ChiefTheLord commited on
Commit
b5d6954
verified
1 Parent(s): a1cdbd2

Upload folder using huggingface_hub

Browse files
flickr8k_checkpoints/checkpoint-1208-2/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f54f5451268a4bbd6b7b6daa39c647e599cf7b5bdf187ab4528357db9387a43c
3
+ size 17064856
flickr8k_checkpoints/checkpoint-1208-2/eval_state.json ADDED
The diff for this file is too large to render. See raw diff
 
flickr8k_checkpoints/checkpoint-1208-2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722e0e32ef157e599cc8d9eaeb50f354d42c5b0f0cf2e8e4d098790c1b7fcd76
3
+ size 8714492
flickr8k_checkpoints/checkpoint-1208-2/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-1208-2/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc0a9e765f39568e86ed4d3a48800049bfc7ae11ff7681b748fea01958f9f05
3
+ size 1064
flickr8k_checkpoints/checkpoint-1208-2/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": 0.13324208557605743,
14
+ "learning_rate": 0.0002191780821917808,
15
+ "loss": 4.2964,
16
+ "step": 16
17
+ },
18
+ {
19
+ "epoch": 0.052980132450331126,
20
+ "grad_norm": 0.1445072889328003,
21
+ "learning_rate": 0.0004383561643835616,
22
+ "loss": 4.2649,
23
+ "step": 32
24
+ },
25
+ {
26
+ "epoch": 0.07947019867549669,
27
+ "grad_norm": 0.14529070258140564,
28
+ "learning_rate": 0.0006575342465753425,
29
+ "loss": 4.3014,
30
+ "step": 48
31
+ },
32
+ {
33
+ "epoch": 0.10596026490066225,
34
+ "grad_norm": 0.2007322758436203,
35
+ "learning_rate": 0.0008767123287671232,
36
+ "loss": 4.3097,
37
+ "step": 64
38
+ },
39
+ {
40
+ "epoch": 0.13245033112582782,
41
+ "grad_norm": NaN,
42
+ "learning_rate": 0.0009999959548269918,
43
+ "loss": 4.3854,
44
+ "step": 80
45
+ },
46
+ {
47
+ "epoch": 0.15894039735099338,
48
+ "grad_norm": 0.2345261424779892,
49
+ "learning_rate": 0.0009998377521727646,
50
+ "loss": 4.4083,
51
+ "step": 96
52
+ },
53
+ {
54
+ "epoch": 0.18543046357615894,
55
+ "grad_norm": 0.14606653153896332,
56
+ "learning_rate": 0.0009994495073085382,
57
+ "loss": 4.3126,
58
+ "step": 112
59
+ },
60
+ {
61
+ "epoch": 0.2119205298013245,
62
+ "grad_norm": 0.12169423699378967,
63
+ "learning_rate": 0.0009988313989177076,
64
+ "loss": 4.2892,
65
+ "step": 128
66
+ },
67
+ {
68
+ "epoch": 0.23841059602649006,
69
+ "grad_norm": 0.21712887287139893,
70
+ "learning_rate": 0.0009979837114746243,
71
+ "loss": 4.2891,
72
+ "step": 144
73
+ },
74
+ {
75
+ "epoch": 0.26490066225165565,
76
+ "grad_norm": 0.09952688217163086,
77
+ "learning_rate": 0.0009969068351136706,
78
+ "loss": 4.2913,
79
+ "step": 160
80
+ },
81
+ {
82
+ "epoch": 0.2913907284768212,
83
+ "grad_norm": 0.1054968312382698,
84
+ "learning_rate": 0.0009956012654497074,
85
+ "loss": 4.2794,
86
+ "step": 176
87
+ },
88
+ {
89
+ "epoch": 0.31788079470198677,
90
+ "grad_norm": 0.11566981673240662,
91
+ "learning_rate": 0.000994067603349975,
92
+ "loss": 4.3372,
93
+ "step": 192
94
+ },
95
+ {
96
+ "epoch": 0.3443708609271523,
97
+ "grad_norm": 0.11426500976085663,
98
+ "learning_rate": 0.0009923065546575544,
99
+ "loss": 4.2932,
100
+ "step": 208
101
+ },
102
+ {
103
+ "epoch": 0.3708609271523179,
104
+ "grad_norm": 0.1628023236989975,
105
+ "learning_rate": 0.000990318929866513,
106
+ "loss": 4.3015,
107
+ "step": 224
108
+ },
109
+ {
110
+ "epoch": 0.3973509933774834,
111
+ "grad_norm": 0.1205693706870079,
112
+ "learning_rate": 0.00098810564374889,
113
+ "loss": 4.2702,
114
+ "step": 240
115
+ },
116
+ {
117
+ "epoch": 0.423841059602649,
118
+ "grad_norm": 0.10916964709758759,
119
+ "learning_rate": 0.0009856677149336858,
120
+ "loss": 4.2937,
121
+ "step": 256
122
+ },
123
+ {
124
+ "epoch": 0.4503311258278146,
125
+ "grad_norm": 0.1388256847858429,
126
+ "learning_rate": 0.0009830062654380548,
127
+ "loss": 4.2742,
128
+ "step": 272
129
+ },
130
+ {
131
+ "epoch": 0.4768211920529801,
132
+ "grad_norm": 0.17313151061534882,
133
+ "learning_rate": 0.0009801225201509158,
134
+ "loss": 4.2593,
135
+ "step": 288
136
+ },
137
+ {
138
+ "epoch": 0.5033112582781457,
139
+ "grad_norm": 0.13390372693538666,
140
+ "learning_rate": 0.0009770178062692165,
141
+ "loss": 4.2749,
142
+ "step": 304
143
+ },
144
+ {
145
+ "epoch": 0.5298013245033113,
146
+ "grad_norm": 0.1548251509666443,
147
+ "learning_rate": 0.000973693552687112,
148
+ "loss": 4.2509,
149
+ "step": 320
150
+ },
151
+ {
152
+ "epoch": 0.5562913907284768,
153
+ "grad_norm": 0.13545338809490204,
154
+ "learning_rate": 0.0009701512893383407,
155
+ "loss": 4.308,
156
+ "step": 336
157
+ },
158
+ {
159
+ "epoch": 0.5827814569536424,
160
+ "grad_norm": 0.12648995220661163,
161
+ "learning_rate": 0.0009663926464920958,
162
+ "loss": 4.2801,
163
+ "step": 352
164
+ },
165
+ {
166
+ "epoch": 0.609271523178808,
167
+ "grad_norm": 0.13534340262413025,
168
+ "learning_rate": 0.0009624193540027217,
169
+ "loss": 4.2898,
170
+ "step": 368
171
+ },
172
+ {
173
+ "epoch": 0.6357615894039735,
174
+ "grad_norm": 0.12199301272630692,
175
+ "learning_rate": 0.0009582332405135758,
176
+ "loss": 4.2394,
177
+ "step": 384
178
+ },
179
+ {
180
+ "epoch": 0.6622516556291391,
181
+ "grad_norm": 0.12553353607654572,
182
+ "learning_rate": 0.0009538362326154249,
183
+ "loss": 4.2391,
184
+ "step": 400
185
+ },
186
+ {
187
+ "epoch": 0.6887417218543046,
188
+ "grad_norm": 0.12340961396694183,
189
+ "learning_rate": 0.0009492303539597636,
190
+ "loss": 4.2676,
191
+ "step": 416
192
+ },
193
+ {
194
+ "epoch": 0.7152317880794702,
195
+ "grad_norm": 0.10325583815574646,
196
+ "learning_rate": 0.0009444177243274617,
197
+ "loss": 4.2635,
198
+ "step": 432
199
+ },
200
+ {
201
+ "epoch": 0.7417218543046358,
202
+ "grad_norm": 0.13559825718402863,
203
+ "learning_rate": 0.0009394005586531688,
204
+ "loss": 4.2688,
205
+ "step": 448
206
+ },
207
+ {
208
+ "epoch": 0.7682119205298014,
209
+ "grad_norm": 0.10041986405849457,
210
+ "learning_rate": 0.0009341811660059271,
211
+ "loss": 4.2227,
212
+ "step": 464
213
+ },
214
+ {
215
+ "epoch": 0.7947019867549668,
216
+ "grad_norm": 0.1226314976811409,
217
+ "learning_rate": 0.0009287619485264596,
218
+ "loss": 4.2819,
219
+ "step": 480
220
+ },
221
+ {
222
+ "epoch": 0.8211920529801324,
223
+ "grad_norm": 0.1134864017367363,
224
+ "learning_rate": 0.0009231454003216239,
225
+ "loss": 4.2315,
226
+ "step": 496
227
+ },
228
+ {
229
+ "epoch": 0.847682119205298,
230
+ "grad_norm": 0.1089298278093338,
231
+ "learning_rate": 0.0009173341063165405,
232
+ "loss": 4.2791,
233
+ "step": 512
234
+ },
235
+ {
236
+ "epoch": 0.8741721854304636,
237
+ "grad_norm": 0.1100950837135315,
238
+ "learning_rate": 0.0009113307410649221,
239
+ "loss": 4.2643,
240
+ "step": 528
241
+ },
242
+ {
243
+ "epoch": 0.9006622516556292,
244
+ "grad_norm": 0.11873114854097366,
245
+ "learning_rate": 0.000905138067518154,
246
+ "loss": 4.2508,
247
+ "step": 544
248
+ },
249
+ {
250
+ "epoch": 0.9271523178807947,
251
+ "grad_norm": 0.10352523624897003,
252
+ "learning_rate": 0.0008987589357536914,
253
+ "loss": 4.277,
254
+ "step": 560
255
+ },
256
+ {
257
+ "epoch": 0.9536423841059603,
258
+ "grad_norm": 0.0963631346821785,
259
+ "learning_rate": 0.0008921962816633561,
260
+ "loss": 4.2486,
261
+ "step": 576
262
+ },
263
+ {
264
+ "epoch": 0.9801324503311258,
265
+ "grad_norm": 0.12682202458381653,
266
+ "learning_rate": 0.000885453125602141,
267
+ "loss": 4.3274,
268
+ "step": 592
269
+ },
270
+ {
271
+ "epoch": 1.0,
272
+ "eval_bleu": 0.11091629800496128,
273
+ "eval_cap_loss": 1.2195911861413362,
274
+ "eval_con_loss": 1.8316854106274663,
275
+ "eval_loss": 3.0512766001240306,
276
+ "step": 604
277
+ },
278
+ {
279
+ "epoch": 1.0,
280
+ "eval_bleu": 0.11091629800496128,
281
+ "eval_cap_loss": 1.2195911861413362,
282
+ "eval_con_loss": 1.8316854106274663,
283
+ "eval_loss": 3.0512766001240306,
284
+ "eval_runtime": 242.8774,
285
+ "eval_samples_per_second": 19.882,
286
+ "eval_steps_per_second": 2.487,
287
+ "step": 604
288
+ },
289
+ {
290
+ "epoch": 1.0066225165562914,
291
+ "grad_norm": 0.16604916751384735,
292
+ "learning_rate": 0.0008785325709981404,
293
+ "loss": 4.226,
294
+ "step": 608
295
+ },
296
+ {
297
+ "epoch": 1.033112582781457,
298
+ "grad_norm": 0.1470925211906433,
299
+ "learning_rate": 0.0008714378029242477,
300
+ "loss": 4.2582,
301
+ "step": 624
302
+ },
303
+ {
304
+ "epoch": 1.0596026490066226,
305
+ "grad_norm": 0.09578409790992737,
306
+ "learning_rate": 0.0008641720866322773,
307
+ "loss": 4.2641,
308
+ "step": 640
309
+ },
310
+ {
311
+ "epoch": 1.086092715231788,
312
+ "grad_norm": 0.13495096564292908,
313
+ "learning_rate": 0.0008567387660501852,
314
+ "loss": 4.2752,
315
+ "step": 656
316
+ },
317
+ {
318
+ "epoch": 1.1125827814569536,
319
+ "grad_norm": 0.18220090866088867,
320
+ "learning_rate": 0.000849141262243081,
321
+ "loss": 4.2859,
322
+ "step": 672
323
+ },
324
+ {
325
+ "epoch": 1.1390728476821192,
326
+ "grad_norm": 0.10595650970935822,
327
+ "learning_rate": 0.0008413830718387375,
328
+ "loss": 4.2599,
329
+ "step": 688
330
+ },
331
+ {
332
+ "epoch": 1.1655629139072847,
333
+ "grad_norm": 0.2255912721157074,
334
+ "learning_rate": 0.0008334677654183254,
335
+ "loss": 4.2598,
336
+ "step": 704
337
+ },
338
+ {
339
+ "epoch": 1.1920529801324504,
340
+ "grad_norm": 0.15248772501945496,
341
+ "learning_rate": 0.0008253989858731106,
342
+ "loss": 4.2828,
343
+ "step": 720
344
+ },
345
+ {
346
+ "epoch": 1.218543046357616,
347
+ "grad_norm": 0.10478087514638901,
348
+ "learning_rate": 0.0008171804467278729,
349
+ "loss": 4.2615,
350
+ "step": 736
351
+ },
352
+ {
353
+ "epoch": 1.2450331125827814,
354
+ "grad_norm": 0.13858726620674133,
355
+ "learning_rate": 0.0008088159304318166,
356
+ "loss": 4.2932,
357
+ "step": 752
358
+ },
359
+ {
360
+ "epoch": 1.271523178807947,
361
+ "grad_norm": 0.13052597641944885,
362
+ "learning_rate": 0.0008003092866177592,
363
+ "loss": 4.2778,
364
+ "step": 768
365
+ },
366
+ {
367
+ "epoch": 1.2980132450331126,
368
+ "grad_norm": 0.1585925668478012,
369
+ "learning_rate": 0.0007916644303304013,
370
+ "loss": 4.2626,
371
+ "step": 784
372
+ },
373
+ {
374
+ "epoch": 1.3245033112582782,
375
+ "grad_norm": 0.15588369965553284,
376
+ "learning_rate": 0.0007828853402244896,
377
+ "loss": 4.3056,
378
+ "step": 800
379
+ },
380
+ {
381
+ "epoch": 1.3509933774834437,
382
+ "grad_norm": 0.09688248485326767,
383
+ "learning_rate": 0.0007739760567337073,
384
+ "loss": 4.2525,
385
+ "step": 816
386
+ },
387
+ {
388
+ "epoch": 1.3774834437086092,
389
+ "grad_norm": 0.12090156972408295,
390
+ "learning_rate": 0.0007649406802111283,
391
+ "loss": 4.223,
392
+ "step": 832
393
+ },
394
+ {
395
+ "epoch": 1.403973509933775,
396
+ "grad_norm": 0.11892067641019821,
397
+ "learning_rate": 0.0007557833690420974,
398
+ "loss": 4.248,
399
+ "step": 848
400
+ },
401
+ {
402
+ "epoch": 1.4304635761589404,
403
+ "grad_norm": 0.1257970631122589,
404
+ "learning_rate": 0.0007465083377304009,
405
+ "loss": 4.2604,
406
+ "step": 864
407
+ },
408
+ {
409
+ "epoch": 1.4569536423841059,
410
+ "grad_norm": 0.1225869208574295,
411
+ "learning_rate": 0.0007371198549586091,
412
+ "loss": 4.2583,
413
+ "step": 880
414
+ },
415
+ {
416
+ "epoch": 1.4834437086092715,
417
+ "grad_norm": 0.12114247679710388,
418
+ "learning_rate": 0.000727622241623485,
419
+ "loss": 4.2293,
420
+ "step": 896
421
+ },
422
+ {
423
+ "epoch": 1.5099337748344372,
424
+ "grad_norm": 0.14327970147132874,
425
+ "learning_rate": 0.0007180198688473614,
426
+ "loss": 4.3047,
427
+ "step": 912
428
+ },
429
+ {
430
+ "epoch": 1.5364238410596025,
431
+ "grad_norm": 0.12314064800739288,
432
+ "learning_rate": 0.0007083171559664032,
433
+ "loss": 4.2156,
434
+ "step": 928
435
+ },
436
+ {
437
+ "epoch": 1.5629139072847682,
438
+ "grad_norm": 0.10841790586709976,
439
+ "learning_rate": 0.0006985185684966791,
440
+ "loss": 4.2602,
441
+ "step": 944
442
+ },
443
+ {
444
+ "epoch": 1.589403973509934,
445
+ "grad_norm": 0.13060128688812256,
446
+ "learning_rate": 0.0006886286160789805,
447
+ "loss": 4.2554,
448
+ "step": 960
449
+ },
450
+ {
451
+ "epoch": 1.6158940397350994,
452
+ "grad_norm": 0.10328269004821777,
453
+ "learning_rate": 0.0006786518504033333,
454
+ "loss": 4.2572,
455
+ "step": 976
456
+ },
457
+ {
458
+ "epoch": 1.6423841059602649,
459
+ "grad_norm": 0.15084649622440338,
460
+ "learning_rate": 0.0006685928631141552,
461
+ "loss": 4.278,
462
+ "step": 992
463
+ },
464
+ {
465
+ "epoch": 1.6688741721854305,
466
+ "grad_norm": 0.1322745680809021,
467
+ "learning_rate": 0.0006584562836970271,
468
+ "loss": 4.2747,
469
+ "step": 1008
470
+ },
471
+ {
472
+ "epoch": 1.695364238410596,
473
+ "grad_norm": 0.09931815415620804,
474
+ "learning_rate": 0.0006482467773480468,
475
+ "loss": 4.2314,
476
+ "step": 1024
477
+ },
478
+ {
479
+ "epoch": 1.7218543046357615,
480
+ "grad_norm": 0.12023808807134628,
481
+ "learning_rate": 0.0006379690428267482,
482
+ "loss": 4.2832,
483
+ "step": 1040
484
+ },
485
+ {
486
+ "epoch": 1.7483443708609272,
487
+ "grad_norm": 0.12222672253847122,
488
+ "learning_rate": 0.000627627810293574,
489
+ "loss": 4.1856,
490
+ "step": 1056
491
+ },
492
+ {
493
+ "epoch": 1.7748344370860927,
494
+ "grad_norm": 0.14069874584674835,
495
+ "learning_rate": 0.0006172278391328957,
496
+ "loss": 4.2394,
497
+ "step": 1072
498
+ },
499
+ {
500
+ "epoch": 1.8013245033112582,
501
+ "grad_norm": 0.12728360295295715,
502
+ "learning_rate": 0.0006067739157625848,
503
+ "loss": 4.3155,
504
+ "step": 1088
505
+ },
506
+ {
507
+ "epoch": 1.8278145695364238,
508
+ "grad_norm": 0.15248538553714752,
509
+ "learning_rate": 0.0005962708514311411,
510
+ "loss": 4.2606,
511
+ "step": 1104
512
+ },
513
+ {
514
+ "epoch": 1.8543046357615895,
515
+ "grad_norm": 0.08556041121482849,
516
+ "learning_rate": 0.0005857234800033936,
517
+ "loss": 4.2379,
518
+ "step": 1120
519
+ },
520
+ {
521
+ "epoch": 1.8807947019867548,
522
+ "grad_norm": 0.10861990600824356,
523
+ "learning_rate": 0.0005751366557357933,
524
+ "loss": 4.2761,
525
+ "step": 1136
526
+ },
527
+ {
528
+ "epoch": 1.9072847682119205,
529
+ "grad_norm": 0.1670146882534027,
530
+ "learning_rate": 0.0005645152510423204,
531
+ "loss": 4.2325,
532
+ "step": 1152
533
+ },
534
+ {
535
+ "epoch": 1.9337748344370862,
536
+ "grad_norm": 0.14551334083080292,
537
+ "learning_rate": 0.0005538641542520343,
538
+ "loss": 4.2249,
539
+ "step": 1168
540
+ },
541
+ {
542
+ "epoch": 1.9602649006622517,
543
+ "grad_norm": 0.12024614959955215,
544
+ "learning_rate": 0.0005431882673592999,
545
+ "loss": 4.2265,
546
+ "step": 1184
547
+ },
548
+ {
549
+ "epoch": 1.9867549668874172,
550
+ "grad_norm": 0.15291069447994232,
551
+ "learning_rate": 0.0005324925037677243,
552
+ "loss": 4.3172,
553
+ "step": 1200
554
+ },
555
+ {
556
+ "epoch": 2.0,
557
+ "eval_bleu": 0.11370215395599652,
558
+ "eval_cap_loss": 1.2129609353889692,
559
+ "eval_con_loss": 1.808429909265594,
560
+ "eval_loss": 3.0213908505755542,
561
+ "step": 1208
562
+ },
563
+ {
564
+ "epoch": 2.0,
565
+ "eval_bleu": 0.11370215395599652,
566
+ "eval_cap_loss": 1.2129609353889692,
567
+ "eval_con_loss": 1.808429909265594,
568
+ "eval_loss": 3.0213908505755542,
569
+ "eval_runtime": 241.5496,
570
+ "eval_samples_per_second": 19.992,
571
+ "eval_steps_per_second": 2.501,
572
+ "step": 1208
573
+ }
574
+ ],
575
+ "logging_steps": 16,
576
+ "max_steps": 2416,
577
+ "num_input_tokens_seen": 0,
578
+ "num_train_epochs": 4,
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": 4.5962
597
+ }