aixk commited on
Commit
ce8f82e
·
verified ·
1 Parent(s): 4e46ab3

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": 8192
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:a2dbf55929ed165e99773d2a65f8e4b201107141c7b37c586901152945e0181f
3
+ size 501755480
checkpoint-900/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c247c8bec10cc5e086ee3a47d56ade45fbee7262b1eeb5118666ffbb2c0a108
3
+ size 254410983
checkpoint-900/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad4a2c48ff38de9e5d71cf1c4397a229273e0d5cfd87c31ed7c2602324502d2b
3
+ size 14645
checkpoint-900/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f966eec798fa73b74e566c003e635e9fa57b0cdef6061cbe1d684120dda7ca
3
+ size 1383
checkpoint-900/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c92f2fb8fad6f382796585fad71fbe8e6267c5b2e4f5d8eb351e2a4e4fd14a2f
3
+ size 1465
checkpoint-900/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-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": 15216.6796875,
15
+ "learning_rate": 1.9999999999999996e-07,
16
+ "loss": 7.628,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.003076804738279297,
21
+ "grad_norm": 539.3572387695312,
22
+ "learning_rate": 1.2e-06,
23
+ "loss": 7.3644,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.004615207107418946,
28
+ "grad_norm": 496.3940734863281,
29
+ "learning_rate": 2.1999999999999997e-06,
30
+ "loss": 7.0137,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.006153609476558594,
35
+ "grad_norm": 110.5931396484375,
36
+ "learning_rate": 3.1999999999999994e-06,
37
+ "loss": 6.9299,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.007692011845698243,
42
+ "grad_norm": 442.7750549316406,
43
+ "learning_rate": 4.2e-06,
44
+ "loss": 6.88,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.009230414214837892,
49
+ "grad_norm": 285.75390625,
50
+ "learning_rate": 5.199999999999999e-06,
51
+ "loss": 6.7252,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.010768816583977539,
56
+ "grad_norm": 238.201416015625,
57
+ "learning_rate": 6.199999999999999e-06,
58
+ "loss": 6.7641,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.012307218953117188,
63
+ "grad_norm": 203.7633514404297,
64
+ "learning_rate": 7.2e-06,
65
+ "loss": 6.6961,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.013845621322256836,
70
+ "grad_norm": 537.8616943359375,
71
+ "learning_rate": 8.2e-06,
72
+ "loss": 6.5996,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.015384023691396485,
77
+ "grad_norm": 643.6299438476562,
78
+ "learning_rate": 9.199999999999998e-06,
79
+ "loss": 6.5856,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.016922426060536132,
84
+ "grad_norm": 679.996337890625,
85
+ "learning_rate": 1.02e-05,
86
+ "loss": 6.599,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.018460828429675783,
91
+ "grad_norm": 452.3795471191406,
92
+ "learning_rate": 1.12e-05,
93
+ "loss": 6.6354,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.01999923079881543,
98
+ "grad_norm": 117.24376678466797,
99
+ "learning_rate": 1.2199999999999998e-05,
100
+ "loss": 6.5363,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.021537633167955077,
105
+ "grad_norm": 145.65036010742188,
106
+ "learning_rate": 1.3199999999999997e-05,
107
+ "loss": 6.5564,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.023076035537094728,
112
+ "grad_norm": 178.4263458251953,
113
+ "learning_rate": 1.4199999999999998e-05,
114
+ "loss": 6.5828,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.024614437906234375,
119
+ "grad_norm": 174.7183837890625,
120
+ "learning_rate": 1.5199999999999998e-05,
121
+ "loss": 6.4821,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.026152840275374026,
126
+ "grad_norm": 145.78704833984375,
127
+ "learning_rate": 1.6199999999999997e-05,
128
+ "loss": 6.4711,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.027691242644513673,
133
+ "grad_norm": 217.81866455078125,
134
+ "learning_rate": 1.7199999999999998e-05,
135
+ "loss": 6.4947,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.02922964501365332,
140
+ "grad_norm": 105.79635620117188,
141
+ "learning_rate": 1.82e-05,
142
+ "loss": 6.4997,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.03076804738279297,
147
+ "grad_norm": 86.61837768554688,
148
+ "learning_rate": 1.92e-05,
149
+ "loss": 6.4604,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.03230644975193262,
154
+ "grad_norm": 102.03221893310547,
155
+ "learning_rate": 2.0199999999999996e-05,
156
+ "loss": 6.4451,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.033844852121072265,
161
+ "grad_norm": 93.15425109863281,
162
+ "learning_rate": 2.12e-05,
163
+ "loss": 6.4653,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.035383254490211916,
168
+ "grad_norm": 120.66065979003906,
169
+ "learning_rate": 2.2199999999999998e-05,
170
+ "loss": 6.3898,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.036921656859351566,
175
+ "grad_norm": 108.00463104248047,
176
+ "learning_rate": 2.3199999999999998e-05,
177
+ "loss": 6.3907,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.03846005922849121,
182
+ "grad_norm": 129.6912841796875,
183
+ "learning_rate": 2.42e-05,
184
+ "loss": 6.3551,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.03999846159763086,
189
+ "grad_norm": 66.96916961669922,
190
+ "learning_rate": 2.52e-05,
191
+ "loss": 6.3443,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.04153686396677051,
196
+ "grad_norm": 44.31541061401367,
197
+ "learning_rate": 2.6199999999999996e-05,
198
+ "loss": 6.3372,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.043075266335910155,
203
+ "grad_norm": 21.828279495239258,
204
+ "learning_rate": 2.72e-05,
205
+ "loss": 6.3368,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.044613668705049805,
210
+ "grad_norm": 38.62431716918945,
211
+ "learning_rate": 2.8199999999999998e-05,
212
+ "loss": 6.2708,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.046152071074189456,
217
+ "grad_norm": 28.7634334564209,
218
+ "learning_rate": 2.9199999999999995e-05,
219
+ "loss": 6.3324,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.0476904734433291,
224
+ "grad_norm": 29.64866065979004,
225
+ "learning_rate": 3.02e-05,
226
+ "loss": 6.329,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.04922887581246875,
231
+ "grad_norm": 27.20194435119629,
232
+ "learning_rate": 3.119999999999999e-05,
233
+ "loss": 6.2864,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.0507672781816084,
238
+ "grad_norm": 24.59855079650879,
239
+ "learning_rate": 3.22e-05,
240
+ "loss": 6.2371,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.05230568055074805,
245
+ "grad_norm": 32.6953239440918,
246
+ "learning_rate": 3.3199999999999994e-05,
247
+ "loss": 6.2824,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.053844082919887695,
252
+ "grad_norm": 36.308067321777344,
253
+ "learning_rate": 3.42e-05,
254
+ "loss": 6.2977,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.055382485289027346,
259
+ "grad_norm": 25.23465347290039,
260
+ "learning_rate": 3.5199999999999995e-05,
261
+ "loss": 6.3222,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.056920887658166996,
266
+ "grad_norm": 47.594947814941406,
267
+ "learning_rate": 3.62e-05,
268
+ "loss": 6.2513,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.05845929002730664,
273
+ "grad_norm": 44.8812370300293,
274
+ "learning_rate": 3.7199999999999996e-05,
275
+ "loss": 6.2244,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.05999769239644629,
280
+ "grad_norm": 22.950286865234375,
281
+ "learning_rate": 3.8199999999999993e-05,
282
+ "loss": 6.1613,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.06153609476558594,
287
+ "grad_norm": 23.65997314453125,
288
+ "learning_rate": 3.919999999999999e-05,
289
+ "loss": 6.1839,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.06307449713472559,
294
+ "grad_norm": 37.60873031616211,
295
+ "learning_rate": 4.02e-05,
296
+ "loss": 6.1783,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.06461289950386524,
301
+ "grad_norm": 30.03960418701172,
302
+ "learning_rate": 4.12e-05,
303
+ "loss": 6.1673,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.06615130187300489,
308
+ "grad_norm": 38.63550567626953,
309
+ "learning_rate": 4.2199999999999996e-05,
310
+ "loss": 6.1151,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.06768970424214453,
315
+ "grad_norm": 24.747684478759766,
316
+ "learning_rate": 4.319999999999999e-05,
317
+ "loss": 6.0666,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.06922810661128419,
322
+ "grad_norm": 22.29100799560547,
323
+ "learning_rate": 4.42e-05,
324
+ "loss": 6.1266,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.07076650898042383,
329
+ "grad_norm": 24.165313720703125,
330
+ "learning_rate": 4.5199999999999994e-05,
331
+ "loss": 6.1199,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.07230491134956347,
336
+ "grad_norm": 19.26260757446289,
337
+ "learning_rate": 4.62e-05,
338
+ "loss": 6.1002,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.07384331371870313,
343
+ "grad_norm": 21.792062759399414,
344
+ "learning_rate": 4.7199999999999995e-05,
345
+ "loss": 6.0919,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.07538171608784278,
350
+ "grad_norm": 25.019775390625,
351
+ "learning_rate": 4.82e-05,
352
+ "loss": 6.1171,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.07692011845698242,
357
+ "grad_norm": 21.131744384765625,
358
+ "learning_rate": 4.9199999999999997e-05,
359
+ "loss": 6.0676,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.07845852082612208,
364
+ "grad_norm": 24.013105392456055,
365
+ "learning_rate": 5.0199999999999994e-05,
366
+ "loss": 6.0463,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.07999692319526172,
371
+ "grad_norm": 20.643056869506836,
372
+ "learning_rate": 5.119999999999999e-05,
373
+ "loss": 6.0317,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.08153532556440136,
378
+ "grad_norm": 27.55217170715332,
379
+ "learning_rate": 5.2199999999999995e-05,
380
+ "loss": 5.9955,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.08307372793354102,
385
+ "grad_norm": 24.888734817504883,
386
+ "learning_rate": 5.32e-05,
387
+ "loss": 6.0481,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.08461213030268067,
392
+ "grad_norm": 19.217220306396484,
393
+ "learning_rate": 5.4199999999999996e-05,
394
+ "loss": 5.9471,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.08615053267182031,
399
+ "grad_norm": 19.650312423706055,
400
+ "learning_rate": 5.519999999999999e-05,
401
+ "loss": 5.9048,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.08768893504095997,
406
+ "grad_norm": 21.437850952148438,
407
+ "learning_rate": 5.619999999999999e-05,
408
+ "loss": 6.0098,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.08922733741009961,
413
+ "grad_norm": 23.66594696044922,
414
+ "learning_rate": 5.72e-05,
415
+ "loss": 5.9389,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.09076573977923925,
420
+ "grad_norm": 33.00392532348633,
421
+ "learning_rate": 5.82e-05,
422
+ "loss": 5.8897,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.09230414214837891,
427
+ "grad_norm": 20.737876892089844,
428
+ "learning_rate": 5.9199999999999996e-05,
429
+ "loss": 5.8598,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.09384254451751856,
434
+ "grad_norm": 23.151851654052734,
435
+ "learning_rate": 6.019999999999999e-05,
436
+ "loss": 5.8652,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.0953809468866582,
441
+ "grad_norm": 23.21453094482422,
442
+ "learning_rate": 6.12e-05,
443
+ "loss": 5.833,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.09691934925579786,
448
+ "grad_norm": 23.856670379638672,
449
+ "learning_rate": 6.22e-05,
450
+ "loss": 5.8686,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.0984577516249375,
455
+ "grad_norm": 18.7842960357666,
456
+ "learning_rate": 6.319999999999999e-05,
457
+ "loss": 5.8517,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.09999615399407714,
462
+ "grad_norm": 16.733356475830078,
463
+ "learning_rate": 6.419999999999999e-05,
464
+ "loss": 5.8614,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.1015345563632168,
469
+ "grad_norm": 18.41499137878418,
470
+ "learning_rate": 6.519999999999999e-05,
471
+ "loss": 5.8441,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.10307295873235645,
476
+ "grad_norm": 20.63882827758789,
477
+ "learning_rate": 6.62e-05,
478
+ "loss": 5.7316,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.1046113611014961,
483
+ "grad_norm": 17.48029899597168,
484
+ "learning_rate": 6.72e-05,
485
+ "loss": 5.6974,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.10614976347063575,
490
+ "grad_norm": 22.546825408935547,
491
+ "learning_rate": 6.819999999999999e-05,
492
+ "loss": 5.7741,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.10768816583977539,
497
+ "grad_norm": 16.246665954589844,
498
+ "learning_rate": 6.919999999999999e-05,
499
+ "loss": 5.6912,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.10922656820891505,
504
+ "grad_norm": 16.516803741455078,
505
+ "learning_rate": 7.02e-05,
506
+ "loss": 5.7397,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.11076497057805469,
511
+ "grad_norm": 19.068937301635742,
512
+ "learning_rate": 7.12e-05,
513
+ "loss": 5.7386,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.11230337294719434,
518
+ "grad_norm": 14.85578727722168,
519
+ "learning_rate": 7.219999999999999e-05,
520
+ "loss": 5.6994,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.11384177531633399,
525
+ "grad_norm": 18.3763427734375,
526
+ "learning_rate": 7.319999999999999e-05,
527
+ "loss": 5.6505,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.11538017768547364,
532
+ "grad_norm": 16.224000930786133,
533
+ "learning_rate": 7.419999999999999e-05,
534
+ "loss": 5.7087,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.11691858005461328,
539
+ "grad_norm": 15.365422248840332,
540
+ "learning_rate": 7.519999999999998e-05,
541
+ "loss": 5.6072,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.11845698242375294,
546
+ "grad_norm": 18.633525848388672,
547
+ "learning_rate": 7.62e-05,
548
+ "loss": 5.5342,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.11999538479289258,
553
+ "grad_norm": 19.027240753173828,
554
+ "learning_rate": 7.72e-05,
555
+ "loss": 5.5611,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.12153378716203223,
560
+ "grad_norm": 16.857473373413086,
561
+ "learning_rate": 7.819999999999999e-05,
562
+ "loss": 5.5638,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.12307218953117188,
567
+ "grad_norm": 15.174002647399902,
568
+ "learning_rate": 7.92e-05,
569
+ "loss": 5.5405,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.12461059190031153,
574
+ "grad_norm": 16.1444034576416,
575
+ "learning_rate": 8.019999999999998e-05,
576
+ "loss": 5.5565,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.12614899426945117,
581
+ "grad_norm": 18.24864959716797,
582
+ "learning_rate": 8.12e-05,
583
+ "loss": 5.4931,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.12768739663859083,
588
+ "grad_norm": 18.213571548461914,
589
+ "learning_rate": 8.22e-05,
590
+ "loss": 5.5312,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.12922579900773049,
595
+ "grad_norm": 17.174373626708984,
596
+ "learning_rate": 8.319999999999999e-05,
597
+ "loss": 5.4435,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.13076420137687012,
602
+ "grad_norm": 15.482538223266602,
603
+ "learning_rate": 8.42e-05,
604
+ "loss": 5.4082,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.13230260374600977,
609
+ "grad_norm": 17.8658504486084,
610
+ "learning_rate": 8.519999999999998e-05,
611
+ "loss": 5.473,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.13384100611514943,
616
+ "grad_norm": 15.455946922302246,
617
+ "learning_rate": 8.62e-05,
618
+ "loss": 5.3541,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.13537940848428906,
623
+ "grad_norm": 15.936956405639648,
624
+ "learning_rate": 8.719999999999999e-05,
625
+ "loss": 5.3488,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.13691781085342872,
630
+ "grad_norm": 19.47191619873047,
631
+ "learning_rate": 8.819999999999999e-05,
632
+ "loss": 5.4054,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.13845621322256838,
637
+ "grad_norm": 12.858948707580566,
638
+ "learning_rate": 8.92e-05,
639
+ "loss": 5.3355,
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": 1.72447977517056e+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 sha256:62417cc687938b852957f7012ea833e7979cfe3f532b1c8c4b1c41687231ccf6
3
+ size 5201