guyhadad01 commited on
Commit
f7166b6
·
verified ·
1 Parent(s): c49e38c

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/config.json CHANGED
@@ -18,7 +18,7 @@
18
  "position_embedding_type": "absolute",
19
  "tokenizer_class": "XLMRobertaTokenizer",
20
  "torch_dtype": "float32",
21
- "transformers_version": "4.52.4",
22
  "type_vocab_size": 2,
23
  "use_cache": true,
24
  "vocab_size": 250037
 
18
  "position_embedding_type": "absolute",
19
  "tokenizer_class": "XLMRobertaTokenizer",
20
  "torch_dtype": "float32",
21
+ "transformers_version": "4.55.2",
22
  "type_vocab_size": 2,
23
  "use_cache": true,
24
  "vocab_size": 250037
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48393895744f0281dcc35ce037f939cbf0fcb9343f0e49a9b5a5800b72bf3aec
3
  size 471641972
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b047a0e786eb1d688011b6ef8ace7e38cf8666e860bf3a1d20a6db01c28377e
3
  size 471641972
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5927d7bb5b738cb043c868545306c06435eb54da996000898577927f1d970803
3
- size 943405434
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5493e50fc6dd02e0330bd689be29ebdf17ddd1e1450ea8d752f0381e29d578
3
+ size 943408715
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81805f5d9be60e795c66f48836696944f5979ee35820fd897c90082596563348
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb53e956d37160bedc46d0adb3a1f88aaddc065e5d5a137bf434121ef2313991
3
+ size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7fa458e54f1f79beba7dd8cf425c5f35ff1c5b914a484c940ab3f4fb17abf3b
3
- size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8d82f2b63956f7a657676c6c14dd16c65381bf4daf3a0e2823620944d3d859
3
+ size 1465
last-checkpoint/tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20bb9e7979b312d46ef417756bf9907e1943529b027576f3a9458ded2caffcb3
3
  size 17082898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6247be075973430c70e5980bd5af624466882ca896e8994078f6707661e890ca
3
  size 17082898
last-checkpoint/trainer_state.json CHANGED
@@ -2,492 +2,44 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.08563368930082611,
6
  "eval_steps": 1000,
7
- "global_step": 3400,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "epoch": 0.0012593189603062663,
14
- "grad_norm": 7.101168155670166,
15
- "learning_rate": 4.993829337094499e-05,
16
- "loss": 8.8771,
17
  "step": 50
18
  },
19
  {
20
- "epoch": 0.0025186379206125326,
21
- "grad_norm": 9.807716369628906,
22
- "learning_rate": 4.987532742292968e-05,
23
- "loss": 7.4158,
24
  "step": 100
25
  },
26
  {
27
- "epoch": 0.003777956880918799,
28
- "grad_norm": 9.843791961669922,
29
- "learning_rate": 4.981236147491437e-05,
30
- "loss": 6.9685,
31
  "step": 150
32
  },
33
  {
34
- "epoch": 0.005037275841225065,
35
- "grad_norm": 8.359281539916992,
36
- "learning_rate": 4.9749395526899055e-05,
37
- "loss": 6.5252,
38
  "step": 200
39
- },
40
- {
41
- "epoch": 0.006296594801531332,
42
- "grad_norm": 8.851263046264648,
43
- "learning_rate": 4.968642957888374e-05,
44
- "loss": 6.1479,
45
- "step": 250
46
- },
47
- {
48
- "epoch": 0.007555913761837598,
49
- "grad_norm": 9.075284957885742,
50
- "learning_rate": 4.962346363086843e-05,
51
- "loss": 6.074,
52
- "step": 300
53
- },
54
- {
55
- "epoch": 0.008815232722143865,
56
- "grad_norm": 9.121552467346191,
57
- "learning_rate": 4.956049768285311e-05,
58
- "loss": 5.8874,
59
- "step": 350
60
- },
61
- {
62
- "epoch": 0.01007455168245013,
63
- "grad_norm": 9.67652416229248,
64
- "learning_rate": 4.9497531734837806e-05,
65
- "loss": 5.7364,
66
- "step": 400
67
- },
68
- {
69
- "epoch": 0.011333870642756398,
70
- "grad_norm": 8.584100723266602,
71
- "learning_rate": 4.943456578682249e-05,
72
- "loss": 5.6092,
73
- "step": 450
74
- },
75
- {
76
- "epoch": 0.012593189603062663,
77
- "grad_norm": 9.832197189331055,
78
- "learning_rate": 4.937159983880718e-05,
79
- "loss": 5.5687,
80
- "step": 500
81
- },
82
- {
83
- "epoch": 0.01385250856336893,
84
- "grad_norm": 10.394134521484375,
85
- "learning_rate": 4.930863389079186e-05,
86
- "loss": 5.3992,
87
- "step": 550
88
- },
89
- {
90
- "epoch": 0.015111827523675197,
91
- "grad_norm": 8.916543960571289,
92
- "learning_rate": 4.924566794277655e-05,
93
- "loss": 5.386,
94
- "step": 600
95
- },
96
- {
97
- "epoch": 0.016371146483981462,
98
- "grad_norm": 9.233148574829102,
99
- "learning_rate": 4.9182701994761235e-05,
100
- "loss": 5.3173,
101
- "step": 650
102
- },
103
- {
104
- "epoch": 0.01763046544428773,
105
- "grad_norm": 9.256299018859863,
106
- "learning_rate": 4.911973604674592e-05,
107
- "loss": 5.2057,
108
- "step": 700
109
- },
110
- {
111
- "epoch": 0.018889784404593997,
112
- "grad_norm": 8.488754272460938,
113
- "learning_rate": 4.9056770098730606e-05,
114
- "loss": 5.0931,
115
- "step": 750
116
- },
117
- {
118
- "epoch": 0.02014910336490026,
119
- "grad_norm": 10.237517356872559,
120
- "learning_rate": 4.899380415071529e-05,
121
- "loss": 5.0613,
122
- "step": 800
123
- },
124
- {
125
- "epoch": 0.021408422325206528,
126
- "grad_norm": 9.483453750610352,
127
- "learning_rate": 4.893083820269998e-05,
128
- "loss": 5.0304,
129
- "step": 850
130
- },
131
- {
132
- "epoch": 0.022667741285512796,
133
- "grad_norm": 8.838459014892578,
134
- "learning_rate": 4.886787225468467e-05,
135
- "loss": 4.9694,
136
- "step": 900
137
- },
138
- {
139
- "epoch": 0.02392706024581906,
140
- "grad_norm": 8.221150398254395,
141
- "learning_rate": 4.880490630666936e-05,
142
- "loss": 4.9632,
143
- "step": 950
144
- },
145
- {
146
- "epoch": 0.025186379206125327,
147
- "grad_norm": 10.936125755310059,
148
- "learning_rate": 4.874194035865404e-05,
149
- "loss": 4.8524,
150
- "step": 1000
151
- },
152
- {
153
- "epoch": 0.026445698166431594,
154
- "grad_norm": 9.897261619567871,
155
- "learning_rate": 4.867897441063873e-05,
156
- "loss": 4.8278,
157
- "step": 1050
158
- },
159
- {
160
- "epoch": 0.02770501712673786,
161
- "grad_norm": 10.429959297180176,
162
- "learning_rate": 4.8616008462623414e-05,
163
- "loss": 4.7999,
164
- "step": 1100
165
- },
166
- {
167
- "epoch": 0.028964336087044126,
168
- "grad_norm": 9.011711120605469,
169
- "learning_rate": 4.855304251460811e-05,
170
- "loss": 4.7221,
171
- "step": 1150
172
- },
173
- {
174
- "epoch": 0.030223655047350393,
175
- "grad_norm": 8.87881088256836,
176
- "learning_rate": 4.849007656659279e-05,
177
- "loss": 4.7191,
178
- "step": 1200
179
- },
180
- {
181
- "epoch": 0.03148297400765666,
182
- "grad_norm": 9.68855094909668,
183
- "learning_rate": 4.842711061857748e-05,
184
- "loss": 4.6946,
185
- "step": 1250
186
- },
187
- {
188
- "epoch": 0.032742292967962924,
189
- "grad_norm": 11.467870712280273,
190
- "learning_rate": 4.8364144670562164e-05,
191
- "loss": 4.6298,
192
- "step": 1300
193
- },
194
- {
195
- "epoch": 0.03400161192826919,
196
- "grad_norm": 10.919625282287598,
197
- "learning_rate": 4.830117872254685e-05,
198
- "loss": 4.6974,
199
- "step": 1350
200
- },
201
- {
202
- "epoch": 0.03526093088857546,
203
- "grad_norm": 10.439410209655762,
204
- "learning_rate": 4.8238212774531536e-05,
205
- "loss": 4.5912,
206
- "step": 1400
207
- },
208
- {
209
- "epoch": 0.036520249848881726,
210
- "grad_norm": 9.361510276794434,
211
- "learning_rate": 4.817524682651622e-05,
212
- "loss": 4.5724,
213
- "step": 1450
214
- },
215
- {
216
- "epoch": 0.037779568809187994,
217
- "grad_norm": 11.82630443572998,
218
- "learning_rate": 4.811228087850091e-05,
219
- "loss": 4.4983,
220
- "step": 1500
221
- },
222
- {
223
- "epoch": 0.039038887769494254,
224
- "grad_norm": 9.679414749145508,
225
- "learning_rate": 4.8049314930485594e-05,
226
- "loss": 4.5179,
227
- "step": 1550
228
- },
229
- {
230
- "epoch": 0.04029820672980052,
231
- "grad_norm": 9.39099407196045,
232
- "learning_rate": 4.798634898247028e-05,
233
- "loss": 4.4314,
234
- "step": 1600
235
- },
236
- {
237
- "epoch": 0.04155752569010679,
238
- "grad_norm": 9.744073867797852,
239
- "learning_rate": 4.792338303445497e-05,
240
- "loss": 4.5181,
241
- "step": 1650
242
- },
243
- {
244
- "epoch": 0.042816844650413056,
245
- "grad_norm": 9.849005699157715,
246
- "learning_rate": 4.786041708643966e-05,
247
- "loss": 4.3855,
248
- "step": 1700
249
- },
250
- {
251
- "epoch": 0.044076163610719324,
252
- "grad_norm": 9.082205772399902,
253
- "learning_rate": 4.7797451138424344e-05,
254
- "loss": 4.4138,
255
- "step": 1750
256
- },
257
- {
258
- "epoch": 0.04533548257102559,
259
- "grad_norm": 8.309534072875977,
260
- "learning_rate": 4.773448519040903e-05,
261
- "loss": 4.4054,
262
- "step": 1800
263
- },
264
- {
265
- "epoch": 0.04659480153133186,
266
- "grad_norm": 8.576716423034668,
267
- "learning_rate": 4.7671519242393715e-05,
268
- "loss": 4.3585,
269
- "step": 1850
270
- },
271
- {
272
- "epoch": 0.04785412049163812,
273
- "grad_norm": 9.32400131225586,
274
- "learning_rate": 4.760855329437841e-05,
275
- "loss": 4.3509,
276
- "step": 1900
277
- },
278
- {
279
- "epoch": 0.049113439451944386,
280
- "grad_norm": 8.500265121459961,
281
- "learning_rate": 4.7545587346363094e-05,
282
- "loss": 4.319,
283
- "step": 1950
284
- },
285
- {
286
- "epoch": 0.050372758412250654,
287
- "grad_norm": 10.848652839660645,
288
- "learning_rate": 4.748262139834777e-05,
289
- "loss": 4.3335,
290
- "step": 2000
291
- },
292
- {
293
- "epoch": 0.05163207737255692,
294
- "grad_norm": 9.254430770874023,
295
- "learning_rate": 4.741965545033246e-05,
296
- "loss": 4.3304,
297
- "step": 2050
298
- },
299
- {
300
- "epoch": 0.05289139633286319,
301
- "grad_norm": 8.308243751525879,
302
- "learning_rate": 4.7356689502317145e-05,
303
- "loss": 4.3164,
304
- "step": 2100
305
- },
306
- {
307
- "epoch": 0.054150715293169456,
308
- "grad_norm": 8.871552467346191,
309
- "learning_rate": 4.729372355430183e-05,
310
- "loss": 4.3035,
311
- "step": 2150
312
- },
313
- {
314
- "epoch": 0.05541003425347572,
315
- "grad_norm": 8.991899490356445,
316
- "learning_rate": 4.723075760628652e-05,
317
- "loss": 4.2802,
318
- "step": 2200
319
- },
320
- {
321
- "epoch": 0.056669353213781984,
322
- "grad_norm": 9.697725296020508,
323
- "learning_rate": 4.716779165827121e-05,
324
- "loss": 4.2517,
325
- "step": 2250
326
- },
327
- {
328
- "epoch": 0.05792867217408825,
329
- "grad_norm": 9.194120407104492,
330
- "learning_rate": 4.7104825710255895e-05,
331
- "loss": 4.2075,
332
- "step": 2300
333
- },
334
- {
335
- "epoch": 0.05918799113439452,
336
- "grad_norm": 8.314126968383789,
337
- "learning_rate": 4.704185976224058e-05,
338
- "loss": 4.2392,
339
- "step": 2350
340
- },
341
- {
342
- "epoch": 0.060447310094700786,
343
- "grad_norm": 10.024466514587402,
344
- "learning_rate": 4.697889381422527e-05,
345
- "loss": 4.2244,
346
- "step": 2400
347
- },
348
- {
349
- "epoch": 0.06170662905500705,
350
- "grad_norm": 8.209784507751465,
351
- "learning_rate": 4.691592786620996e-05,
352
- "loss": 4.1021,
353
- "step": 2450
354
- },
355
- {
356
- "epoch": 0.06296594801531331,
357
- "grad_norm": 8.149948120117188,
358
- "learning_rate": 4.6852961918194645e-05,
359
- "loss": 4.0721,
360
- "step": 2500
361
- },
362
- {
363
- "epoch": 0.06422526697561959,
364
- "grad_norm": 8.410172462463379,
365
- "learning_rate": 4.678999597017933e-05,
366
- "loss": 4.0433,
367
- "step": 2550
368
- },
369
- {
370
- "epoch": 0.06548458593592585,
371
- "grad_norm": 10.219852447509766,
372
- "learning_rate": 4.672703002216402e-05,
373
- "loss": 4.0822,
374
- "step": 2600
375
- },
376
- {
377
- "epoch": 0.06674390489623212,
378
- "grad_norm": 8.766775131225586,
379
- "learning_rate": 4.66640640741487e-05,
380
- "loss": 4.0743,
381
- "step": 2650
382
- },
383
- {
384
- "epoch": 0.06800322385653838,
385
- "grad_norm": 9.098891258239746,
386
- "learning_rate": 4.660109812613339e-05,
387
- "loss": 4.076,
388
- "step": 2700
389
- },
390
- {
391
- "epoch": 0.06926254281684464,
392
- "grad_norm": 8.314194679260254,
393
- "learning_rate": 4.6538132178118074e-05,
394
- "loss": 4.0504,
395
- "step": 2750
396
- },
397
- {
398
- "epoch": 0.07052186177715092,
399
- "grad_norm": 8.34795093536377,
400
- "learning_rate": 4.647516623010276e-05,
401
- "loss": 4.0558,
402
- "step": 2800
403
- },
404
- {
405
- "epoch": 0.07178118073745718,
406
- "grad_norm": 7.737346172332764,
407
- "learning_rate": 4.6412200282087446e-05,
408
- "loss": 4.0603,
409
- "step": 2850
410
- },
411
- {
412
- "epoch": 0.07304049969776345,
413
- "grad_norm": 7.735106945037842,
414
- "learning_rate": 4.634923433407213e-05,
415
- "loss": 3.9872,
416
- "step": 2900
417
- },
418
- {
419
- "epoch": 0.07429981865806971,
420
- "grad_norm": 10.933419227600098,
421
- "learning_rate": 4.6286268386056825e-05,
422
- "loss": 3.913,
423
- "step": 2950
424
- },
425
- {
426
- "epoch": 0.07555913761837599,
427
- "grad_norm": 10.639062881469727,
428
- "learning_rate": 4.622330243804151e-05,
429
- "loss": 3.9741,
430
- "step": 3000
431
- },
432
- {
433
- "epoch": 0.07681845657868225,
434
- "grad_norm": 9.638007164001465,
435
- "learning_rate": 4.6160336490026196e-05,
436
- "loss": 3.871,
437
- "step": 3050
438
- },
439
- {
440
- "epoch": 0.07807777553898851,
441
- "grad_norm": 11.29076099395752,
442
- "learning_rate": 4.609737054201088e-05,
443
- "loss": 3.9504,
444
- "step": 3100
445
- },
446
- {
447
- "epoch": 0.07933709449929478,
448
- "grad_norm": 8.069476127624512,
449
- "learning_rate": 4.603440459399557e-05,
450
- "loss": 3.9563,
451
- "step": 3150
452
- },
453
- {
454
- "epoch": 0.08059641345960104,
455
- "grad_norm": 9.49170207977295,
456
- "learning_rate": 4.597143864598026e-05,
457
- "loss": 3.8954,
458
- "step": 3200
459
- },
460
- {
461
- "epoch": 0.08185573241990732,
462
- "grad_norm": 7.927274227142334,
463
- "learning_rate": 4.5908472697964946e-05,
464
- "loss": 3.9952,
465
- "step": 3250
466
- },
467
- {
468
- "epoch": 0.08311505138021358,
469
- "grad_norm": 9.124794006347656,
470
- "learning_rate": 4.584550674994963e-05,
471
- "loss": 3.8936,
472
- "step": 3300
473
- },
474
- {
475
- "epoch": 0.08437437034051985,
476
- "grad_norm": 8.415815353393555,
477
- "learning_rate": 4.578254080193432e-05,
478
- "loss": 3.9416,
479
- "step": 3350
480
- },
481
- {
482
- "epoch": 0.08563368930082611,
483
- "grad_norm": 7.427456378936768,
484
- "learning_rate": 4.5719574853919e-05,
485
- "loss": 3.8502,
486
- "step": 3400
487
  }
488
  ],
489
  "logging_steps": 50,
490
- "max_steps": 39704,
491
  "num_input_tokens_seen": 0,
492
  "num_train_epochs": 1,
493
  "save_steps": 200,
@@ -503,8 +55,8 @@
503
  "attributes": {}
504
  }
505
  },
506
- "total_flos": 1399136881240896.0,
507
- "train_batch_size": 32,
508
  "trial_name": null,
509
  "trial_params": null
510
  }
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.0025186379206125326,
6
  "eval_steps": 1000,
7
+ "global_step": 200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "epoch": 0.0006296594801531332,
14
+ "grad_norm": 8.148825645446777,
15
+ "learning_rate": 4.99691466854725e-05,
16
+ "loss": 8.805,
17
  "step": 50
18
  },
19
  {
20
+ "epoch": 0.0012593189603062663,
21
+ "grad_norm": 9.406821250915527,
22
+ "learning_rate": 4.993766371146484e-05,
23
+ "loss": 7.6597,
24
  "step": 100
25
  },
26
  {
27
+ "epoch": 0.0018889784404593996,
28
+ "grad_norm": 12.482063293457031,
29
+ "learning_rate": 4.9906180737457186e-05,
30
+ "loss": 7.2093,
31
  "step": 150
32
  },
33
  {
34
+ "epoch": 0.0025186379206125326,
35
+ "grad_norm": 15.39159870147705,
36
+ "learning_rate": 4.987469776344953e-05,
37
+ "loss": 6.813,
38
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  }
40
  ],
41
  "logging_steps": 50,
42
+ "max_steps": 79408,
43
  "num_input_tokens_seen": 0,
44
  "num_train_epochs": 1,
45
  "save_steps": 200,
 
55
  "attributes": {}
56
  }
57
  },
58
+ "total_flos": 62742348630528.0,
59
+ "train_batch_size": 16,
60
  "trial_name": null,
61
  "trial_params": null
62
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce79bc8c825400c8dd4f732cbde41f2404d4382fd9092537ed185c22c52c8b94
3
- size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba024ed71d2a66548909fa4f3d039c74313393df3397391d5c42a5b3a406964
3
+ size 5841