ChiefTheLord commited on
Commit
6696da0
verified
1 Parent(s): 6382633

Upload folder using huggingface_hub

Browse files
flickr8k_checkpoints/checkpoint-1208-4/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:036ae2e3f68d8825f647fd122ccafb02672fdd5778c3ae2173a7ebf151133ec0
3
+ size 17064932
flickr8k_checkpoints/checkpoint-1208-4/eval_state.json ADDED
The diff for this file is too large to render. See raw diff
 
flickr8k_checkpoints/checkpoint-1208-4/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a74396a35b61b52ab12c8535187e9775329dc481983cd70a61f0b20dbfcf419
3
+ size 8714492
flickr8k_checkpoints/checkpoint-1208-4/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-1208-4/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229084bbb0e922d44dba4cc9206f54220a162a8229897c2f3d636ef81c5c5418
3
+ size 1064
flickr8k_checkpoints/checkpoint-1208-4/trainer_state.json ADDED
@@ -0,0 +1,596 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.1006568893790245,
14
+ "learning_rate": 0.0004324324324324325,
15
+ "loss": 4.0361,
16
+ "step": 16
17
+ },
18
+ {
19
+ "epoch": 0.052980132450331126,
20
+ "grad_norm": 0.1183805838227272,
21
+ "learning_rate": 0.000864864864864865,
22
+ "loss": 3.9854,
23
+ "step": 32
24
+ },
25
+ {
26
+ "epoch": 0.07947019867549669,
27
+ "grad_norm": 0.11201324313879013,
28
+ "learning_rate": 0.0009997822892796068,
29
+ "loss": 4.0121,
30
+ "step": 48
31
+ },
32
+ {
33
+ "epoch": 0.10596026490066225,
34
+ "grad_norm": 0.13807597756385803,
35
+ "learning_rate": 0.000998688816161266,
36
+ "loss": 4.0147,
37
+ "step": 64
38
+ },
39
+ {
40
+ "epoch": 0.13245033112582782,
41
+ "grad_norm": 0.1787775456905365,
42
+ "learning_rate": 0.0009966766110013582,
43
+ "loss": 4.0057,
44
+ "step": 80
45
+ },
46
+ {
47
+ "epoch": 0.15894039735099338,
48
+ "grad_norm": 0.1131894588470459,
49
+ "learning_rate": 0.0009937493808759087,
50
+ "loss": 4.0668,
51
+ "step": 96
52
+ },
53
+ {
54
+ "epoch": 0.18543046357615894,
55
+ "grad_norm": 0.13122417032718658,
56
+ "learning_rate": 0.0009899125186070988,
57
+ "loss": 4.0053,
58
+ "step": 112
59
+ },
60
+ {
61
+ "epoch": 0.2119205298013245,
62
+ "grad_norm": 0.1222459226846695,
63
+ "learning_rate": 0.0009851730928280944,
64
+ "loss": 3.9903,
65
+ "step": 128
66
+ },
67
+ {
68
+ "epoch": 0.23841059602649006,
69
+ "grad_norm": 0.11710074543952942,
70
+ "learning_rate": 0.0009795398349605373,
71
+ "loss": 3.9932,
72
+ "step": 144
73
+ },
74
+ {
75
+ "epoch": 0.26490066225165565,
76
+ "grad_norm": 0.11267052590847015,
77
+ "learning_rate": 0.0009730231231286876,
78
+ "loss": 3.9942,
79
+ "step": 160
80
+ },
81
+ {
82
+ "epoch": 0.2913907284768212,
83
+ "grad_norm": 0.11705270409584045,
84
+ "learning_rate": 0.0009656349630398554,
85
+ "loss": 3.9903,
86
+ "step": 176
87
+ },
88
+ {
89
+ "epoch": 0.31788079470198677,
90
+ "grad_norm": 0.11069143563508987,
91
+ "learning_rate": 0.0009573889658663424,
92
+ "loss": 4.0288,
93
+ "step": 192
94
+ },
95
+ {
96
+ "epoch": 0.3443708609271523,
97
+ "grad_norm": 0.12676870822906494,
98
+ "learning_rate": 0.0009483003231696446,
99
+ "loss": 3.9981,
100
+ "step": 208
101
+ },
102
+ {
103
+ "epoch": 0.3708609271523179,
104
+ "grad_norm": 0.1115901842713356,
105
+ "learning_rate": 0.0009383857789131097,
106
+ "loss": 3.9991,
107
+ "step": 224
108
+ },
109
+ {
110
+ "epoch": 0.3973509933774834,
111
+ "grad_norm": 0.10467631369829178,
112
+ "learning_rate": 0.0009276635986146136,
113
+ "loss": 3.9799,
114
+ "step": 240
115
+ },
116
+ {
117
+ "epoch": 0.423841059602649,
118
+ "grad_norm": 0.09870990365743637,
119
+ "learning_rate": 0.0009161535356960828,
120
+ "loss": 4.0001,
121
+ "step": 256
122
+ },
123
+ {
124
+ "epoch": 0.4503311258278146,
125
+ "grad_norm": 0.10558207333087921,
126
+ "learning_rate": 0.0009038767950918592,
127
+ "loss": 3.9763,
128
+ "step": 272
129
+ },
130
+ {
131
+ "epoch": 0.4768211920529801,
132
+ "grad_norm": 0.10417157411575317,
133
+ "learning_rate": 0.0008908559941829497,
134
+ "loss": 3.9728,
135
+ "step": 288
136
+ },
137
+ {
138
+ "epoch": 0.5033112582781457,
139
+ "grad_norm": 0.10544515401124954,
140
+ "learning_rate": 0.0008771151211291332,
141
+ "loss": 3.9765,
142
+ "step": 304
143
+ },
144
+ {
145
+ "epoch": 0.5298013245033113,
146
+ "grad_norm": 0.10653045773506165,
147
+ "learning_rate": 0.0008626794906756866,
148
+ "loss": 3.9607,
149
+ "step": 320
150
+ },
151
+ {
152
+ "epoch": 0.5562913907284768,
153
+ "grad_norm": 0.11847585439682007,
154
+ "learning_rate": 0.0008475756975161504,
155
+ "loss": 3.9961,
156
+ "step": 336
157
+ },
158
+ {
159
+ "epoch": 0.5827814569536424,
160
+ "grad_norm": 0.1187497153878212,
161
+ "learning_rate": 0.00083183156729705,
162
+ "loss": 3.984,
163
+ "step": 352
164
+ },
165
+ {
166
+ "epoch": 0.609271523178808,
167
+ "grad_norm": 0.10147203505039215,
168
+ "learning_rate": 0.0008154761053548404,
169
+ "loss": 3.9921,
170
+ "step": 368
171
+ },
172
+ {
173
+ "epoch": 0.6357615894039735,
174
+ "grad_norm": 0.10544505715370178,
175
+ "learning_rate": 0.000798539443279511,
176
+ "loss": 3.9585,
177
+ "step": 384
178
+ },
179
+ {
180
+ "epoch": 0.6622516556291391,
181
+ "grad_norm": 0.10036241263151169,
182
+ "learning_rate": 0.0007810527834033009,
183
+ "loss": 3.9603,
184
+ "step": 400
185
+ },
186
+ {
187
+ "epoch": 0.6887417218543046,
188
+ "grad_norm": 0.11926663666963577,
189
+ "learning_rate": 0.00076304834131679,
190
+ "loss": 3.9728,
191
+ "step": 416
192
+ },
193
+ {
194
+ "epoch": 0.7152317880794702,
195
+ "grad_norm": 0.16939891874790192,
196
+ "learning_rate": 0.0007445592865182695,
197
+ "loss": 3.9824,
198
+ "step": 432
199
+ },
200
+ {
201
+ "epoch": 0.7417218543046358,
202
+ "grad_norm": 0.10274316370487213,
203
+ "learning_rate": 0.0007256196813057318,
204
+ "loss": 3.979,
205
+ "step": 448
206
+ },
207
+ {
208
+ "epoch": 0.7682119205298014,
209
+ "grad_norm": 0.09025011956691742,
210
+ "learning_rate": 0.0007062644180240614,
211
+ "loss": 3.9383,
212
+ "step": 464
213
+ },
214
+ {
215
+ "epoch": 0.7947019867549668,
216
+ "grad_norm": 0.10321378707885742,
217
+ "learning_rate": 0.0006865291547830324,
218
+ "loss": 3.9936,
219
+ "step": 480
220
+ },
221
+ {
222
+ "epoch": 0.8211920529801324,
223
+ "grad_norm": 0.09555677324533463,
224
+ "learning_rate": 0.000666450249764542,
225
+ "loss": 3.9505,
226
+ "step": 496
227
+ },
228
+ {
229
+ "epoch": 0.847682119205298,
230
+ "grad_norm": 0.11583372205495834,
231
+ "learning_rate": 0.0006460646942401058,
232
+ "loss": 3.9876,
233
+ "step": 512
234
+ },
235
+ {
236
+ "epoch": 0.8741721854304636,
237
+ "grad_norm": 0.09818309545516968,
238
+ "learning_rate": 0.0006254100444220115,
239
+ "loss": 3.9674,
240
+ "step": 528
241
+ },
242
+ {
243
+ "epoch": 0.9006622516556292,
244
+ "grad_norm": 0.12466709315776825,
245
+ "learning_rate": 0.0006045243522736885,
246
+ "loss": 3.9644,
247
+ "step": 544
248
+ },
249
+ {
250
+ "epoch": 0.9271523178807947,
251
+ "grad_norm": 0.10327574610710144,
252
+ "learning_rate": 0.0005834460954067559,
253
+ "loss": 3.9836,
254
+ "step": 560
255
+ },
256
+ {
257
+ "epoch": 0.9536423841059603,
258
+ "grad_norm": 0.10383777320384979,
259
+ "learning_rate": 0.0005622141061939006,
260
+ "loss": 3.9671,
261
+ "step": 576
262
+ },
263
+ {
264
+ "epoch": 0.9801324503311258,
265
+ "grad_norm": 0.09883040934801102,
266
+ "learning_rate": 0.0005408675002281818,
267
+ "loss": 4.0353,
268
+ "step": 592
269
+ },
270
+ {
271
+ "epoch": 1.0,
272
+ "eval_bleu": 0.08384055402908269,
273
+ "eval_cap_loss": 0.8933286312104061,
274
+ "eval_con_loss": 1.7258543496495051,
275
+ "eval_loss": 2.6191829849552635,
276
+ "step": 604
277
+ },
278
+ {
279
+ "epoch": 1.0,
280
+ "eval_bleu": 0.08384055402908269,
281
+ "eval_cap_loss": 0.8933286312104061,
282
+ "eval_con_loss": 1.7258543496495051,
283
+ "eval_loss": 2.6191829849552635,
284
+ "eval_runtime": 254.3476,
285
+ "eval_samples_per_second": 18.986,
286
+ "eval_steps_per_second": 2.375,
287
+ "step": 604
288
+ },
289
+ {
290
+ "epoch": 1.0066225165562914,
291
+ "grad_norm": 0.14657221734523773,
292
+ "learning_rate": 0.0005194456042605587,
293
+ "loss": 3.9395,
294
+ "step": 608
295
+ },
296
+ {
297
+ "epoch": 1.033112582781457,
298
+ "grad_norm": 0.08521195501089096,
299
+ "learning_rate": 0.0004979878837484043,
300
+ "loss": 3.9684,
301
+ "step": 624
302
+ },
303
+ {
304
+ "epoch": 1.0596026490066226,
305
+ "grad_norm": 0.10343234986066818,
306
+ "learning_rate": 0.00047653387014848014,
307
+ "loss": 3.9778,
308
+ "step": 640
309
+ },
310
+ {
311
+ "epoch": 1.086092715231788,
312
+ "grad_norm": 0.1191788986325264,
313
+ "learning_rate": 0.0004551230880883208,
314
+ "loss": 3.9832,
315
+ "step": 656
316
+ },
317
+ {
318
+ "epoch": 1.1125827814569536,
319
+ "grad_norm": 0.10124525427818298,
320
+ "learning_rate": 0.00043379498255020037,
321
+ "loss": 3.9897,
322
+ "step": 672
323
+ },
324
+ {
325
+ "epoch": 1.1390728476821192,
326
+ "grad_norm": 0.11849219352006912,
327
+ "learning_rate": 0.00041258884620182804,
328
+ "loss": 3.9687,
329
+ "step": 688
330
+ },
331
+ {
332
+ "epoch": 1.1655629139072847,
333
+ "grad_norm": 0.12588591873645782,
334
+ "learning_rate": 0.00039154374700765316,
335
+ "loss": 3.9728,
336
+ "step": 704
337
+ },
338
+ {
339
+ "epoch": 1.1920529801324504,
340
+ "grad_norm": 0.1349213719367981,
341
+ "learning_rate": 0.00037069845625413954,
342
+ "loss": 3.9878,
343
+ "step": 720
344
+ },
345
+ {
346
+ "epoch": 1.218543046357616,
347
+ "grad_norm": 0.14282754063606262,
348
+ "learning_rate": 0.0003500913771216081,
349
+ "loss": 3.9699,
350
+ "step": 736
351
+ },
352
+ {
353
+ "epoch": 1.2450331125827814,
354
+ "grad_norm": 0.11279956251382828,
355
+ "learning_rate": 0.0003297604739342396,
356
+ "loss": 3.9934,
357
+ "step": 752
358
+ },
359
+ {
360
+ "epoch": 1.271523178807947,
361
+ "grad_norm": 0.13443419337272644,
362
+ "learning_rate": 0.00030974320221858066,
363
+ "loss": 3.9864,
364
+ "step": 768
365
+ },
366
+ {
367
+ "epoch": 1.2980132450331126,
368
+ "grad_norm": 0.10932871699333191,
369
+ "learning_rate": 0.0002900764396994049,
370
+ "loss": 3.9739,
371
+ "step": 784
372
+ },
373
+ {
374
+ "epoch": 1.3245033112582782,
375
+ "grad_norm": 0.13860152661800385,
376
+ "learning_rate": 0.00027079641836005473,
377
+ "loss": 4.007,
378
+ "step": 800
379
+ },
380
+ {
381
+ "epoch": 1.3509933774834437,
382
+ "grad_norm": 0.10841521620750427,
383
+ "learning_rate": 0.0002519386576924303,
384
+ "loss": 3.9644,
385
+ "step": 816
386
+ },
387
+ {
388
+ "epoch": 1.3774834437086092,
389
+ "grad_norm": 0.12144733220338821,
390
+ "learning_rate": 0.0002335378992595995,
391
+ "loss": 3.9399,
392
+ "step": 832
393
+ },
394
+ {
395
+ "epoch": 1.403973509933775,
396
+ "grad_norm": 0.13902397453784943,
397
+ "learning_rate": 0.0002156280426915786,
398
+ "loss": 3.9591,
399
+ "step": 848
400
+ },
401
+ {
402
+ "epoch": 1.4304635761589404,
403
+ "grad_norm": 0.10983491688966751,
404
+ "learning_rate": 0.00019824208323220656,
405
+ "loss": 3.9748,
406
+ "step": 864
407
+ },
408
+ {
409
+ "epoch": 1.4569536423841059,
410
+ "grad_norm": 0.11976425349712372,
411
+ "learning_rate": 0.00018141205095216294,
412
+ "loss": 3.9727,
413
+ "step": 880
414
+ },
415
+ {
416
+ "epoch": 1.4834437086092715,
417
+ "grad_norm": 0.10822241753339767,
418
+ "learning_rate": 0.00016516895174012043,
419
+ "loss": 3.9448,
420
+ "step": 896
421
+ },
422
+ {
423
+ "epoch": 1.5099337748344372,
424
+ "grad_norm": 0.099924236536026,
425
+ "learning_rate": 0.00014954271018074368,
426
+ "loss": 4.0026,
427
+ "step": 912
428
+ },
429
+ {
430
+ "epoch": 1.5364238410596025,
431
+ "grad_norm": 0.11151504516601562,
432
+ "learning_rate": 0.00013456211442476813,
433
+ "loss": 3.9316,
434
+ "step": 928
435
+ },
436
+ {
437
+ "epoch": 1.5629139072847682,
438
+ "grad_norm": 0.09520285576581955,
439
+ "learning_rate": 0.00012025476315272743,
440
+ "loss": 3.9738,
441
+ "step": 944
442
+ },
443
+ {
444
+ "epoch": 1.589403973509934,
445
+ "grad_norm": 0.10799151659011841,
446
+ "learning_rate": 0.00010664701473003396,
447
+ "loss": 3.9736,
448
+ "step": 960
449
+ },
450
+ {
451
+ "epoch": 1.6158940397350994,
452
+ "grad_norm": 0.09459669888019562,
453
+ "learning_rate": 9.376393864708821e-05,
454
+ "loss": 3.9652,
455
+ "step": 976
456
+ },
457
+ {
458
+ "epoch": 1.6423841059602649,
459
+ "grad_norm": 0.10165199637413025,
460
+ "learning_rate": 8.162926933387499e-05,
461
+ "loss": 3.9841,
462
+ "step": 992
463
+ },
464
+ {
465
+ "epoch": 1.6688741721854305,
466
+ "grad_norm": 0.1313178986310959,
467
+ "learning_rate": 7.026536243413539e-05,
468
+ "loss": 3.98,
469
+ "step": 1008
470
+ },
471
+ {
472
+ "epoch": 1.695364238410596,
473
+ "grad_norm": 0.1009119376540184,
474
+ "learning_rate": 5.969315361967087e-05,
475
+ "loss": 3.9513,
476
+ "step": 1024
477
+ },
478
+ {
479
+ "epoch": 1.7218543046357615,
480
+ "grad_norm": 0.0979105681180954,
481
+ "learning_rate": 4.9932120020654116e-05,
482
+ "loss": 3.9915,
483
+ "step": 1040
484
+ },
485
+ {
486
+ "epoch": 1.7483443708609272,
487
+ "grad_norm": 0.11330430954694748,
488
+ "learning_rate": 4.100024434300437e-05,
489
+ "loss": 3.917,
490
+ "step": 1056
491
+ },
492
+ {
493
+ "epoch": 1.7748344370860927,
494
+ "grad_norm": 0.10902255028486252,
495
+ "learning_rate": 3.2913981738933395e-05,
496
+ "loss": 3.9598,
497
+ "step": 1072
498
+ },
499
+ {
500
+ "epoch": 1.8013245033112582,
501
+ "grad_norm": 0.10667652636766434,
502
+ "learning_rate": 2.5688229491697356e-05,
503
+ "loss": 4.0058,
504
+ "step": 1088
505
+ },
506
+ {
507
+ "epoch": 1.8278145695364238,
508
+ "grad_norm": 0.12808123230934143,
509
+ "learning_rate": 1.9336299570401396e-05,
510
+ "loss": 3.9747,
511
+ "step": 1104
512
+ },
513
+ {
514
+ "epoch": 1.8543046357615895,
515
+ "grad_norm": 0.08537725359201431,
516
+ "learning_rate": 1.3869894105423109e-05,
517
+ "loss": 3.9497,
518
+ "step": 1120
519
+ },
520
+ {
521
+ "epoch": 1.8807947019867548,
522
+ "grad_norm": 0.08839607983827591,
523
+ "learning_rate": 9.299083829632516e-06,
524
+ "loss": 3.9864,
525
+ "step": 1136
526
+ },
527
+ {
528
+ "epoch": 1.9072847682119205,
529
+ "grad_norm": 0.1202566921710968,
530
+ "learning_rate": 5.632289525129064e-06,
531
+ "loss": 3.9474,
532
+ "step": 1152
533
+ },
534
+ {
535
+ "epoch": 1.9337748344370862,
536
+ "grad_norm": 0.1078442707657814,
537
+ "learning_rate": 2.8762665096744854e-06,
538
+ "loss": 3.9471,
539
+ "step": 1168
540
+ },
541
+ {
542
+ "epoch": 1.9602649006622517,
543
+ "grad_norm": 0.09251430630683899,
544
+ "learning_rate": 1.036092191402882e-06,
545
+ "loss": 3.9503,
546
+ "step": 1184
547
+ },
548
+ {
549
+ "epoch": 1.9867549668874172,
550
+ "grad_norm": 0.12372814118862152,
551
+ "learning_rate": 1.1515671473599775e-07,
552
+ "loss": 4.0171,
553
+ "step": 1200
554
+ },
555
+ {
556
+ "epoch": 2.0,
557
+ "eval_bleu": 0.08026931185165223,
558
+ "eval_cap_loss": 0.88608129885023,
559
+ "eval_con_loss": 1.7209573078234464,
560
+ "eval_loss": 2.607038610226271,
561
+ "step": 1208
562
+ },
563
+ {
564
+ "epoch": 2.0,
565
+ "eval_bleu": 0.08026931185165223,
566
+ "eval_cap_loss": 0.88608129885023,
567
+ "eval_con_loss": 1.7209573078234464,
568
+ "eval_loss": 2.607038610226271,
569
+ "eval_runtime": 259.1818,
570
+ "eval_samples_per_second": 18.632,
571
+ "eval_steps_per_second": 2.33,
572
+ "step": 1208
573
+ }
574
+ ],
575
+ "logging_steps": 16,
576
+ "max_steps": 1208,
577
+ "num_input_tokens_seen": 0,
578
+ "num_train_epochs": 2,
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": true
588
+ },
589
+ "attributes": {}
590
+ }
591
+ },
592
+ "total_flos": 0.0,
593
+ "train_batch_size": 32,
594
+ "trial_name": null,
595
+ "trial_params": null
596
+ }