aixk commited on
Commit
eb9ee58
·
verified ·
1 Parent(s): 85c39f8

Upload folder using huggingface_hub

Browse files
checkpoint-900/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": 4096
17
+ }
checkpoint-900/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-900/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-900/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748efc08d832248ca122c41bb1f77814d3315e0835f85a46f8d5f301849b0a3e
3
+ size 484244528
checkpoint-900/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17f2be0219594ac79e579ddbfec817134ea3690d9cb3083f3d52e9e65b3528a
3
+ size 245864587
checkpoint-900/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6589b5ad39259a3ae46337403a02e6bdac37d0119bd95d19e166b46d6ab55bb
3
+ size 14645
checkpoint-900/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6188cab0b9c3c421966530eca2fa1b2c73f1cb3985f68e0e7df2c4b5a3d9fbc8
3
+ size 1383
checkpoint-900/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8fffa0cb399b367da8d8c28498c13570b5ffc6060a0f08298410d41f1bbdbaa
3
+ size 1465
checkpoint-900/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "HFCompatibleHybridTokenizer",
3
+ "vocab_size": 4096,
4
+ "model_max_length": 512,
5
+ "bos_token": "<bos>",
6
+ "eos_token": "<eos>",
7
+ "unk_token": "<unk>",
8
+ "pad_token": "<pad>"
9
+ }
checkpoint-900/trainer_state.json ADDED
@@ -0,0 +1,664 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.13845621322256838,
6
+ "eval_steps": 500,
7
+ "global_step": 900,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0015384023691396484,
14
+ "grad_norm": 11396.142578125,
15
+ "learning_rate": 3e-07,
16
+ "loss": 8.8759,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.003076804738279297,
21
+ "grad_norm": 689.1935424804688,
22
+ "learning_rate": 1.2999999999999998e-06,
23
+ "loss": 8.2644,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.004615207107418946,
28
+ "grad_norm": 454.8230285644531,
29
+ "learning_rate": 2.2999999999999996e-06,
30
+ "loss": 7.2145,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.006153609476558594,
35
+ "grad_norm": 169.3773193359375,
36
+ "learning_rate": 3.2999999999999993e-06,
37
+ "loss": 6.899,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.007692011845698243,
42
+ "grad_norm": 121.77935028076172,
43
+ "learning_rate": 4.2999999999999995e-06,
44
+ "loss": 6.7803,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.009230414214837892,
49
+ "grad_norm": 1289.1287841796875,
50
+ "learning_rate": 5.3e-06,
51
+ "loss": 6.5956,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.010768816583977539,
56
+ "grad_norm": 157.25286865234375,
57
+ "learning_rate": 6.3e-06,
58
+ "loss": 6.6402,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.012307218953117188,
63
+ "grad_norm": 384.85919189453125,
64
+ "learning_rate": 7.299999999999999e-06,
65
+ "loss": 6.4978,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.013845621322256836,
70
+ "grad_norm": 301.0735778808594,
71
+ "learning_rate": 8.299999999999998e-06,
72
+ "loss": 6.3964,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.015384023691396485,
77
+ "grad_norm": 226.9570770263672,
78
+ "learning_rate": 9.299999999999999e-06,
79
+ "loss": 6.3804,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.016922426060536132,
84
+ "grad_norm": 101.4676513671875,
85
+ "learning_rate": 1.03e-05,
86
+ "loss": 6.3698,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.018460828429675783,
91
+ "grad_norm": 230.73281860351562,
92
+ "learning_rate": 1.1299999999999999e-05,
93
+ "loss": 6.4247,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.01999923079881543,
98
+ "grad_norm": 124.10091400146484,
99
+ "learning_rate": 1.2299999999999999e-05,
100
+ "loss": 6.3109,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.021537633167955077,
105
+ "grad_norm": 97.28553009033203,
106
+ "learning_rate": 1.33e-05,
107
+ "loss": 6.3895,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.023076035537094728,
112
+ "grad_norm": 182.08811950683594,
113
+ "learning_rate": 1.43e-05,
114
+ "loss": 6.4089,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.024614437906234375,
119
+ "grad_norm": 433.91973876953125,
120
+ "learning_rate": 1.53e-05,
121
+ "loss": 6.3014,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.026152840275374026,
126
+ "grad_norm": 352.3630065917969,
127
+ "learning_rate": 1.6299999999999996e-05,
128
+ "loss": 6.3332,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.027691242644513673,
133
+ "grad_norm": 74.03328704833984,
134
+ "learning_rate": 1.7299999999999997e-05,
135
+ "loss": 6.315,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.02922964501365332,
140
+ "grad_norm": 264.071044921875,
141
+ "learning_rate": 1.8299999999999998e-05,
142
+ "loss": 6.3367,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.03076804738279297,
147
+ "grad_norm": 92.3805160522461,
148
+ "learning_rate": 1.93e-05,
149
+ "loss": 6.306,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.03230644975193262,
154
+ "grad_norm": 105.78662872314453,
155
+ "learning_rate": 2.03e-05,
156
+ "loss": 6.272,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.033844852121072265,
161
+ "grad_norm": 34.507057189941406,
162
+ "learning_rate": 2.1299999999999996e-05,
163
+ "loss": 6.2943,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.035383254490211916,
168
+ "grad_norm": 29.95108985900879,
169
+ "learning_rate": 2.23e-05,
170
+ "loss": 6.2231,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.036921656859351566,
175
+ "grad_norm": 105.78109741210938,
176
+ "learning_rate": 2.3299999999999997e-05,
177
+ "loss": 6.2223,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.03846005922849121,
182
+ "grad_norm": 115.77278900146484,
183
+ "learning_rate": 2.4299999999999998e-05,
184
+ "loss": 6.1873,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.03999846159763086,
189
+ "grad_norm": 117.57398223876953,
190
+ "learning_rate": 2.53e-05,
191
+ "loss": 6.1889,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.04153686396677051,
196
+ "grad_norm": 27.769681930541992,
197
+ "learning_rate": 2.63e-05,
198
+ "loss": 6.1833,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.043075266335910155,
203
+ "grad_norm": 50.23863220214844,
204
+ "learning_rate": 2.7299999999999996e-05,
205
+ "loss": 6.1718,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.044613668705049805,
210
+ "grad_norm": 16.450408935546875,
211
+ "learning_rate": 2.83e-05,
212
+ "loss": 6.0966,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.046152071074189456,
217
+ "grad_norm": 28.899629592895508,
218
+ "learning_rate": 2.9299999999999997e-05,
219
+ "loss": 6.146,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.0476904734433291,
224
+ "grad_norm": 47.915279388427734,
225
+ "learning_rate": 3.0299999999999998e-05,
226
+ "loss": 6.1493,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.04922887581246875,
231
+ "grad_norm": 27.1001033782959,
232
+ "learning_rate": 3.1299999999999995e-05,
233
+ "loss": 6.1186,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.0507672781816084,
238
+ "grad_norm": 22.059106826782227,
239
+ "learning_rate": 3.229999999999999e-05,
240
+ "loss": 6.0607,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.05230568055074805,
245
+ "grad_norm": 19.7325496673584,
246
+ "learning_rate": 3.3299999999999996e-05,
247
+ "loss": 6.1196,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.053844082919887695,
252
+ "grad_norm": 100.60061645507812,
253
+ "learning_rate": 3.4299999999999993e-05,
254
+ "loss": 6.1176,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.055382485289027346,
259
+ "grad_norm": 18.382129669189453,
260
+ "learning_rate": 3.53e-05,
261
+ "loss": 6.1501,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.056920887658166996,
266
+ "grad_norm": 31.890426635742188,
267
+ "learning_rate": 3.6299999999999995e-05,
268
+ "loss": 6.0863,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.05845929002730664,
273
+ "grad_norm": 22.61912727355957,
274
+ "learning_rate": 3.73e-05,
275
+ "loss": 6.0543,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.05999769239644629,
280
+ "grad_norm": 30.638811111450195,
281
+ "learning_rate": 3.83e-05,
282
+ "loss": 5.989,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.06153609476558594,
287
+ "grad_norm": 45.842227935791016,
288
+ "learning_rate": 3.93e-05,
289
+ "loss": 6.0216,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.06307449713472559,
294
+ "grad_norm": 61.62559127807617,
295
+ "learning_rate": 4.03e-05,
296
+ "loss": 6.0232,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.06461289950386524,
301
+ "grad_norm": 24.91366958618164,
302
+ "learning_rate": 4.1299999999999994e-05,
303
+ "loss": 6.0153,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.06615130187300489,
308
+ "grad_norm": 22.554046630859375,
309
+ "learning_rate": 4.229999999999999e-05,
310
+ "loss": 5.9533,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.06768970424214453,
315
+ "grad_norm": 22.699480056762695,
316
+ "learning_rate": 4.3299999999999995e-05,
317
+ "loss": 5.9179,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.06922810661128419,
322
+ "grad_norm": 17.466867446899414,
323
+ "learning_rate": 4.43e-05,
324
+ "loss": 5.9714,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.07076650898042383,
329
+ "grad_norm": 20.46624183654785,
330
+ "learning_rate": 4.5299999999999997e-05,
331
+ "loss": 5.9621,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.07230491134956347,
336
+ "grad_norm": 15.140242576599121,
337
+ "learning_rate": 4.6299999999999994e-05,
338
+ "loss": 5.94,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.07384331371870313,
343
+ "grad_norm": 23.270614624023438,
344
+ "learning_rate": 4.73e-05,
345
+ "loss": 5.9387,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.07538171608784278,
350
+ "grad_norm": 23.621036529541016,
351
+ "learning_rate": 4.8299999999999995e-05,
352
+ "loss": 5.9683,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.07692011845698242,
357
+ "grad_norm": 16.960304260253906,
358
+ "learning_rate": 4.929999999999999e-05,
359
+ "loss": 5.9136,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.07845852082612208,
364
+ "grad_norm": 17.167306900024414,
365
+ "learning_rate": 5.0299999999999996e-05,
366
+ "loss": 5.9011,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.07999692319526172,
371
+ "grad_norm": 28.44086456298828,
372
+ "learning_rate": 5.13e-05,
373
+ "loss": 5.88,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.08153532556440136,
378
+ "grad_norm": 19.138957977294922,
379
+ "learning_rate": 5.23e-05,
380
+ "loss": 5.8525,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.08307372793354102,
385
+ "grad_norm": 23.37527847290039,
386
+ "learning_rate": 5.3299999999999995e-05,
387
+ "loss": 5.9051,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.08461213030268067,
392
+ "grad_norm": 14.438946723937988,
393
+ "learning_rate": 5.429999999999999e-05,
394
+ "loss": 5.8024,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.08615053267182031,
399
+ "grad_norm": 17.277740478515625,
400
+ "learning_rate": 5.529999999999999e-05,
401
+ "loss": 5.764,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.08768893504095997,
406
+ "grad_norm": 18.269975662231445,
407
+ "learning_rate": 5.63e-05,
408
+ "loss": 5.8667,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.08922733741009961,
413
+ "grad_norm": 17.265398025512695,
414
+ "learning_rate": 5.73e-05,
415
+ "loss": 5.7963,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.09076573977923925,
420
+ "grad_norm": 20.076812744140625,
421
+ "learning_rate": 5.8299999999999994e-05,
422
+ "loss": 5.7426,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.09230414214837891,
427
+ "grad_norm": 25.95227813720703,
428
+ "learning_rate": 5.929999999999999e-05,
429
+ "loss": 5.7171,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.09384254451751856,
434
+ "grad_norm": 21.3321590423584,
435
+ "learning_rate": 6.0299999999999995e-05,
436
+ "loss": 5.7266,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.0953809468866582,
441
+ "grad_norm": 33.217811584472656,
442
+ "learning_rate": 6.13e-05,
443
+ "loss": 5.6971,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.09691934925579786,
448
+ "grad_norm": 16.669315338134766,
449
+ "learning_rate": 6.23e-05,
450
+ "loss": 5.7298,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.0984577516249375,
455
+ "grad_norm": 14.09073543548584,
456
+ "learning_rate": 6.33e-05,
457
+ "loss": 5.7124,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.09999615399407714,
462
+ "grad_norm": 19.583980560302734,
463
+ "learning_rate": 6.429999999999999e-05,
464
+ "loss": 5.7241,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.1015345563632168,
469
+ "grad_norm": 24.256364822387695,
470
+ "learning_rate": 6.53e-05,
471
+ "loss": 5.7128,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.10307295873235645,
476
+ "grad_norm": 23.34236717224121,
477
+ "learning_rate": 6.63e-05,
478
+ "loss": 5.5961,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.1046113611014961,
483
+ "grad_norm": 20.654870986938477,
484
+ "learning_rate": 6.73e-05,
485
+ "loss": 5.5613,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.10614976347063575,
490
+ "grad_norm": 30.639785766601562,
491
+ "learning_rate": 6.829999999999999e-05,
492
+ "loss": 5.6384,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.10768816583977539,
497
+ "grad_norm": 15.175138473510742,
498
+ "learning_rate": 6.93e-05,
499
+ "loss": 5.5526,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.10922656820891505,
504
+ "grad_norm": 20.746421813964844,
505
+ "learning_rate": 7.03e-05,
506
+ "loss": 5.6075,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.11076497057805469,
511
+ "grad_norm": 14.452651023864746,
512
+ "learning_rate": 7.13e-05,
513
+ "loss": 5.6052,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.11230337294719434,
518
+ "grad_norm": 15.90872859954834,
519
+ "learning_rate": 7.23e-05,
520
+ "loss": 5.5681,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.11384177531633399,
525
+ "grad_norm": 19.600723266601562,
526
+ "learning_rate": 7.329999999999999e-05,
527
+ "loss": 5.5155,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.11538017768547364,
532
+ "grad_norm": 15.309789657592773,
533
+ "learning_rate": 7.429999999999999e-05,
534
+ "loss": 5.5764,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.11691858005461328,
539
+ "grad_norm": 19.05169677734375,
540
+ "learning_rate": 7.529999999999999e-05,
541
+ "loss": 5.4731,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.11845698242375294,
546
+ "grad_norm": 19.819692611694336,
547
+ "learning_rate": 7.63e-05,
548
+ "loss": 5.3959,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.11999538479289258,
553
+ "grad_norm": 19.908710479736328,
554
+ "learning_rate": 7.73e-05,
555
+ "loss": 5.43,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.12153378716203223,
560
+ "grad_norm": 22.767356872558594,
561
+ "learning_rate": 7.829999999999999e-05,
562
+ "loss": 5.432,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.12307218953117188,
567
+ "grad_norm": 14.213640213012695,
568
+ "learning_rate": 7.929999999999999e-05,
569
+ "loss": 5.4079,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.12461059190031153,
574
+ "grad_norm": 16.46720314025879,
575
+ "learning_rate": 8.029999999999999e-05,
576
+ "loss": 5.4254,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.12614899426945117,
581
+ "grad_norm": 19.044301986694336,
582
+ "learning_rate": 8.13e-05,
583
+ "loss": 5.3561,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.12768739663859083,
588
+ "grad_norm": 23.400588989257812,
589
+ "learning_rate": 8.23e-05,
590
+ "loss": 5.4002,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.12922579900773049,
595
+ "grad_norm": 17.108936309814453,
596
+ "learning_rate": 8.329999999999999e-05,
597
+ "loss": 5.3148,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.13076420137687012,
602
+ "grad_norm": 13.769838333129883,
603
+ "learning_rate": 8.43e-05,
604
+ "loss": 5.2701,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.13230260374600977,
609
+ "grad_norm": 17.94414520263672,
610
+ "learning_rate": 8.529999999999999e-05,
611
+ "loss": 5.3379,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.13384100611514943,
616
+ "grad_norm": 15.634041786193848,
617
+ "learning_rate": 8.63e-05,
618
+ "loss": 5.2263,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.13537940848428906,
623
+ "grad_norm": 16.440696716308594,
624
+ "learning_rate": 8.729999999999998e-05,
625
+ "loss": 5.2153,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.13691781085342872,
630
+ "grad_norm": 14.667311668395996,
631
+ "learning_rate": 8.829999999999999e-05,
632
+ "loss": 5.2754,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.13845621322256838,
637
+ "grad_norm": 12.900784492492676,
638
+ "learning_rate": 8.93e-05,
639
+ "loss": 5.2061,
640
+ "step": 900
641
+ }
642
+ ],
643
+ "logging_steps": 10,
644
+ "max_steps": 100000,
645
+ "num_input_tokens_seen": 0,
646
+ "num_train_epochs": 16,
647
+ "save_steps": 100,
648
+ "stateful_callbacks": {
649
+ "TrainerControl": {
650
+ "args": {
651
+ "should_epoch_stop": false,
652
+ "should_evaluate": false,
653
+ "should_log": false,
654
+ "should_save": true,
655
+ "should_training_stop": false
656
+ },
657
+ "attributes": {}
658
+ }
659
+ },
660
+ "total_flos": 1.7340526089781248e+16,
661
+ "train_batch_size": 8,
662
+ "trial_name": null,
663
+ "trial_params": null
664
+ }
checkpoint-900/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe063a25a8755f50ff355c4d7a3fb17af44f79bfac09e4b2672cd081c5200ef0
3
+ size 5201