0x70DA commited on
Commit
24eb5e7
1 Parent(s): 66ccd4f

Training in progress, step 1000

Browse files
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae5c725967736f099289262412e35c7b1379a65ca8d5b7a18846a18df51be3d
3
+ size 25279045
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cdf72c7c6e7bd5b777684aad2cf16df5744107b4acbc7a32022b58b61317b56
3
+ size 12653389
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60952bda276fbd7a8c4f91825c50851c944ee0a84a002a372dc97a8d5a066f0f
3
+ size 14575
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68cff80b680ddf6e7abbef98b5f336b97f9b5963e2209307f639383870e8cc71
3
+ size 557
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cdef9f259b2e2737eaf4578e1e39676ce7d63da9cc24a0a87ba473c6003e12f
3
+ size 627
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,1256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.176331877708435,
3
+ "best_model_checkpoint": "outputs/checkpoint-1000",
4
+ "epoch": 0.32,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1e-05,
13
+ "loss": 1.8184,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 2e-05,
19
+ "loss": 1.7858,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 3e-05,
25
+ "loss": 1.7218,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 4e-05,
31
+ "loss": 1.7218,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 5e-05,
37
+ "loss": 1.7009,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 6e-05,
43
+ "loss": 1.6714,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "learning_rate": 7e-05,
49
+ "loss": 1.6582,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 8e-05,
55
+ "loss": 1.5659,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.01,
60
+ "learning_rate": 9e-05,
61
+ "loss": 1.5343,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.02,
66
+ "learning_rate": 0.0001,
67
+ "loss": 1.5252,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.02,
72
+ "learning_rate": 0.00011000000000000002,
73
+ "loss": 1.414,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.02,
78
+ "learning_rate": 0.00012,
79
+ "loss": 1.3919,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "learning_rate": 0.00013000000000000002,
85
+ "loss": 1.352,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.02,
90
+ "learning_rate": 0.00014,
91
+ "loss": 1.3762,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.02,
96
+ "learning_rate": 0.00015000000000000001,
97
+ "loss": 1.3238,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.03,
102
+ "learning_rate": 0.00016,
103
+ "loss": 1.3306,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.03,
108
+ "learning_rate": 0.00017,
109
+ "loss": 1.3423,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.03,
114
+ "learning_rate": 0.00018,
115
+ "loss": 1.3199,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.03,
120
+ "learning_rate": 0.00019,
121
+ "loss": 1.3506,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.03,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.3315,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.03,
132
+ "learning_rate": 0.0001998921832884097,
133
+ "loss": 1.3142,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.04,
138
+ "learning_rate": 0.00019978436657681943,
139
+ "loss": 1.2994,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.04,
144
+ "learning_rate": 0.00019967654986522912,
145
+ "loss": 1.2972,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.04,
150
+ "learning_rate": 0.00019956873315363883,
151
+ "loss": 1.3135,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.04,
156
+ "learning_rate": 0.00019946091644204851,
157
+ "loss": 1.2903,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.04,
162
+ "learning_rate": 0.00019935309973045823,
163
+ "loss": 1.2783,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.04,
168
+ "learning_rate": 0.00019924528301886794,
169
+ "loss": 1.3044,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.04,
174
+ "learning_rate": 0.00019913746630727762,
175
+ "loss": 1.2947,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.05,
180
+ "learning_rate": 0.00019902964959568736,
181
+ "loss": 1.2759,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.05,
186
+ "learning_rate": 0.00019892183288409705,
187
+ "loss": 1.2746,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.05,
192
+ "learning_rate": 0.00019881401617250676,
193
+ "loss": 1.2869,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 0.05,
198
+ "learning_rate": 0.00019870619946091644,
199
+ "loss": 1.26,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 0.05,
204
+ "learning_rate": 0.00019859838274932616,
205
+ "loss": 1.258,
206
+ "step": 165
207
+ },
208
+ {
209
+ "epoch": 0.05,
210
+ "learning_rate": 0.00019849056603773587,
211
+ "loss": 1.2649,
212
+ "step": 170
213
+ },
214
+ {
215
+ "epoch": 0.06,
216
+ "learning_rate": 0.00019838274932614555,
217
+ "loss": 1.2549,
218
+ "step": 175
219
+ },
220
+ {
221
+ "epoch": 0.06,
222
+ "learning_rate": 0.00019827493261455526,
223
+ "loss": 1.2859,
224
+ "step": 180
225
+ },
226
+ {
227
+ "epoch": 0.06,
228
+ "learning_rate": 0.00019816711590296498,
229
+ "loss": 1.2934,
230
+ "step": 185
231
+ },
232
+ {
233
+ "epoch": 0.06,
234
+ "learning_rate": 0.00019805929919137466,
235
+ "loss": 1.3011,
236
+ "step": 190
237
+ },
238
+ {
239
+ "epoch": 0.06,
240
+ "learning_rate": 0.00019795148247978437,
241
+ "loss": 1.2304,
242
+ "step": 195
243
+ },
244
+ {
245
+ "epoch": 0.06,
246
+ "learning_rate": 0.00019784366576819408,
247
+ "loss": 1.2849,
248
+ "step": 200
249
+ },
250
+ {
251
+ "epoch": 0.06,
252
+ "eval_loss": 1.2345943450927734,
253
+ "eval_runtime": 710.2534,
254
+ "eval_samples_per_second": 7.04,
255
+ "eval_steps_per_second": 0.88,
256
+ "step": 200
257
+ },
258
+ {
259
+ "epoch": 0.07,
260
+ "learning_rate": 0.0001977358490566038,
261
+ "loss": 1.2726,
262
+ "step": 205
263
+ },
264
+ {
265
+ "epoch": 0.07,
266
+ "learning_rate": 0.00019762803234501348,
267
+ "loss": 1.2996,
268
+ "step": 210
269
+ },
270
+ {
271
+ "epoch": 0.07,
272
+ "learning_rate": 0.0001975202156334232,
273
+ "loss": 1.2456,
274
+ "step": 215
275
+ },
276
+ {
277
+ "epoch": 0.07,
278
+ "learning_rate": 0.0001974123989218329,
279
+ "loss": 1.2794,
280
+ "step": 220
281
+ },
282
+ {
283
+ "epoch": 0.07,
284
+ "learning_rate": 0.0001973045822102426,
285
+ "loss": 1.2637,
286
+ "step": 225
287
+ },
288
+ {
289
+ "epoch": 0.07,
290
+ "learning_rate": 0.0001971967654986523,
291
+ "loss": 1.252,
292
+ "step": 230
293
+ },
294
+ {
295
+ "epoch": 0.08,
296
+ "learning_rate": 0.000197088948787062,
297
+ "loss": 1.2492,
298
+ "step": 235
299
+ },
300
+ {
301
+ "epoch": 0.08,
302
+ "learning_rate": 0.0001969811320754717,
303
+ "loss": 1.2972,
304
+ "step": 240
305
+ },
306
+ {
307
+ "epoch": 0.08,
308
+ "learning_rate": 0.0001968733153638814,
309
+ "loss": 1.3023,
310
+ "step": 245
311
+ },
312
+ {
313
+ "epoch": 0.08,
314
+ "learning_rate": 0.00019676549865229112,
315
+ "loss": 1.2682,
316
+ "step": 250
317
+ },
318
+ {
319
+ "epoch": 0.08,
320
+ "learning_rate": 0.00019665768194070083,
321
+ "loss": 1.2981,
322
+ "step": 255
323
+ },
324
+ {
325
+ "epoch": 0.08,
326
+ "learning_rate": 0.00019654986522911052,
327
+ "loss": 1.3084,
328
+ "step": 260
329
+ },
330
+ {
331
+ "epoch": 0.08,
332
+ "learning_rate": 0.00019644204851752023,
333
+ "loss": 1.2666,
334
+ "step": 265
335
+ },
336
+ {
337
+ "epoch": 0.09,
338
+ "learning_rate": 0.00019633423180592994,
339
+ "loss": 1.2623,
340
+ "step": 270
341
+ },
342
+ {
343
+ "epoch": 0.09,
344
+ "learning_rate": 0.00019622641509433963,
345
+ "loss": 1.2406,
346
+ "step": 275
347
+ },
348
+ {
349
+ "epoch": 0.09,
350
+ "learning_rate": 0.00019611859838274934,
351
+ "loss": 1.2623,
352
+ "step": 280
353
+ },
354
+ {
355
+ "epoch": 0.09,
356
+ "learning_rate": 0.00019601078167115905,
357
+ "loss": 1.2562,
358
+ "step": 285
359
+ },
360
+ {
361
+ "epoch": 0.09,
362
+ "learning_rate": 0.00019590296495956873,
363
+ "loss": 1.2166,
364
+ "step": 290
365
+ },
366
+ {
367
+ "epoch": 0.09,
368
+ "learning_rate": 0.00019579514824797845,
369
+ "loss": 1.2931,
370
+ "step": 295
371
+ },
372
+ {
373
+ "epoch": 0.1,
374
+ "learning_rate": 0.00019568733153638813,
375
+ "loss": 1.2354,
376
+ "step": 300
377
+ },
378
+ {
379
+ "epoch": 0.1,
380
+ "learning_rate": 0.00019557951482479787,
381
+ "loss": 1.2246,
382
+ "step": 305
383
+ },
384
+ {
385
+ "epoch": 0.1,
386
+ "learning_rate": 0.00019547169811320755,
387
+ "loss": 1.2236,
388
+ "step": 310
389
+ },
390
+ {
391
+ "epoch": 0.1,
392
+ "learning_rate": 0.00019536388140161727,
393
+ "loss": 1.2442,
394
+ "step": 315
395
+ },
396
+ {
397
+ "epoch": 0.1,
398
+ "learning_rate": 0.00019525606469002698,
399
+ "loss": 1.2779,
400
+ "step": 320
401
+ },
402
+ {
403
+ "epoch": 0.1,
404
+ "learning_rate": 0.00019514824797843666,
405
+ "loss": 1.2285,
406
+ "step": 325
407
+ },
408
+ {
409
+ "epoch": 0.11,
410
+ "learning_rate": 0.00019504043126684637,
411
+ "loss": 1.2157,
412
+ "step": 330
413
+ },
414
+ {
415
+ "epoch": 0.11,
416
+ "learning_rate": 0.00019493261455525606,
417
+ "loss": 1.2405,
418
+ "step": 335
419
+ },
420
+ {
421
+ "epoch": 0.11,
422
+ "learning_rate": 0.0001948247978436658,
423
+ "loss": 1.2335,
424
+ "step": 340
425
+ },
426
+ {
427
+ "epoch": 0.11,
428
+ "learning_rate": 0.00019471698113207548,
429
+ "loss": 1.2401,
430
+ "step": 345
431
+ },
432
+ {
433
+ "epoch": 0.11,
434
+ "learning_rate": 0.00019460916442048517,
435
+ "loss": 1.2521,
436
+ "step": 350
437
+ },
438
+ {
439
+ "epoch": 0.11,
440
+ "learning_rate": 0.0001945013477088949,
441
+ "loss": 1.2386,
442
+ "step": 355
443
+ },
444
+ {
445
+ "epoch": 0.12,
446
+ "learning_rate": 0.0001943935309973046,
447
+ "loss": 1.2196,
448
+ "step": 360
449
+ },
450
+ {
451
+ "epoch": 0.12,
452
+ "learning_rate": 0.0001942857142857143,
453
+ "loss": 1.192,
454
+ "step": 365
455
+ },
456
+ {
457
+ "epoch": 0.12,
458
+ "learning_rate": 0.000194177897574124,
459
+ "loss": 1.1964,
460
+ "step": 370
461
+ },
462
+ {
463
+ "epoch": 0.12,
464
+ "learning_rate": 0.0001940700808625337,
465
+ "loss": 1.2876,
466
+ "step": 375
467
+ },
468
+ {
469
+ "epoch": 0.12,
470
+ "learning_rate": 0.0001939622641509434,
471
+ "loss": 1.2622,
472
+ "step": 380
473
+ },
474
+ {
475
+ "epoch": 0.12,
476
+ "learning_rate": 0.0001938544474393531,
477
+ "loss": 1.2183,
478
+ "step": 385
479
+ },
480
+ {
481
+ "epoch": 0.12,
482
+ "learning_rate": 0.00019374663072776284,
483
+ "loss": 1.206,
484
+ "step": 390
485
+ },
486
+ {
487
+ "epoch": 0.13,
488
+ "learning_rate": 0.00019363881401617252,
489
+ "loss": 1.2697,
490
+ "step": 395
491
+ },
492
+ {
493
+ "epoch": 0.13,
494
+ "learning_rate": 0.0001935309973045822,
495
+ "loss": 1.2515,
496
+ "step": 400
497
+ },
498
+ {
499
+ "epoch": 0.13,
500
+ "eval_loss": 1.207701563835144,
501
+ "eval_runtime": 709.7794,
502
+ "eval_samples_per_second": 7.044,
503
+ "eval_steps_per_second": 0.881,
504
+ "step": 400
505
+ },
506
+ {
507
+ "epoch": 0.13,
508
+ "learning_rate": 0.00019342318059299192,
509
+ "loss": 1.2596,
510
+ "step": 405
511
+ },
512
+ {
513
+ "epoch": 0.13,
514
+ "learning_rate": 0.00019331536388140163,
515
+ "loss": 1.2537,
516
+ "step": 410
517
+ },
518
+ {
519
+ "epoch": 0.13,
520
+ "learning_rate": 0.00019320754716981134,
521
+ "loss": 1.2545,
522
+ "step": 415
523
+ },
524
+ {
525
+ "epoch": 0.13,
526
+ "learning_rate": 0.00019309973045822103,
527
+ "loss": 1.2473,
528
+ "step": 420
529
+ },
530
+ {
531
+ "epoch": 0.14,
532
+ "learning_rate": 0.00019299191374663074,
533
+ "loss": 1.2308,
534
+ "step": 425
535
+ },
536
+ {
537
+ "epoch": 0.14,
538
+ "learning_rate": 0.00019288409703504045,
539
+ "loss": 1.2482,
540
+ "step": 430
541
+ },
542
+ {
543
+ "epoch": 0.14,
544
+ "learning_rate": 0.00019277628032345013,
545
+ "loss": 1.2342,
546
+ "step": 435
547
+ },
548
+ {
549
+ "epoch": 0.14,
550
+ "learning_rate": 0.00019266846361185985,
551
+ "loss": 1.2101,
552
+ "step": 440
553
+ },
554
+ {
555
+ "epoch": 0.14,
556
+ "learning_rate": 0.00019256064690026956,
557
+ "loss": 1.233,
558
+ "step": 445
559
+ },
560
+ {
561
+ "epoch": 0.14,
562
+ "learning_rate": 0.00019245283018867927,
563
+ "loss": 1.2401,
564
+ "step": 450
565
+ },
566
+ {
567
+ "epoch": 0.15,
568
+ "learning_rate": 0.00019234501347708895,
569
+ "loss": 1.2088,
570
+ "step": 455
571
+ },
572
+ {
573
+ "epoch": 0.15,
574
+ "learning_rate": 0.00019223719676549864,
575
+ "loss": 1.2205,
576
+ "step": 460
577
+ },
578
+ {
579
+ "epoch": 0.15,
580
+ "learning_rate": 0.00019212938005390838,
581
+ "loss": 1.218,
582
+ "step": 465
583
+ },
584
+ {
585
+ "epoch": 0.15,
586
+ "learning_rate": 0.00019202156334231806,
587
+ "loss": 1.2208,
588
+ "step": 470
589
+ },
590
+ {
591
+ "epoch": 0.15,
592
+ "learning_rate": 0.00019191374663072777,
593
+ "loss": 1.2783,
594
+ "step": 475
595
+ },
596
+ {
597
+ "epoch": 0.15,
598
+ "learning_rate": 0.00019180592991913749,
599
+ "loss": 1.1886,
600
+ "step": 480
601
+ },
602
+ {
603
+ "epoch": 0.16,
604
+ "learning_rate": 0.00019169811320754717,
605
+ "loss": 1.1939,
606
+ "step": 485
607
+ },
608
+ {
609
+ "epoch": 0.16,
610
+ "learning_rate": 0.00019159029649595688,
611
+ "loss": 1.2079,
612
+ "step": 490
613
+ },
614
+ {
615
+ "epoch": 0.16,
616
+ "learning_rate": 0.00019148247978436657,
617
+ "loss": 1.2473,
618
+ "step": 495
619
+ },
620
+ {
621
+ "epoch": 0.16,
622
+ "learning_rate": 0.0001913746630727763,
623
+ "loss": 1.2295,
624
+ "step": 500
625
+ },
626
+ {
627
+ "epoch": 0.16,
628
+ "learning_rate": 0.000191266846361186,
629
+ "loss": 1.2064,
630
+ "step": 505
631
+ },
632
+ {
633
+ "epoch": 0.16,
634
+ "learning_rate": 0.00019115902964959568,
635
+ "loss": 1.2138,
636
+ "step": 510
637
+ },
638
+ {
639
+ "epoch": 0.16,
640
+ "learning_rate": 0.00019105121293800541,
641
+ "loss": 1.2618,
642
+ "step": 515
643
+ },
644
+ {
645
+ "epoch": 0.17,
646
+ "learning_rate": 0.0001909433962264151,
647
+ "loss": 1.2495,
648
+ "step": 520
649
+ },
650
+ {
651
+ "epoch": 0.17,
652
+ "learning_rate": 0.0001908355795148248,
653
+ "loss": 1.2553,
654
+ "step": 525
655
+ },
656
+ {
657
+ "epoch": 0.17,
658
+ "learning_rate": 0.0001907277628032345,
659
+ "loss": 1.2334,
660
+ "step": 530
661
+ },
662
+ {
663
+ "epoch": 0.17,
664
+ "learning_rate": 0.0001906199460916442,
665
+ "loss": 1.2442,
666
+ "step": 535
667
+ },
668
+ {
669
+ "epoch": 0.17,
670
+ "learning_rate": 0.00019051212938005392,
671
+ "loss": 1.2301,
672
+ "step": 540
673
+ },
674
+ {
675
+ "epoch": 0.17,
676
+ "learning_rate": 0.0001904043126684636,
677
+ "loss": 1.2678,
678
+ "step": 545
679
+ },
680
+ {
681
+ "epoch": 0.18,
682
+ "learning_rate": 0.00019029649595687334,
683
+ "loss": 1.2116,
684
+ "step": 550
685
+ },
686
+ {
687
+ "epoch": 0.18,
688
+ "learning_rate": 0.00019018867924528303,
689
+ "loss": 1.2556,
690
+ "step": 555
691
+ },
692
+ {
693
+ "epoch": 0.18,
694
+ "learning_rate": 0.00019008086253369274,
695
+ "loss": 1.2427,
696
+ "step": 560
697
+ },
698
+ {
699
+ "epoch": 0.18,
700
+ "learning_rate": 0.00018997304582210242,
701
+ "loss": 1.2138,
702
+ "step": 565
703
+ },
704
+ {
705
+ "epoch": 0.18,
706
+ "learning_rate": 0.00018986522911051214,
707
+ "loss": 1.248,
708
+ "step": 570
709
+ },
710
+ {
711
+ "epoch": 0.18,
712
+ "learning_rate": 0.00018975741239892185,
713
+ "loss": 1.2415,
714
+ "step": 575
715
+ },
716
+ {
717
+ "epoch": 0.19,
718
+ "learning_rate": 0.00018964959568733153,
719
+ "loss": 1.2303,
720
+ "step": 580
721
+ },
722
+ {
723
+ "epoch": 0.19,
724
+ "learning_rate": 0.00018954177897574125,
725
+ "loss": 1.1939,
726
+ "step": 585
727
+ },
728
+ {
729
+ "epoch": 0.19,
730
+ "learning_rate": 0.00018943396226415096,
731
+ "loss": 1.1927,
732
+ "step": 590
733
+ },
734
+ {
735
+ "epoch": 0.19,
736
+ "learning_rate": 0.00018932614555256064,
737
+ "loss": 1.1982,
738
+ "step": 595
739
+ },
740
+ {
741
+ "epoch": 0.19,
742
+ "learning_rate": 0.00018921832884097035,
743
+ "loss": 1.1859,
744
+ "step": 600
745
+ },
746
+ {
747
+ "epoch": 0.19,
748
+ "eval_loss": 1.1948214769363403,
749
+ "eval_runtime": 709.3061,
750
+ "eval_samples_per_second": 7.049,
751
+ "eval_steps_per_second": 0.881,
752
+ "step": 600
753
+ },
754
+ {
755
+ "epoch": 0.19,
756
+ "learning_rate": 0.00018911051212938007,
757
+ "loss": 1.2265,
758
+ "step": 605
759
+ },
760
+ {
761
+ "epoch": 0.2,
762
+ "learning_rate": 0.00018900269541778978,
763
+ "loss": 1.2402,
764
+ "step": 610
765
+ },
766
+ {
767
+ "epoch": 0.2,
768
+ "learning_rate": 0.00018889487870619946,
769
+ "loss": 1.2261,
770
+ "step": 615
771
+ },
772
+ {
773
+ "epoch": 0.2,
774
+ "learning_rate": 0.00018878706199460917,
775
+ "loss": 1.2264,
776
+ "step": 620
777
+ },
778
+ {
779
+ "epoch": 0.2,
780
+ "learning_rate": 0.00018867924528301889,
781
+ "loss": 1.2044,
782
+ "step": 625
783
+ },
784
+ {
785
+ "epoch": 0.2,
786
+ "learning_rate": 0.00018857142857142857,
787
+ "loss": 1.2203,
788
+ "step": 630
789
+ },
790
+ {
791
+ "epoch": 0.2,
792
+ "learning_rate": 0.00018846361185983828,
793
+ "loss": 1.2258,
794
+ "step": 635
795
+ },
796
+ {
797
+ "epoch": 0.2,
798
+ "learning_rate": 0.000188355795148248,
799
+ "loss": 1.2475,
800
+ "step": 640
801
+ },
802
+ {
803
+ "epoch": 0.21,
804
+ "learning_rate": 0.00018824797843665768,
805
+ "loss": 1.239,
806
+ "step": 645
807
+ },
808
+ {
809
+ "epoch": 0.21,
810
+ "learning_rate": 0.0001881401617250674,
811
+ "loss": 1.2374,
812
+ "step": 650
813
+ },
814
+ {
815
+ "epoch": 0.21,
816
+ "learning_rate": 0.0001880323450134771,
817
+ "loss": 1.2472,
818
+ "step": 655
819
+ },
820
+ {
821
+ "epoch": 0.21,
822
+ "learning_rate": 0.00018792452830188681,
823
+ "loss": 1.2411,
824
+ "step": 660
825
+ },
826
+ {
827
+ "epoch": 0.21,
828
+ "learning_rate": 0.0001878167115902965,
829
+ "loss": 1.1916,
830
+ "step": 665
831
+ },
832
+ {
833
+ "epoch": 0.21,
834
+ "learning_rate": 0.0001877088948787062,
835
+ "loss": 1.2043,
836
+ "step": 670
837
+ },
838
+ {
839
+ "epoch": 0.22,
840
+ "learning_rate": 0.00018760107816711592,
841
+ "loss": 1.2087,
842
+ "step": 675
843
+ },
844
+ {
845
+ "epoch": 0.22,
846
+ "learning_rate": 0.0001874932614555256,
847
+ "loss": 1.2147,
848
+ "step": 680
849
+ },
850
+ {
851
+ "epoch": 0.22,
852
+ "learning_rate": 0.00018738544474393532,
853
+ "loss": 1.1999,
854
+ "step": 685
855
+ },
856
+ {
857
+ "epoch": 0.22,
858
+ "learning_rate": 0.00018727762803234503,
859
+ "loss": 1.2031,
860
+ "step": 690
861
+ },
862
+ {
863
+ "epoch": 0.22,
864
+ "learning_rate": 0.00018716981132075472,
865
+ "loss": 1.268,
866
+ "step": 695
867
+ },
868
+ {
869
+ "epoch": 0.22,
870
+ "learning_rate": 0.00018706199460916443,
871
+ "loss": 1.2181,
872
+ "step": 700
873
+ },
874
+ {
875
+ "epoch": 0.23,
876
+ "learning_rate": 0.0001869541778975741,
877
+ "loss": 1.2187,
878
+ "step": 705
879
+ },
880
+ {
881
+ "epoch": 0.23,
882
+ "learning_rate": 0.00018684636118598385,
883
+ "loss": 1.2475,
884
+ "step": 710
885
+ },
886
+ {
887
+ "epoch": 0.23,
888
+ "learning_rate": 0.00018673854447439354,
889
+ "loss": 1.2043,
890
+ "step": 715
891
+ },
892
+ {
893
+ "epoch": 0.23,
894
+ "learning_rate": 0.00018663072776280325,
895
+ "loss": 1.1833,
896
+ "step": 720
897
+ },
898
+ {
899
+ "epoch": 0.23,
900
+ "learning_rate": 0.00018652291105121296,
901
+ "loss": 1.1899,
902
+ "step": 725
903
+ },
904
+ {
905
+ "epoch": 0.23,
906
+ "learning_rate": 0.00018641509433962264,
907
+ "loss": 1.232,
908
+ "step": 730
909
+ },
910
+ {
911
+ "epoch": 0.24,
912
+ "learning_rate": 0.00018630727762803236,
913
+ "loss": 1.1885,
914
+ "step": 735
915
+ },
916
+ {
917
+ "epoch": 0.24,
918
+ "learning_rate": 0.00018619946091644204,
919
+ "loss": 1.2087,
920
+ "step": 740
921
+ },
922
+ {
923
+ "epoch": 0.24,
924
+ "learning_rate": 0.00018609164420485178,
925
+ "loss": 1.2433,
926
+ "step": 745
927
+ },
928
+ {
929
+ "epoch": 0.24,
930
+ "learning_rate": 0.00018598382749326146,
931
+ "loss": 1.2233,
932
+ "step": 750
933
+ },
934
+ {
935
+ "epoch": 0.24,
936
+ "learning_rate": 0.00018587601078167115,
937
+ "loss": 1.2348,
938
+ "step": 755
939
+ },
940
+ {
941
+ "epoch": 0.24,
942
+ "learning_rate": 0.0001857681940700809,
943
+ "loss": 1.1667,
944
+ "step": 760
945
+ },
946
+ {
947
+ "epoch": 0.24,
948
+ "learning_rate": 0.00018566037735849057,
949
+ "loss": 1.2952,
950
+ "step": 765
951
+ },
952
+ {
953
+ "epoch": 0.25,
954
+ "learning_rate": 0.00018555256064690029,
955
+ "loss": 1.1939,
956
+ "step": 770
957
+ },
958
+ {
959
+ "epoch": 0.25,
960
+ "learning_rate": 0.00018544474393530997,
961
+ "loss": 1.1646,
962
+ "step": 775
963
+ },
964
+ {
965
+ "epoch": 0.25,
966
+ "learning_rate": 0.00018533692722371968,
967
+ "loss": 1.2055,
968
+ "step": 780
969
+ },
970
+ {
971
+ "epoch": 0.25,
972
+ "learning_rate": 0.0001852291105121294,
973
+ "loss": 1.183,
974
+ "step": 785
975
+ },
976
+ {
977
+ "epoch": 0.25,
978
+ "learning_rate": 0.00018512129380053908,
979
+ "loss": 1.2367,
980
+ "step": 790
981
+ },
982
+ {
983
+ "epoch": 0.25,
984
+ "learning_rate": 0.00018501347708894882,
985
+ "loss": 1.2265,
986
+ "step": 795
987
+ },
988
+ {
989
+ "epoch": 0.26,
990
+ "learning_rate": 0.0001849056603773585,
991
+ "loss": 1.2007,
992
+ "step": 800
993
+ },
994
+ {
995
+ "epoch": 0.26,
996
+ "eval_loss": 1.184471845626831,
997
+ "eval_runtime": 708.4336,
998
+ "eval_samples_per_second": 7.058,
999
+ "eval_steps_per_second": 0.882,
1000
+ "step": 800
1001
+ },
1002
+ {
1003
+ "epoch": 0.26,
1004
+ "learning_rate": 0.0001847978436657682,
1005
+ "loss": 1.204,
1006
+ "step": 805
1007
+ },
1008
+ {
1009
+ "epoch": 0.26,
1010
+ "learning_rate": 0.0001846900269541779,
1011
+ "loss": 1.2379,
1012
+ "step": 810
1013
+ },
1014
+ {
1015
+ "epoch": 0.26,
1016
+ "learning_rate": 0.0001845822102425876,
1017
+ "loss": 1.157,
1018
+ "step": 815
1019
+ },
1020
+ {
1021
+ "epoch": 0.26,
1022
+ "learning_rate": 0.00018447439353099732,
1023
+ "loss": 1.2072,
1024
+ "step": 820
1025
+ },
1026
+ {
1027
+ "epoch": 0.26,
1028
+ "learning_rate": 0.000184366576819407,
1029
+ "loss": 1.1764,
1030
+ "step": 825
1031
+ },
1032
+ {
1033
+ "epoch": 0.27,
1034
+ "learning_rate": 0.00018425876010781672,
1035
+ "loss": 1.21,
1036
+ "step": 830
1037
+ },
1038
+ {
1039
+ "epoch": 0.27,
1040
+ "learning_rate": 0.00018415094339622643,
1041
+ "loss": 1.19,
1042
+ "step": 835
1043
+ },
1044
+ {
1045
+ "epoch": 0.27,
1046
+ "learning_rate": 0.00018404312668463612,
1047
+ "loss": 1.1923,
1048
+ "step": 840
1049
+ },
1050
+ {
1051
+ "epoch": 0.27,
1052
+ "learning_rate": 0.00018393530997304583,
1053
+ "loss": 1.2367,
1054
+ "step": 845
1055
+ },
1056
+ {
1057
+ "epoch": 0.27,
1058
+ "learning_rate": 0.00018382749326145554,
1059
+ "loss": 1.2394,
1060
+ "step": 850
1061
+ },
1062
+ {
1063
+ "epoch": 0.27,
1064
+ "learning_rate": 0.00018371967654986525,
1065
+ "loss": 1.2275,
1066
+ "step": 855
1067
+ },
1068
+ {
1069
+ "epoch": 0.28,
1070
+ "learning_rate": 0.00018361185983827494,
1071
+ "loss": 1.2206,
1072
+ "step": 860
1073
+ },
1074
+ {
1075
+ "epoch": 0.28,
1076
+ "learning_rate": 0.00018350404312668465,
1077
+ "loss": 1.2017,
1078
+ "step": 865
1079
+ },
1080
+ {
1081
+ "epoch": 0.28,
1082
+ "learning_rate": 0.00018339622641509436,
1083
+ "loss": 1.2277,
1084
+ "step": 870
1085
+ },
1086
+ {
1087
+ "epoch": 0.28,
1088
+ "learning_rate": 0.00018328840970350404,
1089
+ "loss": 1.1958,
1090
+ "step": 875
1091
+ },
1092
+ {
1093
+ "epoch": 0.28,
1094
+ "learning_rate": 0.00018318059299191376,
1095
+ "loss": 1.2317,
1096
+ "step": 880
1097
+ },
1098
+ {
1099
+ "epoch": 0.28,
1100
+ "learning_rate": 0.00018307277628032347,
1101
+ "loss": 1.2339,
1102
+ "step": 885
1103
+ },
1104
+ {
1105
+ "epoch": 0.28,
1106
+ "learning_rate": 0.00018296495956873315,
1107
+ "loss": 1.2408,
1108
+ "step": 890
1109
+ },
1110
+ {
1111
+ "epoch": 0.29,
1112
+ "learning_rate": 0.00018285714285714286,
1113
+ "loss": 1.1818,
1114
+ "step": 895
1115
+ },
1116
+ {
1117
+ "epoch": 0.29,
1118
+ "learning_rate": 0.00018274932614555258,
1119
+ "loss": 1.2051,
1120
+ "step": 900
1121
+ },
1122
+ {
1123
+ "epoch": 0.29,
1124
+ "learning_rate": 0.0001826415094339623,
1125
+ "loss": 1.2304,
1126
+ "step": 905
1127
+ },
1128
+ {
1129
+ "epoch": 0.29,
1130
+ "learning_rate": 0.00018253369272237197,
1131
+ "loss": 1.1717,
1132
+ "step": 910
1133
+ },
1134
+ {
1135
+ "epoch": 0.29,
1136
+ "learning_rate": 0.00018242587601078168,
1137
+ "loss": 1.1811,
1138
+ "step": 915
1139
+ },
1140
+ {
1141
+ "epoch": 0.29,
1142
+ "learning_rate": 0.0001823180592991914,
1143
+ "loss": 1.2127,
1144
+ "step": 920
1145
+ },
1146
+ {
1147
+ "epoch": 0.3,
1148
+ "learning_rate": 0.00018221024258760108,
1149
+ "loss": 1.2278,
1150
+ "step": 925
1151
+ },
1152
+ {
1153
+ "epoch": 0.3,
1154
+ "learning_rate": 0.0001821024258760108,
1155
+ "loss": 1.223,
1156
+ "step": 930
1157
+ },
1158
+ {
1159
+ "epoch": 0.3,
1160
+ "learning_rate": 0.0001819946091644205,
1161
+ "loss": 1.233,
1162
+ "step": 935
1163
+ },
1164
+ {
1165
+ "epoch": 0.3,
1166
+ "learning_rate": 0.0001818867924528302,
1167
+ "loss": 1.2321,
1168
+ "step": 940
1169
+ },
1170
+ {
1171
+ "epoch": 0.3,
1172
+ "learning_rate": 0.0001817789757412399,
1173
+ "loss": 1.1894,
1174
+ "step": 945
1175
+ },
1176
+ {
1177
+ "epoch": 0.3,
1178
+ "learning_rate": 0.00018167115902964959,
1179
+ "loss": 1.2213,
1180
+ "step": 950
1181
+ },
1182
+ {
1183
+ "epoch": 0.31,
1184
+ "learning_rate": 0.00018156334231805933,
1185
+ "loss": 1.2444,
1186
+ "step": 955
1187
+ },
1188
+ {
1189
+ "epoch": 0.31,
1190
+ "learning_rate": 0.000181455525606469,
1191
+ "loss": 1.1988,
1192
+ "step": 960
1193
+ },
1194
+ {
1195
+ "epoch": 0.31,
1196
+ "learning_rate": 0.00018134770889487872,
1197
+ "loss": 1.2039,
1198
+ "step": 965
1199
+ },
1200
+ {
1201
+ "epoch": 0.31,
1202
+ "learning_rate": 0.00018123989218328843,
1203
+ "loss": 1.1972,
1204
+ "step": 970
1205
+ },
1206
+ {
1207
+ "epoch": 0.31,
1208
+ "learning_rate": 0.00018113207547169812,
1209
+ "loss": 1.2146,
1210
+ "step": 975
1211
+ },
1212
+ {
1213
+ "epoch": 0.31,
1214
+ "learning_rate": 0.00018102425876010783,
1215
+ "loss": 1.2346,
1216
+ "step": 980
1217
+ },
1218
+ {
1219
+ "epoch": 0.32,
1220
+ "learning_rate": 0.00018091644204851751,
1221
+ "loss": 1.2283,
1222
+ "step": 985
1223
+ },
1224
+ {
1225
+ "epoch": 0.32,
1226
+ "learning_rate": 0.00018080862533692723,
1227
+ "loss": 1.201,
1228
+ "step": 990
1229
+ },
1230
+ {
1231
+ "epoch": 0.32,
1232
+ "learning_rate": 0.00018070080862533694,
1233
+ "loss": 1.2149,
1234
+ "step": 995
1235
+ },
1236
+ {
1237
+ "epoch": 0.32,
1238
+ "learning_rate": 0.00018059299191374662,
1239
+ "loss": 1.2085,
1240
+ "step": 1000
1241
+ },
1242
+ {
1243
+ "epoch": 0.32,
1244
+ "eval_loss": 1.176331877708435,
1245
+ "eval_runtime": 709.1565,
1246
+ "eval_samples_per_second": 7.051,
1247
+ "eval_steps_per_second": 0.881,
1248
+ "step": 1000
1249
+ }
1250
+ ],
1251
+ "max_steps": 9375,
1252
+ "num_train_epochs": 3,
1253
+ "total_flos": 5.9559854997504e+16,
1254
+ "trial_name": null,
1255
+ "trial_params": null
1256
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37558cbc88ba261791fbfa1f320a80e38b6c62c51b94e8ff0512ef16db3ba9ad
3
+ size 3963
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81c0462b675a85b248a7b6537c4d3d9a5e4b9c8b322a3e064de8894ce1945002
3
  size 12653389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cdf72c7c6e7bd5b777684aad2cf16df5744107b4acbc7a32022b58b61317b56
3
  size 12653389
runs/May07_17-47-06_bc858596195a/events.out.tfevents.1683481716.bc858596195a.2495.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88d95925162d14f74e114d98637d90fca91ab916db9afd00f301c65c61ba1987
3
- size 30384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572e55450fce163e3772791afe841d2bda83520a192872f6e86336f33093c608
3
+ size 36935