ChiefTheLord commited on
Commit
6382633
verified
1 Parent(s): 8164967

Upload folder using huggingface_hub

Browse files
flickr8k_checkpoints/checkpoint-1208-3/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd6caea71cd8e491a2a43b49a2be0227ad74438b7cd5722c2e703ccb6c3153f5
3
+ size 17064932
flickr8k_checkpoints/checkpoint-1208-3/eval_state.json ADDED
The diff for this file is too large to render. See raw diff
 
flickr8k_checkpoints/checkpoint-1208-3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd1d47860fbb87b0aa1e4bda9a10742f79a7ac607ab40ab8ea6f158d54ce83e1
3
+ size 8714492
flickr8k_checkpoints/checkpoint-1208-3/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
3
+ size 14244
flickr8k_checkpoints/checkpoint-1208-3/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3e73f8453438b5e0ecf34f18571b104730680a22bd17ba39c6cbb4abc3c4e1
3
+ size 1064
flickr8k_checkpoints/checkpoint-1208-3/trainer_state.json ADDED
@@ -0,0 +1,597 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1208,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.026490066225165563,
13
+ "grad_norm": 0.11564613878726959,
14
+ "learning_rate": 0.0002909090909090909,
15
+ "loss": 4.2418,
16
+ "step": 16
17
+ },
18
+ {
19
+ "epoch": 0.052980132450331126,
20
+ "grad_norm": 0.1578957885503769,
21
+ "learning_rate": 0.0005818181818181818,
22
+ "loss": 4.2091,
23
+ "step": 32
24
+ },
25
+ {
26
+ "epoch": 0.07947019867549669,
27
+ "grad_norm": 0.1304423213005066,
28
+ "learning_rate": 0.0008727272727272727,
29
+ "loss": 4.2465,
30
+ "step": 48
31
+ },
32
+ {
33
+ "epoch": 0.10596026490066225,
34
+ "grad_norm": 0.10893953591585159,
35
+ "learning_rate": 0.000999935260121849,
36
+ "loss": 4.2564,
37
+ "step": 64
38
+ },
39
+ {
40
+ "epoch": 0.13245033112582782,
41
+ "grad_norm": NaN,
42
+ "learning_rate": 0.0009996475611356265,
43
+ "loss": 4.3268,
44
+ "step": 80
45
+ },
46
+ {
47
+ "epoch": 0.15894039735099338,
48
+ "grad_norm": 0.27315816283226013,
49
+ "learning_rate": 0.0009989644972149974,
50
+ "loss": 4.5193,
51
+ "step": 96
52
+ },
53
+ {
54
+ "epoch": 0.18543046357615894,
55
+ "grad_norm": 0.15050475299358368,
56
+ "learning_rate": 0.0009978403169274923,
57
+ "loss": 4.3326,
58
+ "step": 112
59
+ },
60
+ {
61
+ "epoch": 0.2119205298013245,
62
+ "grad_norm": 0.1476626694202423,
63
+ "learning_rate": 0.0009963087032372798,
64
+ "loss": 4.2814,
65
+ "step": 128
66
+ },
67
+ {
68
+ "epoch": 0.23841059602649006,
69
+ "grad_norm": 0.1896609663963318,
70
+ "learning_rate": 0.0009943709096197333,
71
+ "loss": 4.2676,
72
+ "step": 144
73
+ },
74
+ {
75
+ "epoch": 0.26490066225165565,
76
+ "grad_norm": 0.1512547880411148,
77
+ "learning_rate": 0.0009920285219686038,
78
+ "loss": 4.2645,
79
+ "step": 160
80
+ },
81
+ {
82
+ "epoch": 0.2913907284768212,
83
+ "grad_norm": 0.12154504656791687,
84
+ "learning_rate": 0.0009892834572981198,
85
+ "loss": 4.2505,
86
+ "step": 176
87
+ },
88
+ {
89
+ "epoch": 0.31788079470198677,
90
+ "grad_norm": 0.13387857377529144,
91
+ "learning_rate": 0.0009861379621741002,
92
+ "loss": 4.3049,
93
+ "step": 192
94
+ },
95
+ {
96
+ "epoch": 0.3443708609271523,
97
+ "grad_norm": 0.16470806300640106,
98
+ "learning_rate": 0.000982594610875361,
99
+ "loss": 4.2596,
100
+ "step": 208
101
+ },
102
+ {
103
+ "epoch": 0.3708609271523179,
104
+ "grad_norm": 0.1650277078151703,
105
+ "learning_rate": 0.0009786563032869206,
106
+ "loss": 4.2672,
107
+ "step": 224
108
+ },
109
+ {
110
+ "epoch": 0.3973509933774834,
111
+ "grad_norm": 0.1540132761001587,
112
+ "learning_rate": 0.0009743262625267291,
113
+ "loss": 4.2312,
114
+ "step": 240
115
+ },
116
+ {
117
+ "epoch": 0.423841059602649,
118
+ "grad_norm": 0.14208297431468964,
119
+ "learning_rate": 0.0009696080323078621,
120
+ "loss": 4.2553,
121
+ "step": 256
122
+ },
123
+ {
124
+ "epoch": 0.4503311258278146,
125
+ "grad_norm": 0.15346458554267883,
126
+ "learning_rate": 0.0009645054740383405,
127
+ "loss": 4.2345,
128
+ "step": 272
129
+ },
130
+ {
131
+ "epoch": 0.4768211920529801,
132
+ "grad_norm": 0.1598355919122696,
133
+ "learning_rate": 0.0009590227636609466,
134
+ "loss": 4.2213,
135
+ "step": 288
136
+ },
137
+ {
138
+ "epoch": 0.5033112582781457,
139
+ "grad_norm": 0.1300026923418045,
140
+ "learning_rate": 0.0009531643882356256,
141
+ "loss": 4.2341,
142
+ "step": 304
143
+ },
144
+ {
145
+ "epoch": 0.5298013245033113,
146
+ "grad_norm": 0.1506415605545044,
147
+ "learning_rate": 0.0009469351422672671,
148
+ "loss": 4.2086,
149
+ "step": 320
150
+ },
151
+ {
152
+ "epoch": 0.5562913907284768,
153
+ "grad_norm": 0.16757439076900482,
154
+ "learning_rate": 0.0009403401237818746,
155
+ "loss": 4.2628,
156
+ "step": 336
157
+ },
158
+ {
159
+ "epoch": 0.5827814569536424,
160
+ "grad_norm": 0.1415826976299286,
161
+ "learning_rate": 0.0009333847301543313,
162
+ "loss": 4.2355,
163
+ "step": 352
164
+ },
165
+ {
166
+ "epoch": 0.609271523178808,
167
+ "grad_norm": 0.13007712364196777,
168
+ "learning_rate": 0.000926074653691179,
169
+ "loss": 4.2479,
170
+ "step": 368
171
+ },
172
+ {
173
+ "epoch": 0.6357615894039735,
174
+ "grad_norm": 0.1218252032995224,
175
+ "learning_rate": 0.0009184158769720245,
176
+ "loss": 4.1968,
177
+ "step": 384
178
+ },
179
+ {
180
+ "epoch": 0.6622516556291391,
181
+ "grad_norm": 0.10318508744239807,
182
+ "learning_rate": 0.0009104146679533853,
183
+ "loss": 4.1951,
184
+ "step": 400
185
+ },
186
+ {
187
+ "epoch": 0.6887417218543046,
188
+ "grad_norm": 0.13795863091945648,
189
+ "learning_rate": 0.0009020775748389835,
190
+ "loss": 4.2211,
191
+ "step": 416
192
+ },
193
+ {
194
+ "epoch": 0.7152317880794702,
195
+ "grad_norm": 0.12145347148180008,
196
+ "learning_rate": 0.0008934114207206839,
197
+ "loss": 4.2205,
198
+ "step": 432
199
+ },
200
+ {
201
+ "epoch": 0.7417218543046358,
202
+ "grad_norm": 0.17534999549388885,
203
+ "learning_rate": 0.0008844232979944625,
204
+ "loss": 4.2268,
205
+ "step": 448
206
+ },
207
+ {
208
+ "epoch": 0.7682119205298014,
209
+ "grad_norm": 0.10548972338438034,
210
+ "learning_rate": 0.0008751205625559793,
211
+ "loss": 4.1812,
212
+ "step": 464
213
+ },
214
+ {
215
+ "epoch": 0.7947019867549668,
216
+ "grad_norm": 0.13653944432735443,
217
+ "learning_rate": 0.0008655108277804975,
218
+ "loss": 4.2384,
219
+ "step": 480
220
+ },
221
+ {
222
+ "epoch": 0.8211920529801324,
223
+ "grad_norm": 0.10747593641281128,
224
+ "learning_rate": 0.0008556019582920858,
225
+ "loss": 4.1865,
226
+ "step": 496
227
+ },
228
+ {
229
+ "epoch": 0.847682119205298,
230
+ "grad_norm": 0.14204978942871094,
231
+ "learning_rate": 0.0008454020635271946,
232
+ "loss": 4.2336,
233
+ "step": 512
234
+ },
235
+ {
236
+ "epoch": 0.8741721854304636,
237
+ "grad_norm": 0.11056042462587357,
238
+ "learning_rate": 0.0008349194910978794,
239
+ "loss": 4.2171,
240
+ "step": 528
241
+ },
242
+ {
243
+ "epoch": 0.9006622516556292,
244
+ "grad_norm": 0.1293727457523346,
245
+ "learning_rate": 0.0008241628199601004,
246
+ "loss": 4.2047,
247
+ "step": 544
248
+ },
249
+ {
250
+ "epoch": 0.9271523178807947,
251
+ "grad_norm": 0.12752275168895721,
252
+ "learning_rate": 0.0008131408533926887,
253
+ "loss": 4.2315,
254
+ "step": 560
255
+ },
256
+ {
257
+ "epoch": 0.9536423841059603,
258
+ "grad_norm": 0.12166760861873627,
259
+ "learning_rate": 0.0008018626117927285,
260
+ "loss": 4.2029,
261
+ "step": 576
262
+ },
263
+ {
264
+ "epoch": 0.9801324503311258,
265
+ "grad_norm": 0.11871915310621262,
266
+ "learning_rate": 0.0007903373252932473,
267
+ "loss": 4.2852,
268
+ "step": 592
269
+ },
270
+ {
271
+ "epoch": 1.0,
272
+ "eval_bleu": 0.11357860800298936,
273
+ "eval_cap_loss": 1.2068630535870988,
274
+ "eval_con_loss": 1.7581481718464402,
275
+ "eval_loss": 2.9650112303676983,
276
+ "step": 604
277
+ },
278
+ {
279
+ "epoch": 1.0,
280
+ "eval_bleu": 0.11357860800298936,
281
+ "eval_cap_loss": 1.2068630535870988,
282
+ "eval_con_loss": 1.7581481718464402,
283
+ "eval_loss": 2.9650112303676983,
284
+ "eval_runtime": 251.6434,
285
+ "eval_samples_per_second": 19.19,
286
+ "eval_steps_per_second": 2.4,
287
+ "step": 604
288
+ },
289
+ {
290
+ "epoch": 1.0066225165562914,
291
+ "grad_norm": 0.138542041182518,
292
+ "learning_rate": 0.0007785744262092583,
293
+ "loss": 4.1782,
294
+ "step": 608
295
+ },
296
+ {
297
+ "epoch": 1.033112582781457,
298
+ "grad_norm": 0.12109135836362839,
299
+ "learning_rate": 0.0007665835413183377,
300
+ "loss": 4.2106,
301
+ "step": 624
302
+ },
303
+ {
304
+ "epoch": 1.0596026490066226,
305
+ "grad_norm": 0.1121225655078888,
306
+ "learning_rate": 0.0007543744839820527,
307
+ "loss": 4.2174,
308
+ "step": 640
309
+ },
310
+ {
311
+ "epoch": 1.086092715231788,
312
+ "grad_norm": 0.13030825555324554,
313
+ "learning_rate": 0.0007419572461146878,
314
+ "loss": 4.2266,
315
+ "step": 656
316
+ },
317
+ {
318
+ "epoch": 1.1125827814569536,
319
+ "grad_norm": 0.13000358641147614,
320
+ "learning_rate": 0.0007293419900058461,
321
+ "loss": 4.2382,
322
+ "step": 672
323
+ },
324
+ {
325
+ "epoch": 1.1390728476821192,
326
+ "grad_norm": 0.11486734449863434,
327
+ "learning_rate": 0.0007165390400036121,
328
+ "loss": 4.2109,
329
+ "step": 688
330
+ },
331
+ {
332
+ "epoch": 1.1655629139072847,
333
+ "grad_norm": 0.14996080100536346,
334
+ "learning_rate": 0.0007035588740650869,
335
+ "loss": 4.2108,
336
+ "step": 704
337
+ },
338
+ {
339
+ "epoch": 1.1920529801324504,
340
+ "grad_norm": 0.14913493394851685,
341
+ "learning_rate": 0.0006904121151812103,
342
+ "loss": 4.2348,
343
+ "step": 720
344
+ },
345
+ {
346
+ "epoch": 1.218543046357616,
347
+ "grad_norm": 0.13646364212036133,
348
+ "learning_rate": 0.0006771095226828851,
349
+ "loss": 4.2132,
350
+ "step": 736
351
+ },
352
+ {
353
+ "epoch": 1.2450331125827814,
354
+ "grad_norm": 0.13403132557868958,
355
+ "learning_rate": 0.000663661983435522,
356
+ "loss": 4.2449,
357
+ "step": 752
358
+ },
359
+ {
360
+ "epoch": 1.271523178807947,
361
+ "grad_norm": 0.1351315826177597,
362
+ "learning_rate": 0.0006500805029292096,
363
+ "loss": 4.2279,
364
+ "step": 768
365
+ },
366
+ {
367
+ "epoch": 1.2980132450331126,
368
+ "grad_norm": 0.14671947062015533,
369
+ "learning_rate": 0.0006363761962718013,
370
+ "loss": 4.2138,
371
+ "step": 784
372
+ },
373
+ {
374
+ "epoch": 1.3245033112582782,
375
+ "grad_norm": 0.1569669097661972,
376
+ "learning_rate": 0.0006225602790922919,
377
+ "loss": 4.2576,
378
+ "step": 800
379
+ },
380
+ {
381
+ "epoch": 1.3509933774834437,
382
+ "grad_norm": 0.12304583936929703,
383
+ "learning_rate": 0.0006086440583619257,
384
+ "loss": 4.204,
385
+ "step": 816
386
+ },
387
+ {
388
+ "epoch": 1.3774834437086092,
389
+ "grad_norm": 0.13470305502414703,
390
+ "learning_rate": 0.0005946389231405527,
391
+ "loss": 4.1778,
392
+ "step": 832
393
+ },
394
+ {
395
+ "epoch": 1.403973509933775,
396
+ "grad_norm": 0.13378113508224487,
397
+ "learning_rate": 0.0005805563352558001,
398
+ "loss": 4.2009,
399
+ "step": 848
400
+ },
401
+ {
402
+ "epoch": 1.4304635761589404,
403
+ "grad_norm": 0.12280265986919403,
404
+ "learning_rate": 0.0005664078199226932,
405
+ "loss": 4.2123,
406
+ "step": 864
407
+ },
408
+ {
409
+ "epoch": 1.4569536423841059,
410
+ "grad_norm": 0.12556259334087372,
411
+ "learning_rate": 0.0005522049563113985,
412
+ "loss": 4.2105,
413
+ "step": 880
414
+ },
415
+ {
416
+ "epoch": 1.4834437086092715,
417
+ "grad_norm": 0.15261654555797577,
418
+ "learning_rate": 0.00053795936807081,
419
+ "loss": 4.1831,
420
+ "step": 896
421
+ },
422
+ {
423
+ "epoch": 1.5099337748344372,
424
+ "grad_norm": 0.13838866353034973,
425
+ "learning_rate": 0.000523682713815735,
426
+ "loss": 4.2642,
427
+ "step": 912
428
+ },
429
+ {
430
+ "epoch": 1.5364238410596025,
431
+ "grad_norm": 0.15466028451919556,
432
+ "learning_rate": 0.0005093866775854617,
433
+ "loss": 4.171,
434
+ "step": 928
435
+ },
436
+ {
437
+ "epoch": 1.5629139072847682,
438
+ "grad_norm": 0.11547879874706268,
439
+ "learning_rate": 0.0004950829592815223,
440
+ "loss": 4.2169,
441
+ "step": 944
442
+ },
443
+ {
444
+ "epoch": 1.589403973509934,
445
+ "grad_norm": 0.12350811809301376,
446
+ "learning_rate": 0.00048078326509247063,
447
+ "loss": 4.2108,
448
+ "step": 960
449
+ },
450
+ {
451
+ "epoch": 1.6158940397350994,
452
+ "grad_norm": 0.10781528055667877,
453
+ "learning_rate": 0.00046649929791351845,
454
+ "loss": 4.206,
455
+ "step": 976
456
+ },
457
+ {
458
+ "epoch": 1.6423841059602649,
459
+ "grad_norm": 0.13244616985321045,
460
+ "learning_rate": 0.0004522427477688645,
461
+ "loss": 4.2317,
462
+ "step": 992
463
+ },
464
+ {
465
+ "epoch": 1.6688741721854305,
466
+ "grad_norm": 0.1263062059879303,
467
+ "learning_rate": 0.0004380252822445577,
468
+ "loss": 4.2293,
469
+ "step": 1008
470
+ },
471
+ {
472
+ "epoch": 1.695364238410596,
473
+ "grad_norm": 0.1073961853981018,
474
+ "learning_rate": 0.0004238585369397234,
475
+ "loss": 4.1844,
476
+ "step": 1024
477
+ },
478
+ {
479
+ "epoch": 1.7218543046357615,
480
+ "grad_norm": 0.13431046903133392,
481
+ "learning_rate": 0.0004097541059439698,
482
+ "loss": 4.238,
483
+ "step": 1040
484
+ },
485
+ {
486
+ "epoch": 1.7483443708609272,
487
+ "grad_norm": 0.15358257293701172,
488
+ "learning_rate": 0.0003957235323487627,
489
+ "loss": 4.1404,
490
+ "step": 1056
491
+ },
492
+ {
493
+ "epoch": 1.7748344370860927,
494
+ "grad_norm": 0.1152401864528656,
495
+ "learning_rate": 0.0003817782988005406,
496
+ "loss": 4.193,
497
+ "step": 1072
498
+ },
499
+ {
500
+ "epoch": 1.8013245033112582,
501
+ "grad_norm": 0.13397790491580963,
502
+ "learning_rate": 0.0003679298181032945,
503
+ "loss": 4.2675,
504
+ "step": 1088
505
+ },
506
+ {
507
+ "epoch": 1.8278145695364238,
508
+ "grad_norm": 0.162140354514122,
509
+ "learning_rate": 0.0003541894238783103,
510
+ "loss": 4.2154,
511
+ "step": 1104
512
+ },
513
+ {
514
+ "epoch": 1.8543046357615895,
515
+ "grad_norm": 0.1030549705028534,
516
+ "learning_rate": 0.0003405683612887119,
517
+ "loss": 4.1875,
518
+ "step": 1120
519
+ },
520
+ {
521
+ "epoch": 1.8807947019867548,
522
+ "grad_norm": 0.10110848397016525,
523
+ "learning_rate": 0.0003270777778364006,
524
+ "loss": 4.2297,
525
+ "step": 1136
526
+ },
527
+ {
528
+ "epoch": 1.9072847682119205,
529
+ "grad_norm": 0.14263297617435455,
530
+ "learning_rate": 0.0003137287142389189,
531
+ "loss": 4.1828,
532
+ "step": 1152
533
+ },
534
+ {
535
+ "epoch": 1.9337748344370862,
536
+ "grad_norm": 0.13545271754264832,
537
+ "learning_rate": 0.00030053209539370796,
538
+ "loss": 4.1771,
539
+ "step": 1168
540
+ },
541
+ {
542
+ "epoch": 1.9602649006622517,
543
+ "grad_norm": 0.11357877403497696,
544
+ "learning_rate": 0.00028749872143715184,
545
+ "loss": 4.1762,
546
+ "step": 1184
547
+ },
548
+ {
549
+ "epoch": 1.9867549668874172,
550
+ "grad_norm": 0.13197988271713257,
551
+ "learning_rate": 0.00027463925890572647,
552
+ "loss": 4.2652,
553
+ "step": 1200
554
+ },
555
+ {
556
+ "epoch": 2.0,
557
+ "eval_bleu": 0.11904233957006984,
558
+ "eval_cap_loss": 1.1917654163395333,
559
+ "eval_con_loss": 1.7444044217368624,
560
+ "eval_loss": 2.936169837089564,
561
+ "step": 1208
562
+ },
563
+ {
564
+ "epoch": 2.0,
565
+ "eval_bleu": 0.11904233957006984,
566
+ "eval_cap_loss": 1.1917654163395333,
567
+ "eval_con_loss": 1.7444044217368624,
568
+ "eval_loss": 2.936169837089564,
569
+ "eval_runtime": 251.4943,
570
+ "eval_samples_per_second": 19.201,
571
+ "eval_steps_per_second": 2.402,
572
+ "step": 1208
573
+ }
574
+ ],
575
+ "logging_steps": 16,
576
+ "max_steps": 1812,
577
+ "num_input_tokens_seen": 0,
578
+ "num_train_epochs": 3,
579
+ "save_steps": 500,
580
+ "stateful_callbacks": {
581
+ "TrainerControl": {
582
+ "args": {
583
+ "should_epoch_stop": false,
584
+ "should_evaluate": false,
585
+ "should_log": false,
586
+ "should_save": true,
587
+ "should_training_stop": false
588
+ },
589
+ "attributes": {}
590
+ }
591
+ },
592
+ "total_flos": 0.0,
593
+ "train_batch_size": 32,
594
+ "trial_name": null,
595
+ "trial_params": null,
596
+ "tau_value": 6.0390
597
+ }