aixk commited on
Commit
01566bb
·
verified ·
1 Parent(s): e48d6da

Upload folder using huggingface_hub

Browse files
checkpoint-1000/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-1000/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-1000/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a92ee74fb9bd214aa442d3d70db0b8437949b1ca7dc34a6d13032005f691aa3
3
+ size 501759848
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069477fc045ef8a0dc68d2a2931236c70188a00308b624a9168b541bd7fe67bc
3
+ size 254410983
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e15d61ae50463fb0897ed8ddff92564540094e210dd20cfd3ccd9d2437f74b6
3
+ size 14645
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b06d6616d99bc7602ffa7f907485a55f6f39bc045ff342b0d10adb44c57b76ee
3
+ size 1383
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb7a11ee7f695f536acc1d54507d83c18a36e0e58fe031bf7e9be4f428cd6649
3
+ size 1465
checkpoint-1000/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-1000/trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.6153609476558594,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.006153609476558594,
14
+ "grad_norm": 26290.87109375,
15
+ "learning_rate": 1.9999999999999996e-07,
16
+ "loss": 8.2122,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.012307218953117188,
21
+ "grad_norm": 1750.26953125,
22
+ "learning_rate": 1.2e-06,
23
+ "loss": 7.6386,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.018460828429675783,
28
+ "grad_norm": 235.5290985107422,
29
+ "learning_rate": 2.1999999999999997e-06,
30
+ "loss": 7.0511,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.024614437906234375,
35
+ "grad_norm": 317.7790222167969,
36
+ "learning_rate": 3.1999999999999994e-06,
37
+ "loss": 6.889,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.03076804738279297,
42
+ "grad_norm": 906.6453247070312,
43
+ "learning_rate": 4.2e-06,
44
+ "loss": 6.8145,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.036921656859351566,
49
+ "grad_norm": 1056.044189453125,
50
+ "learning_rate": 5.199999999999999e-06,
51
+ "loss": 6.7193,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.043075266335910155,
56
+ "grad_norm": 830.0984497070312,
57
+ "learning_rate": 6.199999999999999e-06,
58
+ "loss": 6.6406,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.04922887581246875,
63
+ "grad_norm": 259.50299072265625,
64
+ "learning_rate": 7.2e-06,
65
+ "loss": 6.6149,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.055382485289027346,
70
+ "grad_norm": 143.87599182128906,
71
+ "learning_rate": 8.2e-06,
72
+ "loss": 6.6122,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.06153609476558594,
77
+ "grad_norm": 435.93017578125,
78
+ "learning_rate": 9.199999999999998e-06,
79
+ "loss": 6.5612,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.06768970424214453,
84
+ "grad_norm": 557.260498046875,
85
+ "learning_rate": 1.02e-05,
86
+ "loss": 6.5083,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.07384331371870313,
91
+ "grad_norm": 291.8673095703125,
92
+ "learning_rate": 1.12e-05,
93
+ "loss": 6.5365,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.07999692319526172,
98
+ "grad_norm": 434.8012390136719,
99
+ "learning_rate": 1.2199999999999998e-05,
100
+ "loss": 6.5229,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.08615053267182031,
105
+ "grad_norm": 1767.30908203125,
106
+ "learning_rate": 1.3199999999999997e-05,
107
+ "loss": 6.4961,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.09230414214837891,
112
+ "grad_norm": 548.34228515625,
113
+ "learning_rate": 1.4199999999999998e-05,
114
+ "loss": 6.5135,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.0984577516249375,
119
+ "grad_norm": 212.0412139892578,
120
+ "learning_rate": 1.5199999999999998e-05,
121
+ "loss": 6.47,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.1046113611014961,
126
+ "grad_norm": 220.91732788085938,
127
+ "learning_rate": 1.6199999999999997e-05,
128
+ "loss": 6.4492,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.11076497057805469,
133
+ "grad_norm": 275.8125305175781,
134
+ "learning_rate": 1.7199999999999998e-05,
135
+ "loss": 6.5087,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.11691858005461328,
140
+ "grad_norm": 205.40353393554688,
141
+ "learning_rate": 1.82e-05,
142
+ "loss": 6.4695,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.12307218953117188,
147
+ "grad_norm": 170.36024475097656,
148
+ "learning_rate": 1.92e-05,
149
+ "loss": 6.4184,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.12922579900773049,
154
+ "grad_norm": 240.3199462890625,
155
+ "learning_rate": 2.0199999999999996e-05,
156
+ "loss": 6.4329,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.13537940848428906,
161
+ "grad_norm": 508.4911193847656,
162
+ "learning_rate": 2.12e-05,
163
+ "loss": 6.3826,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.14153301796084766,
168
+ "grad_norm": 117.4170150756836,
169
+ "learning_rate": 2.2199999999999998e-05,
170
+ "loss": 6.394,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.14768662743740626,
175
+ "grad_norm": 76.04037475585938,
176
+ "learning_rate": 2.3199999999999998e-05,
177
+ "loss": 6.3696,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.15384023691396484,
182
+ "grad_norm": 243.4922332763672,
183
+ "learning_rate": 2.42e-05,
184
+ "loss": 6.3843,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.15999384639052344,
189
+ "grad_norm": 84.42725372314453,
190
+ "learning_rate": 2.52e-05,
191
+ "loss": 6.3401,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.16614745586708204,
196
+ "grad_norm": 119.90478515625,
197
+ "learning_rate": 2.6199999999999996e-05,
198
+ "loss": 6.3586,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.17230106534364062,
203
+ "grad_norm": 101.67578125,
204
+ "learning_rate": 2.72e-05,
205
+ "loss": 6.3315,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.17845467482019922,
210
+ "grad_norm": 64.19589233398438,
211
+ "learning_rate": 2.8199999999999998e-05,
212
+ "loss": 6.3033,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.18460828429675782,
217
+ "grad_norm": 43.22764205932617,
218
+ "learning_rate": 2.9199999999999995e-05,
219
+ "loss": 6.3065,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.1907618937733164,
224
+ "grad_norm": 70.01463317871094,
225
+ "learning_rate": 3.02e-05,
226
+ "loss": 6.3044,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.196915503249875,
231
+ "grad_norm": 48.240699768066406,
232
+ "learning_rate": 3.119999999999999e-05,
233
+ "loss": 6.2598,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.2030691127264336,
238
+ "grad_norm": 59.44075012207031,
239
+ "learning_rate": 3.22e-05,
240
+ "loss": 6.2607,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.2092227222029922,
245
+ "grad_norm": 61.2050666809082,
246
+ "learning_rate": 3.3199999999999994e-05,
247
+ "loss": 6.2497,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.21537633167955078,
252
+ "grad_norm": 60.02091598510742,
253
+ "learning_rate": 3.42e-05,
254
+ "loss": 6.2319,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.22152994115610938,
259
+ "grad_norm": 41.094627380371094,
260
+ "learning_rate": 3.5199999999999995e-05,
261
+ "loss": 6.219,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.22768355063266799,
266
+ "grad_norm": 64.33719635009766,
267
+ "learning_rate": 3.62e-05,
268
+ "loss": 6.2147,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.23383716010922656,
273
+ "grad_norm": 62.03013610839844,
274
+ "learning_rate": 3.7199999999999996e-05,
275
+ "loss": 6.1763,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.23999076958578516,
280
+ "grad_norm": 181.71493530273438,
281
+ "learning_rate": 3.8199999999999993e-05,
282
+ "loss": 6.1753,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.24614437906234377,
287
+ "grad_norm": 80.83346557617188,
288
+ "learning_rate": 3.919999999999999e-05,
289
+ "loss": 6.1614,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.25229798853890234,
294
+ "grad_norm": 35.45427703857422,
295
+ "learning_rate": 4.02e-05,
296
+ "loss": 6.1271,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.25845159801546097,
301
+ "grad_norm": 44.923248291015625,
302
+ "learning_rate": 4.12e-05,
303
+ "loss": 6.1036,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.26460520749201955,
308
+ "grad_norm": 53.389827728271484,
309
+ "learning_rate": 4.2199999999999996e-05,
310
+ "loss": 6.0938,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.2707588169685781,
315
+ "grad_norm": 36.64761734008789,
316
+ "learning_rate": 4.319999999999999e-05,
317
+ "loss": 6.1188,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.27691242644513675,
322
+ "grad_norm": 73.00870513916016,
323
+ "learning_rate": 4.42e-05,
324
+ "loss": 6.0647,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.2830660359216953,
329
+ "grad_norm": 54.08327865600586,
330
+ "learning_rate": 4.5199999999999994e-05,
331
+ "loss": 6.0432,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.2892196453982539,
336
+ "grad_norm": 40.13100051879883,
337
+ "learning_rate": 4.62e-05,
338
+ "loss": 6.0383,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.29537325487481253,
343
+ "grad_norm": 39.69797134399414,
344
+ "learning_rate": 4.7199999999999995e-05,
345
+ "loss": 6.0178,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.3015268643513711,
350
+ "grad_norm": 47.64400863647461,
351
+ "learning_rate": 4.82e-05,
352
+ "loss": 6.0412,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.3076804738279297,
357
+ "grad_norm": 59.538387298583984,
358
+ "learning_rate": 4.9199999999999997e-05,
359
+ "loss": 5.9841,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.3138340833044883,
364
+ "grad_norm": 63.603389739990234,
365
+ "learning_rate": 5.0199999999999994e-05,
366
+ "loss": 6.0088,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.3199876927810469,
371
+ "grad_norm": 50.28224563598633,
372
+ "learning_rate": 5.119999999999999e-05,
373
+ "loss": 5.9469,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.32614130225760546,
378
+ "grad_norm": 43.31625747680664,
379
+ "learning_rate": 5.2199999999999995e-05,
380
+ "loss": 5.9464,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.3322949117341641,
385
+ "grad_norm": 56.94966506958008,
386
+ "learning_rate": 5.32e-05,
387
+ "loss": 5.9139,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.33844852121072266,
392
+ "grad_norm": 97.49286651611328,
393
+ "learning_rate": 5.4199999999999996e-05,
394
+ "loss": 5.9177,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.34460213068728124,
399
+ "grad_norm": 57.25851058959961,
400
+ "learning_rate": 5.519999999999999e-05,
401
+ "loss": 5.8818,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.35075574016383987,
406
+ "grad_norm": 40.23714065551758,
407
+ "learning_rate": 5.619999999999999e-05,
408
+ "loss": 5.8755,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.35690934964039844,
413
+ "grad_norm": 39.241878509521484,
414
+ "learning_rate": 5.72e-05,
415
+ "loss": 5.8417,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.363062959116957,
420
+ "grad_norm": 46.391117095947266,
421
+ "learning_rate": 5.82e-05,
422
+ "loss": 5.8327,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.36921656859351565,
427
+ "grad_norm": 51.62196350097656,
428
+ "learning_rate": 5.9199999999999996e-05,
429
+ "loss": 5.7876,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.3753701780700742,
434
+ "grad_norm": 45.93042755126953,
435
+ "learning_rate": 6.019999999999999e-05,
436
+ "loss": 5.7931,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.3815237875466328,
441
+ "grad_norm": 47.86789321899414,
442
+ "learning_rate": 6.12e-05,
443
+ "loss": 5.7766,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.38767739702319143,
448
+ "grad_norm": 51.02197265625,
449
+ "learning_rate": 6.22e-05,
450
+ "loss": 5.7919,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.39383100649975,
455
+ "grad_norm": 43.17515182495117,
456
+ "learning_rate": 6.319999999999999e-05,
457
+ "loss": 5.7334,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.3999846159763086,
462
+ "grad_norm": 38.8260612487793,
463
+ "learning_rate": 6.419999999999999e-05,
464
+ "loss": 5.7261,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.4061382254528672,
469
+ "grad_norm": 46.640254974365234,
470
+ "learning_rate": 6.519999999999999e-05,
471
+ "loss": 5.7115,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.4122918349294258,
476
+ "grad_norm": 44.81010818481445,
477
+ "learning_rate": 6.62e-05,
478
+ "loss": 5.6818,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.4184454444059844,
483
+ "grad_norm": 49.53409957885742,
484
+ "learning_rate": 6.72e-05,
485
+ "loss": 5.6717,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.424599053882543,
490
+ "grad_norm": 43.571102142333984,
491
+ "learning_rate": 6.819999999999999e-05,
492
+ "loss": 5.6472,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.43075266335910156,
497
+ "grad_norm": 52.427913665771484,
498
+ "learning_rate": 6.919999999999999e-05,
499
+ "loss": 5.6295,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.4369062728356602,
504
+ "grad_norm": 41.11359786987305,
505
+ "learning_rate": 7.02e-05,
506
+ "loss": 5.6157,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.44305988231221877,
511
+ "grad_norm": 46.67518997192383,
512
+ "learning_rate": 7.12e-05,
513
+ "loss": 5.5794,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.44921349178877734,
518
+ "grad_norm": 33.07991409301758,
519
+ "learning_rate": 7.219999999999999e-05,
520
+ "loss": 5.573,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.45536710126533597,
525
+ "grad_norm": 42.006980895996094,
526
+ "learning_rate": 7.319999999999999e-05,
527
+ "loss": 5.5528,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.46152071074189455,
532
+ "grad_norm": 48.60676956176758,
533
+ "learning_rate": 7.419999999999999e-05,
534
+ "loss": 5.539,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.4676743202184531,
539
+ "grad_norm": 37.12602996826172,
540
+ "learning_rate": 7.519999999999998e-05,
541
+ "loss": 5.5043,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.47382792969501175,
546
+ "grad_norm": 34.83266830444336,
547
+ "learning_rate": 7.62e-05,
548
+ "loss": 5.4856,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.4799815391715703,
553
+ "grad_norm": 33.03480911254883,
554
+ "learning_rate": 7.72e-05,
555
+ "loss": 5.4737,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.4861351486481289,
560
+ "grad_norm": 36.85569381713867,
561
+ "learning_rate": 7.819999999999999e-05,
562
+ "loss": 5.469,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.49228875812468753,
567
+ "grad_norm": 40.46368408203125,
568
+ "learning_rate": 7.92e-05,
569
+ "loss": 5.4437,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.4984423676012461,
574
+ "grad_norm": 33.625606536865234,
575
+ "learning_rate": 8.019999999999998e-05,
576
+ "loss": 5.4013,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.5045959770778047,
581
+ "grad_norm": 35.79458999633789,
582
+ "learning_rate": 8.12e-05,
583
+ "loss": 5.3827,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.5107495865543633,
588
+ "grad_norm": 37.801612854003906,
589
+ "learning_rate": 8.22e-05,
590
+ "loss": 5.3446,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.5169031960309219,
595
+ "grad_norm": 33.58802032470703,
596
+ "learning_rate": 8.319999999999999e-05,
597
+ "loss": 5.3542,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.5230568055074805,
602
+ "grad_norm": 37.697425842285156,
603
+ "learning_rate": 8.42e-05,
604
+ "loss": 5.3266,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.5292104149840391,
609
+ "grad_norm": 38.74336624145508,
610
+ "learning_rate": 8.519999999999998e-05,
611
+ "loss": 5.3135,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.5353640244605977,
616
+ "grad_norm": 32.21394729614258,
617
+ "learning_rate": 8.62e-05,
618
+ "loss": 5.2788,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.5415176339371562,
623
+ "grad_norm": 35.30025863647461,
624
+ "learning_rate": 8.719999999999999e-05,
625
+ "loss": 5.2661,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.5476712434137149,
630
+ "grad_norm": 36.422908782958984,
631
+ "learning_rate": 8.819999999999999e-05,
632
+ "loss": 5.2477,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.5538248528902735,
637
+ "grad_norm": 32.94489288330078,
638
+ "learning_rate": 8.92e-05,
639
+ "loss": 5.2301,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.559978462366832,
644
+ "grad_norm": 34.97354507446289,
645
+ "learning_rate": 9.02e-05,
646
+ "loss": 5.1976,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.5661320718433906,
651
+ "grad_norm": 32.73971176147461,
652
+ "learning_rate": 9.12e-05,
653
+ "loss": 5.1602,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.5722856813199493,
658
+ "grad_norm": 32.485565185546875,
659
+ "learning_rate": 9.219999999999999e-05,
660
+ "loss": 5.1333,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.5784392907965078,
665
+ "grad_norm": 33.628658294677734,
666
+ "learning_rate": 9.319999999999999e-05,
667
+ "loss": 5.1348,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.5845929002730664,
672
+ "grad_norm": 34.83700942993164,
673
+ "learning_rate": 9.419999999999999e-05,
674
+ "loss": 5.1186,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.5907465097496251,
679
+ "grad_norm": 34.83583068847656,
680
+ "learning_rate": 9.52e-05,
681
+ "loss": 5.0643,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.5969001192261836,
686
+ "grad_norm": 32.99680709838867,
687
+ "learning_rate": 9.62e-05,
688
+ "loss": 5.0916,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.6030537287027422,
693
+ "grad_norm": 35.826412200927734,
694
+ "learning_rate": 9.719999999999999e-05,
695
+ "loss": 5.0586,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.6092073381793008,
700
+ "grad_norm": 121.20379638671875,
701
+ "learning_rate": 9.819999999999999e-05,
702
+ "loss": 5.0194,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.6153609476558594,
707
+ "grad_norm": 33.31888198852539,
708
+ "learning_rate": 9.919999999999999e-05,
709
+ "loss": 5.0377,
710
+ "step": 1000
711
+ }
712
+ ],
713
+ "logging_steps": 10,
714
+ "max_steps": 100000,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 62,
717
+ "save_steps": 100,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": false
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 7.57685886959616e+16,
731
+ "train_batch_size": 16,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67d8a04beb8e0a03960173726e811f1b8582eccdf1b28b006a6664bc6f7605bb
3
+ size 5201