_accuracy": 0.8121212121212121,
137
+ "eval_loss": 0.37680599093437195,
138
+ "eval_runtime": 2.6485,
139
+ "eval_samples_per_second": 62.3,
140
+ "eval_steps_per_second": 2.265,
141
+ "step": 42
142
+ },
143
+ {
144
+ "epoch": 15.0,
145
+ "eval_accuracy": 0.8424242424242424,
146
+ "eval_loss": 0.36290910840034485,
147
+ "eval_runtime": 3.3518,
148
+ "eval_samples_per_second": 49.227,
149
+ "eval_steps_per_second": 1.79,
150
+ "step": 45
151
+ },
152
+ {
153
+ "epoch": 16.0,
154
+ "eval_accuracy": 0.8545454545454545,
155
+ "eval_loss": 0.31888607144355774,
156
+ "eval_runtime": 3.4102,
157
+ "eval_samples_per_second": 48.385,
158
+ "eval_steps_per_second": 1.759,
159
+ "step": 48
160
+ },
161
+ {
162
+ "epoch": 17.0,
163
+ "eval_accuracy": 0.8484848484848485,
164
+ "eval_loss": 0.27646660804748535,
165
+ "eval_runtime": 3.2469,
166
+ "eval_samples_per_second": 50.818,
167
+ "eval_steps_per_second": 1.848,
168
+ "step": 51
169
+ },
170
+ {
171
+ "epoch": 18.0,
172
+ "eval_accuracy": 0.9030303030303031,
173
+ "eval_loss": 0.22981072962284088,
174
+ "eval_runtime": 3.3886,
175
+ "eval_samples_per_second": 48.692,
176
+ "eval_steps_per_second": 1.771,
177
+ "step": 54
178
+ },
179
+ {
180
+ "epoch": 19.0,
181
+ "eval_accuracy": 0.8242424242424242,
182
+ "eval_loss": 0.4056190848350525,
183
+ "eval_runtime": 3.359,
184
+ "eval_samples_per_second": 49.122,
185
+ "eval_steps_per_second": 1.786,
186
+ "step": 57
187
+ },
188
+ {
189
+ "epoch": 20.0,
190
+ "learning_rate": 4.4444444444444447e-05,
191
+ "loss": 0.2047,
192
+ "step": 60
193
+ },
194
+ {
195
+ "epoch": 20.0,
196
+ "eval_accuracy": 0.8848484848484849,
197
+ "eval_loss": 0.2524569034576416,
198
+ "eval_runtime": 3.3911,
199
+ "eval_samples_per_second": 48.657,
200
+ "eval_steps_per_second": 1.769,
201
+ "step": 60
202
+ },
203
+ {
204
+ "epoch": 21.0,
205
+ "eval_accuracy": 0.9393939393939394,
206
+ "eval_loss": 0.179116889834404,
207
+ "eval_runtime": 3.4087,
208
+ "eval_samples_per_second": 48.406,
209
+ "eval_steps_per_second": 1.76,
210
+ "step": 63
211
+ },
212
+ {
213
+ "epoch": 22.0,
214
+ "eval_accuracy": 0.8606060606060606,
215
+ "eval_loss": 0.34358078241348267,
216
+ "eval_runtime": 3.4132,
217
+ "eval_samples_per_second": 48.342,
218
+ "eval_steps_per_second": 1.758,
219
+ "step": 66
220
+ },
221
+ {
222
+ "epoch": 23.0,
223
+ "eval_accuracy": 0.8545454545454545,
224
+ "eval_loss": 0.37361884117126465,
225
+ "eval_runtime": 2.5007,
226
+ "eval_samples_per_second": 65.981,
227
+ "eval_steps_per_second": 2.399,
228
+ "step": 69
229
+ },
230
+ {
231
+ "epoch": 24.0,
232
+ "eval_accuracy": 0.9272727272727272,
233
+ "eval_loss": 0.20224401354789734,
234
+ "eval_runtime": 3.4453,
235
+ "eval_samples_per_second": 47.891,
236
+ "eval_steps_per_second": 1.741,
237
+ "step": 72
238
+ },
239
+ {
240
+ "epoch": 25.0,
241
+ "eval_accuracy": 0.896969696969697,
242
+ "eval_loss": 0.2309740036725998,
243
+ "eval_runtime": 3.4325,
244
+ "eval_samples_per_second": 48.07,
245
+ "eval_steps_per_second": 1.748,
246
+ "step": 75
247
+ },
248
+ {
249
+ "epoch": 26.0,
250
+ "eval_accuracy": 0.8484848484848485,
251
+ "eval_loss": 0.4356694221496582,
252
+ "eval_runtime": 3.4524,
253
+ "eval_samples_per_second": 47.792,
254
+ "eval_steps_per_second": 1.738,
255
+ "step": 78
256
+ },
257
+ {
258
+ "epoch": 27.0,
259
+ "eval_accuracy": 0.8909090909090909,
260
+ "eval_loss": 0.23648156225681305,
261
+ "eval_runtime": 3.3817,
262
+ "eval_samples_per_second": 48.792,
263
+ "eval_steps_per_second": 1.774,
264
+ "step": 81
265
+ },
266
+ {
267
+ "epoch": 28.0,
268
+ "eval_accuracy": 0.896969696969697,
269
+ "eval_loss": 0.2242034673690796,
270
+ "eval_runtime": 3.5408,
271
+ "eval_samples_per_second": 46.6,
272
+ "eval_steps_per_second": 1.695,
273
+ "step": 84
274
+ },
275
+ {
276
+ "epoch": 29.0,
277
+ "eval_accuracy": 0.8787878787878788,
278
+ "eval_loss": 0.3519549071788788,
279
+ "eval_runtime": 3.5339,
280
+ "eval_samples_per_second": 46.69,
281
+ "eval_steps_per_second": 1.698,
282
+ "step": 87
283
+ },
284
+ {
285
+ "epoch": 30.0,
286
+ "learning_rate": 3.888888888888889e-05,
287
+ "loss": 0.1214,
288
+ "step": 90
289
+ },
290
+ {
291
+ "epoch": 30.0,
292
+ "eval_accuracy": 0.8666666666666667,
293
+ "eval_loss": 0.3405221700668335,
294
+ "eval_runtime": 3.3876,
295
+ "eval_samples_per_second": 48.707,
296
+ "eval_steps_per_second": 1.771,
297
+ "step": 90
298
+ },
299
+ {
300
+ "epoch": 31.0,
301
+ "eval_accuracy": 0.8848484848484849,
302
+ "eval_loss": 0.26643767952919006,
303
+ "eval_runtime": 3.5147,
304
+ "eval_samples_per_second": 46.946,
305
+ "eval_steps_per_second": 1.707,
306
+ "step": 93
307
+ },
308
+ {
309
+ "epoch": 32.0,
310
+ "eval_accuracy": 0.896969696969697,
311
+ "eval_loss": 0.30635523796081543,
312
+ "eval_runtime": 3.4904,
313
+ "eval_samples_per_second": 47.273,
314
+ "eval_steps_per_second": 1.719,
315
+ "step": 96
316
+ },
317
+ {
318
+ "epoch": 33.0,
319
+ "eval_accuracy": 0.8909090909090909,
320
+ "eval_loss": 0.28046053647994995,
321
+ "eval_runtime": 3.4457,
322
+ "eval_samples_per_second": 47.886,
323
+ "eval_steps_per_second": 1.741,
324
+ "step": 99
325
+ },
326
+ {
327
+ "epoch": 34.0,
328
+ "eval_accuracy": 0.9090909090909091,
329
+ "eval_loss": 0.2581537067890167,
330
+ "eval_runtime": 3.3583,
331
+ "eval_samples_per_second": 49.131,
332
+ "eval_steps_per_second": 1.787,
333
+ "step": 102
334
+ },
335
+ {
336
+ "epoch": 35.0,
337
+ "eval_accuracy": 0.896969696969697,
338
+ "eval_loss": 0.3365895748138428,
339
+ "eval_runtime": 3.5154,
340
+ "eval_samples_per_second": 46.936,
341
+ "eval_steps_per_second": 1.707,
342
+ "step": 105
343
+ },
344
+ {
345
+ "epoch": 36.0,
346
+ "eval_accuracy": 0.8242424242424242,
347
+ "eval_loss": 0.4986293315887451,
348
+ "eval_runtime": 3.4596,
349
+ "eval_samples_per_second": 47.693,
350
+ "eval_steps_per_second": 1.734,
351
+ "step": 108
352
+ },
353
+ {
354
+ "epoch": 37.0,
355
+ "eval_accuracy": 0.896969696969697,
356
+ "eval_loss": 0.33538326621055603,
357
+ "eval_runtime": 3.4043,
358
+ "eval_samples_per_second": 48.468,
359
+ "eval_steps_per_second": 1.762,
360
+ "step": 111
361
+ },
362
+ {
363
+ "epoch": 38.0,
364
+ "eval_accuracy": 0.9151515151515152,
365
+ "eval_loss": 0.28124478459358215,
366
+ "eval_runtime": 3.3948,
367
+ "eval_samples_per_second": 48.604,
368
+ "eval_steps_per_second": 1.767,
369
+ "step": 114
370
+ },
371
+ {
372
+ "epoch": 39.0,
373
+ "eval_accuracy": 0.9151515151515152,
374
+ "eval_loss": 0.28065553307533264,
375
+ "eval_runtime": 2.327,
376
+ "eval_samples_per_second": 70.907,
377
+ "eval_steps_per_second": 2.578,
378
+ "step": 117
379
+ },
380
+ {
381
+ "epoch": 40.0,
382
+ "learning_rate": 3.3333333333333335e-05,
383
+ "loss": 0.0667,
384
+ "step": 120
385
+ },
386
+ {
387
+ "epoch": 40.0,
388
+ "eval_accuracy": 0.8787878787878788,
389
+ "eval_loss": 0.33923324942588806,
390
+ "eval_runtime": 2.2919,
391
+ "eval_samples_per_second": 71.992,
392
+ "eval_steps_per_second": 2.618,
393
+ "step": 120
394
+ },
395
+ {
396
+ "epoch": 41.0,
397
+ "eval_accuracy": 0.9212121212121213,
398
+ "eval_loss": 0.2863142192363739,
399
+ "eval_runtime": 2.4128,
400
+ "eval_samples_per_second": 68.385,
401
+ "eval_steps_per_second": 2.487,
402
+ "step": 123
403
+ },
404
+ {
405
+ "epoch": 42.0,
406
+ "eval_accuracy": 0.9090909090909091,
407
+ "eval_loss": 0.29716795682907104,
408
+ "eval_runtime": 2.3275,
409
+ "eval_samples_per_second": 70.891,
410
+ "eval_steps_per_second": 2.578,
411
+ "step": 126
412
+ },
413
+ {
414
+ "epoch": 43.0,
415
+ "eval_accuracy": 0.9090909090909091,
416
+ "eval_loss": 0.3144596815109253,
417
+ "eval_runtime": 2.3029,
418
+ "eval_samples_per_second": 71.647,
419
+ "eval_steps_per_second": 2.605,
420
+ "step": 129
421
+ },
422
+ {
423
+ "epoch": 44.0,
424
+ "eval_accuracy": 0.896969696969697,
425
+ "eval_loss": 0.3420035243034363,
426
+ "eval_runtime": 2.3671,
427
+ "eval_samples_per_second": 69.706,
428
+ "eval_steps_per_second": 2.535,
429
+ "step": 132
430
+ },
431
+ {
432
+ "epoch": 45.0,
433
+ "eval_accuracy": 0.9030303030303031,
434
+ "eval_loss": 0.2978503704071045,
435
+ "eval_runtime": 2.3504,
436
+ "eval_samples_per_second": 70.202,
437
+ "eval_steps_per_second": 2.553,
438
+ "step": 135
439
+ },
440
+ {
441
+ "epoch": 46.0,
442
+ "eval_accuracy": 0.9090909090909091,
443
+ "eval_loss": 0.305865615606308,
444
+ "eval_runtime": 2.328,
445
+ "eval_samples_per_second": 70.877,
446
+ "eval_steps_per_second": 2.577,
447
+ "step": 138
448
+ },
449
+ {
450
+ "epoch": 47.0,
451
+ "eval_accuracy": 0.9090909090909091,
452
+ "eval_loss": 0.33988600969314575,
453
+ "eval_runtime": 2.3424,
454
+ "eval_samples_per_second": 70.44,
455
+ "eval_steps_per_second": 2.561,
456
+ "step": 141
457
+ },
458
+ {
459
+ "epoch": 48.0,
460
+ "eval_accuracy": 0.896969696969697,
461
+ "eval_loss": 0.3573344945907593,
462
+ "eval_runtime": 2.3771,
463
+ "eval_samples_per_second": 69.411,
464
+ "eval_steps_per_second": 2.524,
465
+ "step": 144
466
+ },
467
+ {
468
+ "epoch": 49.0,
469
+ "eval_accuracy": 0.9090909090909091,
470
+ "eval_loss": 0.3080121874809265,
471
+ "eval_runtime": 2.3669,
472
+ "eval_samples_per_second": 69.711,
473
+ "eval_steps_per_second": 2.535,
474
+ "step": 147
475
+ },
476
+ {
477
+ "epoch": 50.0,
478
+ "learning_rate": 2.777777777777778e-05,
479
+ "loss": 0.0489,
480
+ "step": 150
481
+ },
482
+ {
483
+ "epoch": 50.0,
484
+ "eval_accuracy": 0.9090909090909091,
485
+ "eval_loss": 0.3075540363788605,
486
+ "eval_runtime": 2.3013,
487
+ "eval_samples_per_second": 71.698,
488
+ "eval_steps_per_second": 2.607,
489
+ "step": 150
490
+ },
491
+ {
492
+ "epoch": 51.0,
493
+ "eval_accuracy": 0.896969696969697,
494
+ "eval_loss": 0.36510610580444336,
495
+ "eval_runtime": 2.3178,
496
+ "eval_samples_per_second": 71.189,
497
+ "eval_steps_per_second": 2.589,
498
+ "step": 153
499
+ },
500
+ {
501
+ "epoch": 52.0,
502
+ "eval_accuracy": 0.9030303030303031,
503
+ "eval_loss": 0.31200146675109863,
504
+ "eval_runtime": 2.3395,
505
+ "eval_samples_per_second": 70.528,
506
+ "eval_steps_per_second": 2.565,
507
+ "step": 156
508
+ },
509
+ {
510
+ "epoch": 53.0,
511
+ "eval_accuracy": 0.9151515151515152,
512
+ "eval_loss": 0.3011230528354645,
513
+ "eval_runtime": 2.349,
514
+ "eval_samples_per_second": 70.244,
515
+ "eval_steps_per_second": 2.554,
516
+ "step": 159
517
+ },
518
+ {
519
+ "epoch": 54.0,
520
+ "eval_accuracy": 0.896969696969697,
521
+ "eval_loss": 0.33502820134162903,
522
+ "eval_runtime": 2.3148,
523
+ "eval_samples_per_second": 71.282,
524
+ "eval_steps_per_second": 2.592,
525
+ "step": 162
526
+ },
527
+ {
528
+ "epoch": 55.0,
529
+ "eval_accuracy": 0.8727272727272727,
530
+ "eval_loss": 0.42433637380599976,
531
+ "eval_runtime": 2.3813,
532
+ "eval_samples_per_second": 69.288,
533
+ "eval_steps_per_second": 2.52,
534
+ "step": 165
535
+ },
536
+ {
537
+ "epoch": 56.0,
538
+ "eval_accuracy": 0.896969696969697,
539
+ "eval_loss": 0.39749395847320557,
540
+ "eval_runtime": 2.3457,
541
+ "eval_samples_per_second": 70.341,
542
+ "eval_steps_per_second": 2.558,
543
+ "step": 168
544
+ },
545
+ {
546
+ "epoch": 57.0,
547
+ "eval_accuracy": 0.8848484848484849,
548
+ "eval_loss": 0.3484455943107605,
549
+ "eval_runtime": 2.3486,
550
+ "eval_samples_per_second": 70.254,
551
+ "eval_steps_per_second": 2.555,
552
+ "step": 171
553
+ },
554
+ {
555
+ "epoch": 58.0,
556
+ "eval_accuracy": 0.8727272727272727,
557
+ "eval_loss": 0.4501076340675354,
558
+ "eval_runtime": 2.3305,
559
+ "eval_samples_per_second": 70.8,
560
+ "eval_steps_per_second": 2.575,
561
+ "step": 174
562
+ },
563
+ {
564
+ "epoch": 59.0,
565
+ "eval_accuracy": 0.8303030303030303,
566
+ "eval_loss": 0.550175130367279,
567
+ "eval_runtime": 2.33,
568
+ "eval_samples_per_second": 70.814,
569
+ "eval_steps_per_second": 2.575,
570
+ "step": 177
571
+ },
572
+ {
573
+ "epoch": 60.0,
574
+ "learning_rate": 2.2222222222222223e-05,
575
+ "loss": 0.0497,
576
+ "step": 180
577
+ },
578
+ {
579
+ "epoch": 60.0,
580
+ "eval_accuracy": 0.8727272727272727,
581
+ "eval_loss": 0.4404814839363098,
582
+ "eval_runtime": 2.3704,
583
+ "eval_samples_per_second": 69.608,
584
+ "eval_steps_per_second": 2.531,
585
+ "step": 180
586
+ },
587
+ {
588
+ "epoch": 61.0,
589
+ "eval_accuracy": 0.8909090909090909,
590
+ "eval_loss": 0.36748144030570984,
591
+ "eval_runtime": 2.3087,
592
+ "eval_samples_per_second": 71.47,
593
+ "eval_steps_per_second": 2.599,
594
+ "step": 183
595
+ },
596
+ {
597
+ "epoch": 62.0,
598
+ "eval_accuracy": 0.8909090909090909,
599
+ "eval_loss": 0.3592420518398285,
600
+ "eval_runtime": 2.6613,
601
+ "eval_samples_per_second": 61.999,
602
+ "eval_steps_per_second": 2.255,
603
+ "step": 186
604
+ },
605
+ {
606
+ "epoch": 63.0,
607
+ "eval_accuracy": 0.9090909090909091,
608
+ "eval_loss": 0.3651820421218872,
609
+ "eval_runtime": 2.4228,
610
+ "eval_samples_per_second": 68.102,
611
+ "eval_steps_per_second": 2.476,
612
+ "step": 189
613
+ },
614
+ {
615
+ "epoch": 64.0,
616
+ "eval_accuracy": 0.8848484848484849,
617
+ "eval_loss": 0.42894408106803894,
618
+ "eval_runtime": 2.4722,
619
+ "eval_samples_per_second": 66.741,
620
+ "eval_steps_per_second": 2.427,
621
+ "step": 192
622
+ },
623
+ {
624
+ "epoch": 65.0,
625
+ "eval_accuracy": 0.896969696969697,
626
+ "eval_loss": 0.3802632987499237,
627
+ "eval_runtime": 2.4846,
628
+ "eval_samples_per_second": 66.408,
629
+ "eval_steps_per_second": 2.415,
630
+ "step": 195
631
+ },
632
+ {
633
+ "epoch": 66.0,
634
+ "eval_accuracy": 0.9030303030303031,
635
+ "eval_loss": 0.35655370354652405,
636
+ "eval_runtime": 2.3659,
637
+ "eval_samples_per_second": 69.74,
638
+ "eval_steps_per_second": 2.536,
639
+ "step": 198
640
+ },
641
+ {
642
+ "epoch": 67.0,
643
+ "eval_accuracy": 0.9030303030303031,
644
+ "eval_loss": 0.3601439297199249,
645
+ "eval_runtime": 2.4242,
646
+ "eval_samples_per_second": 68.063,
647
+ "eval_steps_per_second": 2.475,
648
+ "step": 201
649
+ },
650
+ {
651
+ "epoch": 68.0,
652
+ "eval_accuracy": 0.8787878787878788,
653
+ "eval_loss": 0.38698670268058777,
654
+ "eval_runtime": 2.4852,
655
+ "eval_samples_per_second": 66.394,
656
+ "eval_steps_per_second": 2.414,
657
+ "step": 204
658
+ },
659
+ {
660
+ "epoch": 69.0,
661
+ "eval_accuracy": 0.8363636363636363,
662
+ "eval_loss": 0.5403356552124023,
663
+ "eval_runtime": 2.7549,
664
+ "eval_samples_per_second": 59.894,
665
+ "eval_steps_per_second": 2.178,
666
+ "step": 207
667
+ },
668
+ {
669
+ "epoch": 70.0,
670
+ "learning_rate": 1.6666666666666667e-05,
671
+ "loss": 0.0335,
672
+ "step": 210
673
+ },
674
+ {
675
+ "epoch": 70.0,
676
+ "eval_accuracy": 0.8121212121212121,
677
+ "eval_loss": 0.5928748846054077,
678
+ "eval_runtime": 2.456,
679
+ "eval_samples_per_second": 67.181,
680
+ "eval_steps_per_second": 2.443,
681
+ "step": 210
682
+ },
683
+ {
684
+ "epoch": 71.0,
685
+ "eval_accuracy": 0.8606060606060606,
686
+ "eval_loss": 0.4446137547492981,
687
+ "eval_runtime": 3.4376,
688
+ "eval_samples_per_second": 47.998,
689
+ "eval_steps_per_second": 1.745,
690
+ "step": 213
691
+ },
692
+ {
693
+ "epoch": 72.0,
694
+ "eval_accuracy": 0.9030303030303031,
695
+ "eval_loss": 0.3456382155418396,
696
+ "eval_runtime": 3.4289,
697
+ "eval_samples_per_second": 48.12,
698
+ "eval_steps_per_second": 1.75,
699
+ "step": 216
700
+ },
701
+ {
702
+ "epoch": 73.0,
703
+ "eval_accuracy": 0.9030303030303031,
704
+ "eval_loss": 0.3497260808944702,
705
+ "eval_runtime": 3.448,
706
+ "eval_samples_per_second": 47.854,
707
+ "eval_steps_per_second": 1.74,
708
+ "step": 219
709
+ },
710
+ {
711
+ "epoch": 74.0,
712
+ "eval_accuracy": 0.8909090909090909,
713
+ "eval_loss": 0.3460451066493988,
714
+ "eval_runtime": 3.5723,
715
+ "eval_samples_per_second": 46.189,
716
+ "eval_steps_per_second": 1.68,
717
+ "step": 222
718
+ },
719
+ {
720
+ "epoch": 75.0,
721
+ "eval_accuracy": 0.9030303030303031,
722
+ "eval_loss": 0.35541394352912903,
723
+ "eval_runtime": 3.3617,
724
+ "eval_samples_per_second": 49.082,
725
+ "eval_steps_per_second": 1.785,
726
+ "step": 225
727
+ },
728
+ {
729
+ "epoch": 76.0,
730
+ "eval_accuracy": 0.9151515151515152,
731
+ "eval_loss": 0.37109458446502686,
732
+ "eval_runtime": 3.3954,
733
+ "eval_samples_per_second": 48.596,
734
+ "eval_steps_per_second": 1.767,
735
+ "step": 228
736
+ },
737
+ {
738
+ "epoch": 77.0,
739
+ "eval_accuracy": 0.8909090909090909,
740
+ "eval_loss": 0.3966122567653656,
741
+ "eval_runtime": 3.39,
742
+ "eval_samples_per_second": 48.673,
743
+ "eval_steps_per_second": 1.77,
744
+ "step": 231
745
+ },
746
+ {
747
+ "epoch": 78.0,
748
+ "eval_accuracy": 0.896969696969697,
749
+ "eval_loss": 0.37558913230895996,
750
+ "eval_runtime": 2.4777,
751
+ "eval_samples_per_second": 66.594,
752
+ "eval_steps_per_second": 2.422,
753
+ "step": 234
754
+ },
755
+ {
756
+ "epoch": 79.0,
757
+ "eval_accuracy": 0.8848484848484849,
758
+ "eval_loss": 0.3648350238800049,
759
+ "eval_runtime": 2.4024,
760
+ "eval_samples_per_second": 68.681,
761
+ "eval_steps_per_second": 2.497,
762
+ "step": 237
763
+ },
764
+ {
765
+ "epoch": 80.0,
766
+ "learning_rate": 1.1111111111111112e-05,
767
+ "loss": 0.0354,
768
+ "step": 240
769
+ },
770
+ {
771
+ "epoch": 80.0,
772
+ "eval_accuracy": 0.8848484848484849,
773
+ "eval_loss": 0.364296555519104,
774
+ "eval_runtime": 2.4061,
775
+ "eval_samples_per_second": 68.576,
776
+ "eval_steps_per_second": 2.494,
777
+ "step": 240
778
+ },
779
+ {
780
+ "epoch": 81.0,
781
+ "eval_accuracy": 0.8787878787878788,
782
+ "eval_loss": 0.37478142976760864,
783
+ "eval_runtime": 2.4973,
784
+ "eval_samples_per_second": 66.07,
785
+ "eval_steps_per_second": 2.403,
786
+ "step": 243
787
+ },
788
+ {
789
+ "epoch": 82.0,
790
+ "eval_accuracy": 0.8848484848484849,
791
+ "eval_loss": 0.38661420345306396,
792
+ "eval_runtime": 3.4194,
793
+ "eval_samples_per_second": 48.254,
794
+ "eval_steps_per_second": 1.755,
795
+ "step": 246
796
+ },
797
+ {
798
+ "epoch": 83.0,
799
+ "eval_accuracy": 0.8787878787878788,
800
+ "eval_loss": 0.3912670314311981,
801
+ "eval_runtime": 3.4156,
802
+ "eval_samples_per_second": 48.308,
803
+ "eval_steps_per_second": 1.757,
804
+ "step": 249
805
+ },
806
+ {
807
+ "epoch": 84.0,
808
+ "eval_accuracy": 0.896969696969697,
809
+ "eval_loss": 0.39883953332901,
810
+ "eval_runtime": 3.3424,
811
+ "eval_samples_per_second": 49.366,
812
+ "eval_steps_per_second": 1.795,
813
+ "step": 252
814
+ },
815
+ {
816
+ "epoch": 85.0,
817
+ "eval_accuracy": 0.896969696969697,
818
+ "eval_loss": 0.3957526981830597,
819
+ "eval_runtime": 3.493,
820
+ "eval_samples_per_second": 47.238,
821
+ "eval_steps_per_second": 1.718,
822
+ "step": 255
823
+ },
824
+ {
825
+ "epoch": 86.0,
826
+ "eval_accuracy": 0.8909090909090909,
827
+ "eval_loss": 0.3850858211517334,
828
+ "eval_runtime": 3.5272,
829
+ "eval_samples_per_second": 46.779,
830
+ "eval_steps_per_second": 1.701,
831
+ "step": 258
832
+ },
833
+ {
834
+ "epoch": 87.0,
835
+ "eval_accuracy": 0.9030303030303031,
836
+ "eval_loss": 0.3711934983730316,
837
+ "eval_runtime": 3.5137,
838
+ "eval_samples_per_second": 46.958,
839
+ "eval_steps_per_second": 1.708,
840
+ "step": 261
841
+ },
842
+ {
843
+ "epoch": 88.0,
844
+ "eval_accuracy": 0.9090909090909091,
845
+ "eval_loss": 0.36674121022224426,
846
+ "eval_runtime": 3.4451,
847
+ "eval_samples_per_second": 47.895,
848
+ "eval_steps_per_second": 1.742,
849
+ "step": 264
850
+ },
851
+ {
852
+ "epoch": 89.0,
853
+ "eval_accuracy": 0.9090909090909091,
854
+ "eval_loss": 0.3646032214164734,
855
+ "eval_runtime": 3.4393,
856
+ "eval_samples_per_second": 47.975,
857
+ "eval_steps_per_second": 1.745,
858
+ "step": 267
859
+ },
860
+ {
861
+ "epoch": 90.0,
862
+ "learning_rate": 5.555555555555556e-06,
863
+ "loss": 0.0221,
864
+ "step": 270
865
+ },
866
+ {
867
+ "epoch": 90.0,
868
+ "eval_accuracy": 0.896969696969697,
869
+ "eval_loss": 0.3635583221912384,
870
+ "eval_runtime": 3.3452,
871
+ "eval_samples_per_second": 49.324,
872
+ "eval_steps_per_second": 1.794,
873
+ "step": 270
874
+ },
875
+ {
876
+ "epoch": 91.0,
877
+ "eval_accuracy": 0.896969696969697,
878
+ "eval_loss": 0.36410683393478394,
879
+ "eval_runtime": 2.9568,
880
+ "eval_samples_per_second": 55.804,
881
+ "eval_steps_per_second": 2.029,
882
+ "step": 273
883
+ },
884
+ {
885
+ "epoch": 92.0,
886
+ "eval_accuracy": 0.9090909090909091,
887
+ "eval_loss": 0.36949315667152405,
888
+ "eval_runtime": 2.4369,
889
+ "eval_samples_per_second": 67.709,
890
+ "eval_steps_per_second": 2.462,
891
+ "step": 276
892
+ },
893
+ {
894
+ "epoch": 93.0,
895
+ "eval_accuracy": 0.9090909090909091,
896
+ "eval_loss": 0.3717237412929535,
897
+ "eval_runtime": 2.381,
898
+ "eval_samples_per_second": 69.298,
899
+ "eval_steps_per_second": 2.52,
900
+ "step": 279
901
+ },
902
+ {
903
+ "epoch": 94.0,
904
+ "eval_accuracy": 0.9090909090909091,
905
+ "eval_loss": 0.3703281879425049,
906
+ "eval_runtime": 3.4459,
907
+ "eval_samples_per_second": 47.883,
908
+ "eval_steps_per_second": 1.741,
909
+ "step": 282
910
+ },
911
+ {
912
+ "epoch": 95.0,
913
+ "eval_accuracy": 0.9090909090909091,
914
+ "eval_loss": 0.3681131899356842,
915
+ "eval_runtime": 3.3629,
916
+ "eval_samples_per_second": 49.064,
917
+ "eval_steps_per_second": 1.784,
918
+ "step": 285
919
+ },
920
+ {
921
+ "epoch": 96.0,
922
+ "eval_accuracy": 0.9151515151515152,
923
+ "eval_loss": 0.36634162068367004,
924
+ "eval_runtime": 2.3736,
925
+ "eval_samples_per_second": 69.515,
926
+ "eval_steps_per_second": 2.528,
927
+ "step": 288
928
+ },
929
+ {
930
+ "epoch": 97.0,
931
+ "eval_accuracy": 0.9090909090909091,
932
+ "eval_loss": 0.3671952784061432,
933
+ "eval_runtime": 2.5265,
934
+ "eval_samples_per_second": 65.309,
935
+ "eval_steps_per_second": 2.375,
936
+ "step": 291
937
+ },
938
+ {
939
+ "epoch": 98.0,
940
+ "eval_accuracy": 0.9090909090909091,
941
+ "eval_loss": 0.3688179850578308,
942
+ "eval_runtime": 2.477,
943
+ "eval_samples_per_second": 66.614,
944
+ "eval_steps_per_second": 2.422,
945
+ "step": 294
946
+ },
947
+ {
948
+ "epoch": 99.0,
949
+ "eval_accuracy": 0.9090909090909091,
950
+ "eval_loss": 0.3698950707912445,
951
+ "eval_runtime": 2.8966,
952
+ "eval_samples_per_second": 56.963,
953
+ "eval_steps_per_second": 2.071,
954
+ "step": 297
955
+ },
956
+ {
957
+ "epoch": 100.0,
958
+ "learning_rate": 0.0,
959
+ "loss": 0.0225,
960
+ "step": 300
961
+ },
962
+ {
963
+ "epoch": 100.0,
964
+ "eval_accuracy": 0.9090909090909091,
965
+ "eval_loss": 0.3700920343399048,
966
+ "eval_runtime": 2.4031,
967
+ "eval_samples_per_second": 68.662,
968
+ "eval_steps_per_second": 2.497,
969
+ "step": 300
970
+ }
971
+ ],
972
+ "logging_steps": 30,
973
+ "max_steps": 300,
974
+ "num_train_epochs": 100,
975
+ "save_steps": 500,
976
+ "total_flos": 9.494987792596992e+17,
977
+ "trial_name": null,
978
+ "trial_params": null
979
+ }
swin-tiny-patch4-window7-224-finetuned-kiru/checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c1754d42d9157fdb31ac4f5b344d0cbbe3b67a8c00ad98ea5c4544f4552d7f
3
+ size 4219
swin-tiny-patch4-window7-224-finetuned-kiru/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
3
+ "architectures": [
4
+ "SwinForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "depths": [
8
+ 2,
9
+ 2,
10
+ 6,
11
+ 2
12
+ ],
13
+ "drop_path_rate": 0.1,
14
+ "embed_dim": 96,
15
+ "encoder_stride": 32,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.0,
18
+ "hidden_size": 768,
19
+ "id2label": {
20
+ "0": "true",
21
+ "1": "false"
22
+ },
23
+ "image_size": 224,
24
+ "initializer_range": 0.02,
25
+ "label2id": {
26
+ "false": 1,
27
+ "true": 0
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "mlp_ratio": 4.0,
31
+ "model_type": "swin",
32
+ "num_channels": 3,
33
+ "num_heads": [
34
+ 3,
35
+ 6,
36
+ 12,
37
+ 24
38
+ ],
39
+ "num_layers": 4,
40
+ "out_features": [
41
+ "stage4"
42
+ ],
43
+ "out_indices": [
44
+ 4
45
+ ],
46
+ "patch_size": 4,
47
+ "path_norm": true,
48
+ "problem_type": "single_label_classification",
49
+ "qkv_bias": true,
50
+ "stage_names": [
51
+ "stem",
52
+ "stage1",
53
+ "stage2",
54
+ "stage3",
55
+ "stage4"
56
+ ],
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.35.0",
59
+ "use_absolute_embeddings": false,
60
+ "window_size": 7
61
+ }
swin-tiny-patch4-window7-224-finetuned-kiru/eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_accuracy": 0.9333333333333333,
4
+ "eval_loss": 0.252092570066452,
5
+ "eval_runtime": 3.0916,
6
+ "eval_samples_per_second": 53.37,
7
+ "eval_steps_per_second": 1.941
8
+ }
swin-tiny-patch4-window7-224-finetuned-kiru/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20cd67122ace0f221e7c6781ec45e7dc1b36cabab73e940284ed7c0f0974e9a3
3
+ size 110342832
swin-tiny-patch4-window7-224-finetuned-kiru/preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.485,
7
+ 0.456,
8
+ 0.406
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.229,
13
+ 0.224,
14
+ 0.225
15
+ ],
16
+ "resample": 3,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
swin-tiny-patch4-window7-224-finetuned-kiru/runs/Nov10_17-13-00_DESKTOP-0P1K3MU/events.out.tfevents.1699603993.DESKTOP-0P1K3MU.11396.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:addbc84882265fc11d3ca5b454bdbcc49f5796d679510771d7c1cd69ceddce6c
3
+ size 73729
swin-tiny-patch4-window7-224-finetuned-kiru/runs/Nov10_17-36-22_DESKTOP-0P1K3MU/events.out.tfevents.1699605389.DESKTOP-0P1K3MU.18804.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d6ce685a320df6a5e9bd2af898a670eeb7d0ec49ed445b19d1b9be11c001ff0
3
+ size 74363
swin-tiny-patch4-window7-224-finetuned-kiru/runs/Nov10_17-37-34_DESKTOP-0P1K3MU/events.out.tfevents.1699605454.DESKTOP-0P1K3MU.22564.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ee21514f975016066079539b6da43a8f3b64d80836dc5d28da2372ed2b0637
3
+ size 107689
swin-tiny-patch4-window7-224-finetuned-kiru/runs/Nov10_17-37-34_DESKTOP-0P1K3MU/events.out.tfevents.1699606603.DESKTOP-0P1K3MU.22564.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcbbf378d037af02536c02f218071aa2bbea8e4d3c367a59eed2faa5bc3e2f00
3
+ size 411
swin-tiny-patch4-window7-224-finetuned-kiru/runs/Nov10_18-01-44_DESKTOP-0P1K3MU/events.out.tfevents.1699606911.DESKTOP-0P1K3MU.22564.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11dbce1a6e7c937d39e320dc9e7e8868cf967a7086ed9bdb81bad445317e0ea0
3
+ size 38639
swin-tiny-patch4-window7-224-finetuned-kiru/train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "train_loss": 0.11401470561822255,
4
+ "train_runtime": 1213.3224,
5
+ "train_samples_per_second": 31.484,
6
+ "train_steps_per_second": 0.247
7
+ }
swin-tiny-patch4-window7-224-finetuned-kiru/trainer_state.json ADDED
@@ -0,0 +1,988 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9393939393939394,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-kiru\\checkpoint-63",
4
+ "epoch": 100.0,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
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": 0.2,
14
+ "eval_loss": 0.9137158989906311,
15
+ "eval_runtime": 2.4017,
16
+ "eval_samples_per_second": 68.703,
17
+ "eval_steps_per_second": 2.498,
18
+ "step": 3
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.41818181818181815,
23
+ "eval_loss": 0.7433991432189941,
24
+ "eval_runtime": 2.3854,
25
+ "eval_samples_per_second": 69.171,
26
+ "eval_steps_per_second": 2.515,
27
+ "step": 6
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.7757575757575758,
32
+ "eval_loss": 0.558496356010437,
33
+ "eval_runtime": 2.91,
34
+ "eval_samples_per_second": 56.702,
35
+ "eval_steps_per_second": 2.062,
36
+ "step": 9
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.7757575757575758,
41
+ "eval_loss": 0.4807980954647064,
42
+ "eval_runtime": 2.7225,
43
+ "eval_samples_per_second": 60.606,
44
+ "eval_steps_per_second": 2.204,
45
+ "step": 12
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_accuracy": 0.7757575757575758,
50
+ "eval_loss": 0.44610753655433655,
51
+ "eval_runtime": 2.8794,
52
+ "eval_samples_per_second": 57.303,
53
+ "eval_steps_per_second": 2.084,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 6.0,
58
+ "eval_accuracy": 0.8,
59
+ "eval_loss": 0.41230690479278564,
60
+ "eval_runtime": 2.7147,
61
+ "eval_samples_per_second": 60.781,
62
+ "eval_steps_per_second": 2.21,
63
+ "step": 18
64
+ },
65
+ {
66
+ "epoch": 7.0,
67
+ "eval_accuracy": 0.8545454545454545,
68
+ "eval_loss": 0.4499864876270294,
69
+ "eval_runtime": 2.9708,
70
+ "eval_samples_per_second": 55.54,
71
+ "eval_steps_per_second": 2.02,
72
+ "step": 21
73
+ },
74
+ {
75
+ "epoch": 8.0,
76
+ "eval_accuracy": 0.7636363636363637,
77
+ "eval_loss": 0.4703312814235687,
78
+ "eval_runtime": 2.7665,
79
+ "eval_samples_per_second": 59.642,
80
+ "eval_steps_per_second": 2.169,
81
+ "step": 24
82
+ },
83
+ {
84
+ "epoch": 9.0,
85
+ "eval_accuracy": 0.8,
86
+ "eval_loss": 0.41265082359313965,
87
+ "eval_runtime": 2.7687,
88
+ "eval_samples_per_second": 59.595,
89
+ "eval_steps_per_second": 2.167,
90
+ "step": 27
91
+ },
92
+ {
93
+ "epoch": 10.0,
94
+ "learning_rate": 5e-05,
95
+ "loss": 0.5353,
96
+ "step": 30
97
+ },
98
+ {
99
+ "epoch": 10.0,
100
+ "eval_accuracy": 0.8787878787878788,
101
+ "eval_loss": 0.3097422420978546,
102
+ "eval_runtime": 2.932,
103
+ "eval_samples_per_second": 56.276,
104
+ "eval_steps_per_second": 2.046,
105
+ "step": 30
106
+ },
107
+ {
108
+ "epoch": 11.0,
109
+ "eval_accuracy": 0.7696969696969697,
110
+ "eval_loss": 0.45016413927078247,
111
+ "eval_runtime": 2.8763,
112
+ "eval_samples_per_second": 57.366,
113
+ "eval_steps_per_second": 2.086,
114
+ "step": 33
115
+ },
116
+ {
117
+ "epoch": 12.0,
118
+ "eval_accuracy": 0.8121212121212121,
119
+ "eval_loss": 0.3948935270309448,
120
+ "eval_runtime": 2.4262,
121
+ "eval_samples_per_second": 68.008,
122
+ "eval_steps_per_second": 2.473,
123
+ "step": 36
124
+ },
125
+ {
126
+ "epoch": 13.0,
127
+ "eval_accuracy": 0.8727272727272727,
128
+ "eval_loss": 0.2976933419704437,
129
+ "eval_runtime": 2.9565,
130
+ "eval_samples_per_second": 55.809,
131
+ "eval_steps_per_second": 2.029,
132
+ "step": 39
133
+ },
134
+ {
135
+ "epoch": 14.0,
136
+ "eval_accuracy": 0.8121212121212121,
137
+ "eval_loss": 0.37680599093437195,
138
+ "eval_runtime": 2.6485,
139
+ "eval_samples_per_second": 62.3,
140
+ "eval_steps_per_second": 2.265,
141
+ "step": 42
142
+ },
143
+ {
144
+ "epoch": 15.0,
145
+ "eval_accuracy": 0.8424242424242424,
146
+ "eval_loss": 0.36290910840034485,
147
+ "eval_runtime": 3.3518,
148
+ "eval_samples_per_second": 49.227,
149
+ "eval_steps_per_second": 1.79,
150
+ "step": 45
151
+ },
152
+ {
153
+ "epoch": 16.0,
154
+ "eval_accuracy": 0.8545454545454545,
155
+ "eval_loss": 0.31888607144355774,
156
+ "eval_runtime": 3.4102,
157
+ "eval_samples_per_second": 48.385,
158
+ "eval_steps_per_second": 1.759,
159
+ "step": 48
160
+ },
161
+ {
162
+ "epoch": 17.0,
163
+ "eval_accuracy": 0.8484848484848485,
164
+ "eval_loss": 0.27646660804748535,
165
+ "eval_runtime": 3.2469,
166
+ "eval_samples_per_second": 50.818,
167
+ "eval_steps_per_second": 1.848,
168
+ "step": 51
169
+ },
170
+ {
171
+ "epoch": 18.0,
172
+ "eval_accuracy": 0.9030303030303031,
173
+ "eval_loss": 0.22981072962284088,
174
+ "eval_runtime": 3.3886,
175
+ "eval_samples_per_second": 48.692,
176
+ "eval_steps_per_second": 1.771,
177
+ "step": 54
178
+ },
179
+ {
180
+ "epoch": 19.0,
181
+ "eval_accuracy": 0.8242424242424242,
182
+ "eval_loss": 0.4056190848350525,
183
+ "eval_runtime": 3.359,
184
+ "eval_samples_per_second": 49.122,
185
+ "eval_steps_per_second": 1.786,
186
+ "step": 57
187
+ },
188
+ {
189
+ "epoch": 20.0,
190
+ "learning_rate": 4.4444444444444447e-05,
191
+ "loss": 0.2047,
192
+ "step": 60
193
+ },
194
+ {
195
+ "epoch": 20.0,
196
+ "eval_accuracy": 0.8848484848484849,
197
+ "eval_loss": 0.2524569034576416,
198
+ "eval_runtime": 3.3911,
199
+ "eval_samples_per_second": 48.657,
200
+ "eval_steps_per_second": 1.769,
201
+ "step": 60
202
+ },
203
+ {
204
+ "epoch": 21.0,
205
+ "eval_accuracy": 0.9393939393939394,
206
+ "eval_loss": 0.179116889834404,
207
+ "eval_runtime": 3.4087,
208
+ "eval_samples_per_second": 48.406,
209
+ "eval_steps_per_second": 1.76,
210
+ "step": 63
211
+ },
212
+ {
213
+ "epoch": 22.0,
214
+ "eval_accuracy": 0.8606060606060606,
215
+ "eval_loss": 0.34358078241348267,
216
+ "eval_runtime": 3.4132,
217
+ "eval_samples_per_second": 48.342,
218
+ "eval_steps_per_second": 1.758,
219
+ "step": 66
220
+ },
221
+ {
222
+ "epoch": 23.0,
223
+ "eval_accuracy": 0.8545454545454545,
224
+ "eval_loss": 0.37361884117126465,
225
+ "eval_runtime": 2.5007,
226
+ "eval_samples_per_second": 65.981,
227
+ "eval_steps_per_second": 2.399,
228
+ "step": 69
229
+ },
230
+ {
231
+ "epoch": 24.0,
232
+ "eval_accuracy": 0.9272727272727272,
233
+ "eval_loss": 0.20224401354789734,
234
+ "eval_runtime": 3.4453,
235
+ "eval_samples_per_second": 47.891,
236
+ "eval_steps_per_second": 1.741,
237
+ "step": 72
238
+ },
239
+ {
240
+ "epoch": 25.0,
241
+ "eval_accuracy": 0.896969696969697,
242
+ "eval_loss": 0.2309740036725998,
243
+ "eval_runtime": 3.4325,
244
+ "eval_samples_per_second": 48.07,
245
+ "eval_steps_per_second": 1.748,
246
+ "step": 75
247
+ },
248
+ {
249
+ "epoch": 26.0,
250
+ "eval_accuracy": 0.8484848484848485,
251
+ "eval_loss": 0.4356694221496582,
252
+ "eval_runtime": 3.4524,
253
+ "eval_samples_per_second": 47.792,
254
+ "eval_steps_per_second": 1.738,
255
+ "step": 78
256
+ },
257
+ {
258
+ "epoch": 27.0,
259
+ "eval_accuracy": 0.8909090909090909,
260
+ "eval_loss": 0.23648156225681305,
261
+ "eval_runtime": 3.3817,
262
+ "eval_samples_per_second": 48.792,
263
+ "eval_steps_per_second": 1.774,
264
+ "step": 81
265
+ },
266
+ {
267
+ "epoch": 28.0,
268
+ "eval_accuracy": 0.896969696969697,
269
+ "eval_loss": 0.2242034673690796,
270
+ "eval_runtime": 3.5408,
271
+ "eval_samples_per_second": 46.6,
272
+ "eval_steps_per_second": 1.695,
273
+ "step": 84
274
+ },
275
+ {
276
+ "epoch": 29.0,
277
+ "eval_accuracy": 0.8787878787878788,
278
+ "eval_loss": 0.3519549071788788,
279
+ "eval_runtime": 3.5339,
280
+ "eval_samples_per_second": 46.69,
281
+ "eval_steps_per_second": 1.698,
282
+ "step": 87
283
+ },
284
+ {
285
+ "epoch": 30.0,
286
+ "learning_rate": 3.888888888888889e-05,
287
+ "loss": 0.1214,
288
+ "step": 90
289
+ },
290
+ {
291
+ "epoch": 30.0,
292
+ "eval_accuracy": 0.8666666666666667,
293
+ "eval_loss": 0.3405221700668335,
294
+ "eval_runtime": 3.3876,
295
+ "eval_samples_per_second": 48.707,
296
+ "eval_steps_per_second": 1.771,
297
+ "step": 90
298
+ },
299
+ {
300
+ "epoch": 31.0,
301
+ "eval_accuracy": 0.8848484848484849,
302
+ "eval_loss": 0.26643767952919006,
303
+ "eval_runtime": 3.5147,
304
+ "eval_samples_per_second": 46.946,
305
+ "eval_steps_per_second": 1.707,
306
+ "step": 93
307
+ },
308
+ {
309
+ "epoch": 32.0,
310
+ "eval_accuracy": 0.896969696969697,
311
+ "eval_loss": 0.30635523796081543,
312
+ "eval_runtime": 3.4904,
313
+ "eval_samples_per_second": 47.273,
314
+ "eval_steps_per_second": 1.719,
315
+ "step": 96
316
+ },
317
+ {
318
+ "epoch": 33.0,
319
+ "eval_accuracy": 0.8909090909090909,
320
+ "eval_loss": 0.28046053647994995,
321
+ "eval_runtime": 3.4457,
322
+ "eval_samples_per_second": 47.886,
323
+ "eval_steps_per_second": 1.741,
324
+ "step": 99
325
+ },
326
+ {
327
+ "epoch": 34.0,
328
+ "eval_accuracy": 0.9090909090909091,
329
+ "eval_loss": 0.2581537067890167,
330
+ "eval_runtime": 3.3583,
331
+ "eval_samples_per_second": 49.131,
332
+ "eval_steps_per_second": 1.787,
333
+ "step": 102
334
+ },
335
+ {
336
+ "epoch": 35.0,
337
+ "eval_accuracy": 0.896969696969697,
338
+ "eval_loss": 0.3365895748138428,
339
+ "eval_runtime": 3.5154,
340
+ "eval_samples_per_second": 46.936,
341
+ "eval_steps_per_second": 1.707,
342
+ "step": 105
343
+ },
344
+ {
345
+ "epoch": 36.0,
346
+ "eval_accuracy": 0.8242424242424242,
347
+ "eval_loss": 0.4986293315887451,
348
+ "eval_runtime": 3.4596,
349
+ "eval_samples_per_second": 47.693,
350
+ "eval_steps_per_second": 1.734,
351
+ "step": 108
352
+ },
353
+ {
354
+ "epoch": 37.0,
355
+ "eval_accuracy": 0.896969696969697,
356
+ "eval_loss": 0.33538326621055603,
357
+ "eval_runtime": 3.4043,
358
+ "eval_samples_per_second": 48.468,
359
+ "eval_steps_per_second": 1.762,
360
+ "step": 111
361
+ },
362
+ {
363
+ "epoch": 38.0,
364
+ "eval_accuracy": 0.9151515151515152,
365
+ "eval_loss": 0.28124478459358215,
366
+ "eval_runtime": 3.3948,
367
+ "eval_samples_per_second": 48.604,
368
+ "eval_steps_per_second": 1.767,
369
+ "step": 114
370
+ },
371
+ {
372
+ "epoch": 39.0,
373
+ "eval_accuracy": 0.9151515151515152,
374
+ "eval_loss": 0.28065553307533264,
375
+ "eval_runtime": 2.327,
376
+ "eval_samples_per_second": 70.907,
377
+ "eval_steps_per_second": 2.578,
378
+ "step": 117
379
+ },
380
+ {
381
+ "epoch": 40.0,
382
+ "learning_rate": 3.3333333333333335e-05,
383
+ "loss": 0.0667,
384
+ "step": 120
385
+ },
386
+ {
387
+ "epoch": 40.0,
388
+ "eval_accuracy": 0.8787878787878788,
389
+ "eval_loss": 0.33923324942588806,
390
+ "eval_runtime": 2.2919,
391
+ "eval_samples_per_second": 71.992,
392
+ "eval_steps_per_second": 2.618,
393
+ "step": 120
394
+ },
395
+ {
396
+ "epoch": 41.0,
397
+ "eval_accuracy": 0.9212121212121213,
398
+ "eval_loss": 0.2863142192363739,
399
+ "eval_runtime": 2.4128,
400
+ "eval_samples_per_second": 68.385,
401
+ "eval_steps_per_second": 2.487,
402
+ "step": 123
403
+ },
404
+ {
405
+ "epoch": 42.0,
406
+ "eval_accuracy": 0.9090909090909091,
407
+ "eval_loss": 0.29716795682907104,
408
+ "eval_runtime": 2.3275,
409
+ "eval_samples_per_second": 70.891,
410
+ "eval_steps_per_second": 2.578,
411
+ "step": 126
412
+ },
413
+ {
414
+ "epoch": 43.0,
415
+ "eval_accuracy": 0.9090909090909091,
416
+ "eval_loss": 0.3144596815109253,
417
+ "eval_runtime": 2.3029,
418
+ "eval_samples_per_second": 71.647,
419
+ "eval_steps_per_second": 2.605,
420
+ "step": 129
421
+ },
422
+ {
423
+ "epoch": 44.0,
424
+ "eval_accuracy": 0.896969696969697,
425
+ "eval_loss": 0.3420035243034363,
426
+ "eval_runtime": 2.3671,
427
+ "eval_samples_per_second": 69.706,
428
+ "eval_steps_per_second": 2.535,
429
+ "step": 132
430
+ },
431
+ {
432
+ "epoch": 45.0,
433
+ "eval_accuracy": 0.9030303030303031,
434
+ "eval_loss": 0.2978503704071045,
435
+ "eval_runtime": 2.3504,
436
+ "eval_samples_per_second": 70.202,
437
+ "eval_steps_per_second": 2.553,
438
+ "step": 135
439
+ },
440
+ {
441
+ "epoch": 46.0,
442
+ "eval_accuracy": 0.9090909090909091,
443
+ "eval_loss": 0.305865615606308,
444
+ "eval_runtime": 2.328,
445
+ "eval_samples_per_second": 70.877,
446
+ "eval_steps_per_second": 2.577,
447
+ "step": 138
448
+ },
449
+ {
450
+ "epoch": 47.0,
451
+ "eval_accuracy": 0.9090909090909091,
452
+ "eval_loss": 0.33988600969314575,
453
+ "eval_runtime": 2.3424,
454
+ "eval_samples_per_second": 70.44,
455
+ "eval_steps_per_second": 2.561,
456
+ "step": 141
457
+ },
458
+ {
459
+ "epoch": 48.0,
460
+ "eval_accuracy": 0.896969696969697,
461
+ "eval_loss": 0.3573344945907593,
462
+ "eval_runtime": 2.3771,
463
+ "eval_samples_per_second": 69.411,
464
+ "eval_steps_per_second": 2.524,
465
+ "step": 144
466
+ },
467
+ {
468
+ "epoch": 49.0,
469
+ "eval_accuracy": 0.9090909090909091,
470
+ "eval_loss": 0.3080121874809265,
471
+ "eval_runtime": 2.3669,
472
+ "eval_samples_per_second": 69.711,
473
+ "eval_steps_per_second": 2.535,
474
+ "step": 147
475
+ },
476
+ {
477
+ "epoch": 50.0,
478
+ "learning_rate": 2.777777777777778e-05,
479
+ "loss": 0.0489,
480
+ "step": 150
481
+ },
482
+ {
483
+ "epoch": 50.0,
484
+ "eval_accuracy": 0.9090909090909091,
485
+ "eval_loss": 0.3075540363788605,
486
+ "eval_runtime": 2.3013,
487
+ "eval_samples_per_second": 71.698,
488
+ "eval_steps_per_second": 2.607,
489
+ "step": 150
490
+ },
491
+ {
492
+ "epoch": 51.0,
493
+ "eval_accuracy": 0.896969696969697,
494
+ "eval_loss": 0.36510610580444336,
495
+ "eval_runtime": 2.3178,
496
+ "eval_samples_per_second": 71.189,
497
+ "eval_steps_per_second": 2.589,
498
+ "step": 153
499
+ },
500
+ {
501
+ "epoch": 52.0,
502
+ "eval_accuracy": 0.9030303030303031,
503
+ "eval_loss": 0.31200146675109863,
504
+ "eval_runtime": 2.3395,
505
+ "eval_samples_per_second": 70.528,
506
+ "eval_steps_per_second": 2.565,
507
+ "step": 156
508
+ },
509
+ {
510
+ "epoch": 53.0,
511
+ "eval_accuracy": 0.9151515151515152,
512
+ "eval_loss": 0.3011230528354645,
513
+ "eval_runtime": 2.349,
514
+ "eval_samples_per_second": 70.244,
515
+ "eval_steps_per_second": 2.554,
516
+ "step": 159
517
+ },
518
+ {
519
+ "epoch": 54.0,
520
+ "eval_accuracy": 0.896969696969697,
521
+ "eval_loss": 0.33502820134162903,
522
+ "eval_runtime": 2.3148,
523
+ "eval_samples_per_second": 71.282,
524
+ "eval_steps_per_second": 2.592,
525
+ "step": 162
526
+ },
527
+ {
528
+ "epoch": 55.0,
529
+ "eval_accuracy": 0.8727272727272727,
530
+ "eval_loss": 0.42433637380599976,
531
+ "eval_runtime": 2.3813,
532
+ "eval_samples_per_second": 69.288,
533
+ "eval_steps_per_second": 2.52,
534
+ "step": 165
535
+ },
536
+ {
537
+ "epoch": 56.0,
538
+ "eval_accuracy": 0.896969696969697,
539
+ "eval_loss": 0.39749395847320557,
540
+ "eval_runtime": 2.3457,
541
+ "eval_samples_per_second": 70.341,
542
+ "eval_steps_per_second": 2.558,
543
+ "step": 168
544
+ },
545
+ {
546
+ "epoch": 57.0,
547
+ "eval_accuracy": 0.8848484848484849,
548
+ "eval_loss": 0.3484455943107605,
549
+ "eval_runtime": 2.3486,
550
+ "eval_samples_per_second": 70.254,
551
+ "eval_steps_per_second": 2.555,
552
+ "step": 171
553
+ },
554
+ {
555
+ "epoch": 58.0,
556
+ "eval_accuracy": 0.8727272727272727,
557
+ "eval_loss": 0.4501076340675354,
558
+ "eval_runtime": 2.3305,
559
+ "eval_samples_per_second": 70.8,
560
+ "eval_steps_per_second": 2.575,
561
+ "step": 174
562
+ },
563
+ {
564
+ "epoch": 59.0,
565
+ "eval_accuracy": 0.8303030303030303,
566
+ "eval_loss": 0.550175130367279,
567
+ "eval_runtime": 2.33,
568
+ "eval_samples_per_second": 70.814,
569
+ "eval_steps_per_second": 2.575,
570
+ "step": 177
571
+ },
572
+ {
573
+ "epoch": 60.0,
574
+ "learning_rate": 2.2222222222222223e-05,
575
+ "loss": 0.0497,
576
+ "step": 180
577
+ },
578
+ {
579
+ "epoch": 60.0,
580
+ "eval_accuracy": 0.8727272727272727,
581
+ "eval_loss": 0.4404814839363098,
582
+ "eval_runtime": 2.3704,
583
+ "eval_samples_per_second": 69.608,
584
+ "eval_steps_per_second": 2.531,
585
+ "step": 180
586
+ },
587
+ {
588
+ "epoch": 61.0,
589
+ "eval_accuracy": 0.8909090909090909,
590
+ "eval_loss": 0.36748144030570984,
591
+ "eval_runtime": 2.3087,
592
+ "eval_samples_per_second": 71.47,
593
+ "eval_steps_per_second": 2.599,
594
+ "step": 183
595
+ },
596
+ {
597
+ "epoch": 62.0,
598
+ "eval_accuracy": 0.8909090909090909,
599
+ "eval_loss": 0.3592420518398285,
600
+ "eval_runtime": 2.6613,
601
+ "eval_samples_per_second": 61.999,
602
+ "eval_steps_per_second": 2.255,
603
+ "step": 186
604
+ },
605
+ {
606
+ "epoch": 63.0,
607
+ "eval_accuracy": 0.9090909090909091,
608
+ "eval_loss": 0.3651820421218872,
609
+ "eval_runtime": 2.4228,
610
+ "eval_samples_per_second": 68.102,
611
+ "eval_steps_per_second": 2.476,
612
+ "step": 189
613
+ },
614
+ {
615
+ "epoch": 64.0,
616
+ "eval_accuracy": 0.8848484848484849,
617
+ "eval_loss": 0.42894408106803894,
618
+ "eval_runtime": 2.4722,
619
+ "eval_samples_per_second": 66.741,
620
+ "eval_steps_per_second": 2.427,
621
+ "step": 192
622
+ },
623
+ {
624
+ "epoch": 65.0,
625
+ "eval_accuracy": 0.896969696969697,
626
+ "eval_loss": 0.3802632987499237,
627
+ "eval_runtime": 2.4846,
628
+ "eval_samples_per_second": 66.408,
629
+ "eval_steps_per_second": 2.415,
630
+ "step": 195
631
+ },
632
+ {
633
+ "epoch": 66.0,
634
+ "eval_accuracy": 0.9030303030303031,
635
+ "eval_loss": 0.35655370354652405,
636
+ "eval_runtime": 2.3659,
637
+ "eval_samples_per_second": 69.74,
638
+ "eval_steps_per_second": 2.536,
639
+ "step": 198
640
+ },
641
+ {
642
+ "epoch": 67.0,
643
+ "eval_accuracy": 0.9030303030303031,
644
+ "eval_loss": 0.3601439297199249,
645
+ "eval_runtime": 2.4242,
646
+ "eval_samples_per_second": 68.063,
647
+ "eval_steps_per_second": 2.475,
648
+ "step": 201
649
+ },
650
+ {
651
+ "epoch": 68.0,
652
+ "eval_accuracy": 0.8787878787878788,
653
+ "eval_loss": 0.38698670268058777,
654
+ "eval_runtime": 2.4852,
655
+ "eval_samples_per_second": 66.394,
656
+ "eval_steps_per_second": 2.414,
657
+ "step": 204
658
+ },
659
+ {
660
+ "epoch": 69.0,
661
+ "eval_accuracy": 0.8363636363636363,
662
+ "eval_loss": 0.5403356552124023,
663
+ "eval_runtime": 2.7549,
664
+ "eval_samples_per_second": 59.894,
665
+ "eval_steps_per_second": 2.178,
666
+ "step": 207
667
+ },
668
+ {
669
+ "epoch": 70.0,
670
+ "learning_rate": 1.6666666666666667e-05,
671
+ "loss": 0.0335,
672
+ "step": 210
673
+ },
674
+ {
675
+ "epoch": 70.0,
676
+ "eval_accuracy": 0.8121212121212121,
677
+ "eval_loss": 0.5928748846054077,
678
+ "eval_runtime": 2.456,
679
+ "eval_samples_per_second": 67.181,
680
+ "eval_steps_per_second": 2.443,
681
+ "step": 210
682
+ },
683
+ {
684
+ "epoch": 71.0,
685
+ "eval_accuracy": 0.8606060606060606,
686
+ "eval_loss": 0.4446137547492981,
687
+ "eval_runtime": 3.4376,
688
+ "eval_samples_per_second": 47.998,
689
+ "eval_steps_per_second": 1.745,
690
+ "step": 213
691
+ },
692
+ {
693
+ "epoch": 72.0,
694
+ "eval_accuracy": 0.9030303030303031,
695
+ "eval_loss": 0.3456382155418396,
696
+ "eval_runtime": 3.4289,
697
+ "eval_samples_per_second": 48.12,
698
+ "eval_steps_per_second": 1.75,
699
+ "step": 216
700
+ },
701
+ {
702
+ "epoch": 73.0,
703
+ "eval_accuracy": 0.9030303030303031,
704
+ "eval_loss": 0.3497260808944702,
705
+ "eval_runtime": 3.448,
706
+ "eval_samples_per_second": 47.854,
707
+ "eval_steps_per_second": 1.74,
708
+ "step": 219
709
+ },
710
+ {
711
+ "epoch": 74.0,
712
+ "eval_accuracy": 0.8909090909090909,
713
+ "eval_loss": 0.3460451066493988,
714
+ "eval_runtime": 3.5723,
715
+ "eval_samples_per_second": 46.189,
716
+ "eval_steps_per_second": 1.68,
717
+ "step": 222
718
+ },
719
+ {
720
+ "epoch": 75.0,
721
+ "eval_accuracy": 0.9030303030303031,
722
+ "eval_loss": 0.35541394352912903,
723
+ "eval_runtime": 3.3617,
724
+ "eval_samples_per_second": 49.082,
725
+ "eval_steps_per_second": 1.785,
726
+ "step": 225
727
+ },
728
+ {
729
+ "epoch": 76.0,
730
+ "eval_accuracy": 0.9151515151515152,
731
+ "eval_loss": 0.37109458446502686,
732
+ "eval_runtime": 3.3954,
733
+ "eval_samples_per_second": 48.596,
734
+ "eval_steps_per_second": 1.767,
735
+ "step": 228
736
+ },
737
+ {
738
+ "epoch": 77.0,
739
+ "eval_accuracy": 0.8909090909090909,
740
+ "eval_loss": 0.3966122567653656,
741
+ "eval_runtime": 3.39,
742
+ "eval_samples_per_second": 48.673,
743
+ "eval_steps_per_second": 1.77,
744
+ "step": 231
745
+ },
746
+ {
747
+ "epoch": 78.0,
748
+ "eval_accuracy": 0.896969696969697,
749
+ "eval_loss": 0.37558913230895996,
750
+ "eval_runtime": 2.4777,
751
+ "eval_samples_per_second": 66.594,
752
+ "eval_steps_per_second": 2.422,
753
+ "step": 234
754
+ },
755
+ {
756
+ "epoch": 79.0,
757
+ "eval_accuracy": 0.8848484848484849,
758
+ "eval_loss": 0.3648350238800049,
759
+ "eval_runtime": 2.4024,
760
+ "eval_samples_per_second": 68.681,
761
+ "eval_steps_per_second": 2.497,
762
+ "step": 237
763
+ },
764
+ {
765
+ "epoch": 80.0,
766
+ "learning_rate": 1.1111111111111112e-05,
767
+ "loss": 0.0354,
768
+ "step": 240
769
+ },
770
+ {
771
+ "epoch": 80.0,
772
+ "eval_accuracy": 0.8848484848484849,
773
+ "eval_loss": 0.364296555519104,
774
+ "eval_runtime": 2.4061,
775
+ "eval_samples_per_second": 68.576,
776
+ "eval_steps_per_second": 2.494,
777
+ "step": 240
778
+ },
779
+ {
780
+ "epoch": 81.0,
781
+ "eval_accuracy": 0.8787878787878788,
782
+ "eval_loss": 0.37478142976760864,
783
+ "eval_runtime": 2.4973,
784
+ "eval_samples_per_second": 66.07,
785
+ "eval_steps_per_second": 2.403,
786
+ "step": 243
787
+ },
788
+ {
789
+ "epoch": 82.0,
790
+ "eval_accuracy": 0.8848484848484849,
791
+ "eval_loss": 0.38661420345306396,
792
+ "eval_runtime": 3.4194,
793
+ "eval_samples_per_second": 48.254,
794
+ "eval_steps_per_second": 1.755,
795
+ "step": 246
796
+ },
797
+ {
798
+ "epoch": 83.0,
799
+ "eval_accuracy": 0.8787878787878788,
800
+ "eval_loss": 0.3912670314311981,
801
+ "eval_runtime": 3.4156,
802
+ "eval_samples_per_second": 48.308,
803
+ "eval_steps_per_second": 1.757,
804
+ "step": 249
805
+ },
806
+ {
807
+ "epoch": 84.0,
808
+ "eval_accuracy": 0.896969696969697,
809
+ "eval_loss": 0.39883953332901,
810
+ "eval_runtime": 3.3424,
811
+ "eval_samples_per_second": 49.366,
812
+ "eval_steps_per_second": 1.795,
813
+ "step": 252
814
+ },
815
+ {
816
+ "epoch": 85.0,
817
+ "eval_accuracy": 0.896969696969697,
818
+ "eval_loss": 0.3957526981830597,
819
+ "eval_runtime": 3.493,
820
+ "eval_samples_per_second": 47.238,
821
+ "eval_steps_per_second": 1.718,
822
+ "step": 255
823
+ },
824
+ {
825
+ "epoch": 86.0,
826
+ "eval_accuracy": 0.8909090909090909,
827
+ "eval_loss": 0.3850858211517334,
828
+ "eval_runtime": 3.5272,
829
+ "eval_samples_per_second": 46.779,
830
+ "eval_steps_per_second": 1.701,
831
+ "step": 258
832
+ },
833
+ {
834
+ "epoch": 87.0,
835
+ "eval_accuracy": 0.9030303030303031,
836
+ "eval_loss": 0.3711934983730316,
837
+ "eval_runtime": 3.5137,
838
+ "eval_samples_per_second": 46.958,
839
+ "eval_steps_per_second": 1.708,
840
+ "step": 261
841
+ },
842
+ {
843
+ "epoch": 88.0,
844
+ "eval_accuracy": 0.9090909090909091,
845
+ "eval_loss": 0.36674121022224426,
846
+ "eval_runtime": 3.4451,
847
+ "eval_samples_per_second": 47.895,
848
+ "eval_steps_per_second": 1.742,
849
+ "step": 264
850
+ },
851
+ {
852
+ "epoch": 89.0,
853
+ "eval_accuracy": 0.9090909090909091,
854
+ "eval_loss": 0.3646032214164734,
855
+ "eval_runtime": 3.4393,
856
+ "eval_samples_per_second": 47.975,
857
+ "eval_steps_per_second": 1.745,
858
+ "step": 267
859
+ },
860
+ {
861
+ "epoch": 90.0,
862
+ "learning_rate": 5.555555555555556e-06,
863
+ "loss": 0.0221,
864
+ "step": 270
865
+ },
866
+ {
867
+ "epoch": 90.0,
868
+ "eval_accuracy": 0.896969696969697,
869
+ "eval_loss": 0.3635583221912384,
870
+ "eval_runtime": 3.3452,
871
+ "eval_samples_per_second": 49.324,
872
+ "eval_steps_per_second": 1.794,
873
+ "step": 270
874
+ },
875
+ {
876
+ "epoch": 91.0,
877
+ "eval_accuracy": 0.896969696969697,
878
+ "eval_loss": 0.36410683393478394,
879
+ "eval_runtime": 2.9568,
880
+ "eval_samples_per_second": 55.804,
881
+ "eval_steps_per_second": 2.029,
882
+ "step": 273
883
+ },
884
+ {
885
+ "epoch": 92.0,
886
+ "eval_accuracy": 0.9090909090909091,
887
+ "eval_loss": 0.36949315667152405,
888
+ "eval_runtime": 2.4369,
889
+ "eval_samples_per_second": 67.709,
890
+ "eval_steps_per_second": 2.462,
891
+ "step": 276
892
+ },
893
+ {
894
+ "epoch": 93.0,
895
+ "eval_accuracy": 0.9090909090909091,
896
+ "eval_loss": 0.3717237412929535,
897
+ "eval_runtime": 2.381,
898
+ "eval_samples_per_second": 69.298,
899
+ "eval_steps_per_second": 2.52,
900
+ "step": 279
901
+ },
902
+ {
903
+ "epoch": 94.0,
904
+ "eval_accuracy": 0.9090909090909091,
905
+ "eval_loss": 0.3703281879425049,
906
+ "eval_runtime": 3.4459,
907
+ "eval_samples_per_second": 47.883,
908
+ "eval_steps_per_second": 1.741,
909
+ "step": 282
910
+ },
911
+ {
912
+ "epoch": 95.0,
913
+ "eval_accuracy": 0.9090909090909091,
914
+ "eval_loss": 0.3681131899356842,
915
+ "eval_runtime": 3.3629,
916
+ "eval_samples_per_second": 49.064,
917
+ "eval_steps_per_second": 1.784,
918
+ "step": 285
919
+ },
920
+ {
921
+ "epoch": 96.0,
922
+ "eval_accuracy": 0.9151515151515152,
923
+ "eval_loss": 0.36634162068367004,
924
+ "eval_runtime": 2.3736,
925
+ "eval_samples_per_second": 69.515,
926
+ "eval_steps_per_second": 2.528,
927
+ "step": 288
928
+ },
929
+ {
930
+ "epoch": 97.0,
931
+ "eval_accuracy": 0.9090909090909091,
932
+ "eval_loss": 0.3671952784061432,
933
+ "eval_runtime": 2.5265,
934
+ "eval_samples_per_second": 65.309,
935
+ "eval_steps_per_second": 2.375,
936
+ "step": 291
937
+ },
938
+ {
939
+ "epoch": 98.0,
940
+ "eval_accuracy": 0.9090909090909091,
941
+ "eval_loss": 0.3688179850578308,
942
+ "eval_runtime": 2.477,
943
+ "eval_samples_per_second": 66.614,
944
+ "eval_steps_per_second": 2.422,
945
+ "step": 294
946
+ },
947
+ {
948
+ "epoch": 99.0,
949
+ "eval_accuracy": 0.9090909090909091,
950
+ "eval_loss": 0.3698950707912445,
951
+ "eval_runtime": 2.8966,
952
+ "eval_samples_per_second": 56.963,
953
+ "eval_steps_per_second": 2.071,
954
+ "step": 297
955
+ },
956
+ {
957
+ "epoch": 100.0,
958
+ "learning_rate": 0.0,
959
+ "loss": 0.0225,
960
+ "step": 300
961
+ },
962
+ {
963
+ "epoch": 100.0,
964
+ "eval_accuracy": 0.9090909090909091,
965
+ "eval_loss": 0.3700920343399048,
966
+ "eval_runtime": 2.4031,
967
+ "eval_samples_per_second": 68.662,
968
+ "eval_steps_per_second": 2.497,
969
+ "step": 300
970
+ },
971
+ {
972
+ "epoch": 100.0,
973
+ "step": 300,
974
+ "total_flos": 9.494987792596992e+17,
975
+ "train_loss": 0.11401470561822255,
976
+ "train_runtime": 1213.3224,
977
+ "train_samples_per_second": 31.484,
978
+ "train_steps_per_second": 0.247
979
+ }
980
+ ],
981
+ "logging_steps": 30,
982
+ "max_steps": 300,
983
+ "num_train_epochs": 100,
984
+ "save_steps": 500,
985
+ "total_flos": 9.494987792596992e+17,
986
+ "trial_name": null,
987
+ "trial_params": null
988
+ }
swin-tiny-patch4-window7-224-finetuned-kiru/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c1754d42d9157fdb31ac4f5b344d0cbbe3b67a8c00ad98ea5c4544f4552d7f
3
+ size 4219