aixk commited on
Commit
86fd238
·
verified ·
1 Parent(s): d9e1266

Upload folder using huggingface_hub

Browse files
checkpoint-1300/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-1300/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-1300/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c406ba3960221057cce7746b348ca7e23877c92c578acd5b1fccd5f134ca9f
3
+ size 501755480
checkpoint-1300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa29cf2ef396bacab5de3c28144c37f94ebf6ab1530a6d4a18deb75b57b4a85a
3
+ size 254028555
checkpoint-1300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d35eeb2a0e4467f0e53169a7ae6489c79956056634f958165d2246a950eebc1
3
+ size 14645
checkpoint-1300/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a7fe24a6a7d949455b7ff99e8fd30107337e5b94419f856251bbb54d32a1661
3
+ size 1383
checkpoint-1300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad5d183b15b9fbf06a192fec3ddfec67526ed9bfdaca51b6825748ad2cf0fa5
3
+ size 1465
checkpoint-1300/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-1300/trainer_state.json ADDED
@@ -0,0 +1,944 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.06824594789684363,
6
+ "eval_steps": 500,
7
+ "global_step": 1300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0005249688299757202,
14
+ "grad_norm": 4051.18359375,
15
+ "learning_rate": 9e-07,
16
+ "loss": 7.93,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0010499376599514404,
21
+ "grad_norm": 111.26915740966797,
22
+ "learning_rate": 3.899999999999999e-06,
23
+ "loss": 7.7273,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0015749064899271605,
28
+ "grad_norm": 176.40713500976562,
29
+ "learning_rate": 6.899999999999999e-06,
30
+ "loss": 7.5271,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.002099875319902881,
35
+ "grad_norm": 668.3442993164062,
36
+ "learning_rate": 9.9e-06,
37
+ "loss": 7.6155,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.002624844149878601,
42
+ "grad_norm": 171.85369873046875,
43
+ "learning_rate": 1.2899999999999998e-05,
44
+ "loss": 7.4873,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.003149812979854321,
49
+ "grad_norm": 477.1031494140625,
50
+ "learning_rate": 1.5899999999999997e-05,
51
+ "loss": 7.4295,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0036747818098300414,
56
+ "grad_norm": 256.7841491699219,
57
+ "learning_rate": 1.89e-05,
58
+ "loss": 7.3037,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.004199750639805762,
63
+ "grad_norm": 240.86167907714844,
64
+ "learning_rate": 2.1899999999999997e-05,
65
+ "loss": 7.3488,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0047247194697814816,
70
+ "grad_norm": 151.8752899169922,
71
+ "learning_rate": 2.49e-05,
72
+ "loss": 7.1664,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.005249688299757202,
77
+ "grad_norm": 92.41702270507812,
78
+ "learning_rate": 2.7899999999999997e-05,
79
+ "loss": 7.2001,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.005774657129732922,
84
+ "grad_norm": 125.6628189086914,
85
+ "learning_rate": 3.09e-05,
86
+ "loss": 7.1956,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.006299625959708642,
91
+ "grad_norm": 105.1700210571289,
92
+ "learning_rate": 3.39e-05,
93
+ "loss": 7.2136,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.006824594789684363,
98
+ "grad_norm": 95.49678039550781,
99
+ "learning_rate": 3.6899999999999996e-05,
100
+ "loss": 7.2046,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.007349563619660083,
105
+ "grad_norm": 70.33267974853516,
106
+ "learning_rate": 3.99e-05,
107
+ "loss": 7.0895,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.007874532449635803,
112
+ "grad_norm": 42.994972229003906,
113
+ "learning_rate": 4.289999999999999e-05,
114
+ "loss": 7.1157,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.008399501279611523,
119
+ "grad_norm": 87.23907470703125,
120
+ "learning_rate": 4.59e-05,
121
+ "loss": 7.1537,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.008924470109587244,
126
+ "grad_norm": 53.14045333862305,
127
+ "learning_rate": 4.8899999999999996e-05,
128
+ "loss": 7.0126,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.009449438939562963,
133
+ "grad_norm": 44.222225189208984,
134
+ "learning_rate": 5.1899999999999994e-05,
135
+ "loss": 7.1067,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.009974407769538684,
140
+ "grad_norm": 65.67877197265625,
141
+ "learning_rate": 5.489999999999999e-05,
142
+ "loss": 7.0359,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.010499376599514405,
147
+ "grad_norm": 34.80784225463867,
148
+ "learning_rate": 5.79e-05,
149
+ "loss": 7.0124,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.011024345429490124,
154
+ "grad_norm": 80.05706024169922,
155
+ "learning_rate": 6.0899999999999996e-05,
156
+ "loss": 6.9882,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.011549314259465844,
161
+ "grad_norm": 18.072044372558594,
162
+ "learning_rate": 6.39e-05,
163
+ "loss": 7.082,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.012074283089441565,
168
+ "grad_norm": 27.460533142089844,
169
+ "learning_rate": 6.69e-05,
170
+ "loss": 7.0056,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.012599251919417284,
175
+ "grad_norm": 20.942256927490234,
176
+ "learning_rate": 6.989999999999999e-05,
177
+ "loss": 7.0385,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.013124220749393005,
182
+ "grad_norm": 21.205760955810547,
183
+ "learning_rate": 7.29e-05,
184
+ "loss": 6.9065,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.013649189579368726,
189
+ "grad_norm": 30.357505798339844,
190
+ "learning_rate": 7.589999999999999e-05,
191
+ "loss": 6.9887,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.014174158409344445,
196
+ "grad_norm": 21.6142520904541,
197
+ "learning_rate": 7.89e-05,
198
+ "loss": 7.0671,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.014699127239320165,
203
+ "grad_norm": 34.31865310668945,
204
+ "learning_rate": 8.19e-05,
205
+ "loss": 6.9352,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.015224096069295886,
210
+ "grad_norm": 31.643892288208008,
211
+ "learning_rate": 8.489999999999999e-05,
212
+ "loss": 7.0615,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.015749064899271605,
217
+ "grad_norm": 21.246601104736328,
218
+ "learning_rate": 8.789999999999998e-05,
219
+ "loss": 6.8747,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.016274033729247326,
224
+ "grad_norm": 17.99869155883789,
225
+ "learning_rate": 9.089999999999999e-05,
226
+ "loss": 6.9325,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.016799002559223047,
231
+ "grad_norm": 10.438518524169922,
232
+ "learning_rate": 9.389999999999999e-05,
233
+ "loss": 6.975,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.017323971389198767,
238
+ "grad_norm": 38.324283599853516,
239
+ "learning_rate": 9.69e-05,
240
+ "loss": 6.8833,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.017848940219174488,
245
+ "grad_norm": 25.789045333862305,
246
+ "learning_rate": 9.99e-05,
247
+ "loss": 6.869,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.018373909049150206,
252
+ "grad_norm": 26.649545669555664,
253
+ "learning_rate": 0.0001029,
254
+ "loss": 6.8773,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.018898877879125926,
259
+ "grad_norm": 24.452266693115234,
260
+ "learning_rate": 0.00010589999999999999,
261
+ "loss": 6.7558,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.019423846709101647,
266
+ "grad_norm": 14.234713554382324,
267
+ "learning_rate": 0.00010889999999999999,
268
+ "loss": 6.9624,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.019948815539077368,
273
+ "grad_norm": 16.222957611083984,
274
+ "learning_rate": 0.0001119,
275
+ "loss": 6.9116,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.02047378436905309,
280
+ "grad_norm": 14.955327033996582,
281
+ "learning_rate": 0.00011489999999999999,
282
+ "loss": 6.8227,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.02099875319902881,
287
+ "grad_norm": 13.272610664367676,
288
+ "learning_rate": 0.00011789999999999999,
289
+ "loss": 6.8292,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.021523722029004527,
294
+ "grad_norm": 14.966605186462402,
295
+ "learning_rate": 0.0001209,
296
+ "loss": 6.8364,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.022048690858980247,
301
+ "grad_norm": 11.822840690612793,
302
+ "learning_rate": 0.00012389999999999998,
303
+ "loss": 6.668,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.022573659688955968,
308
+ "grad_norm": 12.50557804107666,
309
+ "learning_rate": 0.0001269,
310
+ "loss": 6.6604,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.02309862851893169,
315
+ "grad_norm": 13.769299507141113,
316
+ "learning_rate": 0.00012989999999999999,
317
+ "loss": 6.6969,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.02362359734890741,
322
+ "grad_norm": 9.62465763092041,
323
+ "learning_rate": 0.00013289999999999998,
324
+ "loss": 6.7391,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.02414856617888313,
329
+ "grad_norm": 8.241267204284668,
330
+ "learning_rate": 0.0001359,
331
+ "loss": 6.7064,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.024673535008858848,
336
+ "grad_norm": 14.394071578979492,
337
+ "learning_rate": 0.0001389,
338
+ "loss": 6.7164,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.02519850383883457,
343
+ "grad_norm": 8.198172569274902,
344
+ "learning_rate": 0.00014189999999999998,
345
+ "loss": 6.7228,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.02572347266881029,
350
+ "grad_norm": 17.51156997680664,
351
+ "learning_rate": 0.00014489999999999997,
352
+ "loss": 6.6933,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.02624844149878601,
357
+ "grad_norm": 14.444514274597168,
358
+ "learning_rate": 0.0001479,
359
+ "loss": 6.5789,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.02677341032876173,
364
+ "grad_norm": 8.710993766784668,
365
+ "learning_rate": 0.00015089999999999998,
366
+ "loss": 6.6053,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.02729837915873745,
371
+ "grad_norm": 11.155731201171875,
372
+ "learning_rate": 0.0001539,
373
+ "loss": 6.6003,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.02782334798871317,
378
+ "grad_norm": 9.0637845993042,
379
+ "learning_rate": 0.0001569,
380
+ "loss": 6.5253,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.02834831681868889,
385
+ "grad_norm": 7.813695907592773,
386
+ "learning_rate": 0.00015989999999999998,
387
+ "loss": 6.5777,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.02887328564866461,
392
+ "grad_norm": 9.640409469604492,
393
+ "learning_rate": 0.0001629,
394
+ "loss": 6.5582,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.02939825447864033,
399
+ "grad_norm": 10.287951469421387,
400
+ "learning_rate": 0.0001659,
401
+ "loss": 6.5429,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.02992322330861605,
406
+ "grad_norm": 8.388657569885254,
407
+ "learning_rate": 0.00016889999999999996,
408
+ "loss": 6.4797,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.030448192138591772,
413
+ "grad_norm": 6.651219844818115,
414
+ "learning_rate": 0.00017189999999999998,
415
+ "loss": 6.472,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.03097316096856749,
420
+ "grad_norm": 6.32115364074707,
421
+ "learning_rate": 0.00017489999999999997,
422
+ "loss": 6.4754,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.03149812979854321,
427
+ "grad_norm": 10.339417457580566,
428
+ "learning_rate": 0.0001779,
429
+ "loss": 6.4067,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.03202309862851893,
434
+ "grad_norm": 7.705801963806152,
435
+ "learning_rate": 0.00018089999999999998,
436
+ "loss": 6.4035,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.03254806745849465,
441
+ "grad_norm": 6.596720218658447,
442
+ "learning_rate": 0.00018389999999999997,
443
+ "loss": 6.3301,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.03307303628847037,
448
+ "grad_norm": 10.351055145263672,
449
+ "learning_rate": 0.0001869,
450
+ "loss": 6.3362,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.03359800511844609,
455
+ "grad_norm": 8.058084487915039,
456
+ "learning_rate": 0.00018989999999999998,
457
+ "loss": 6.4833,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.034122973948421814,
462
+ "grad_norm": 8.515560150146484,
463
+ "learning_rate": 0.0001929,
464
+ "loss": 6.2454,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.034647942778397535,
469
+ "grad_norm": 7.069362640380859,
470
+ "learning_rate": 0.0001959,
471
+ "loss": 6.2539,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.035172911608373256,
476
+ "grad_norm": 6.835115909576416,
477
+ "learning_rate": 0.00019889999999999998,
478
+ "loss": 6.2121,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.035697880438348976,
483
+ "grad_norm": 9.131962776184082,
484
+ "learning_rate": 0.0002019,
485
+ "loss": 6.1163,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.03622284926832469,
490
+ "grad_norm": 6.500721454620361,
491
+ "learning_rate": 0.0002049,
492
+ "loss": 6.2233,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.03674781809830041,
497
+ "grad_norm": 6.955876350402832,
498
+ "learning_rate": 0.00020789999999999996,
499
+ "loss": 6.2746,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.03727278692827613,
504
+ "grad_norm": 12.63397216796875,
505
+ "learning_rate": 0.00021089999999999998,
506
+ "loss": 6.2639,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.03779775575825185,
511
+ "grad_norm": 6.766085624694824,
512
+ "learning_rate": 0.00021389999999999997,
513
+ "loss": 6.2185,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.03832272458822757,
518
+ "grad_norm": 7.125621795654297,
519
+ "learning_rate": 0.0002169,
520
+ "loss": 6.2077,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.038847693418203294,
525
+ "grad_norm": 6.098615646362305,
526
+ "learning_rate": 0.00021989999999999998,
527
+ "loss": 6.1988,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.039372662248179015,
532
+ "grad_norm": 6.724160671234131,
533
+ "learning_rate": 0.00022289999999999997,
534
+ "loss": 6.1645,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.039897631078154736,
539
+ "grad_norm": 6.864727973937988,
540
+ "learning_rate": 0.0002259,
541
+ "loss": 5.9853,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.040422599908130456,
546
+ "grad_norm": 7.888518810272217,
547
+ "learning_rate": 0.00022889999999999998,
548
+ "loss": 6.0459,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.04094756873810618,
553
+ "grad_norm": 5.348147392272949,
554
+ "learning_rate": 0.0002319,
555
+ "loss": 6.0306,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.0414725375680819,
560
+ "grad_norm": 7.666118621826172,
561
+ "learning_rate": 0.0002349,
562
+ "loss": 6.0464,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.04199750639805762,
567
+ "grad_norm": 12.02874755859375,
568
+ "learning_rate": 0.00023789999999999998,
569
+ "loss": 5.9991,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.04252247522803333,
574
+ "grad_norm": 6.495911598205566,
575
+ "learning_rate": 0.0002409,
576
+ "loss": 5.9451,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.04304744405800905,
581
+ "grad_norm": 9.461275100708008,
582
+ "learning_rate": 0.00024389999999999997,
583
+ "loss": 5.9558,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.043572412887984774,
588
+ "grad_norm": 6.616198539733887,
589
+ "learning_rate": 0.0002469,
590
+ "loss": 5.9853,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.044097381717960495,
595
+ "grad_norm": 6.1858086585998535,
596
+ "learning_rate": 0.00024989999999999995,
597
+ "loss": 5.9692,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.044622350547936215,
602
+ "grad_norm": 5.398629188537598,
603
+ "learning_rate": 0.00025289999999999997,
604
+ "loss": 5.9193,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.045147319377911936,
609
+ "grad_norm": 7.980245113372803,
610
+ "learning_rate": 0.0002559,
611
+ "loss": 5.8701,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.04567228820788766,
616
+ "grad_norm": 6.517972946166992,
617
+ "learning_rate": 0.00025889999999999995,
618
+ "loss": 5.905,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.04619725703786338,
623
+ "grad_norm": 6.580096244812012,
624
+ "learning_rate": 0.00026189999999999997,
625
+ "loss": 5.7834,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.0467222258678391,
630
+ "grad_norm": 6.371602535247803,
631
+ "learning_rate": 0.0002649,
632
+ "loss": 5.8452,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.04724719469781482,
637
+ "grad_norm": 6.168027400970459,
638
+ "learning_rate": 0.0002679,
639
+ "loss": 5.6781,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.04777216352779054,
644
+ "grad_norm": 6.000701427459717,
645
+ "learning_rate": 0.00027089999999999997,
646
+ "loss": 5.6675,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.04829713235776626,
651
+ "grad_norm": 6.960968971252441,
652
+ "learning_rate": 0.0002739,
653
+ "loss": 5.5692,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.048822101187741974,
658
+ "grad_norm": 10.075114250183105,
659
+ "learning_rate": 0.0002769,
660
+ "loss": 5.7553,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.049347070017717695,
665
+ "grad_norm": 5.733921527862549,
666
+ "learning_rate": 0.0002799,
667
+ "loss": 5.5125,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.049872038847693416,
672
+ "grad_norm": 7.427346706390381,
673
+ "learning_rate": 0.00028289999999999994,
674
+ "loss": 5.6595,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.05039700767766914,
679
+ "grad_norm": 5.955673694610596,
680
+ "learning_rate": 0.00028589999999999996,
681
+ "loss": 5.5868,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.05092197650764486,
686
+ "grad_norm": 7.7476420402526855,
687
+ "learning_rate": 0.0002889,
688
+ "loss": 5.632,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.05144694533762058,
693
+ "grad_norm": 6.524439811706543,
694
+ "learning_rate": 0.0002919,
695
+ "loss": 5.6333,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.0519719141675963,
700
+ "grad_norm": 6.380852699279785,
701
+ "learning_rate": 0.00029489999999999996,
702
+ "loss": 5.6931,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.05249688299757202,
707
+ "grad_norm": 6.871588706970215,
708
+ "learning_rate": 0.0002979,
709
+ "loss": 5.4705,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.05302185182754774,
714
+ "grad_norm": 5.873289585113525,
715
+ "learning_rate": 0.00029999999999993335,
716
+ "loss": 5.659,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.05354682065752346,
721
+ "grad_norm": 6.722020626068115,
722
+ "learning_rate": 0.00029999999999874875,
723
+ "loss": 5.5263,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.05407178948749918,
728
+ "grad_norm": 7.375940799713135,
729
+ "learning_rate": 0.00029999999999608346,
730
+ "loss": 5.4849,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.0545967583174749,
735
+ "grad_norm": 6.465951919555664,
736
+ "learning_rate": 0.00029999999999193736,
737
+ "loss": 5.4179,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.05512172714745062,
742
+ "grad_norm": 6.1253156661987305,
743
+ "learning_rate": 0.00029999999998631057,
744
+ "loss": 5.415,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.05564669597742634,
749
+ "grad_norm": 6.320364475250244,
750
+ "learning_rate": 0.000299999999979203,
751
+ "loss": 5.2886,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.05617166480740206,
756
+ "grad_norm": 5.7049880027771,
757
+ "learning_rate": 0.00029999999997061473,
758
+ "loss": 5.3008,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.05669663363737778,
763
+ "grad_norm": 7.153939247131348,
764
+ "learning_rate": 0.00029999999996054575,
765
+ "loss": 5.336,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.0572216024673535,
770
+ "grad_norm": 6.331596374511719,
771
+ "learning_rate": 0.00029999999994899596,
772
+ "loss": 5.2242,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.05774657129732922,
777
+ "grad_norm": 6.270790100097656,
778
+ "learning_rate": 0.00029999999993596553,
779
+ "loss": 5.2873,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.05827154012730494,
784
+ "grad_norm": 6.87438440322876,
785
+ "learning_rate": 0.0002999999999214543,
786
+ "loss": 5.2111,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.05879650895728066,
791
+ "grad_norm": 6.366969585418701,
792
+ "learning_rate": 0.0002999999999054623,
793
+ "loss": 5.1685,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.05932147778725638,
798
+ "grad_norm": 6.2817816734313965,
799
+ "learning_rate": 0.00029999999988798964,
800
+ "loss": 5.3457,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.0598464466172321,
805
+ "grad_norm": 5.789464950561523,
806
+ "learning_rate": 0.0002999999998690362,
807
+ "loss": 5.0926,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.060371415447207824,
812
+ "grad_norm": 6.459042072296143,
813
+ "learning_rate": 0.00029999999984860204,
814
+ "loss": 5.0385,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.060896384277183545,
819
+ "grad_norm": 6.7204413414001465,
820
+ "learning_rate": 0.00029999999982668717,
821
+ "loss": 5.2199,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.061421353107159266,
826
+ "grad_norm": 6.44543981552124,
827
+ "learning_rate": 0.0002999999998032915,
828
+ "loss": 5.1449,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.06194632193713498,
833
+ "grad_norm": 5.885377407073975,
834
+ "learning_rate": 0.0002999999997784151,
835
+ "loss": 5.1175,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.0624712907671107,
840
+ "grad_norm": 6.293627738952637,
841
+ "learning_rate": 0.000299999999752058,
842
+ "loss": 5.0933,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.06299625959708642,
847
+ "grad_norm": 6.686017990112305,
848
+ "learning_rate": 0.0002999999997242202,
849
+ "loss": 4.9613,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.06352122842706215,
854
+ "grad_norm": 5.605543613433838,
855
+ "learning_rate": 0.0002999999996949016,
856
+ "loss": 5.0621,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.06404619725703786,
861
+ "grad_norm": 6.000121593475342,
862
+ "learning_rate": 0.0002999999996641022,
863
+ "loss": 5.0555,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.06457116608701359,
868
+ "grad_norm": 7.083418369293213,
869
+ "learning_rate": 0.00029999999963182215,
870
+ "loss": 5.0052,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.0650961349169893,
875
+ "grad_norm": 6.544703483581543,
876
+ "learning_rate": 0.00029999999959806135,
877
+ "loss": 5.0612,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.06562110374696502,
882
+ "grad_norm": 6.990364074707031,
883
+ "learning_rate": 0.0002999999995628198,
884
+ "loss": 5.0725,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.06614607257694075,
889
+ "grad_norm": 6.532026290893555,
890
+ "learning_rate": 0.0002999999995260976,
891
+ "loss": 5.0609,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.06667104140691646,
896
+ "grad_norm": 6.3640522956848145,
897
+ "learning_rate": 0.00029999999948789453,
898
+ "loss": 4.9563,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.06719601023689219,
903
+ "grad_norm": 7.006086349487305,
904
+ "learning_rate": 0.00029999999944821084,
905
+ "loss": 4.9507,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.0677209790668679,
910
+ "grad_norm": 6.476901531219482,
911
+ "learning_rate": 0.00029999999940704634,
912
+ "loss": 4.9325,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.06824594789684363,
917
+ "grad_norm": 6.32811975479126,
918
+ "learning_rate": 0.00029999999936440114,
919
+ "loss": 4.819,
920
+ "step": 1300
921
+ }
922
+ ],
923
+ "logging_steps": 10,
924
+ "max_steps": 10000000,
925
+ "num_input_tokens_seen": 0,
926
+ "num_train_epochs": 525,
927
+ "save_steps": 100,
928
+ "stateful_callbacks": {
929
+ "TrainerControl": {
930
+ "args": {
931
+ "should_epoch_stop": false,
932
+ "should_evaluate": false,
933
+ "should_log": false,
934
+ "should_save": true,
935
+ "should_training_stop": false
936
+ },
937
+ "attributes": {}
938
+ }
939
+ },
940
+ "total_flos": 1.95492649783296e+16,
941
+ "train_batch_size": 8,
942
+ "trial_name": null,
943
+ "trial_params": null
944
+ }
checkpoint-1300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a40bbf14bc866e7549dd7e35b2f1efa93574f3325f7dcb8eac5341e7f4b4f035
3
+ size 5201