aixk commited on
Commit
fcba4d0
·
verified ·
1 Parent(s): 205984d

Upload folder using huggingface_hub

Browse files
checkpoint-800/config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FastHyperNet125mForCausalLM"
4
+ ],
5
+ "dtype": "float32",
6
+ "hidden_size": 768,
7
+ "hyperbolic_dim": 16,
8
+ "initializer_range": 0.02,
9
+ "intermediate_size": 2048,
10
+ "max_position_embeddings": 512,
11
+ "model_type": "fasthypernet_125m_tagless",
12
+ "num_attention_heads": 12,
13
+ "num_hidden_layers": 16,
14
+ "transformers_version": "5.13.1",
15
+ "use_cache": false,
16
+ "vocab_size": 8192
17
+ }
checkpoint-800/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.13.1"
6
+ }
checkpoint-800/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33677cfc05fcf40daf5924547ff01133aaa22cc7f019a5980206d837aee9e733
3
+ size 501759848
checkpoint-800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:213ce93d57a9232bfd98d279033be54df66d14e134785bfcd0ac933b3cdafe9e
3
+ size 254028555
checkpoint-800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b96d4e51c4f86d2cee78856005e2c78db9b93c75ac4cf6acdb7f927c30e89a6
3
+ size 14645
checkpoint-800/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f81d7b3764f877c3bca769445ca10e8fb66dfeda30ed271849b420b5b8b5230
3
+ size 1383
checkpoint-800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdeaa56f68e97289a092e63ebd3b670c93f9063f8ce8bde42fab78b46faf7d73
3
+ size 1465
checkpoint-800/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "HFCompatibleHybridTokenizer",
3
+ "vocab_size": 8192,
4
+ "model_max_length": 512,
5
+ "bos_token": "<bos>",
6
+ "eos_token": "<eos>",
7
+ "unk_token": "<unk>",
8
+ "pad_token": "<pad>"
9
+ }
checkpoint-800/trainer_state.json ADDED
@@ -0,0 +1,594 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.16798782088298597,
6
+ "eval_steps": 500,
7
+ "global_step": 800,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002099847761037325,
14
+ "grad_norm": 22925.884765625,
15
+ "learning_rate": 1.9999999999999996e-07,
16
+ "loss": 9.5004,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.00419969552207465,
21
+ "grad_norm": 1589.221435546875,
22
+ "learning_rate": 1.2e-06,
23
+ "loss": 8.7173,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.006299543283111974,
28
+ "grad_norm": 577.2943115234375,
29
+ "learning_rate": 2.1999999999999997e-06,
30
+ "loss": 7.6284,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0083993910441493,
35
+ "grad_norm": 308.8800048828125,
36
+ "learning_rate": 3.1999999999999994e-06,
37
+ "loss": 7.2988,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.010499238805186623,
42
+ "grad_norm": 458.5738220214844,
43
+ "learning_rate": 4.2e-06,
44
+ "loss": 7.1397,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.012599086566223949,
49
+ "grad_norm": 2117.726806640625,
50
+ "learning_rate": 5.199999999999999e-06,
51
+ "loss": 7.0424,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.014698934327261274,
56
+ "grad_norm": 784.7866821289062,
57
+ "learning_rate": 6.199999999999999e-06,
58
+ "loss": 6.9896,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.0167987820882986,
63
+ "grad_norm": 719.2965087890625,
64
+ "learning_rate": 7.2e-06,
65
+ "loss": 6.9514,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.018898629849335925,
70
+ "grad_norm": 887.7239379882812,
71
+ "learning_rate": 8.2e-06,
72
+ "loss": 6.9188,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.020998477610373247,
77
+ "grad_norm": 657.1996459960938,
78
+ "learning_rate": 9.199999999999998e-06,
79
+ "loss": 6.9113,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.023098325371410572,
84
+ "grad_norm": 1241.19482421875,
85
+ "learning_rate": 1.02e-05,
86
+ "loss": 6.8953,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.025198173132447897,
91
+ "grad_norm": 411.5585021972656,
92
+ "learning_rate": 1.12e-05,
93
+ "loss": 6.8474,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.027298020893485223,
98
+ "grad_norm": 1062.7774658203125,
99
+ "learning_rate": 1.2199999999999998e-05,
100
+ "loss": 6.8514,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.029397868654522548,
105
+ "grad_norm": 148.0970001220703,
106
+ "learning_rate": 1.3199999999999997e-05,
107
+ "loss": 6.8698,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.03149771641555987,
112
+ "grad_norm": 280.5868835449219,
113
+ "learning_rate": 1.4199999999999998e-05,
114
+ "loss": 6.8395,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.0335975641765972,
119
+ "grad_norm": 407.1022644042969,
120
+ "learning_rate": 1.5199999999999998e-05,
121
+ "loss": 6.8029,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.035697411937634524,
126
+ "grad_norm": 166.18153381347656,
127
+ "learning_rate": 1.6199999999999997e-05,
128
+ "loss": 6.7946,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.03779725969867185,
133
+ "grad_norm": 234.69805908203125,
134
+ "learning_rate": 1.7199999999999998e-05,
135
+ "loss": 6.7898,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.03989710745970917,
140
+ "grad_norm": 917.2261352539062,
141
+ "learning_rate": 1.82e-05,
142
+ "loss": 6.7996,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.04199695522074649,
147
+ "grad_norm": 237.35519409179688,
148
+ "learning_rate": 1.92e-05,
149
+ "loss": 6.7733,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.04409680298178382,
154
+ "grad_norm": 49.55766296386719,
155
+ "learning_rate": 2.0199999999999996e-05,
156
+ "loss": 6.7318,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.046196650742821144,
161
+ "grad_norm": 152.66554260253906,
162
+ "learning_rate": 2.12e-05,
163
+ "loss": 6.6867,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.04829649850385847,
168
+ "grad_norm": 284.306640625,
169
+ "learning_rate": 2.2199999999999998e-05,
170
+ "loss": 6.6555,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.050396346264895794,
175
+ "grad_norm": 127.93234252929688,
176
+ "learning_rate": 2.3199999999999998e-05,
177
+ "loss": 6.6263,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.05249619402593312,
182
+ "grad_norm": 119.77033996582031,
183
+ "learning_rate": 2.42e-05,
184
+ "loss": 6.649,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.054596041786970445,
189
+ "grad_norm": 389.56536865234375,
190
+ "learning_rate": 2.52e-05,
191
+ "loss": 6.6383,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.05669588954800777,
196
+ "grad_norm": 427.01580810546875,
197
+ "learning_rate": 2.6199999999999996e-05,
198
+ "loss": 6.593,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.058795737309045096,
203
+ "grad_norm": 222.83114624023438,
204
+ "learning_rate": 2.72e-05,
205
+ "loss": 6.5701,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.06089558507008242,
210
+ "grad_norm": 92.09854125976562,
211
+ "learning_rate": 2.8199999999999998e-05,
212
+ "loss": 6.5495,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.06299543283111975,
217
+ "grad_norm": 137.1016082763672,
218
+ "learning_rate": 2.9199999999999995e-05,
219
+ "loss": 6.5433,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.06509528059215706,
224
+ "grad_norm": 165.11099243164062,
225
+ "learning_rate": 3.02e-05,
226
+ "loss": 6.5528,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.0671951283531944,
231
+ "grad_norm": 193.72972106933594,
232
+ "learning_rate": 3.119999999999999e-05,
233
+ "loss": 6.4983,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.06929497611423172,
238
+ "grad_norm": 168.2730255126953,
239
+ "learning_rate": 3.22e-05,
240
+ "loss": 6.4875,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.07139482387526905,
245
+ "grad_norm": 204.45751953125,
246
+ "learning_rate": 3.3199999999999994e-05,
247
+ "loss": 6.4667,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.07349467163630637,
252
+ "grad_norm": 200.1185302734375,
253
+ "learning_rate": 3.42e-05,
254
+ "loss": 6.4163,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.0755945193973437,
259
+ "grad_norm": 212.8289337158203,
260
+ "learning_rate": 3.5199999999999995e-05,
261
+ "loss": 6.4009,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.07769436715838102,
266
+ "grad_norm": 67.6531982421875,
267
+ "learning_rate": 3.62e-05,
268
+ "loss": 6.3942,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.07979421491941834,
273
+ "grad_norm": 103.08153533935547,
274
+ "learning_rate": 3.7199999999999996e-05,
275
+ "loss": 6.37,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.08189406268045567,
280
+ "grad_norm": 155.30517578125,
281
+ "learning_rate": 3.8199999999999993e-05,
282
+ "loss": 6.3541,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.08399391044149299,
287
+ "grad_norm": 78.574462890625,
288
+ "learning_rate": 3.919999999999999e-05,
289
+ "loss": 6.331,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.08609375820253032,
294
+ "grad_norm": 293.90155029296875,
295
+ "learning_rate": 4.02e-05,
296
+ "loss": 6.2978,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.08819360596356764,
301
+ "grad_norm": 133.43336486816406,
302
+ "learning_rate": 4.12e-05,
303
+ "loss": 6.2921,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.09029345372460497,
308
+ "grad_norm": 105.68527221679688,
309
+ "learning_rate": 4.2199999999999996e-05,
310
+ "loss": 6.2955,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.09239330148564229,
315
+ "grad_norm": 91.55309295654297,
316
+ "learning_rate": 4.319999999999999e-05,
317
+ "loss": 6.2592,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.09449314924667962,
322
+ "grad_norm": 72.15143585205078,
323
+ "learning_rate": 4.42e-05,
324
+ "loss": 6.2545,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.09659299700771694,
329
+ "grad_norm": 109.66728210449219,
330
+ "learning_rate": 4.5199999999999994e-05,
331
+ "loss": 6.2325,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.09869284476875427,
336
+ "grad_norm": 69.46297454833984,
337
+ "learning_rate": 4.62e-05,
338
+ "loss": 6.1691,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.10079269252979159,
343
+ "grad_norm": 137.57276916503906,
344
+ "learning_rate": 4.7199999999999995e-05,
345
+ "loss": 6.1748,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.10289254029082892,
350
+ "grad_norm": 142.85269165039062,
351
+ "learning_rate": 4.82e-05,
352
+ "loss": 6.1763,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.10499238805186624,
357
+ "grad_norm": 68.21001434326172,
358
+ "learning_rate": 4.9199999999999997e-05,
359
+ "loss": 6.1683,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.10709223581290356,
364
+ "grad_norm": 190.91734313964844,
365
+ "learning_rate": 5.0199999999999994e-05,
366
+ "loss": 6.1276,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.10919208357394089,
371
+ "grad_norm": 96.1802978515625,
372
+ "learning_rate": 5.119999999999999e-05,
373
+ "loss": 6.1462,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.11129193133497821,
378
+ "grad_norm": 67.83528137207031,
379
+ "learning_rate": 5.2199999999999995e-05,
380
+ "loss": 6.1067,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.11339177909601554,
385
+ "grad_norm": 42.651100158691406,
386
+ "learning_rate": 5.32e-05,
387
+ "loss": 6.0776,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.11549162685705286,
392
+ "grad_norm": 79.75711822509766,
393
+ "learning_rate": 5.4199999999999996e-05,
394
+ "loss": 6.0815,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.11759147461809019,
399
+ "grad_norm": 46.156211853027344,
400
+ "learning_rate": 5.519999999999999e-05,
401
+ "loss": 6.053,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.11969132237912751,
406
+ "grad_norm": 45.88727951049805,
407
+ "learning_rate": 5.619999999999999e-05,
408
+ "loss": 6.0348,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.12179117014016484,
413
+ "grad_norm": 46.44386672973633,
414
+ "learning_rate": 5.72e-05,
415
+ "loss": 6.0195,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.12389101790120216,
420
+ "grad_norm": 70.52837371826172,
421
+ "learning_rate": 5.82e-05,
422
+ "loss": 5.9979,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.1259908656622395,
427
+ "grad_norm": 59.506553649902344,
428
+ "learning_rate": 5.9199999999999996e-05,
429
+ "loss": 5.983,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.12809071342327683,
434
+ "grad_norm": 38.77995681762695,
435
+ "learning_rate": 6.019999999999999e-05,
436
+ "loss": 5.9576,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.13019056118431413,
441
+ "grad_norm": 62.45197677612305,
442
+ "learning_rate": 6.12e-05,
443
+ "loss": 5.951,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.13229040894535146,
448
+ "grad_norm": 46.94855499267578,
449
+ "learning_rate": 6.22e-05,
450
+ "loss": 5.9626,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.1343902567063888,
455
+ "grad_norm": 54.95368194580078,
456
+ "learning_rate": 6.319999999999999e-05,
457
+ "loss": 5.9268,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.1364901044674261,
462
+ "grad_norm": 47.36136245727539,
463
+ "learning_rate": 6.419999999999999e-05,
464
+ "loss": 5.8941,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.13858995222846343,
469
+ "grad_norm": 40.393096923828125,
470
+ "learning_rate": 6.519999999999999e-05,
471
+ "loss": 5.8787,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.14068979998950076,
476
+ "grad_norm": 41.42562484741211,
477
+ "learning_rate": 6.62e-05,
478
+ "loss": 5.8632,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.1427896477505381,
483
+ "grad_norm": 41.52008056640625,
484
+ "learning_rate": 6.72e-05,
485
+ "loss": 5.8166,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.1448894955115754,
490
+ "grad_norm": 60.34001922607422,
491
+ "learning_rate": 6.819999999999999e-05,
492
+ "loss": 5.8412,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.14698934327261273,
497
+ "grad_norm": 45.22390365600586,
498
+ "learning_rate": 6.919999999999999e-05,
499
+ "loss": 5.7904,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.14908919103365006,
504
+ "grad_norm": 40.19221496582031,
505
+ "learning_rate": 7.02e-05,
506
+ "loss": 5.7796,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.1511890387946874,
511
+ "grad_norm": 38.9415283203125,
512
+ "learning_rate": 7.12e-05,
513
+ "loss": 5.7776,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.1532888865557247,
518
+ "grad_norm": 36.409732818603516,
519
+ "learning_rate": 7.219999999999999e-05,
520
+ "loss": 5.7442,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.15538873431676203,
525
+ "grad_norm": 33.082157135009766,
526
+ "learning_rate": 7.319999999999999e-05,
527
+ "loss": 5.7215,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.15748858207779937,
532
+ "grad_norm": 40.2638053894043,
533
+ "learning_rate": 7.419999999999999e-05,
534
+ "loss": 5.6798,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.15958842983883667,
539
+ "grad_norm": 36.72783660888672,
540
+ "learning_rate": 7.519999999999998e-05,
541
+ "loss": 5.6984,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.161688277599874,
546
+ "grad_norm": 40.32900619506836,
547
+ "learning_rate": 7.62e-05,
548
+ "loss": 5.6429,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.16378812536091134,
553
+ "grad_norm": 31.345502853393555,
554
+ "learning_rate": 7.72e-05,
555
+ "loss": 5.6839,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.16588797312194867,
560
+ "grad_norm": 42.13299560546875,
561
+ "learning_rate": 7.819999999999999e-05,
562
+ "loss": 5.641,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.16798782088298597,
567
+ "grad_norm": 42.9160270690918,
568
+ "learning_rate": 7.92e-05,
569
+ "loss": 5.6259,
570
+ "step": 800
571
+ }
572
+ ],
573
+ "logging_steps": 10,
574
+ "max_steps": 100000,
575
+ "num_input_tokens_seen": 0,
576
+ "num_train_epochs": 21,
577
+ "save_steps": 100,
578
+ "stateful_callbacks": {
579
+ "TrainerControl": {
580
+ "args": {
581
+ "should_epoch_stop": false,
582
+ "should_evaluate": false,
583
+ "should_log": false,
584
+ "should_save": true,
585
+ "should_training_stop": false
586
+ },
587
+ "attributes": {}
588
+ }
589
+ },
590
+ "total_flos": 5.21741415112704e+16,
591
+ "train_batch_size": 16,
592
+ "trial_name": null,
593
+ "trial_params": null
594
+ }
checkpoint-800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4273736f78f1a1a756fad9c1dcb6f595241640fb3898b11c26e020ad95062f5
3
+ size 5201