hwm21 commited on
Commit
f3cf05b
1 Parent(s): c2123b3

Training in progress, step 2100, checkpoint

Browse files
checkpoint-2100/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/detr-resnet-50-dc5",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "DetrForObjectDetection"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auxiliary_loss": false,
10
+ "backbone": "resnet50",
11
+ "backbone_config": null,
12
+ "backbone_kwargs": {
13
+ "in_chans": 3,
14
+ "out_indices": [
15
+ 1,
16
+ 2,
17
+ 3,
18
+ 4
19
+ ],
20
+ "output_stride": 16
21
+ },
22
+ "bbox_cost": 5,
23
+ "bbox_loss_coefficient": 5,
24
+ "class_cost": 1,
25
+ "classifier_dropout": 0.0,
26
+ "d_model": 256,
27
+ "decoder_attention_heads": 8,
28
+ "decoder_ffn_dim": 2048,
29
+ "decoder_layerdrop": 0.0,
30
+ "decoder_layers": 6,
31
+ "dice_loss_coefficient": 1,
32
+ "dilation": true,
33
+ "dropout": 0.1,
34
+ "encoder_attention_heads": 8,
35
+ "encoder_ffn_dim": 2048,
36
+ "encoder_layerdrop": 0.0,
37
+ "encoder_layers": 6,
38
+ "eos_coefficient": 0.1,
39
+ "giou_cost": 2,
40
+ "giou_loss_coefficient": 2,
41
+ "id2label": {
42
+ "0": "segment"
43
+ },
44
+ "init_std": 0.02,
45
+ "init_xavier_std": 1.0,
46
+ "is_encoder_decoder": true,
47
+ "label2id": {
48
+ "segment": 0
49
+ },
50
+ "mask_loss_coefficient": 1,
51
+ "max_position_embeddings": 1024,
52
+ "model_type": "detr",
53
+ "num_channels": 3,
54
+ "num_hidden_layers": 6,
55
+ "num_queries": 500,
56
+ "position_embedding_type": "sine",
57
+ "scale_embedding": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.44.1",
60
+ "use_pretrained_backbone": true,
61
+ "use_timm_backbone": true
62
+ }
checkpoint-2100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90ae38837f1e733badfc73a43242a4b8c8d56843178a0d785333546baf6fb2b
3
+ size 166904424
checkpoint-2100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e036a79fdba23ceec982787214c48726f26bb23a3b013092c9c1cfa3aa230285
3
+ size 331310970
checkpoint-2100/preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_annotations": true,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "format": "coco_detection",
8
+ "image_mean": [
9
+ 0.485,
10
+ 0.456,
11
+ 0.406
12
+ ],
13
+ "image_processor_type": "DetrImageProcessor",
14
+ "image_std": [
15
+ 0.229,
16
+ 0.224,
17
+ 0.225
18
+ ],
19
+ "pad_size": null,
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 1333,
24
+ "shortest_edge": 800
25
+ }
26
+ }
checkpoint-2100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c21c38dbf12020e8c34eb8b10fbb69147356c7d85f50a0493d74211a9c3cd00
3
+ size 14180
checkpoint-2100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:922a7e9dee60dc5b51b4097f8cf06a5bcd6afd1ebe70fa0c2f03de4959cd05b0
3
+ size 1064
checkpoint-2100/trainer_state.json ADDED
@@ -0,0 +1,327 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 25.925925925925927,
5
+ "eval_steps": 500,
6
+ "global_step": 2100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6172839506172839,
13
+ "grad_norm": 62.88630294799805,
14
+ "learning_rate": 9.916000000000001e-06,
15
+ "loss": 6.6856,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 1.2345679012345678,
20
+ "grad_norm": 387.6339111328125,
21
+ "learning_rate": 9.818000000000002e-06,
22
+ "loss": 5.5869,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 1.8518518518518519,
27
+ "grad_norm": 245.18975830078125,
28
+ "learning_rate": 9.718e-06,
29
+ "loss": 5.159,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 2.4691358024691357,
34
+ "grad_norm": 330.3158264160156,
35
+ "learning_rate": 9.618e-06,
36
+ "loss": 4.0494,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 3.0864197530864197,
41
+ "grad_norm": 138.14215087890625,
42
+ "learning_rate": 9.518000000000001e-06,
43
+ "loss": 3.6313,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 3.7037037037037037,
48
+ "grad_norm": 166.69479370117188,
49
+ "learning_rate": 9.418e-06,
50
+ "loss": 3.3391,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 4.320987654320987,
55
+ "grad_norm": 107.54407501220703,
56
+ "learning_rate": 9.318e-06,
57
+ "loss": 3.3295,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 4.938271604938271,
62
+ "grad_norm": 293.8923034667969,
63
+ "learning_rate": 9.218e-06,
64
+ "loss": 3.0956,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 5.555555555555555,
69
+ "grad_norm": 226.05360412597656,
70
+ "learning_rate": 9.118000000000001e-06,
71
+ "loss": 3.0271,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 6.172839506172839,
76
+ "grad_norm": 352.8487854003906,
77
+ "learning_rate": 9.018e-06,
78
+ "loss": 3.0627,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 6.790123456790123,
83
+ "grad_norm": 97.6641616821289,
84
+ "learning_rate": 8.918000000000002e-06,
85
+ "loss": 3.0312,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 7.407407407407407,
90
+ "grad_norm": 90.92312622070312,
91
+ "learning_rate": 8.818000000000001e-06,
92
+ "loss": 3.0228,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 8.024691358024691,
97
+ "grad_norm": 241.7625732421875,
98
+ "learning_rate": 8.718e-06,
99
+ "loss": 3.0873,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 8.641975308641975,
104
+ "grad_norm": 162.14071655273438,
105
+ "learning_rate": 8.618000000000001e-06,
106
+ "loss": 2.9582,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 9.25925925925926,
111
+ "grad_norm": 128.74766540527344,
112
+ "learning_rate": 8.518e-06,
113
+ "loss": 2.9787,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 9.876543209876543,
118
+ "grad_norm": 164.0232391357422,
119
+ "learning_rate": 8.418000000000001e-06,
120
+ "loss": 2.969,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 10.493827160493828,
125
+ "grad_norm": 110.58142852783203,
126
+ "learning_rate": 8.318e-06,
127
+ "loss": 2.884,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 11.11111111111111,
132
+ "grad_norm": 111.70948791503906,
133
+ "learning_rate": 8.218e-06,
134
+ "loss": 2.8216,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 11.728395061728396,
139
+ "grad_norm": 111.31181335449219,
140
+ "learning_rate": 8.118000000000001e-06,
141
+ "loss": 2.8621,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 12.345679012345679,
146
+ "grad_norm": 84.1104507446289,
147
+ "learning_rate": 8.018e-06,
148
+ "loss": 2.7653,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 12.962962962962964,
153
+ "grad_norm": 85.67730712890625,
154
+ "learning_rate": 7.918e-06,
155
+ "loss": 2.8418,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 13.580246913580247,
160
+ "grad_norm": 567.8911743164062,
161
+ "learning_rate": 7.818e-06,
162
+ "loss": 2.789,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 14.197530864197532,
167
+ "grad_norm": 98.47197723388672,
168
+ "learning_rate": 7.718000000000001e-06,
169
+ "loss": 2.7996,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 14.814814814814815,
174
+ "grad_norm": 86.87311553955078,
175
+ "learning_rate": 7.618000000000001e-06,
176
+ "loss": 2.7087,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 15.432098765432098,
181
+ "grad_norm": 115.806640625,
182
+ "learning_rate": 7.518000000000001e-06,
183
+ "loss": 2.6898,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 16.049382716049383,
188
+ "grad_norm": 108.76448059082031,
189
+ "learning_rate": 7.418000000000001e-06,
190
+ "loss": 2.7533,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 16.666666666666668,
195
+ "grad_norm": 137.66285705566406,
196
+ "learning_rate": 7.318000000000001e-06,
197
+ "loss": 2.6817,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 17.28395061728395,
202
+ "grad_norm": 167.23983764648438,
203
+ "learning_rate": 7.218e-06,
204
+ "loss": 2.6612,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 17.901234567901234,
209
+ "grad_norm": 80.27250671386719,
210
+ "learning_rate": 7.118e-06,
211
+ "loss": 2.7053,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 18.51851851851852,
216
+ "grad_norm": 87.89417266845703,
217
+ "learning_rate": 7.018e-06,
218
+ "loss": 2.6016,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 19.135802469135804,
223
+ "grad_norm": 244.07081604003906,
224
+ "learning_rate": 6.9180000000000005e-06,
225
+ "loss": 2.6377,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 19.753086419753085,
230
+ "grad_norm": 66.56304931640625,
231
+ "learning_rate": 6.818e-06,
232
+ "loss": 2.5969,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 20.37037037037037,
237
+ "grad_norm": 146.2065887451172,
238
+ "learning_rate": 6.718e-06,
239
+ "loss": 2.5849,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 20.987654320987655,
244
+ "grad_norm": 105.38662719726562,
245
+ "learning_rate": 6.618000000000001e-06,
246
+ "loss": 2.588,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 21.604938271604937,
251
+ "grad_norm": 172.37232971191406,
252
+ "learning_rate": 6.518000000000001e-06,
253
+ "loss": 2.5201,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 22.22222222222222,
258
+ "grad_norm": 1186.192626953125,
259
+ "learning_rate": 6.418000000000001e-06,
260
+ "loss": 2.5618,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 22.839506172839506,
265
+ "grad_norm": 181.00384521484375,
266
+ "learning_rate": 6.318000000000001e-06,
267
+ "loss": 2.496,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 23.45679012345679,
272
+ "grad_norm": 90.32185363769531,
273
+ "learning_rate": 6.2180000000000004e-06,
274
+ "loss": 2.5254,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 24.074074074074073,
279
+ "grad_norm": 117.39266967773438,
280
+ "learning_rate": 6.1180000000000005e-06,
281
+ "loss": 2.4665,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 24.691358024691358,
286
+ "grad_norm": 117.4901123046875,
287
+ "learning_rate": 6.018000000000001e-06,
288
+ "loss": 2.4541,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 25.308641975308642,
293
+ "grad_norm": 112.75492095947266,
294
+ "learning_rate": 5.918000000000001e-06,
295
+ "loss": 2.4716,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 25.925925925925927,
300
+ "grad_norm": 75.71508026123047,
301
+ "learning_rate": 5.818e-06,
302
+ "loss": 2.4643,
303
+ "step": 2100
304
+ }
305
+ ],
306
+ "logging_steps": 50,
307
+ "max_steps": 5000,
308
+ "num_input_tokens_seen": 0,
309
+ "num_train_epochs": 62,
310
+ "save_steps": 100,
311
+ "stateful_callbacks": {
312
+ "TrainerControl": {
313
+ "args": {
314
+ "should_epoch_stop": false,
315
+ "should_evaluate": false,
316
+ "should_log": false,
317
+ "should_save": true,
318
+ "should_training_stop": false
319
+ },
320
+ "attributes": {}
321
+ }
322
+ },
323
+ "total_flos": 8.027106490368e+18,
324
+ "train_batch_size": 8,
325
+ "trial_name": null,
326
+ "trial_params": null
327
+ }
checkpoint-2100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dae0b4d732b15d565b589748a29a09a17e2ddd7d7ab9df017470bce43888a34
3
+ size 5240