fxwang commited on
Commit
b1ea9e5
1 Parent(s): e8f2ab1

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +22 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +441 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-base-patch32",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 512,
10
+ "text_config": {
11
+ "bos_token_id": 0,
12
+ "dropout": 0.0,
13
+ "eos_token_id": 2,
14
+ "model_type": "clip_text_model"
15
+ },
16
+ "torch_dtype": "float32",
17
+ "transformers_version": "4.36.2",
18
+ "vision_config": {
19
+ "dropout": 0.0,
20
+ "model_type": "clip_vision_model"
21
+ }
22
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df32edcf9a76b7d2ac2936bcce5e2f2ca1ccb9f0ca675b5c2d86b6882a85caba
3
+ size 605156676
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a76e83cda632b71887ada13ea516dd7e37f167c33af892e089e938778b1cce
3
+ size 1210551612
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70f9d0090172bbb9c1d52483acd239cbffb274e74b320c4ab6d283972210b740
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76582beb49f9a4a4794e0830d49935c660c227cfaa6e5bb4096530bdf00d5b4a
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.7073170731707317,
5
+ "eval_steps": 500,
6
+ "global_step": 70,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 4.9995000000000005e-05,
14
+ "loss": 1.5986,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 4.999e-05,
20
+ "loss": 2.5591,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "learning_rate": 4.9985e-05,
26
+ "loss": 1.8778,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "learning_rate": 4.9980000000000006e-05,
32
+ "loss": 2.6038,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.12,
37
+ "learning_rate": 4.9975e-05,
38
+ "loss": 1.7417,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.15,
43
+ "learning_rate": 4.997e-05,
44
+ "loss": 1.6722,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.17,
49
+ "learning_rate": 4.9965e-05,
50
+ "loss": 1.4006,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.2,
55
+ "learning_rate": 4.996e-05,
56
+ "loss": 1.2633,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.22,
61
+ "learning_rate": 4.9955e-05,
62
+ "loss": 1.1828,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.24,
67
+ "learning_rate": 4.995e-05,
68
+ "loss": 1.0802,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.27,
73
+ "learning_rate": 4.9945000000000004e-05,
74
+ "loss": 0.9983,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.29,
79
+ "learning_rate": 4.9940000000000006e-05,
80
+ "loss": 1.0225,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.32,
85
+ "learning_rate": 4.9935e-05,
86
+ "loss": 0.996,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.34,
91
+ "learning_rate": 4.9930000000000005e-05,
92
+ "loss": 0.9677,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.37,
97
+ "learning_rate": 4.992500000000001e-05,
98
+ "loss": 0.8863,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.39,
103
+ "learning_rate": 4.992e-05,
104
+ "loss": 0.925,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.41,
109
+ "learning_rate": 4.9915e-05,
110
+ "loss": 0.8541,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.44,
115
+ "learning_rate": 4.991e-05,
116
+ "loss": 0.8547,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.46,
121
+ "learning_rate": 4.9905000000000004e-05,
122
+ "loss": 0.8159,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.49,
127
+ "learning_rate": 4.99e-05,
128
+ "loss": 0.8186,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.51,
133
+ "learning_rate": 4.9895e-05,
134
+ "loss": 0.7936,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.54,
139
+ "learning_rate": 4.9890000000000005e-05,
140
+ "loss": 0.792,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.56,
145
+ "learning_rate": 4.9885e-05,
146
+ "loss": 0.7438,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.59,
151
+ "learning_rate": 4.9880000000000004e-05,
152
+ "loss": 0.7641,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.61,
157
+ "learning_rate": 4.9875000000000006e-05,
158
+ "loss": 0.7644,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.63,
163
+ "learning_rate": 4.987e-05,
164
+ "loss": 0.7188,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.66,
169
+ "learning_rate": 4.9865e-05,
170
+ "loss": 0.7475,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.68,
175
+ "learning_rate": 4.986e-05,
176
+ "loss": 0.729,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.71,
181
+ "learning_rate": 4.9855e-05,
182
+ "loss": 0.719,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.73,
187
+ "learning_rate": 4.9850000000000006e-05,
188
+ "loss": 0.69,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.76,
193
+ "learning_rate": 4.9845e-05,
194
+ "loss": 0.6842,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.78,
199
+ "learning_rate": 4.9840000000000004e-05,
200
+ "loss": 0.7492,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.8,
205
+ "learning_rate": 4.9835000000000007e-05,
206
+ "loss": 0.697,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.83,
211
+ "learning_rate": 4.983e-05,
212
+ "loss": 0.6985,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.85,
217
+ "learning_rate": 4.9825000000000005e-05,
218
+ "loss": 0.6432,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.88,
223
+ "learning_rate": 4.982e-05,
224
+ "loss": 0.6493,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.9,
229
+ "learning_rate": 4.9815e-05,
230
+ "loss": 0.6856,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.93,
235
+ "learning_rate": 4.981e-05,
236
+ "loss": 0.6806,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.95,
241
+ "learning_rate": 4.9805e-05,
242
+ "loss": 0.6369,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.98,
247
+ "learning_rate": 4.9800000000000004e-05,
248
+ "loss": 0.612,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 1.0,
253
+ "learning_rate": 4.9795e-05,
254
+ "loss": 0.4179,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 1.02,
259
+ "learning_rate": 4.979e-05,
260
+ "loss": 0.3876,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 1.05,
265
+ "learning_rate": 4.9785000000000005e-05,
266
+ "loss": 0.3741,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 1.07,
271
+ "learning_rate": 4.978e-05,
272
+ "loss": 0.3549,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 1.1,
277
+ "learning_rate": 4.9775000000000004e-05,
278
+ "loss": 0.3766,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 1.12,
283
+ "learning_rate": 4.977e-05,
284
+ "loss": 0.3832,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 1.15,
289
+ "learning_rate": 4.9765e-05,
290
+ "loss": 0.3699,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 1.17,
295
+ "learning_rate": 4.976e-05,
296
+ "loss": 0.3682,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 1.2,
301
+ "learning_rate": 4.9755e-05,
302
+ "loss": 0.4074,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 1.22,
307
+ "learning_rate": 4.975e-05,
308
+ "loss": 0.3591,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 1.24,
313
+ "learning_rate": 4.9745000000000006e-05,
314
+ "loss": 0.3841,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 1.27,
319
+ "learning_rate": 4.974e-05,
320
+ "loss": 0.376,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 1.29,
325
+ "learning_rate": 4.9735000000000004e-05,
326
+ "loss": 0.4079,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 1.32,
331
+ "learning_rate": 4.973000000000001e-05,
332
+ "loss": 0.3882,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 1.34,
337
+ "learning_rate": 4.9725e-05,
338
+ "loss": 0.3948,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 1.37,
343
+ "learning_rate": 4.972e-05,
344
+ "loss": 0.4103,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 1.39,
349
+ "learning_rate": 4.9715e-05,
350
+ "loss": 0.4097,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 1.41,
355
+ "learning_rate": 4.9710000000000003e-05,
356
+ "loss": 0.3772,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 1.44,
361
+ "learning_rate": 4.9705e-05,
362
+ "loss": 0.402,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 1.46,
367
+ "learning_rate": 4.97e-05,
368
+ "loss": 0.386,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 1.49,
373
+ "learning_rate": 4.9695000000000004e-05,
374
+ "loss": 0.3865,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 1.51,
379
+ "learning_rate": 4.969e-05,
380
+ "loss": 0.4051,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 1.54,
385
+ "learning_rate": 4.9685e-05,
386
+ "loss": 0.4221,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 1.56,
391
+ "learning_rate": 4.9680000000000005e-05,
392
+ "loss": 0.4148,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 1.59,
397
+ "learning_rate": 4.967500000000001e-05,
398
+ "loss": 0.3827,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 1.61,
403
+ "learning_rate": 4.967e-05,
404
+ "loss": 0.4125,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 1.63,
409
+ "learning_rate": 4.9665e-05,
410
+ "loss": 0.3854,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 1.66,
415
+ "learning_rate": 4.966e-05,
416
+ "loss": 0.3953,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 1.68,
421
+ "learning_rate": 4.9655000000000005e-05,
422
+ "loss": 0.3818,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 1.71,
427
+ "learning_rate": 4.965e-05,
428
+ "loss": 0.3764,
429
+ "step": 70
430
+ }
431
+ ],
432
+ "logging_steps": 1,
433
+ "max_steps": 10000,
434
+ "num_input_tokens_seen": 0,
435
+ "num_train_epochs": 244,
436
+ "save_steps": 10,
437
+ "total_flos": 1.1687420870583696e+16,
438
+ "train_batch_size": 3584,
439
+ "trial_name": null,
440
+ "trial_params": null
441
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd267734380b181e34dfef34e0ee3300fd8441ca7d8784e4a2c5e660587fddb
3
+ size 4664