TinyPixel commited on
Commit
b0d0aa7
1 Parent(s): 8e12113

Upload folder using huggingface_hub

Browse files
adapter_config.json CHANGED
@@ -19,9 +19,9 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "dense_h_to_4h",
23
- "dense",
24
  "query_key_value",
 
 
25
  "dense_4h_to_h"
26
  ],
27
  "task_type": "CAUSAL_LM",
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "query_key_value",
23
+ "dense",
24
+ "dense_h_to_4h",
25
  "dense_4h_to_h"
26
  ],
27
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8bc9e8b8fa5ab20fe49e7ad22db3834f345b8d39a2ab8dce84f24a39e9efd6c
3
  size 134235712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fddb2469e6ffe1163534c9cea4ae13c8a9672bf68d3d2abe558cce949943902e
3
  size 134235712
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bcab11211f58b01afa256e63e81135b8cbf84c3ec0790e7eb1bb1223fdd80cb
3
- size 268515002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:314d2ba87e948610c2ad9be021f9d9906adc2aed9ce526e3d2329042f35ff5c2
3
+ size 268514874
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28b7d813a624fe8658b7f7e2cbd72b69959aab96c5c1f4020b7daca9eb41da70
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a8122975853f947e69e03187a29428024ead29190ec994e53ee279eeb7c9ad
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c79c66b60a0abe3dc1f1792ced2b6c99f10b3ada4ba94ee60000ba5931c603a9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
3
  size 1064
special_tokens_map.json CHANGED
@@ -1,13 +1,29 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
- "content": "<|endoftext|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|endoftext|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_end|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_start|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
  "bos_token": {
19
+ "content": "<|im_start|>",
20
  "lstrip": false,
21
  "normalized": false,
22
  "rstrip": false,
23
  "single_word": false
24
  },
25
  "eos_token": {
26
+ "content": "<|im_end|>",
27
  "lstrip": false,
28
  "normalized": false,
29
  "rstrip": false,
tokenizer.json CHANGED
@@ -241,6 +241,24 @@
241
  "rstrip": false,
242
  "normalized": false,
243
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
244
  }
245
  ],
246
  "normalizer": {
 
241
  "rstrip": false,
242
  "normalized": false,
243
  "special": true
244
+ },
245
+ {
246
+ "id": 50278,
247
+ "content": "<|im_end|>",
248
+ "single_word": false,
249
+ "lstrip": false,
250
+ "rstrip": false,
251
+ "normalized": false,
252
+ "special": true
253
+ },
254
+ {
255
+ "id": 50279,
256
+ "content": "<|im_start|>",
257
+ "single_word": false,
258
+ "lstrip": false,
259
+ "rstrip": false,
260
+ "normalized": false,
261
+ "special": true
262
  }
263
  ],
264
  "normalizer": {
tokenizer_config.json CHANGED
@@ -208,11 +208,31 @@
208
  "rstrip": false,
209
  "single_word": false,
210
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
211
  }
212
  },
213
- "bos_token": "<|endoftext|>",
 
 
 
 
214
  "clean_up_tokenization_spaces": true,
215
- "eos_token": "<|endoftext|>",
216
  "model_max_length": 1000000000000000019884624838656,
217
  "pad_token": "[PAD]",
218
  "tokenizer_class": "GPTNeoXTokenizer",
 
208
  "rstrip": false,
209
  "single_word": false,
210
  "special": true
211
+ },
212
+ "50278": {
213
+ "content": "<|im_end|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "50279": {
221
+ "content": "<|im_start|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
  }
228
  },
229
+ "additional_special_tokens": [
230
+ "<|im_end|>",
231
+ "<|im_start|>"
232
+ ],
233
+ "bos_token": "<|im_start|>",
234
  "clean_up_tokenization_spaces": true,
235
+ "eos_token": "<|im_end|>",
236
  "model_max_length": 1000000000000000019884624838656,
237
  "pad_token": "[PAD]",
238
  "tokenizer_class": "GPTNeoXTokenizer",
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.983219390926041,
5
  "eval_steps": 500,
6
- "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -11,910 +11,310 @@
11
  {
12
  "epoch": 0.02,
13
  "learning_rate": 0.0002,
14
- "loss": 2.7995,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.04,
19
  "learning_rate": 0.0002,
20
- "loss": 2.6136,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.06,
25
  "learning_rate": 0.0002,
26
- "loss": 2.5334,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.08,
31
  "learning_rate": 0.0002,
32
- "loss": 2.3354,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.1,
37
  "learning_rate": 0.0002,
38
- "loss": 2.2897,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.12,
43
  "learning_rate": 0.0002,
44
- "loss": 2.4492,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.14,
49
  "learning_rate": 0.0002,
50
- "loss": 2.3472,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.16,
55
  "learning_rate": 0.0002,
56
- "loss": 2.3725,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.18,
61
  "learning_rate": 0.0002,
62
- "loss": 2.171,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.2,
67
  "learning_rate": 0.0002,
68
- "loss": 2.006,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.22,
73
  "learning_rate": 0.0002,
74
- "loss": 2.061,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.24,
79
  "learning_rate": 0.0002,
80
- "loss": 2.1283,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.26,
85
  "learning_rate": 0.0002,
86
- "loss": 1.9722,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.28,
91
  "learning_rate": 0.0002,
92
- "loss": 2.2341,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.3,
97
  "learning_rate": 0.0002,
98
- "loss": 2.1143,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.32,
103
  "learning_rate": 0.0002,
104
- "loss": 2.1717,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.34,
109
  "learning_rate": 0.0002,
110
- "loss": 2.2766,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 0.36,
115
  "learning_rate": 0.0002,
116
- "loss": 2.2678,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 0.38,
121
  "learning_rate": 0.0002,
122
- "loss": 2.2475,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 0.4,
127
  "learning_rate": 0.0002,
128
- "loss": 2.175,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 0.42,
133
  "learning_rate": 0.0002,
134
- "loss": 2.2936,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 0.44,
139
  "learning_rate": 0.0002,
140
- "loss": 1.9248,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 0.46,
145
  "learning_rate": 0.0002,
146
- "loss": 1.9746,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 0.48,
151
  "learning_rate": 0.0002,
152
- "loss": 1.9783,
153
  "step": 48
154
  },
155
  {
156
  "epoch": 0.5,
157
  "learning_rate": 0.0002,
158
- "loss": 1.996,
159
  "step": 50
160
  },
161
  {
162
  "epoch": 0.52,
163
  "learning_rate": 0.0002,
164
- "loss": 2.1721,
165
  "step": 52
166
  },
167
  {
168
  "epoch": 0.54,
169
  "learning_rate": 0.0002,
170
- "loss": 2.1123,
171
  "step": 54
172
  },
173
  {
174
  "epoch": 0.56,
175
  "learning_rate": 0.0002,
176
- "loss": 2.1182,
177
  "step": 56
178
  },
179
  {
180
  "epoch": 0.58,
181
  "learning_rate": 0.0002,
182
- "loss": 2.2188,
183
  "step": 58
184
  },
185
  {
186
  "epoch": 0.6,
187
  "learning_rate": 0.0002,
188
- "loss": 2.2285,
189
  "step": 60
190
  },
191
  {
192
  "epoch": 0.62,
193
  "learning_rate": 0.0002,
194
- "loss": 2.2411,
195
  "step": 62
196
  },
197
  {
198
  "epoch": 0.64,
199
  "learning_rate": 0.0002,
200
- "loss": 2.1371,
201
  "step": 64
202
  },
203
  {
204
  "epoch": 0.66,
205
  "learning_rate": 0.0002,
206
- "loss": 2.2014,
207
  "step": 66
208
  },
209
  {
210
  "epoch": 0.68,
211
  "learning_rate": 0.0002,
212
- "loss": 2.1145,
213
  "step": 68
214
  },
215
  {
216
  "epoch": 0.7,
217
  "learning_rate": 0.0002,
218
- "loss": 1.9422,
219
  "step": 70
220
  },
221
  {
222
  "epoch": 0.72,
223
  "learning_rate": 0.0002,
224
- "loss": 2.25,
225
  "step": 72
226
  },
227
  {
228
  "epoch": 0.74,
229
  "learning_rate": 0.0002,
230
- "loss": 2.021,
231
  "step": 74
232
  },
233
  {
234
  "epoch": 0.76,
235
  "learning_rate": 0.0002,
236
- "loss": 1.9697,
237
  "step": 76
238
  },
239
  {
240
  "epoch": 0.78,
241
  "learning_rate": 0.0002,
242
- "loss": 2.1596,
243
  "step": 78
244
  },
245
  {
246
  "epoch": 0.8,
247
  "learning_rate": 0.0002,
248
- "loss": 2.2133,
249
  "step": 80
250
  },
251
  {
252
  "epoch": 0.82,
253
  "learning_rate": 0.0002,
254
- "loss": 2.0871,
255
  "step": 82
256
  },
257
  {
258
  "epoch": 0.84,
259
  "learning_rate": 0.0002,
260
- "loss": 2.1383,
261
  "step": 84
262
  },
263
  {
264
  "epoch": 0.86,
265
  "learning_rate": 0.0002,
266
- "loss": 2.113,
267
  "step": 86
268
  },
269
  {
270
  "epoch": 0.88,
271
  "learning_rate": 0.0002,
272
- "loss": 2.157,
273
  "step": 88
274
  },
275
  {
276
  "epoch": 0.89,
277
  "learning_rate": 0.0002,
278
- "loss": 2.0908,
279
  "step": 90
280
  },
281
  {
282
  "epoch": 0.91,
283
  "learning_rate": 0.0002,
284
- "loss": 2.1134,
285
  "step": 92
286
  },
287
  {
288
  "epoch": 0.93,
289
  "learning_rate": 0.0002,
290
- "loss": 1.9216,
291
  "step": 94
292
  },
293
  {
294
  "epoch": 0.95,
295
  "learning_rate": 0.0002,
296
- "loss": 1.9645,
297
  "step": 96
298
  },
299
  {
300
  "epoch": 0.97,
301
  "learning_rate": 0.0002,
302
- "loss": 2.0131,
303
  "step": 98
304
  },
305
  {
306
  "epoch": 0.99,
307
  "learning_rate": 0.0002,
308
- "loss": 1.771,
309
  "step": 100
310
- },
311
- {
312
- "epoch": 1.01,
313
- "learning_rate": 0.0002,
314
- "loss": 2.2615,
315
- "step": 102
316
- },
317
- {
318
- "epoch": 1.03,
319
- "learning_rate": 0.0002,
320
- "loss": 2.1583,
321
- "step": 104
322
- },
323
- {
324
- "epoch": 1.05,
325
- "learning_rate": 0.0002,
326
- "loss": 2.1306,
327
- "step": 106
328
- },
329
- {
330
- "epoch": 1.07,
331
- "learning_rate": 0.0002,
332
- "loss": 2.0571,
333
- "step": 108
334
- },
335
- {
336
- "epoch": 1.09,
337
- "learning_rate": 0.0002,
338
- "loss": 2.0018,
339
- "step": 110
340
- },
341
- {
342
- "epoch": 1.11,
343
- "learning_rate": 0.0002,
344
- "loss": 2.2008,
345
- "step": 112
346
- },
347
- {
348
- "epoch": 1.13,
349
- "learning_rate": 0.0002,
350
- "loss": 1.9969,
351
- "step": 114
352
- },
353
- {
354
- "epoch": 1.15,
355
- "learning_rate": 0.0002,
356
- "loss": 2.1301,
357
- "step": 116
358
- },
359
- {
360
- "epoch": 1.17,
361
- "learning_rate": 0.0002,
362
- "loss": 2.1158,
363
- "step": 118
364
- },
365
- {
366
- "epoch": 1.19,
367
- "learning_rate": 0.0002,
368
- "loss": 2.058,
369
- "step": 120
370
- },
371
- {
372
- "epoch": 1.21,
373
- "learning_rate": 0.0002,
374
- "loss": 1.9263,
375
- "step": 122
376
- },
377
- {
378
- "epoch": 1.23,
379
- "learning_rate": 0.0002,
380
- "loss": 1.976,
381
- "step": 124
382
- },
383
- {
384
- "epoch": 1.25,
385
- "learning_rate": 0.0002,
386
- "loss": 1.7705,
387
- "step": 126
388
- },
389
- {
390
- "epoch": 1.27,
391
- "learning_rate": 0.0002,
392
- "loss": 2.1356,
393
- "step": 128
394
- },
395
- {
396
- "epoch": 1.29,
397
- "learning_rate": 0.0002,
398
- "loss": 2.0895,
399
- "step": 130
400
- },
401
- {
402
- "epoch": 1.31,
403
- "learning_rate": 0.0002,
404
- "loss": 2.0903,
405
- "step": 132
406
- },
407
- {
408
- "epoch": 1.33,
409
- "learning_rate": 0.0002,
410
- "loss": 2.1718,
411
- "step": 134
412
- },
413
- {
414
- "epoch": 1.35,
415
- "learning_rate": 0.0002,
416
- "loss": 2.0289,
417
- "step": 136
418
- },
419
- {
420
- "epoch": 1.37,
421
- "learning_rate": 0.0002,
422
- "loss": 2.0385,
423
- "step": 138
424
- },
425
- {
426
- "epoch": 1.39,
427
- "learning_rate": 0.0002,
428
- "loss": 2.1406,
429
- "step": 140
430
- },
431
- {
432
- "epoch": 1.41,
433
- "learning_rate": 0.0002,
434
- "loss": 2.0461,
435
- "step": 142
436
- },
437
- {
438
- "epoch": 1.43,
439
- "learning_rate": 0.0002,
440
- "loss": 1.8267,
441
- "step": 144
442
- },
443
- {
444
- "epoch": 1.45,
445
- "learning_rate": 0.0002,
446
- "loss": 1.7962,
447
- "step": 146
448
- },
449
- {
450
- "epoch": 1.47,
451
- "learning_rate": 0.0002,
452
- "loss": 1.9104,
453
- "step": 148
454
- },
455
- {
456
- "epoch": 1.49,
457
- "learning_rate": 0.0002,
458
- "loss": 1.9261,
459
- "step": 150
460
- },
461
- {
462
- "epoch": 1.51,
463
- "learning_rate": 0.0002,
464
- "loss": 2.0658,
465
- "step": 152
466
- },
467
- {
468
- "epoch": 1.53,
469
- "learning_rate": 0.0002,
470
- "loss": 1.9514,
471
- "step": 154
472
- },
473
- {
474
- "epoch": 1.55,
475
- "learning_rate": 0.0002,
476
- "loss": 1.9531,
477
- "step": 156
478
- },
479
- {
480
- "epoch": 1.57,
481
- "learning_rate": 0.0002,
482
- "loss": 2.0651,
483
- "step": 158
484
- },
485
- {
486
- "epoch": 1.59,
487
- "learning_rate": 0.0002,
488
- "loss": 2.1144,
489
- "step": 160
490
- },
491
- {
492
- "epoch": 1.61,
493
- "learning_rate": 0.0002,
494
- "loss": 2.1396,
495
- "step": 162
496
- },
497
- {
498
- "epoch": 1.63,
499
- "learning_rate": 0.0002,
500
- "loss": 2.1084,
501
- "step": 164
502
- },
503
- {
504
- "epoch": 1.65,
505
- "learning_rate": 0.0002,
506
- "loss": 1.9944,
507
- "step": 166
508
- },
509
- {
510
- "epoch": 1.67,
511
- "learning_rate": 0.0002,
512
- "loss": 1.9001,
513
- "step": 168
514
- },
515
- {
516
- "epoch": 1.69,
517
- "learning_rate": 0.0002,
518
- "loss": 1.8781,
519
- "step": 170
520
- },
521
- {
522
- "epoch": 1.71,
523
- "learning_rate": 0.0002,
524
- "loss": 2.016,
525
- "step": 172
526
- },
527
- {
528
- "epoch": 1.73,
529
- "learning_rate": 0.0002,
530
- "loss": 1.8475,
531
- "step": 174
532
- },
533
- {
534
- "epoch": 1.75,
535
- "learning_rate": 0.0002,
536
- "loss": 1.8842,
537
- "step": 176
538
- },
539
- {
540
- "epoch": 1.77,
541
- "learning_rate": 0.0002,
542
- "loss": 2.0971,
543
- "step": 178
544
- },
545
- {
546
- "epoch": 1.79,
547
- "learning_rate": 0.0002,
548
- "loss": 2.1377,
549
- "step": 180
550
- },
551
- {
552
- "epoch": 1.81,
553
- "learning_rate": 0.0002,
554
- "loss": 2.1522,
555
- "step": 182
556
- },
557
- {
558
- "epoch": 1.83,
559
- "learning_rate": 0.0002,
560
- "loss": 2.1235,
561
- "step": 184
562
- },
563
- {
564
- "epoch": 1.85,
565
- "learning_rate": 0.0002,
566
- "loss": 2.1875,
567
- "step": 186
568
- },
569
- {
570
- "epoch": 1.87,
571
- "learning_rate": 0.0002,
572
- "loss": 2.1081,
573
- "step": 188
574
- },
575
- {
576
- "epoch": 1.89,
577
- "learning_rate": 0.0002,
578
- "loss": 2.0388,
579
- "step": 190
580
- },
581
- {
582
- "epoch": 1.91,
583
- "learning_rate": 0.0002,
584
- "loss": 2.1445,
585
- "step": 192
586
- },
587
- {
588
- "epoch": 1.93,
589
- "learning_rate": 0.0002,
590
- "loss": 1.9927,
591
- "step": 194
592
- },
593
- {
594
- "epoch": 1.95,
595
- "learning_rate": 0.0002,
596
- "loss": 1.9217,
597
- "step": 196
598
- },
599
- {
600
- "epoch": 1.97,
601
- "learning_rate": 0.0002,
602
- "loss": 2.0054,
603
- "step": 198
604
- },
605
- {
606
- "epoch": 1.99,
607
- "learning_rate": 0.0002,
608
- "loss": 2.0122,
609
- "step": 200
610
- },
611
- {
612
- "epoch": 2.01,
613
- "learning_rate": 0.0002,
614
- "loss": 1.9734,
615
- "step": 202
616
- },
617
- {
618
- "epoch": 2.03,
619
- "learning_rate": 0.0002,
620
- "loss": 2.0048,
621
- "step": 204
622
- },
623
- {
624
- "epoch": 2.05,
625
- "learning_rate": 0.0002,
626
- "loss": 2.1303,
627
- "step": 206
628
- },
629
- {
630
- "epoch": 2.07,
631
- "learning_rate": 0.0002,
632
- "loss": 2.1415,
633
- "step": 208
634
- },
635
- {
636
- "epoch": 2.09,
637
- "learning_rate": 0.0002,
638
- "loss": 2.0024,
639
- "step": 210
640
- },
641
- {
642
- "epoch": 2.11,
643
- "learning_rate": 0.0002,
644
- "loss": 2.022,
645
- "step": 212
646
- },
647
- {
648
- "epoch": 2.13,
649
- "learning_rate": 0.0002,
650
- "loss": 2.0235,
651
- "step": 214
652
- },
653
- {
654
- "epoch": 2.15,
655
- "learning_rate": 0.0002,
656
- "loss": 1.9017,
657
- "step": 216
658
- },
659
- {
660
- "epoch": 2.17,
661
- "learning_rate": 0.0002,
662
- "loss": 2.0065,
663
- "step": 218
664
- },
665
- {
666
- "epoch": 2.19,
667
- "learning_rate": 0.0002,
668
- "loss": 1.8304,
669
- "step": 220
670
- },
671
- {
672
- "epoch": 2.21,
673
- "learning_rate": 0.0002,
674
- "loss": 1.8986,
675
- "step": 222
676
- },
677
- {
678
- "epoch": 2.23,
679
- "learning_rate": 0.0002,
680
- "loss": 1.8563,
681
- "step": 224
682
- },
683
- {
684
- "epoch": 2.25,
685
- "learning_rate": 0.0002,
686
- "loss": 1.6831,
687
- "step": 226
688
- },
689
- {
690
- "epoch": 2.27,
691
- "learning_rate": 0.0002,
692
- "loss": 2.1172,
693
- "step": 228
694
- },
695
- {
696
- "epoch": 2.29,
697
- "learning_rate": 0.0002,
698
- "loss": 2.0506,
699
- "step": 230
700
- },
701
- {
702
- "epoch": 2.31,
703
- "learning_rate": 0.0002,
704
- "loss": 2.0761,
705
- "step": 232
706
- },
707
- {
708
- "epoch": 2.33,
709
- "learning_rate": 0.0002,
710
- "loss": 1.9416,
711
- "step": 234
712
- },
713
- {
714
- "epoch": 2.35,
715
- "learning_rate": 0.0002,
716
- "loss": 2.0938,
717
- "step": 236
718
- },
719
- {
720
- "epoch": 2.37,
721
- "learning_rate": 0.0002,
722
- "loss": 2.1338,
723
- "step": 238
724
- },
725
- {
726
- "epoch": 2.39,
727
- "learning_rate": 0.0002,
728
- "loss": 1.9816,
729
- "step": 240
730
- },
731
- {
732
- "epoch": 2.41,
733
- "learning_rate": 0.0002,
734
- "loss": 1.9698,
735
- "step": 242
736
- },
737
- {
738
- "epoch": 2.43,
739
- "learning_rate": 0.0002,
740
- "loss": 1.8987,
741
- "step": 244
742
- },
743
- {
744
- "epoch": 2.45,
745
- "learning_rate": 0.0002,
746
- "loss": 1.7703,
747
- "step": 246
748
- },
749
- {
750
- "epoch": 2.47,
751
- "learning_rate": 0.0002,
752
- "loss": 1.972,
753
- "step": 248
754
- },
755
- {
756
- "epoch": 2.49,
757
- "learning_rate": 0.0002,
758
- "loss": 1.7901,
759
- "step": 250
760
- },
761
- {
762
- "epoch": 2.51,
763
- "learning_rate": 0.0002,
764
- "loss": 1.7711,
765
- "step": 252
766
- },
767
- {
768
- "epoch": 2.53,
769
- "learning_rate": 0.0002,
770
- "loss": 2.0413,
771
- "step": 254
772
- },
773
- {
774
- "epoch": 2.55,
775
- "learning_rate": 0.0002,
776
- "loss": 2.1376,
777
- "step": 256
778
- },
779
- {
780
- "epoch": 2.57,
781
- "learning_rate": 0.0002,
782
- "loss": 2.0942,
783
- "step": 258
784
- },
785
- {
786
- "epoch": 2.59,
787
- "learning_rate": 0.0002,
788
- "loss": 2.0144,
789
- "step": 260
790
- },
791
- {
792
- "epoch": 2.61,
793
- "learning_rate": 0.0002,
794
- "loss": 2.0191,
795
- "step": 262
796
- },
797
- {
798
- "epoch": 2.63,
799
- "learning_rate": 0.0002,
800
- "loss": 2.0158,
801
- "step": 264
802
- },
803
- {
804
- "epoch": 2.65,
805
- "learning_rate": 0.0002,
806
- "loss": 1.9745,
807
- "step": 266
808
- },
809
- {
810
- "epoch": 2.67,
811
- "learning_rate": 0.0002,
812
- "loss": 2.0842,
813
- "step": 268
814
- },
815
- {
816
- "epoch": 2.68,
817
- "learning_rate": 0.0002,
818
- "loss": 1.7788,
819
- "step": 270
820
- },
821
- {
822
- "epoch": 2.7,
823
- "learning_rate": 0.0002,
824
- "loss": 1.9144,
825
- "step": 272
826
- },
827
- {
828
- "epoch": 2.72,
829
- "learning_rate": 0.0002,
830
- "loss": 2.0329,
831
- "step": 274
832
- },
833
- {
834
- "epoch": 2.74,
835
- "learning_rate": 0.0002,
836
- "loss": 1.8356,
837
- "step": 276
838
- },
839
- {
840
- "epoch": 2.76,
841
- "learning_rate": 0.0002,
842
- "loss": 1.9365,
843
- "step": 278
844
- },
845
- {
846
- "epoch": 2.78,
847
- "learning_rate": 0.0002,
848
- "loss": 2.0144,
849
- "step": 280
850
- },
851
- {
852
- "epoch": 2.8,
853
- "learning_rate": 0.0002,
854
- "loss": 2.1001,
855
- "step": 282
856
- },
857
- {
858
- "epoch": 2.82,
859
- "learning_rate": 0.0002,
860
- "loss": 2.0506,
861
- "step": 284
862
- },
863
- {
864
- "epoch": 2.84,
865
- "learning_rate": 0.0002,
866
- "loss": 2.0066,
867
- "step": 286
868
- },
869
- {
870
- "epoch": 2.86,
871
- "learning_rate": 0.0002,
872
- "loss": 1.9752,
873
- "step": 288
874
- },
875
- {
876
- "epoch": 2.88,
877
- "learning_rate": 0.0002,
878
- "loss": 2.0953,
879
- "step": 290
880
- },
881
- {
882
- "epoch": 2.9,
883
- "learning_rate": 0.0002,
884
- "loss": 2.0454,
885
- "step": 292
886
- },
887
- {
888
- "epoch": 2.92,
889
- "learning_rate": 0.0002,
890
- "loss": 1.9639,
891
- "step": 294
892
- },
893
- {
894
- "epoch": 2.94,
895
- "learning_rate": 0.0002,
896
- "loss": 1.9039,
897
- "step": 296
898
- },
899
- {
900
- "epoch": 2.96,
901
- "learning_rate": 0.0002,
902
- "loss": 1.7684,
903
- "step": 298
904
- },
905
- {
906
- "epoch": 2.98,
907
- "learning_rate": 0.0002,
908
- "loss": 1.719,
909
- "step": 300
910
  }
911
  ],
912
  "logging_steps": 2,
913
- "max_steps": 300,
914
  "num_input_tokens_seen": 0,
915
- "num_train_epochs": 3,
916
  "save_steps": 500,
917
- "total_flos": 2.612372246097101e+16,
918
  "train_batch_size": 1,
919
  "trial_name": null,
920
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9944064636420137,
5
  "eval_steps": 500,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
11
  {
12
  "epoch": 0.02,
13
  "learning_rate": 0.0002,
14
+ "loss": 2.6734,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.04,
19
  "learning_rate": 0.0002,
20
+ "loss": 2.5223,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.06,
25
  "learning_rate": 0.0002,
26
+ "loss": 2.5395,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.08,
31
  "learning_rate": 0.0002,
32
+ "loss": 2.4201,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.1,
37
  "learning_rate": 0.0002,
38
+ "loss": 2.4077,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.12,
43
  "learning_rate": 0.0002,
44
+ "loss": 2.46,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.14,
49
  "learning_rate": 0.0002,
50
+ "loss": 2.3741,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.16,
55
  "learning_rate": 0.0002,
56
+ "loss": 2.5008,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.18,
61
  "learning_rate": 0.0002,
62
+ "loss": 2.3597,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.2,
67
  "learning_rate": 0.0002,
68
+ "loss": 2.1931,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.22,
73
  "learning_rate": 0.0002,
74
+ "loss": 2.3606,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.24,
79
  "learning_rate": 0.0002,
80
+ "loss": 2.4487,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.26,
85
  "learning_rate": 0.0002,
86
+ "loss": 2.2416,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.28,
91
  "learning_rate": 0.0002,
92
+ "loss": 2.3211,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.3,
97
  "learning_rate": 0.0002,
98
+ "loss": 2.3693,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.32,
103
  "learning_rate": 0.0002,
104
+ "loss": 2.3048,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.34,
109
  "learning_rate": 0.0002,
110
+ "loss": 2.2307,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 0.36,
115
  "learning_rate": 0.0002,
116
+ "loss": 2.3252,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 0.38,
121
  "learning_rate": 0.0002,
122
+ "loss": 2.3334,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 0.4,
127
  "learning_rate": 0.0002,
128
+ "loss": 2.1768,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 0.42,
133
  "learning_rate": 0.0002,
134
+ "loss": 2.1346,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 0.44,
139
  "learning_rate": 0.0002,
140
+ "loss": 2.1112,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 0.46,
145
  "learning_rate": 0.0002,
146
+ "loss": 2.1268,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 0.48,
151
  "learning_rate": 0.0002,
152
+ "loss": 2.0301,
153
  "step": 48
154
  },
155
  {
156
  "epoch": 0.5,
157
  "learning_rate": 0.0002,
158
+ "loss": 2.104,
159
  "step": 50
160
  },
161
  {
162
  "epoch": 0.52,
163
  "learning_rate": 0.0002,
164
+ "loss": 2.1416,
165
  "step": 52
166
  },
167
  {
168
  "epoch": 0.54,
169
  "learning_rate": 0.0002,
170
+ "loss": 2.2677,
171
  "step": 54
172
  },
173
  {
174
  "epoch": 0.56,
175
  "learning_rate": 0.0002,
176
+ "loss": 2.2711,
177
  "step": 56
178
  },
179
  {
180
  "epoch": 0.58,
181
  "learning_rate": 0.0002,
182
+ "loss": 2.1959,
183
  "step": 58
184
  },
185
  {
186
  "epoch": 0.6,
187
  "learning_rate": 0.0002,
188
+ "loss": 2.2885,
189
  "step": 60
190
  },
191
  {
192
  "epoch": 0.62,
193
  "learning_rate": 0.0002,
194
+ "loss": 2.293,
195
  "step": 62
196
  },
197
  {
198
  "epoch": 0.64,
199
  "learning_rate": 0.0002,
200
+ "loss": 2.3157,
201
  "step": 64
202
  },
203
  {
204
  "epoch": 0.66,
205
  "learning_rate": 0.0002,
206
+ "loss": 2.2223,
207
  "step": 66
208
  },
209
  {
210
  "epoch": 0.68,
211
  "learning_rate": 0.0002,
212
+ "loss": 2.1248,
213
  "step": 68
214
  },
215
  {
216
  "epoch": 0.7,
217
  "learning_rate": 0.0002,
218
+ "loss": 2.0144,
219
  "step": 70
220
  },
221
  {
222
  "epoch": 0.72,
223
  "learning_rate": 0.0002,
224
+ "loss": 2.1136,
225
  "step": 72
226
  },
227
  {
228
  "epoch": 0.74,
229
  "learning_rate": 0.0002,
230
+ "loss": 2.2022,
231
  "step": 74
232
  },
233
  {
234
  "epoch": 0.76,
235
  "learning_rate": 0.0002,
236
+ "loss": 2.0508,
237
  "step": 76
238
  },
239
  {
240
  "epoch": 0.78,
241
  "learning_rate": 0.0002,
242
+ "loss": 2.1912,
243
  "step": 78
244
  },
245
  {
246
  "epoch": 0.8,
247
  "learning_rate": 0.0002,
248
+ "loss": 2.3011,
249
  "step": 80
250
  },
251
  {
252
  "epoch": 0.82,
253
  "learning_rate": 0.0002,
254
+ "loss": 2.1513,
255
  "step": 82
256
  },
257
  {
258
  "epoch": 0.84,
259
  "learning_rate": 0.0002,
260
+ "loss": 2.2956,
261
  "step": 84
262
  },
263
  {
264
  "epoch": 0.86,
265
  "learning_rate": 0.0002,
266
+ "loss": 2.1961,
267
  "step": 86
268
  },
269
  {
270
  "epoch": 0.88,
271
  "learning_rate": 0.0002,
272
+ "loss": 2.1879,
273
  "step": 88
274
  },
275
  {
276
  "epoch": 0.89,
277
  "learning_rate": 0.0002,
278
+ "loss": 2.0191,
279
  "step": 90
280
  },
281
  {
282
  "epoch": 0.91,
283
  "learning_rate": 0.0002,
284
+ "loss": 2.1988,
285
  "step": 92
286
  },
287
  {
288
  "epoch": 0.93,
289
  "learning_rate": 0.0002,
290
+ "loss": 1.9186,
291
  "step": 94
292
  },
293
  {
294
  "epoch": 0.95,
295
  "learning_rate": 0.0002,
296
+ "loss": 1.9487,
297
  "step": 96
298
  },
299
  {
300
  "epoch": 0.97,
301
  "learning_rate": 0.0002,
302
+ "loss": 1.9328,
303
  "step": 98
304
  },
305
  {
306
  "epoch": 0.99,
307
  "learning_rate": 0.0002,
308
+ "loss": 2.0568,
309
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
310
  }
311
  ],
312
  "logging_steps": 2,
313
+ "max_steps": 100,
314
  "num_input_tokens_seen": 0,
315
+ "num_train_epochs": 1,
316
  "save_steps": 500,
317
+ "total_flos": 8622354846867456.0,
318
  "train_batch_size": 1,
319
  "trial_name": null,
320
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:adfe46aed346f74908f655d2e2f142221a67caf58bc32c87cb4f0db24880e60a
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e0bf11052fc5400b27a40e0097429b7b7441842497f5cd45007f996e627210
3
  size 4728