aixk commited on
Commit
58c3a02
·
verified ·
1 Parent(s): e162804

Upload folder using huggingface_hub

Browse files
checkpoint-1600/config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FastHyperNet125mForCausalLM"
4
+ ],
5
+ "dtype": "float32",
6
+ "hidden_size": 768,
7
+ "hyperbolic_dim": 16,
8
+ "initializer_range": 0.02,
9
+ "intermediate_size": 2048,
10
+ "max_position_embeddings": 512,
11
+ "model_type": "fasthypernet_125m_tagless",
12
+ "num_attention_heads": 12,
13
+ "num_hidden_layers": 16,
14
+ "transformers_version": "5.13.1",
15
+ "use_cache": false,
16
+ "vocab_size": 8192
17
+ }
checkpoint-1600/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.13.1"
6
+ }
checkpoint-1600/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6cdca5df66791409d1e647c7f799b54fd5828b80f2eaf1fd6d4c260a44ec55
3
+ size 501759848
checkpoint-1600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb8aa232cf025021565bd028bd4c1b5aac9f50a71f35e82f0e4bc74e817afb2
3
+ size 254410983
checkpoint-1600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc03cfd5000f3b6a13e6e8bbf70ae721c704631b24ca356a809d2ae8ed40da20
3
+ size 14645
checkpoint-1600/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efef99b5aba611808d39370947b72711b21c379c65127ed9170c970e09f961fe
3
+ size 1383
checkpoint-1600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f8939e4727b27d73cadd8b5252c33ae643c7627104c9ae668340c0da984d03
3
+ size 1465
checkpoint-1600/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "HFCompatibleHybridTokenizer",
3
+ "vocab_size": 8192,
4
+ "model_max_length": 512,
5
+ "bos_token": "<bos>",
6
+ "eos_token": "<eos>",
7
+ "unk_token": "<unk>",
8
+ "pad_token": "<pad>"
9
+ }
checkpoint-1600/trainer_state.json ADDED
@@ -0,0 +1,1154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9845775162493751,
6
+ "eval_steps": 500,
7
+ "global_step": 1600,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.006153609476558594,
14
+ "grad_norm": 25468.8046875,
15
+ "learning_rate": 1.9999999999999996e-07,
16
+ "loss": 8.7082,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.012307218953117188,
21
+ "grad_norm": 1228.4501953125,
22
+ "learning_rate": 1.2e-06,
23
+ "loss": 8.0776,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.018460828429675783,
28
+ "grad_norm": 355.1081237792969,
29
+ "learning_rate": 2.1999999999999997e-06,
30
+ "loss": 7.2372,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.024614437906234375,
35
+ "grad_norm": 255.58433532714844,
36
+ "learning_rate": 3.1999999999999994e-06,
37
+ "loss": 6.9725,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.03076804738279297,
42
+ "grad_norm": 253.23995971679688,
43
+ "learning_rate": 4.2e-06,
44
+ "loss": 6.8585,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.036921656859351566,
49
+ "grad_norm": 241.82064819335938,
50
+ "learning_rate": 5.199999999999999e-06,
51
+ "loss": 6.7367,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.043075266335910155,
56
+ "grad_norm": 229.0261993408203,
57
+ "learning_rate": 6.199999999999999e-06,
58
+ "loss": 6.6534,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.04922887581246875,
63
+ "grad_norm": 321.6871337890625,
64
+ "learning_rate": 7.2e-06,
65
+ "loss": 6.6305,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.055382485289027346,
70
+ "grad_norm": 465.00543212890625,
71
+ "learning_rate": 8.2e-06,
72
+ "loss": 6.6253,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.06153609476558594,
77
+ "grad_norm": 566.6929321289062,
78
+ "learning_rate": 9.199999999999998e-06,
79
+ "loss": 6.5724,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.06768970424214453,
84
+ "grad_norm": 432.230712890625,
85
+ "learning_rate": 1.02e-05,
86
+ "loss": 6.5328,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.07384331371870313,
91
+ "grad_norm": 289.2374267578125,
92
+ "learning_rate": 1.12e-05,
93
+ "loss": 6.5547,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.07999692319526172,
98
+ "grad_norm": 595.7386474609375,
99
+ "learning_rate": 1.2199999999999998e-05,
100
+ "loss": 6.5651,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.08615053267182031,
105
+ "grad_norm": 861.4376220703125,
106
+ "learning_rate": 1.3199999999999997e-05,
107
+ "loss": 6.5337,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.09230414214837891,
112
+ "grad_norm": 689.42919921875,
113
+ "learning_rate": 1.4199999999999998e-05,
114
+ "loss": 6.4927,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.0984577516249375,
119
+ "grad_norm": 380.9496765136719,
120
+ "learning_rate": 1.5199999999999998e-05,
121
+ "loss": 6.4812,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.1046113611014961,
126
+ "grad_norm": 221.21005249023438,
127
+ "learning_rate": 1.6199999999999997e-05,
128
+ "loss": 6.4508,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.11076497057805469,
133
+ "grad_norm": 199.30874633789062,
134
+ "learning_rate": 1.7199999999999998e-05,
135
+ "loss": 6.4642,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.11691858005461328,
140
+ "grad_norm": 252.44459533691406,
141
+ "learning_rate": 1.82e-05,
142
+ "loss": 6.45,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.12307218953117188,
147
+ "grad_norm": 121.32320404052734,
148
+ "learning_rate": 1.92e-05,
149
+ "loss": 6.4115,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.12922579900773049,
154
+ "grad_norm": 207.04344177246094,
155
+ "learning_rate": 2.0199999999999996e-05,
156
+ "loss": 6.4532,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.13537940848428906,
161
+ "grad_norm": 296.6274719238281,
162
+ "learning_rate": 2.12e-05,
163
+ "loss": 6.3985,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.14153301796084766,
168
+ "grad_norm": 140.3836212158203,
169
+ "learning_rate": 2.2199999999999998e-05,
170
+ "loss": 6.4152,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.14768662743740626,
175
+ "grad_norm": 168.14443969726562,
176
+ "learning_rate": 2.3199999999999998e-05,
177
+ "loss": 6.3686,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.15384023691396484,
182
+ "grad_norm": 141.07810974121094,
183
+ "learning_rate": 2.42e-05,
184
+ "loss": 6.3809,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.15999384639052344,
189
+ "grad_norm": 117.08052062988281,
190
+ "learning_rate": 2.52e-05,
191
+ "loss": 6.3423,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.16614745586708204,
196
+ "grad_norm": 122.97789764404297,
197
+ "learning_rate": 2.6199999999999996e-05,
198
+ "loss": 6.3486,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.17230106534364062,
203
+ "grad_norm": 73.85701751708984,
204
+ "learning_rate": 2.72e-05,
205
+ "loss": 6.329,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.17845467482019922,
210
+ "grad_norm": 78.00408935546875,
211
+ "learning_rate": 2.8199999999999998e-05,
212
+ "loss": 6.3096,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.18460828429675782,
217
+ "grad_norm": 150.3341827392578,
218
+ "learning_rate": 2.9199999999999995e-05,
219
+ "loss": 6.3063,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.1907618937733164,
224
+ "grad_norm": 61.75702667236328,
225
+ "learning_rate": 3.02e-05,
226
+ "loss": 6.3004,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.196915503249875,
231
+ "grad_norm": 83.836181640625,
232
+ "learning_rate": 3.119999999999999e-05,
233
+ "loss": 6.2534,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.2030691127264336,
238
+ "grad_norm": 190.2839813232422,
239
+ "learning_rate": 3.22e-05,
240
+ "loss": 6.2603,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.2092227222029922,
245
+ "grad_norm": 52.196563720703125,
246
+ "learning_rate": 3.3199999999999994e-05,
247
+ "loss": 6.2439,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.21537633167955078,
252
+ "grad_norm": 65.71736907958984,
253
+ "learning_rate": 3.42e-05,
254
+ "loss": 6.227,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.22152994115610938,
259
+ "grad_norm": 66.71468353271484,
260
+ "learning_rate": 3.5199999999999995e-05,
261
+ "loss": 6.2164,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.22768355063266799,
266
+ "grad_norm": 37.26243209838867,
267
+ "learning_rate": 3.62e-05,
268
+ "loss": 6.212,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.23383716010922656,
273
+ "grad_norm": 190.98501586914062,
274
+ "learning_rate": 3.7199999999999996e-05,
275
+ "loss": 6.1833,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.23999076958578516,
280
+ "grad_norm": 51.51064682006836,
281
+ "learning_rate": 3.8199999999999993e-05,
282
+ "loss": 6.1796,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.24614437906234377,
287
+ "grad_norm": 71.14685821533203,
288
+ "learning_rate": 3.919999999999999e-05,
289
+ "loss": 6.1614,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.25229798853890234,
294
+ "grad_norm": 47.48910140991211,
295
+ "learning_rate": 4.02e-05,
296
+ "loss": 6.1277,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.25845159801546097,
301
+ "grad_norm": 49.60618209838867,
302
+ "learning_rate": 4.12e-05,
303
+ "loss": 6.107,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.26460520749201955,
308
+ "grad_norm": 38.03694534301758,
309
+ "learning_rate": 4.2199999999999996e-05,
310
+ "loss": 6.0939,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.2707588169685781,
315
+ "grad_norm": 38.81101989746094,
316
+ "learning_rate": 4.319999999999999e-05,
317
+ "loss": 6.118,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.27691242644513675,
322
+ "grad_norm": 45.36625671386719,
323
+ "learning_rate": 4.42e-05,
324
+ "loss": 6.0641,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.2830660359216953,
329
+ "grad_norm": 44.09037780761719,
330
+ "learning_rate": 4.5199999999999994e-05,
331
+ "loss": 6.0417,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.2892196453982539,
336
+ "grad_norm": 39.48929214477539,
337
+ "learning_rate": 4.62e-05,
338
+ "loss": 6.0371,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.29537325487481253,
343
+ "grad_norm": 44.747039794921875,
344
+ "learning_rate": 4.7199999999999995e-05,
345
+ "loss": 6.0157,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.3015268643513711,
350
+ "grad_norm": 51.372249603271484,
351
+ "learning_rate": 4.82e-05,
352
+ "loss": 6.0378,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.3076804738279297,
357
+ "grad_norm": 46.31863021850586,
358
+ "learning_rate": 4.9199999999999997e-05,
359
+ "loss": 5.9815,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.3138340833044883,
364
+ "grad_norm": 74.35610961914062,
365
+ "learning_rate": 5.0199999999999994e-05,
366
+ "loss": 6.0108,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.3199876927810469,
371
+ "grad_norm": 31.986116409301758,
372
+ "learning_rate": 5.119999999999999e-05,
373
+ "loss": 5.9452,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.32614130225760546,
378
+ "grad_norm": 62.82748794555664,
379
+ "learning_rate": 5.2199999999999995e-05,
380
+ "loss": 5.9396,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.3322949117341641,
385
+ "grad_norm": 36.623085021972656,
386
+ "learning_rate": 5.32e-05,
387
+ "loss": 5.9078,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.33844852121072266,
392
+ "grad_norm": 66.77005004882812,
393
+ "learning_rate": 5.4199999999999996e-05,
394
+ "loss": 5.9127,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.34460213068728124,
399
+ "grad_norm": 42.2696533203125,
400
+ "learning_rate": 5.519999999999999e-05,
401
+ "loss": 5.8751,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.35075574016383987,
406
+ "grad_norm": 36.03275680541992,
407
+ "learning_rate": 5.619999999999999e-05,
408
+ "loss": 5.8704,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.35690934964039844,
413
+ "grad_norm": 34.99599838256836,
414
+ "learning_rate": 5.72e-05,
415
+ "loss": 5.8357,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.363062959116957,
420
+ "grad_norm": 37.03520584106445,
421
+ "learning_rate": 5.82e-05,
422
+ "loss": 5.8248,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.36921656859351565,
427
+ "grad_norm": 39.70176696777344,
428
+ "learning_rate": 5.9199999999999996e-05,
429
+ "loss": 5.782,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.3753701780700742,
434
+ "grad_norm": 39.41380310058594,
435
+ "learning_rate": 6.019999999999999e-05,
436
+ "loss": 5.7875,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.3815237875466328,
441
+ "grad_norm": 36.758148193359375,
442
+ "learning_rate": 6.12e-05,
443
+ "loss": 5.7705,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.38767739702319143,
448
+ "grad_norm": 47.42232894897461,
449
+ "learning_rate": 6.22e-05,
450
+ "loss": 5.7891,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.39383100649975,
455
+ "grad_norm": 41.998783111572266,
456
+ "learning_rate": 6.319999999999999e-05,
457
+ "loss": 5.735,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.3999846159763086,
462
+ "grad_norm": 35.05141830444336,
463
+ "learning_rate": 6.419999999999999e-05,
464
+ "loss": 5.7239,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.4061382254528672,
469
+ "grad_norm": 38.990840911865234,
470
+ "learning_rate": 6.519999999999999e-05,
471
+ "loss": 5.7106,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.4122918349294258,
476
+ "grad_norm": 38.231101989746094,
477
+ "learning_rate": 6.62e-05,
478
+ "loss": 5.6812,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.4184454444059844,
483
+ "grad_norm": 35.416473388671875,
484
+ "learning_rate": 6.72e-05,
485
+ "loss": 5.6728,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.424599053882543,
490
+ "grad_norm": 45.61351776123047,
491
+ "learning_rate": 6.819999999999999e-05,
492
+ "loss": 5.6484,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.43075266335910156,
497
+ "grad_norm": 41.97138595581055,
498
+ "learning_rate": 6.919999999999999e-05,
499
+ "loss": 5.6279,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.4369062728356602,
504
+ "grad_norm": 35.231204986572266,
505
+ "learning_rate": 7.02e-05,
506
+ "loss": 5.6131,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.44305988231221877,
511
+ "grad_norm": 43.76620864868164,
512
+ "learning_rate": 7.12e-05,
513
+ "loss": 5.576,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.44921349178877734,
518
+ "grad_norm": 34.20133972167969,
519
+ "learning_rate": 7.219999999999999e-05,
520
+ "loss": 5.5689,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.45536710126533597,
525
+ "grad_norm": 37.153480529785156,
526
+ "learning_rate": 7.319999999999999e-05,
527
+ "loss": 5.5499,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.46152071074189455,
532
+ "grad_norm": 55.655784606933594,
533
+ "learning_rate": 7.419999999999999e-05,
534
+ "loss": 5.5353,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.4676743202184531,
539
+ "grad_norm": 33.66733169555664,
540
+ "learning_rate": 7.519999999999998e-05,
541
+ "loss": 5.5018,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.47382792969501175,
546
+ "grad_norm": 33.522857666015625,
547
+ "learning_rate": 7.62e-05,
548
+ "loss": 5.483,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.4799815391715703,
553
+ "grad_norm": 35.31947326660156,
554
+ "learning_rate": 7.72e-05,
555
+ "loss": 5.4719,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.4861351486481289,
560
+ "grad_norm": 34.84073257446289,
561
+ "learning_rate": 7.819999999999999e-05,
562
+ "loss": 5.4676,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.49228875812468753,
567
+ "grad_norm": 31.39910316467285,
568
+ "learning_rate": 7.92e-05,
569
+ "loss": 5.4421,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.4984423676012461,
574
+ "grad_norm": 33.14794158935547,
575
+ "learning_rate": 8.019999999999998e-05,
576
+ "loss": 5.3994,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.5045959770778047,
581
+ "grad_norm": 36.15346145629883,
582
+ "learning_rate": 8.12e-05,
583
+ "loss": 5.3823,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.5107495865543633,
588
+ "grad_norm": 32.183895111083984,
589
+ "learning_rate": 8.22e-05,
590
+ "loss": 5.3428,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.5169031960309219,
595
+ "grad_norm": 32.388916015625,
596
+ "learning_rate": 8.319999999999999e-05,
597
+ "loss": 5.3514,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.5230568055074805,
602
+ "grad_norm": 31.176891326904297,
603
+ "learning_rate": 8.42e-05,
604
+ "loss": 5.3256,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.5292104149840391,
609
+ "grad_norm": 33.613014221191406,
610
+ "learning_rate": 8.519999999999998e-05,
611
+ "loss": 5.3117,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.5353640244605977,
616
+ "grad_norm": 30.59576416015625,
617
+ "learning_rate": 8.62e-05,
618
+ "loss": 5.2776,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.5415176339371562,
623
+ "grad_norm": 34.864505767822266,
624
+ "learning_rate": 8.719999999999999e-05,
625
+ "loss": 5.2651,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.5476712434137149,
630
+ "grad_norm": 33.03851318359375,
631
+ "learning_rate": 8.819999999999999e-05,
632
+ "loss": 5.2467,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.5538248528902735,
637
+ "grad_norm": 36.94324493408203,
638
+ "learning_rate": 8.92e-05,
639
+ "loss": 5.2287,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.559978462366832,
644
+ "grad_norm": 32.03374481201172,
645
+ "learning_rate": 9.02e-05,
646
+ "loss": 5.197,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.5661320718433906,
651
+ "grad_norm": 31.21794891357422,
652
+ "learning_rate": 9.12e-05,
653
+ "loss": 5.1565,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.5722856813199493,
658
+ "grad_norm": 29.664560317993164,
659
+ "learning_rate": 9.219999999999999e-05,
660
+ "loss": 5.1325,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.5784392907965078,
665
+ "grad_norm": 29.547014236450195,
666
+ "learning_rate": 9.319999999999999e-05,
667
+ "loss": 5.1322,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.5845929002730664,
672
+ "grad_norm": 30.9229679107666,
673
+ "learning_rate": 9.419999999999999e-05,
674
+ "loss": 5.1176,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.5907465097496251,
679
+ "grad_norm": 32.148712158203125,
680
+ "learning_rate": 9.52e-05,
681
+ "loss": 5.0631,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.5969001192261836,
686
+ "grad_norm": 30.888355255126953,
687
+ "learning_rate": 9.62e-05,
688
+ "loss": 5.0937,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.6030537287027422,
693
+ "grad_norm": 37.31905746459961,
694
+ "learning_rate": 9.719999999999999e-05,
695
+ "loss": 5.0572,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.6092073381793008,
700
+ "grad_norm": 27.809349060058594,
701
+ "learning_rate": 9.819999999999999e-05,
702
+ "loss": 5.0144,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.6153609476558594,
707
+ "grad_norm": 34.41085433959961,
708
+ "learning_rate": 9.919999999999999e-05,
709
+ "loss": 5.0256,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.621514557132418,
714
+ "grad_norm": 29.413028717041016,
715
+ "learning_rate": 0.0001002,
716
+ "loss": 4.9648,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.6276681666089766,
721
+ "grad_norm": 30.73712158203125,
722
+ "learning_rate": 0.0001012,
723
+ "loss": 4.9744,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.6338217760855351,
728
+ "grad_norm": 30.328628540039062,
729
+ "learning_rate": 0.00010219999999999999,
730
+ "loss": 4.9165,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.6399753855620938,
735
+ "grad_norm": 29.132736206054688,
736
+ "learning_rate": 0.00010319999999999999,
737
+ "loss": 4.9574,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.6461289950386524,
742
+ "grad_norm": 28.395519256591797,
743
+ "learning_rate": 0.00010419999999999998,
744
+ "loss": 4.8759,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.6522826045152109,
749
+ "grad_norm": 26.395824432373047,
750
+ "learning_rate": 0.0001052,
751
+ "loss": 4.9002,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.6584362139917695,
756
+ "grad_norm": 27.33197593688965,
757
+ "learning_rate": 0.00010619999999999998,
758
+ "loss": 4.8743,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.6645898234683282,
763
+ "grad_norm": 25.773096084594727,
764
+ "learning_rate": 0.00010719999999999999,
765
+ "loss": 4.8093,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.6707434329448867,
770
+ "grad_norm": 27.487308502197266,
771
+ "learning_rate": 0.0001082,
772
+ "loss": 4.8178,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.6768970424214453,
777
+ "grad_norm": 26.95354652404785,
778
+ "learning_rate": 0.00010919999999999998,
779
+ "loss": 4.7463,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.683050651898004,
784
+ "grad_norm": 30.955183029174805,
785
+ "learning_rate": 0.0001102,
786
+ "loss": 4.7438,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.6892042613745625,
791
+ "grad_norm": 29.22182846069336,
792
+ "learning_rate": 0.00011119999999999998,
793
+ "loss": 4.739,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.6953578708511211,
798
+ "grad_norm": 25.642513275146484,
799
+ "learning_rate": 0.00011219999999999999,
800
+ "loss": 4.6881,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.7015114803276797,
805
+ "grad_norm": 28.86591148376465,
806
+ "learning_rate": 0.0001132,
807
+ "loss": 4.6853,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.7076650898042383,
812
+ "grad_norm": 28.62666130065918,
813
+ "learning_rate": 0.00011419999999999998,
814
+ "loss": 4.6572,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.7138186992807969,
819
+ "grad_norm": 27.118507385253906,
820
+ "learning_rate": 0.0001152,
821
+ "loss": 4.6118,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.7199723087573555,
826
+ "grad_norm": 28.83325958251953,
827
+ "learning_rate": 0.00011619999999999998,
828
+ "loss": 4.6325,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.726125918233914,
833
+ "grad_norm": 27.323766708374023,
834
+ "learning_rate": 0.00011719999999999999,
835
+ "loss": 4.5598,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.7322795277104727,
840
+ "grad_norm": 28.03806495666504,
841
+ "learning_rate": 0.0001182,
842
+ "loss": 4.5404,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.7384331371870313,
847
+ "grad_norm": 30.81092071533203,
848
+ "learning_rate": 0.00011919999999999998,
849
+ "loss": 4.5604,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.7445867466635898,
854
+ "grad_norm": 26.44489288330078,
855
+ "learning_rate": 0.0001202,
856
+ "loss": 4.5447,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.7507403561401484,
861
+ "grad_norm": 27.878007888793945,
862
+ "learning_rate": 0.00012119999999999999,
863
+ "loss": 4.5259,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.7568939656167071,
868
+ "grad_norm": 29.378477096557617,
869
+ "learning_rate": 0.0001222,
870
+ "loss": 4.4411,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.7630475750932656,
875
+ "grad_norm": 25.017864227294922,
876
+ "learning_rate": 0.00012319999999999999,
877
+ "loss": 4.4634,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.7692011845698242,
882
+ "grad_norm": 26.963115692138672,
883
+ "learning_rate": 0.00012419999999999998,
884
+ "loss": 4.4299,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.7753547940463829,
889
+ "grad_norm": 28.014739990234375,
890
+ "learning_rate": 0.00012519999999999998,
891
+ "loss": 4.4148,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.7815084035229414,
896
+ "grad_norm": 27.028656005859375,
897
+ "learning_rate": 0.0001262,
898
+ "loss": 4.4078,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.7876620129995,
903
+ "grad_norm": 28.67365264892578,
904
+ "learning_rate": 0.00012719999999999997,
905
+ "loss": 4.3355,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.7938156224760586,
910
+ "grad_norm": 26.66254997253418,
911
+ "learning_rate": 0.0001282,
912
+ "loss": 4.3166,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.7999692319526172,
917
+ "grad_norm": 27.120641708374023,
918
+ "learning_rate": 0.00012919999999999997,
919
+ "loss": 4.2582,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.8061228414291758,
924
+ "grad_norm": 24.28302001953125,
925
+ "learning_rate": 0.0001302,
926
+ "loss": 4.2967,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.8122764509057344,
931
+ "grad_norm": 27.492734909057617,
932
+ "learning_rate": 0.0001312,
933
+ "loss": 4.263,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.8184300603822929,
938
+ "grad_norm": 22.861173629760742,
939
+ "learning_rate": 0.0001322,
940
+ "loss": 4.2387,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.8245836698588516,
945
+ "grad_norm": 24.373743057250977,
946
+ "learning_rate": 0.00013319999999999999,
947
+ "loss": 4.2242,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.8307372793354102,
952
+ "grad_norm": 28.591249465942383,
953
+ "learning_rate": 0.0001342,
954
+ "loss": 4.1666,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.8368908888119688,
959
+ "grad_norm": 24.015104293823242,
960
+ "learning_rate": 0.00013519999999999998,
961
+ "loss": 4.1729,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.8430444982885273,
966
+ "grad_norm": 28.374052047729492,
967
+ "learning_rate": 0.0001362,
968
+ "loss": 4.1558,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.849198107765086,
973
+ "grad_norm": 24.058826446533203,
974
+ "learning_rate": 0.00013719999999999997,
975
+ "loss": 4.086,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.8553517172416446,
980
+ "grad_norm": 24.95467185974121,
981
+ "learning_rate": 0.0001382,
982
+ "loss": 4.0687,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.8615053267182031,
987
+ "grad_norm": 26.37350082397461,
988
+ "learning_rate": 0.0001392,
989
+ "loss": 4.0863,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.8676589361947618,
994
+ "grad_norm": 25.355846405029297,
995
+ "learning_rate": 0.0001402,
996
+ "loss": 4.0348,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.8738125456713204,
1001
+ "grad_norm": 24.209243774414062,
1002
+ "learning_rate": 0.0001412,
1003
+ "loss": 4.0416,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.8799661551478789,
1008
+ "grad_norm": 27.465925216674805,
1009
+ "learning_rate": 0.0001422,
1010
+ "loss": 3.9939,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.8861197646244375,
1015
+ "grad_norm": 25.085203170776367,
1016
+ "learning_rate": 0.00014319999999999998,
1017
+ "loss": 4.0192,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.8922733741009962,
1022
+ "grad_norm": 23.539377212524414,
1023
+ "learning_rate": 0.00014419999999999998,
1024
+ "loss": 3.9236,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.8984269835775547,
1029
+ "grad_norm": 26.392433166503906,
1030
+ "learning_rate": 0.00014519999999999998,
1031
+ "loss": 3.9303,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.9045805930541133,
1036
+ "grad_norm": 23.23287582397461,
1037
+ "learning_rate": 0.0001462,
1038
+ "loss": 3.9163,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.9107342025306719,
1043
+ "grad_norm": 24.316932678222656,
1044
+ "learning_rate": 0.00014719999999999997,
1045
+ "loss": 3.868,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.9168878120072305,
1050
+ "grad_norm": 23.149797439575195,
1051
+ "learning_rate": 0.0001482,
1052
+ "loss": 3.8912,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.9230414214837891,
1057
+ "grad_norm": 25.656810760498047,
1058
+ "learning_rate": 0.0001492,
1059
+ "loss": 3.7883,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.9291950309603477,
1064
+ "grad_norm": 24.43971824645996,
1065
+ "learning_rate": 0.0001502,
1066
+ "loss": 3.8087,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.9353486404369062,
1071
+ "grad_norm": 24.23967170715332,
1072
+ "learning_rate": 0.0001512,
1073
+ "loss": 3.7772,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.9415022499134649,
1078
+ "grad_norm": 33.623390197753906,
1079
+ "learning_rate": 0.00015219999999999999,
1080
+ "loss": 3.7577,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.9476558593900235,
1085
+ "grad_norm": 21.980667114257812,
1086
+ "learning_rate": 0.0001532,
1087
+ "loss": 3.7378,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.953809468866582,
1092
+ "grad_norm": 22.828100204467773,
1093
+ "learning_rate": 0.00015419999999999998,
1094
+ "loss": 3.701,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.9599630783431407,
1099
+ "grad_norm": 22.391563415527344,
1100
+ "learning_rate": 0.00015519999999999998,
1101
+ "loss": 3.6866,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.9661166878196993,
1106
+ "grad_norm": 21.836578369140625,
1107
+ "learning_rate": 0.0001562,
1108
+ "loss": 3.6618,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.9722702972962578,
1113
+ "grad_norm": 24.34965705871582,
1114
+ "learning_rate": 0.0001572,
1115
+ "loss": 3.6196,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.9784239067728164,
1120
+ "grad_norm": 23.68498420715332,
1121
+ "learning_rate": 0.00015819999999999997,
1122
+ "loss": 3.5995,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.9845775162493751,
1127
+ "grad_norm": 23.469165802001953,
1128
+ "learning_rate": 0.00015919999999999997,
1129
+ "loss": 3.602,
1130
+ "step": 1600
1131
+ }
1132
+ ],
1133
+ "logging_steps": 10,
1134
+ "max_steps": 100000,
1135
+ "num_input_tokens_seen": 0,
1136
+ "num_train_epochs": 62,
1137
+ "save_steps": 100,
1138
+ "stateful_callbacks": {
1139
+ "TrainerControl": {
1140
+ "args": {
1141
+ "should_epoch_stop": false,
1142
+ "should_evaluate": false,
1143
+ "should_log": false,
1144
+ "should_save": true,
1145
+ "should_training_stop": false
1146
+ },
1147
+ "attributes": {}
1148
+ }
1149
+ },
1150
+ "total_flos": 1.211805703888896e+17,
1151
+ "train_batch_size": 16,
1152
+ "trial_name": null,
1153
+ "trial_params": null
1154
+ }
checkpoint-1600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4183c4264061f851b0692158bc778140daa0082cbcdb75e934ec1d340f04b990
3
+ size 5201