louijiec commited on
Commit
2f3b145
·
verified ·
1 Parent(s): 2c70bec

Upload folder using huggingface_hub

Browse files
checkpoint-500/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ViTForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "encoder_stride": 16,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.0,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "airplane",
12
+ "1": "automobile",
13
+ "2": "bird",
14
+ "3": "cat",
15
+ "4": "deer",
16
+ "5": "dog",
17
+ "6": "frog",
18
+ "7": "horse",
19
+ "8": "ship",
20
+ "9": "truck"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "airplane": 0,
27
+ "automobile": 1,
28
+ "bird": 2,
29
+ "cat": 3,
30
+ "deer": 4,
31
+ "dog": 5,
32
+ "frog": 6,
33
+ "horse": 7,
34
+ "ship": 8,
35
+ "truck": 9
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "model_type": "vit",
39
+ "num_attention_heads": 12,
40
+ "num_channels": 3,
41
+ "num_hidden_layers": 12,
42
+ "patch_size": 16,
43
+ "pooler_act": "tanh",
44
+ "pooler_output_size": 768,
45
+ "problem_type": "single_label_classification",
46
+ "qkv_bias": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.52.4"
49
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d115d2a5ed514b73c8872aa5167269e3e87f0332195613beca2e2a97d9ee3e
3
+ size 343248584
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90e50bf4aa98f7bf48f64e4a7af951e0e1a09656b83a7d90d968b81aa750d997
3
+ size 686618042
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa634b0dea1bd3527ae1b074e622370675923bec43a6da879374cc6a80c2f23
3
+ size 1064
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.64,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0128,
14
+ "grad_norm": 1.1307092905044556,
15
+ "learning_rate": 5.69620253164557e-06,
16
+ "loss": 2.3042,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0256,
21
+ "grad_norm": 1.0256341695785522,
22
+ "learning_rate": 1.2025316455696203e-05,
23
+ "loss": 2.2764,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0384,
28
+ "grad_norm": 1.3286596536636353,
29
+ "learning_rate": 1.8354430379746836e-05,
30
+ "loss": 2.2167,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0512,
35
+ "grad_norm": 1.343770146369934,
36
+ "learning_rate": 2.468354430379747e-05,
37
+ "loss": 2.1222,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.064,
42
+ "grad_norm": 1.2992122173309326,
43
+ "learning_rate": 3.10126582278481e-05,
44
+ "loss": 1.9886,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0768,
49
+ "grad_norm": 1.2733649015426636,
50
+ "learning_rate": 3.7341772151898736e-05,
51
+ "loss": 1.8062,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0896,
56
+ "grad_norm": 1.3380931615829468,
57
+ "learning_rate": 4.367088607594937e-05,
58
+ "loss": 1.5562,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.1024,
63
+ "grad_norm": 1.5014597177505493,
64
+ "learning_rate": 5e-05,
65
+ "loss": 1.2747,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1152,
70
+ "grad_norm": 1.443360447883606,
71
+ "learning_rate": 4.928876244665719e-05,
72
+ "loss": 1.0305,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.128,
77
+ "grad_norm": 1.4796088933944702,
78
+ "learning_rate": 4.8577524893314366e-05,
79
+ "loss": 0.8814,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.1408,
84
+ "grad_norm": 1.3090192079544067,
85
+ "learning_rate": 4.786628733997156e-05,
86
+ "loss": 0.7241,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.1536,
91
+ "grad_norm": 1.7807539701461792,
92
+ "learning_rate": 4.7155049786628736e-05,
93
+ "loss": 0.6109,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.1664,
98
+ "grad_norm": 1.611634373664856,
99
+ "learning_rate": 4.644381223328592e-05,
100
+ "loss": 0.5711,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.1792,
105
+ "grad_norm": 2.08296275138855,
106
+ "learning_rate": 4.57325746799431e-05,
107
+ "loss": 0.5387,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.192,
112
+ "grad_norm": 3.6438846588134766,
113
+ "learning_rate": 4.5021337126600285e-05,
114
+ "loss": 0.4422,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.2048,
119
+ "grad_norm": 1.203041672706604,
120
+ "learning_rate": 4.431009957325747e-05,
121
+ "loss": 0.4451,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.2176,
126
+ "grad_norm": 2.097452402114868,
127
+ "learning_rate": 4.3598862019914656e-05,
128
+ "loss": 0.398,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.2304,
133
+ "grad_norm": 1.494523286819458,
134
+ "learning_rate": 4.2887624466571834e-05,
135
+ "loss": 0.3843,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.2432,
140
+ "grad_norm": 1.4821765422821045,
141
+ "learning_rate": 4.217638691322902e-05,
142
+ "loss": 0.3476,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.256,
147
+ "grad_norm": 2.9275362491607666,
148
+ "learning_rate": 4.1465149359886204e-05,
149
+ "loss": 0.3174,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.2688,
154
+ "grad_norm": 1.4172513484954834,
155
+ "learning_rate": 4.075391180654339e-05,
156
+ "loss": 0.3109,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.2816,
161
+ "grad_norm": 1.1657588481903076,
162
+ "learning_rate": 4.004267425320057e-05,
163
+ "loss": 0.3018,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.2944,
168
+ "grad_norm": 1.3319698572158813,
169
+ "learning_rate": 3.933143669985775e-05,
170
+ "loss": 0.2832,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.3072,
175
+ "grad_norm": 2.535245895385742,
176
+ "learning_rate": 3.862019914651494e-05,
177
+ "loss": 0.2797,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.32,
182
+ "grad_norm": 0.751595675945282,
183
+ "learning_rate": 3.7908961593172124e-05,
184
+ "loss": 0.2447,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.3328,
189
+ "grad_norm": 0.8638726472854614,
190
+ "learning_rate": 3.719772403982931e-05,
191
+ "loss": 0.2543,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.3456,
196
+ "grad_norm": 1.3161370754241943,
197
+ "learning_rate": 3.648648648648649e-05,
198
+ "loss": 0.2463,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.3584,
203
+ "grad_norm": 3.076375722885132,
204
+ "learning_rate": 3.577524893314367e-05,
205
+ "loss": 0.2827,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.3712,
210
+ "grad_norm": 2.2279860973358154,
211
+ "learning_rate": 3.506401137980085e-05,
212
+ "loss": 0.2331,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.384,
217
+ "grad_norm": 2.4004101753234863,
218
+ "learning_rate": 3.435277382645804e-05,
219
+ "loss": 0.2339,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.3968,
224
+ "grad_norm": 1.4494019746780396,
225
+ "learning_rate": 3.364153627311522e-05,
226
+ "loss": 0.2065,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.4096,
231
+ "grad_norm": 1.3410875797271729,
232
+ "learning_rate": 3.2930298719772407e-05,
233
+ "loss": 0.1922,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.4224,
238
+ "grad_norm": 1.7173815965652466,
239
+ "learning_rate": 3.2219061166429585e-05,
240
+ "loss": 0.2119,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.4352,
245
+ "grad_norm": 1.0749174356460571,
246
+ "learning_rate": 3.150782361308677e-05,
247
+ "loss": 0.1977,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.448,
252
+ "grad_norm": 0.7908509969711304,
253
+ "learning_rate": 3.0796586059743955e-05,
254
+ "loss": 0.1854,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.4608,
259
+ "grad_norm": 1.1467453241348267,
260
+ "learning_rate": 3.008534850640114e-05,
261
+ "loss": 0.1926,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.4736,
266
+ "grad_norm": 1.608503818511963,
267
+ "learning_rate": 2.937411095305832e-05,
268
+ "loss": 0.1781,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.4864,
273
+ "grad_norm": 2.599217653274536,
274
+ "learning_rate": 2.8662873399715508e-05,
275
+ "loss": 0.2127,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.4992,
280
+ "grad_norm": 1.2717839479446411,
281
+ "learning_rate": 2.7951635846372693e-05,
282
+ "loss": 0.168,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.512,
287
+ "grad_norm": 2.1473703384399414,
288
+ "learning_rate": 2.724039829302987e-05,
289
+ "loss": 0.1828,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.5248,
294
+ "grad_norm": 1.7585045099258423,
295
+ "learning_rate": 2.652916073968706e-05,
296
+ "loss": 0.1568,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.5376,
301
+ "grad_norm": 1.8754886388778687,
302
+ "learning_rate": 2.5817923186344238e-05,
303
+ "loss": 0.1705,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.5504,
308
+ "grad_norm": 2.195056438446045,
309
+ "learning_rate": 2.5106685633001427e-05,
310
+ "loss": 0.2045,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.5632,
315
+ "grad_norm": 2.0642194747924805,
316
+ "learning_rate": 2.4395448079658605e-05,
317
+ "loss": 0.1629,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.576,
322
+ "grad_norm": 1.7358914613723755,
323
+ "learning_rate": 2.368421052631579e-05,
324
+ "loss": 0.1558,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.5888,
329
+ "grad_norm": 0.8537180423736572,
330
+ "learning_rate": 2.2972972972972976e-05,
331
+ "loss": 0.1462,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.6016,
336
+ "grad_norm": 2.212674379348755,
337
+ "learning_rate": 2.2261735419630157e-05,
338
+ "loss": 0.1653,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.6144,
343
+ "grad_norm": 2.300081253051758,
344
+ "learning_rate": 2.1550497866287343e-05,
345
+ "loss": 0.144,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.6272,
350
+ "grad_norm": 3.1487064361572266,
351
+ "learning_rate": 2.0839260312944524e-05,
352
+ "loss": 0.1805,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.64,
357
+ "grad_norm": 0.2501735985279083,
358
+ "learning_rate": 2.012802275960171e-05,
359
+ "loss": 0.1401,
360
+ "step": 500
361
+ }
362
+ ],
363
+ "logging_steps": 10,
364
+ "max_steps": 782,
365
+ "num_input_tokens_seen": 0,
366
+ "num_train_epochs": 1,
367
+ "save_steps": 500,
368
+ "stateful_callbacks": {
369
+ "TrainerControl": {
370
+ "args": {
371
+ "should_epoch_stop": false,
372
+ "should_evaluate": false,
373
+ "should_log": false,
374
+ "should_save": true,
375
+ "should_training_stop": false
376
+ },
377
+ "attributes": {}
378
+ }
379
+ },
380
+ "total_flos": 2.479921468932096e+18,
381
+ "train_batch_size": 16,
382
+ "trial_name": null,
383
+ "trial_params": null
384
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73228c9c9b79557db4fdb3eafbe9dbafed6cf81a87b3a5c2708d1adbc4800c7
3
+ size 5304
checkpoint-782/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ViTForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "encoder_stride": 16,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.0,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "airplane",
12
+ "1": "automobile",
13
+ "2": "bird",
14
+ "3": "cat",
15
+ "4": "deer",
16
+ "5": "dog",
17
+ "6": "frog",
18
+ "7": "horse",
19
+ "8": "ship",
20
+ "9": "truck"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "airplane": 0,
27
+ "automobile": 1,
28
+ "bird": 2,
29
+ "cat": 3,
30
+ "deer": 4,
31
+ "dog": 5,
32
+ "frog": 6,
33
+ "horse": 7,
34
+ "ship": 8,
35
+ "truck": 9
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "model_type": "vit",
39
+ "num_attention_heads": 12,
40
+ "num_channels": 3,
41
+ "num_hidden_layers": 12,
42
+ "patch_size": 16,
43
+ "pooler_act": "tanh",
44
+ "pooler_output_size": 768,
45
+ "problem_type": "single_label_classification",
46
+ "qkv_bias": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.52.4"
49
+ }
checkpoint-782/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9045985c6be2c3c895cf371fb5381c583308b4a9c4611af794643f7797add6
3
+ size 343248584
checkpoint-782/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5e8dc3895a8c45a817fbcb41f5ca0843f4e86eb60c8d3137cbc8c525ac3d93a
3
+ size 686618042
checkpoint-782/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
3
+ size 14244
checkpoint-782/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a17869f814f28c1756dc139dba11558dfcf7a75c76da9d35392eb914aee7d2c
3
+ size 1064
checkpoint-782/trainer_state.json ADDED
@@ -0,0 +1,580 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 782,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0128,
14
+ "grad_norm": 1.1307092905044556,
15
+ "learning_rate": 5.69620253164557e-06,
16
+ "loss": 2.3042,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0256,
21
+ "grad_norm": 1.0256341695785522,
22
+ "learning_rate": 1.2025316455696203e-05,
23
+ "loss": 2.2764,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0384,
28
+ "grad_norm": 1.3286596536636353,
29
+ "learning_rate": 1.8354430379746836e-05,
30
+ "loss": 2.2167,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0512,
35
+ "grad_norm": 1.343770146369934,
36
+ "learning_rate": 2.468354430379747e-05,
37
+ "loss": 2.1222,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.064,
42
+ "grad_norm": 1.2992122173309326,
43
+ "learning_rate": 3.10126582278481e-05,
44
+ "loss": 1.9886,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0768,
49
+ "grad_norm": 1.2733649015426636,
50
+ "learning_rate": 3.7341772151898736e-05,
51
+ "loss": 1.8062,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0896,
56
+ "grad_norm": 1.3380931615829468,
57
+ "learning_rate": 4.367088607594937e-05,
58
+ "loss": 1.5562,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.1024,
63
+ "grad_norm": 1.5014597177505493,
64
+ "learning_rate": 5e-05,
65
+ "loss": 1.2747,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1152,
70
+ "grad_norm": 1.443360447883606,
71
+ "learning_rate": 4.928876244665719e-05,
72
+ "loss": 1.0305,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.128,
77
+ "grad_norm": 1.4796088933944702,
78
+ "learning_rate": 4.8577524893314366e-05,
79
+ "loss": 0.8814,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.1408,
84
+ "grad_norm": 1.3090192079544067,
85
+ "learning_rate": 4.786628733997156e-05,
86
+ "loss": 0.7241,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.1536,
91
+ "grad_norm": 1.7807539701461792,
92
+ "learning_rate": 4.7155049786628736e-05,
93
+ "loss": 0.6109,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.1664,
98
+ "grad_norm": 1.611634373664856,
99
+ "learning_rate": 4.644381223328592e-05,
100
+ "loss": 0.5711,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.1792,
105
+ "grad_norm": 2.08296275138855,
106
+ "learning_rate": 4.57325746799431e-05,
107
+ "loss": 0.5387,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.192,
112
+ "grad_norm": 3.6438846588134766,
113
+ "learning_rate": 4.5021337126600285e-05,
114
+ "loss": 0.4422,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.2048,
119
+ "grad_norm": 1.203041672706604,
120
+ "learning_rate": 4.431009957325747e-05,
121
+ "loss": 0.4451,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.2176,
126
+ "grad_norm": 2.097452402114868,
127
+ "learning_rate": 4.3598862019914656e-05,
128
+ "loss": 0.398,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.2304,
133
+ "grad_norm": 1.494523286819458,
134
+ "learning_rate": 4.2887624466571834e-05,
135
+ "loss": 0.3843,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.2432,
140
+ "grad_norm": 1.4821765422821045,
141
+ "learning_rate": 4.217638691322902e-05,
142
+ "loss": 0.3476,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.256,
147
+ "grad_norm": 2.9275362491607666,
148
+ "learning_rate": 4.1465149359886204e-05,
149
+ "loss": 0.3174,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.2688,
154
+ "grad_norm": 1.4172513484954834,
155
+ "learning_rate": 4.075391180654339e-05,
156
+ "loss": 0.3109,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.2816,
161
+ "grad_norm": 1.1657588481903076,
162
+ "learning_rate": 4.004267425320057e-05,
163
+ "loss": 0.3018,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.2944,
168
+ "grad_norm": 1.3319698572158813,
169
+ "learning_rate": 3.933143669985775e-05,
170
+ "loss": 0.2832,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.3072,
175
+ "grad_norm": 2.535245895385742,
176
+ "learning_rate": 3.862019914651494e-05,
177
+ "loss": 0.2797,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.32,
182
+ "grad_norm": 0.751595675945282,
183
+ "learning_rate": 3.7908961593172124e-05,
184
+ "loss": 0.2447,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.3328,
189
+ "grad_norm": 0.8638726472854614,
190
+ "learning_rate": 3.719772403982931e-05,
191
+ "loss": 0.2543,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.3456,
196
+ "grad_norm": 1.3161370754241943,
197
+ "learning_rate": 3.648648648648649e-05,
198
+ "loss": 0.2463,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.3584,
203
+ "grad_norm": 3.076375722885132,
204
+ "learning_rate": 3.577524893314367e-05,
205
+ "loss": 0.2827,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.3712,
210
+ "grad_norm": 2.2279860973358154,
211
+ "learning_rate": 3.506401137980085e-05,
212
+ "loss": 0.2331,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.384,
217
+ "grad_norm": 2.4004101753234863,
218
+ "learning_rate": 3.435277382645804e-05,
219
+ "loss": 0.2339,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.3968,
224
+ "grad_norm": 1.4494019746780396,
225
+ "learning_rate": 3.364153627311522e-05,
226
+ "loss": 0.2065,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.4096,
231
+ "grad_norm": 1.3410875797271729,
232
+ "learning_rate": 3.2930298719772407e-05,
233
+ "loss": 0.1922,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.4224,
238
+ "grad_norm": 1.7173815965652466,
239
+ "learning_rate": 3.2219061166429585e-05,
240
+ "loss": 0.2119,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.4352,
245
+ "grad_norm": 1.0749174356460571,
246
+ "learning_rate": 3.150782361308677e-05,
247
+ "loss": 0.1977,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.448,
252
+ "grad_norm": 0.7908509969711304,
253
+ "learning_rate": 3.0796586059743955e-05,
254
+ "loss": 0.1854,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.4608,
259
+ "grad_norm": 1.1467453241348267,
260
+ "learning_rate": 3.008534850640114e-05,
261
+ "loss": 0.1926,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.4736,
266
+ "grad_norm": 1.608503818511963,
267
+ "learning_rate": 2.937411095305832e-05,
268
+ "loss": 0.1781,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.4864,
273
+ "grad_norm": 2.599217653274536,
274
+ "learning_rate": 2.8662873399715508e-05,
275
+ "loss": 0.2127,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.4992,
280
+ "grad_norm": 1.2717839479446411,
281
+ "learning_rate": 2.7951635846372693e-05,
282
+ "loss": 0.168,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.512,
287
+ "grad_norm": 2.1473703384399414,
288
+ "learning_rate": 2.724039829302987e-05,
289
+ "loss": 0.1828,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.5248,
294
+ "grad_norm": 1.7585045099258423,
295
+ "learning_rate": 2.652916073968706e-05,
296
+ "loss": 0.1568,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.5376,
301
+ "grad_norm": 1.8754886388778687,
302
+ "learning_rate": 2.5817923186344238e-05,
303
+ "loss": 0.1705,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.5504,
308
+ "grad_norm": 2.195056438446045,
309
+ "learning_rate": 2.5106685633001427e-05,
310
+ "loss": 0.2045,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.5632,
315
+ "grad_norm": 2.0642194747924805,
316
+ "learning_rate": 2.4395448079658605e-05,
317
+ "loss": 0.1629,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.576,
322
+ "grad_norm": 1.7358914613723755,
323
+ "learning_rate": 2.368421052631579e-05,
324
+ "loss": 0.1558,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.5888,
329
+ "grad_norm": 0.8537180423736572,
330
+ "learning_rate": 2.2972972972972976e-05,
331
+ "loss": 0.1462,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.6016,
336
+ "grad_norm": 2.212674379348755,
337
+ "learning_rate": 2.2261735419630157e-05,
338
+ "loss": 0.1653,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.6144,
343
+ "grad_norm": 2.300081253051758,
344
+ "learning_rate": 2.1550497866287343e-05,
345
+ "loss": 0.144,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.6272,
350
+ "grad_norm": 3.1487064361572266,
351
+ "learning_rate": 2.0839260312944524e-05,
352
+ "loss": 0.1805,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.64,
357
+ "grad_norm": 0.2501735985279083,
358
+ "learning_rate": 2.012802275960171e-05,
359
+ "loss": 0.1401,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.6528,
364
+ "grad_norm": 1.3786312341690063,
365
+ "learning_rate": 1.941678520625889e-05,
366
+ "loss": 0.1413,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.6656,
371
+ "grad_norm": 1.6031897068023682,
372
+ "learning_rate": 1.8705547652916077e-05,
373
+ "loss": 0.1713,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.6784,
378
+ "grad_norm": 2.491154193878174,
379
+ "learning_rate": 1.799431009957326e-05,
380
+ "loss": 0.1608,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.6912,
385
+ "grad_norm": 0.6285232901573181,
386
+ "learning_rate": 1.728307254623044e-05,
387
+ "loss": 0.167,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.704,
392
+ "grad_norm": 1.172988772392273,
393
+ "learning_rate": 1.6571834992887625e-05,
394
+ "loss": 0.1381,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.7168,
399
+ "grad_norm": 1.201684832572937,
400
+ "learning_rate": 1.5860597439544807e-05,
401
+ "loss": 0.1482,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.7296,
406
+ "grad_norm": 0.21398985385894775,
407
+ "learning_rate": 1.514935988620199e-05,
408
+ "loss": 0.1511,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.7424,
413
+ "grad_norm": 2.8409345149993896,
414
+ "learning_rate": 1.4438122332859174e-05,
415
+ "loss": 0.1473,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.7552,
420
+ "grad_norm": 0.6168693900108337,
421
+ "learning_rate": 1.3726884779516358e-05,
422
+ "loss": 0.1546,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.768,
427
+ "grad_norm": 0.5086041688919067,
428
+ "learning_rate": 1.3015647226173541e-05,
429
+ "loss": 0.117,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.7808,
434
+ "grad_norm": 1.5305429697036743,
435
+ "learning_rate": 1.2304409672830727e-05,
436
+ "loss": 0.1153,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.7936,
441
+ "grad_norm": 2.4478514194488525,
442
+ "learning_rate": 1.159317211948791e-05,
443
+ "loss": 0.1218,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.8064,
448
+ "grad_norm": 0.5004878640174866,
449
+ "learning_rate": 1.0881934566145092e-05,
450
+ "loss": 0.1251,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.8192,
455
+ "grad_norm": 1.8452993631362915,
456
+ "learning_rate": 1.0170697012802275e-05,
457
+ "loss": 0.1262,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.832,
462
+ "grad_norm": 0.27904263138771057,
463
+ "learning_rate": 9.45945945945946e-06,
464
+ "loss": 0.117,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.8448,
469
+ "grad_norm": 3.8056581020355225,
470
+ "learning_rate": 8.748221906116644e-06,
471
+ "loss": 0.1365,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.8576,
476
+ "grad_norm": 0.2850014567375183,
477
+ "learning_rate": 8.036984352773828e-06,
478
+ "loss": 0.1282,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.8704,
483
+ "grad_norm": 0.9787055850028992,
484
+ "learning_rate": 7.32574679943101e-06,
485
+ "loss": 0.1233,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.8832,
490
+ "grad_norm": 1.6102838516235352,
491
+ "learning_rate": 6.614509246088194e-06,
492
+ "loss": 0.1556,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.896,
497
+ "grad_norm": 3.462890386581421,
498
+ "learning_rate": 5.903271692745377e-06,
499
+ "loss": 0.1408,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.9088,
504
+ "grad_norm": 0.9203911423683167,
505
+ "learning_rate": 5.192034139402561e-06,
506
+ "loss": 0.1092,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.9216,
511
+ "grad_norm": 1.5195368528366089,
512
+ "learning_rate": 4.480796586059744e-06,
513
+ "loss": 0.1297,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.9344,
518
+ "grad_norm": 0.3575367331504822,
519
+ "learning_rate": 3.7695590327169273e-06,
520
+ "loss": 0.1205,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.9472,
525
+ "grad_norm": 0.2838120460510254,
526
+ "learning_rate": 3.058321479374111e-06,
527
+ "loss": 0.1125,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.96,
532
+ "grad_norm": 0.9937814474105835,
533
+ "learning_rate": 2.3470839260312948e-06,
534
+ "loss": 0.1301,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.9728,
539
+ "grad_norm": 1.7535674571990967,
540
+ "learning_rate": 1.6358463726884779e-06,
541
+ "loss": 0.1293,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.9856,
546
+ "grad_norm": 0.32280606031417847,
547
+ "learning_rate": 9.246088193456616e-07,
548
+ "loss": 0.1126,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.9984,
553
+ "grad_norm": 1.821584939956665,
554
+ "learning_rate": 2.1337126600284497e-07,
555
+ "loss": 0.1106,
556
+ "step": 780
557
+ }
558
+ ],
559
+ "logging_steps": 10,
560
+ "max_steps": 782,
561
+ "num_input_tokens_seen": 0,
562
+ "num_train_epochs": 1,
563
+ "save_steps": 500,
564
+ "stateful_callbacks": {
565
+ "TrainerControl": {
566
+ "args": {
567
+ "should_epoch_stop": false,
568
+ "should_evaluate": false,
569
+ "should_log": false,
570
+ "should_save": true,
571
+ "should_training_stop": true
572
+ },
573
+ "attributes": {}
574
+ }
575
+ },
576
+ "total_flos": 3.8748772952064e+18,
577
+ "train_batch_size": 16,
578
+ "trial_name": null,
579
+ "trial_params": null
580
+ }
checkpoint-782/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73228c9c9b79557db4fdb3eafbe9dbafed6cf81a87b3a5c2708d1adbc4800c7
3
+ size 5304
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }