aixk commited on
Commit
cbf4c04
·
verified ·
1 Parent(s): fd7328b

Upload folder using huggingface_hub

Browse files
checkpoint-1400/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_16k",
12
+ "num_attention_heads": 12,
13
+ "num_hidden_layers": 16,
14
+ "transformers_version": "5.13.1",
15
+ "use_cache": false,
16
+ "vocab_size": 16384
17
+ }
checkpoint-1400/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-1400/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0674a7b4c2de9dd2e1ae64eb8e73525553310890551442486ed1f96cb8c31a
3
+ size 543870712
checkpoint-1400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87542d45ba2debf4b299871a84dfcaa531333cb677355361c1768e25d6430f53
3
+ size 276872907
checkpoint-1400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e16593db67ba1afd5b9b7829688ee28830ae65253b7192923010ed26669dca
3
+ size 14645
checkpoint-1400/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a568eec3f87760ee4aeb5248fddf702419d222f4bd083722e19dd6407e9774a
3
+ size 1383
checkpoint-1400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f4ee110e92da206d39d09b4e3b401512d33989b2e844f9ed5af2ca3c43dbdc
3
+ size 1465
checkpoint-1400/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "HFCompatibleLinguisticTokenizer",
3
+ "vocab_size": 16384,
4
+ "model_max_length": 512,
5
+ "bos_token": "<bos>",
6
+ "eos_token": "<eos>",
7
+ "unk_token": "<unk>",
8
+ "pad_token": "<pad>"
9
+ }
checkpoint-1400/trainer_state.json ADDED
@@ -0,0 +1,1014 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.004840605767236014,
6
+ "eval_steps": 500,
7
+ "global_step": 1400,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 3.4575755480257244e-05,
14
+ "grad_norm": 38.12546920776367,
15
+ "learning_rate": 4.8e-07,
16
+ "loss": 9.3097,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 6.915151096051449e-05,
21
+ "grad_norm": 31.766887664794922,
22
+ "learning_rate": 1.0799999999999998e-06,
23
+ "loss": 9.293,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.00010372726644077173,
28
+ "grad_norm": 48.67866897583008,
29
+ "learning_rate": 1.6799999999999998e-06,
30
+ "loss": 9.2784,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.00013830302192102898,
35
+ "grad_norm": 33.25461959838867,
36
+ "learning_rate": 2.2799999999999998e-06,
37
+ "loss": 9.2793,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.00017287877740128623,
42
+ "grad_norm": 35.62735366821289,
43
+ "learning_rate": 2.8799999999999995e-06,
44
+ "loss": 9.2657,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.00020745453288154345,
49
+ "grad_norm": 43.818328857421875,
50
+ "learning_rate": 3.4799999999999993e-06,
51
+ "loss": 9.2616,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0002420302883618007,
56
+ "grad_norm": 43.82963943481445,
57
+ "learning_rate": 4.079999999999999e-06,
58
+ "loss": 9.2633,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.00027660604384205796,
63
+ "grad_norm": 57.38799285888672,
64
+ "learning_rate": 4.679999999999999e-06,
65
+ "loss": 9.2308,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0003111817993223152,
70
+ "grad_norm": 44.78755187988281,
71
+ "learning_rate": 5.28e-06,
72
+ "loss": 9.2083,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.00034575755480257246,
77
+ "grad_norm": 40.440338134765625,
78
+ "learning_rate": 5.88e-06,
79
+ "loss": 9.2418,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.00038033331028282965,
84
+ "grad_norm": 36.28009033203125,
85
+ "learning_rate": 6.48e-06,
86
+ "loss": 9.2208,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.0004149090657630869,
91
+ "grad_norm": 42.1943473815918,
92
+ "learning_rate": 7.079999999999999e-06,
93
+ "loss": 9.2197,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.00044948482124334416,
98
+ "grad_norm": 37.897483825683594,
99
+ "learning_rate": 7.68e-06,
100
+ "loss": 9.2271,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.0004840605767236014,
105
+ "grad_norm": 33.77066421508789,
106
+ "learning_rate": 8.279999999999999e-06,
107
+ "loss": 9.2311,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.0005186363322038587,
112
+ "grad_norm": 34.798553466796875,
113
+ "learning_rate": 8.88e-06,
114
+ "loss": 9.2079,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.0005532120876841159,
119
+ "grad_norm": 39.236812591552734,
120
+ "learning_rate": 9.48e-06,
121
+ "loss": 9.2186,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.0005877878431643732,
126
+ "grad_norm": 37.878868103027344,
127
+ "learning_rate": 1.0079999999999998e-05,
128
+ "loss": 9.2176,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.0006223635986446304,
133
+ "grad_norm": 64.34676361083984,
134
+ "learning_rate": 1.068e-05,
135
+ "loss": 9.2086,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.0006569393541248877,
140
+ "grad_norm": 35.60507583618164,
141
+ "learning_rate": 1.1279999999999999e-05,
142
+ "loss": 9.2045,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.0006915151096051449,
147
+ "grad_norm": 45.516971588134766,
148
+ "learning_rate": 1.188e-05,
149
+ "loss": 9.2144,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.0007260908650854022,
154
+ "grad_norm": 33.20392608642578,
155
+ "learning_rate": 1.2479999999999999e-05,
156
+ "loss": 9.1846,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.0007606666205656593,
161
+ "grad_norm": 33.04153060913086,
162
+ "learning_rate": 1.3019999999999999e-05,
163
+ "loss": 9.1875,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.0007952423760459166,
168
+ "grad_norm": 29.512754440307617,
169
+ "learning_rate": 1.362e-05,
170
+ "loss": 9.1849,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.0008298181315261738,
175
+ "grad_norm": 24.111255645751953,
176
+ "learning_rate": 1.4219999999999998e-05,
177
+ "loss": 9.2074,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.0008643938870064311,
182
+ "grad_norm": 36.84242630004883,
183
+ "learning_rate": 1.4819999999999999e-05,
184
+ "loss": 9.1818,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.0008989696424866883,
189
+ "grad_norm": 22.629037857055664,
190
+ "learning_rate": 1.5419999999999998e-05,
191
+ "loss": 9.1991,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.0009335453979669456,
196
+ "grad_norm": 28.257951736450195,
197
+ "learning_rate": 1.602e-05,
198
+ "loss": 9.1579,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.0009681211534472028,
203
+ "grad_norm": 26.29328155517578,
204
+ "learning_rate": 1.6619999999999997e-05,
205
+ "loss": 9.1753,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.00100269690892746,
210
+ "grad_norm": 30.55463981628418,
211
+ "learning_rate": 1.7219999999999998e-05,
212
+ "loss": 9.1663,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.0010372726644077173,
217
+ "grad_norm": 30.852642059326172,
218
+ "learning_rate": 1.782e-05,
219
+ "loss": 9.1624,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.0010718484198879745,
224
+ "grad_norm": 30.8385009765625,
225
+ "learning_rate": 1.842e-05,
226
+ "loss": 9.1754,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.0011064241753682318,
231
+ "grad_norm": 16.846324920654297,
232
+ "learning_rate": 1.9019999999999997e-05,
233
+ "loss": 9.1774,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.001140999930848489,
238
+ "grad_norm": 26.020891189575195,
239
+ "learning_rate": 1.962e-05,
240
+ "loss": 9.1461,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.0011755756863287463,
245
+ "grad_norm": 24.087093353271484,
246
+ "learning_rate": 2.022e-05,
247
+ "loss": 9.1698,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.0012101514418090035,
252
+ "grad_norm": 22.612030029296875,
253
+ "learning_rate": 2.082e-05,
254
+ "loss": 9.1564,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.0012447271972892608,
259
+ "grad_norm": 24.23309898376465,
260
+ "learning_rate": 2.1419999999999998e-05,
261
+ "loss": 9.1407,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.001279302952769518,
266
+ "grad_norm": 19.798912048339844,
267
+ "learning_rate": 2.202e-05,
268
+ "loss": 9.1916,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.0013138787082497753,
273
+ "grad_norm": 17.621305465698242,
274
+ "learning_rate": 2.2619999999999997e-05,
275
+ "loss": 9.1724,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.0013484544637300325,
280
+ "grad_norm": 19.028974533081055,
281
+ "learning_rate": 2.3219999999999998e-05,
282
+ "loss": 9.1416,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.0013830302192102898,
287
+ "grad_norm": 15.816458702087402,
288
+ "learning_rate": 2.382e-05,
289
+ "loss": 9.1704,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.001417605974690547,
294
+ "grad_norm": 19.060916900634766,
295
+ "learning_rate": 2.4419999999999997e-05,
296
+ "loss": 9.1527,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.0014521817301708043,
301
+ "grad_norm": 23.854291915893555,
302
+ "learning_rate": 2.5019999999999998e-05,
303
+ "loss": 9.146,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.0014867574856510615,
308
+ "grad_norm": 20.823823928833008,
309
+ "learning_rate": 2.562e-05,
310
+ "loss": 9.1528,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.0015213332411313186,
315
+ "grad_norm": 20.012248992919922,
316
+ "learning_rate": 2.622e-05,
317
+ "loss": 9.133,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.001555908996611576,
322
+ "grad_norm": 17.968521118164062,
323
+ "learning_rate": 2.6819999999999997e-05,
324
+ "loss": 9.1451,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.0015904847520918331,
329
+ "grad_norm": 19.263395309448242,
330
+ "learning_rate": 2.7419999999999995e-05,
331
+ "loss": 9.1414,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.0016250605075720905,
336
+ "grad_norm": 19.886655807495117,
337
+ "learning_rate": 2.8019999999999996e-05,
338
+ "loss": 9.1132,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.0016596362630523476,
343
+ "grad_norm": 20.179471969604492,
344
+ "learning_rate": 2.8619999999999997e-05,
345
+ "loss": 9.1274,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.001694212018532605,
350
+ "grad_norm": 16.05131721496582,
351
+ "learning_rate": 2.9219999999999998e-05,
352
+ "loss": 9.1407,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.0017287877740128621,
357
+ "grad_norm": 16.787809371948242,
358
+ "learning_rate": 2.982e-05,
359
+ "loss": 9.1274,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.0017633635294931195,
364
+ "grad_norm": 14.712662696838379,
365
+ "learning_rate": 3.042e-05,
366
+ "loss": 9.1694,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.0017979392849733766,
371
+ "grad_norm": 14.417969703674316,
372
+ "learning_rate": 3.102e-05,
373
+ "loss": 9.1474,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.001832515040453634,
378
+ "grad_norm": 29.00182342529297,
379
+ "learning_rate": 3.161999999999999e-05,
380
+ "loss": 9.1549,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.0018670907959338911,
385
+ "grad_norm": 16.824987411499023,
386
+ "learning_rate": 3.221999999999999e-05,
387
+ "loss": 9.1384,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.0019016665514141485,
392
+ "grad_norm": 18.04323387145996,
393
+ "learning_rate": 3.2819999999999994e-05,
394
+ "loss": 9.1522,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.0019362423068944056,
399
+ "grad_norm": 14.293987274169922,
400
+ "learning_rate": 3.3419999999999995e-05,
401
+ "loss": 9.1301,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.0019708180623746628,
406
+ "grad_norm": 19.81171226501465,
407
+ "learning_rate": 3.4019999999999996e-05,
408
+ "loss": 9.1233,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.00200539381785492,
413
+ "grad_norm": 14.640559196472168,
414
+ "learning_rate": 3.462e-05,
415
+ "loss": 9.1311,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.0020399695733351775,
420
+ "grad_norm": 18.38323974609375,
421
+ "learning_rate": 3.522e-05,
422
+ "loss": 9.1222,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.0020745453288154346,
427
+ "grad_norm": 17.136762619018555,
428
+ "learning_rate": 3.582e-05,
429
+ "loss": 9.1199,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.0021091210842956918,
434
+ "grad_norm": 15.868051528930664,
435
+ "learning_rate": 3.6419999999999994e-05,
436
+ "loss": 9.1615,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.002143696839775949,
441
+ "grad_norm": 12.776758193969727,
442
+ "learning_rate": 3.7019999999999995e-05,
443
+ "loss": 9.1367,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.0021782725952562065,
448
+ "grad_norm": 24.72905731201172,
449
+ "learning_rate": 3.762e-05,
450
+ "loss": 9.0972,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.0022128483507364636,
455
+ "grad_norm": 10.394266128540039,
456
+ "learning_rate": 3.822e-05,
457
+ "loss": 9.1424,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.002247424106216721,
462
+ "grad_norm": 23.022293090820312,
463
+ "learning_rate": 3.881999999999999e-05,
464
+ "loss": 9.1513,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.002281999861696978,
469
+ "grad_norm": 13.62468147277832,
470
+ "learning_rate": 3.941999999999999e-05,
471
+ "loss": 9.1056,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.0023165756171772355,
476
+ "grad_norm": 10.622007369995117,
477
+ "learning_rate": 4.001999999999999e-05,
478
+ "loss": 9.1389,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.0023511513726574926,
483
+ "grad_norm": 12.142419815063477,
484
+ "learning_rate": 4.0619999999999994e-05,
485
+ "loss": 9.1279,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.00238572712813775,
490
+ "grad_norm": 11.485246658325195,
491
+ "learning_rate": 4.1219999999999995e-05,
492
+ "loss": 9.1175,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.002420302883618007,
497
+ "grad_norm": 10.780238151550293,
498
+ "learning_rate": 4.1819999999999996e-05,
499
+ "loss": 9.1417,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.0024548786390982645,
504
+ "grad_norm": 11.59386157989502,
505
+ "learning_rate": 4.242e-05,
506
+ "loss": 9.1246,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.0024894543945785217,
511
+ "grad_norm": 24.624088287353516,
512
+ "learning_rate": 4.302e-05,
513
+ "loss": 9.121,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.002524030150058779,
518
+ "grad_norm": 11.020679473876953,
519
+ "learning_rate": 4.362e-05,
520
+ "loss": 9.1379,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.002558605905539036,
525
+ "grad_norm": 14.969200134277344,
526
+ "learning_rate": 4.422e-05,
527
+ "loss": 9.1268,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.002593181661019293,
532
+ "grad_norm": 14.996768951416016,
533
+ "learning_rate": 4.4819999999999994e-05,
534
+ "loss": 9.1071,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.0026277574164995507,
539
+ "grad_norm": 16.976953506469727,
540
+ "learning_rate": 4.5419999999999995e-05,
541
+ "loss": 9.1073,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.002662333171979808,
546
+ "grad_norm": 17.404489517211914,
547
+ "learning_rate": 4.6019999999999996e-05,
548
+ "loss": 9.0887,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.002696908927460065,
553
+ "grad_norm": 11.283190727233887,
554
+ "learning_rate": 4.662e-05,
555
+ "loss": 9.1061,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.002731484682940322,
560
+ "grad_norm": 30.573930740356445,
561
+ "learning_rate": 4.722e-05,
562
+ "loss": 9.0974,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.0027660604384205797,
567
+ "grad_norm": 13.684494972229004,
568
+ "learning_rate": 4.781999999999999e-05,
569
+ "loss": 9.1181,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.002800636193900837,
574
+ "grad_norm": 8.140137672424316,
575
+ "learning_rate": 4.8419999999999994e-05,
576
+ "loss": 9.1429,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.002835211949381094,
581
+ "grad_norm": 11.793691635131836,
582
+ "learning_rate": 4.9019999999999995e-05,
583
+ "loss": 9.1238,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.002869787704861351,
588
+ "grad_norm": 10.155129432678223,
589
+ "learning_rate": 4.956e-05,
590
+ "loss": 9.1099,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.0029043634603416087,
595
+ "grad_norm": 18.905136108398438,
596
+ "learning_rate": 5.0159999999999994e-05,
597
+ "loss": 9.118,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.002938939215821866,
602
+ "grad_norm": 14.191570281982422,
603
+ "learning_rate": 5.0759999999999995e-05,
604
+ "loss": 9.0971,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.002973514971302123,
609
+ "grad_norm": 13.144892692565918,
610
+ "learning_rate": 5.1359999999999996e-05,
611
+ "loss": 9.1168,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.00300809072678238,
616
+ "grad_norm": 17.27440643310547,
617
+ "learning_rate": 5.195999999999999e-05,
618
+ "loss": 9.1007,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.0030426664822626372,
623
+ "grad_norm": 14.852960586547852,
624
+ "learning_rate": 5.255999999999999e-05,
625
+ "loss": 9.1023,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.003077242237742895,
630
+ "grad_norm": 12.116819381713867,
631
+ "learning_rate": 5.315999999999999e-05,
632
+ "loss": 9.1209,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.003111817993223152,
637
+ "grad_norm": 13.627985000610352,
638
+ "learning_rate": 5.3759999999999994e-05,
639
+ "loss": 9.1106,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.003146393748703409,
644
+ "grad_norm": 16.725046157836914,
645
+ "learning_rate": 5.4359999999999995e-05,
646
+ "loss": 9.1138,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.0031809695041836662,
651
+ "grad_norm": 19.617530822753906,
652
+ "learning_rate": 5.4959999999999996e-05,
653
+ "loss": 9.1102,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.003215545259663924,
658
+ "grad_norm": 14.019784927368164,
659
+ "learning_rate": 5.5559999999999997e-05,
660
+ "loss": 9.1069,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.003250121015144181,
665
+ "grad_norm": 15.217008590698242,
666
+ "learning_rate": 5.616e-05,
667
+ "loss": 9.0959,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.003284696770624438,
672
+ "grad_norm": 23.325428009033203,
673
+ "learning_rate": 5.6699999999999996e-05,
674
+ "loss": 9.0977,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.0033192725261046952,
679
+ "grad_norm": 11.030868530273438,
680
+ "learning_rate": 5.73e-05,
681
+ "loss": 9.1116,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.003353848281584953,
686
+ "grad_norm": 13.278918266296387,
687
+ "learning_rate": 5.79e-05,
688
+ "loss": 9.0861,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.00338842403706521,
693
+ "grad_norm": 13.311212539672852,
694
+ "learning_rate": 5.85e-05,
695
+ "loss": 9.088,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.003422999792545467,
700
+ "grad_norm": 10.462119102478027,
701
+ "learning_rate": 5.91e-05,
702
+ "loss": 9.0808,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.0034575755480257243,
707
+ "grad_norm": 68.89077758789062,
708
+ "learning_rate": 5.97e-05,
709
+ "loss": 9.0981,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.0034921513035059814,
714
+ "grad_norm": 12.376023292541504,
715
+ "learning_rate": 6.0299999999999995e-05,
716
+ "loss": 9.1087,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.003526727058986239,
721
+ "grad_norm": 11.641372680664062,
722
+ "learning_rate": 6.0899999999999996e-05,
723
+ "loss": 9.1097,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.003561302814466496,
728
+ "grad_norm": 17.008573532104492,
729
+ "learning_rate": 6.149999999999999e-05,
730
+ "loss": 9.118,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.0035958785699467533,
735
+ "grad_norm": 13.044571876525879,
736
+ "learning_rate": 6.209999999999999e-05,
737
+ "loss": 9.1045,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.0036304543254270104,
742
+ "grad_norm": 8.668659210205078,
743
+ "learning_rate": 6.269999999999999e-05,
744
+ "loss": 9.1138,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.003665030080907268,
749
+ "grad_norm": 13.858012199401855,
750
+ "learning_rate": 6.33e-05,
751
+ "loss": 9.1086,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.003699605836387525,
756
+ "grad_norm": 9.014534950256348,
757
+ "learning_rate": 6.39e-05,
758
+ "loss": 9.125,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.0037341815918677823,
763
+ "grad_norm": 9.205188751220703,
764
+ "learning_rate": 6.45e-05,
765
+ "loss": 9.1078,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.0037687573473480394,
770
+ "grad_norm": 16.21772003173828,
771
+ "learning_rate": 6.51e-05,
772
+ "loss": 9.0993,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.003803333102828297,
777
+ "grad_norm": 10.28536319732666,
778
+ "learning_rate": 6.57e-05,
779
+ "loss": 9.0929,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.003837908858308554,
784
+ "grad_norm": 11.15615177154541,
785
+ "learning_rate": 6.63e-05,
786
+ "loss": 9.0807,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.0038724846137888113,
791
+ "grad_norm": 8.5701322555542,
792
+ "learning_rate": 6.69e-05,
793
+ "loss": 9.0883,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.003907060369269069,
798
+ "grad_norm": 10.674054145812988,
799
+ "learning_rate": 6.75e-05,
800
+ "loss": 9.0875,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.0039416361247493256,
805
+ "grad_norm": 9.421123504638672,
806
+ "learning_rate": 6.81e-05,
807
+ "loss": 9.0875,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.003976211880229583,
812
+ "grad_norm": 8.26066780090332,
813
+ "learning_rate": 6.87e-05,
814
+ "loss": 9.0797,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.00401078763570984,
819
+ "grad_norm": 10.132837295532227,
820
+ "learning_rate": 6.93e-05,
821
+ "loss": 9.0935,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.004045363391190097,
826
+ "grad_norm": 10.218791007995605,
827
+ "learning_rate": 6.989999999999999e-05,
828
+ "loss": 9.0963,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.004079939146670355,
833
+ "grad_norm": 13.95479679107666,
834
+ "learning_rate": 7.049999999999999e-05,
835
+ "loss": 9.0497,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.004114514902150612,
840
+ "grad_norm": 8.425973892211914,
841
+ "learning_rate": 7.11e-05,
842
+ "loss": 9.0762,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.004149090657630869,
847
+ "grad_norm": 5.935906887054443,
848
+ "learning_rate": 7.17e-05,
849
+ "loss": 9.1127,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.004183666413111127,
854
+ "grad_norm": 7.9404168128967285,
855
+ "learning_rate": 7.23e-05,
856
+ "loss": 9.0896,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.0042182421685913836,
861
+ "grad_norm": 9.45516586303711,
862
+ "learning_rate": 7.29e-05,
863
+ "loss": 9.0694,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.004252817924071641,
868
+ "grad_norm": 10.396097183227539,
869
+ "learning_rate": 7.35e-05,
870
+ "loss": 9.0839,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.004287393679551898,
875
+ "grad_norm": 12.011253356933594,
876
+ "learning_rate": 7.41e-05,
877
+ "loss": 9.0603,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.004321969435032155,
882
+ "grad_norm": 8.560672760009766,
883
+ "learning_rate": 7.47e-05,
884
+ "loss": 9.086,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.004356545190512413,
889
+ "grad_norm": 8.79507827758789,
890
+ "learning_rate": 7.529999999999999e-05,
891
+ "loss": 9.0915,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.00439112094599267,
896
+ "grad_norm": 9.286111831665039,
897
+ "learning_rate": 7.589999999999999e-05,
898
+ "loss": 9.0783,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.004425696701472927,
903
+ "grad_norm": 9.932263374328613,
904
+ "learning_rate": 7.649999999999999e-05,
905
+ "loss": 9.0808,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.004460272456953184,
910
+ "grad_norm": 13.201107025146484,
911
+ "learning_rate": 7.709999999999999e-05,
912
+ "loss": 9.0991,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.004494848212433442,
917
+ "grad_norm": 8.324228286743164,
918
+ "learning_rate": 7.769999999999999e-05,
919
+ "loss": 9.0859,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.004529423967913699,
924
+ "grad_norm": 11.608538627624512,
925
+ "learning_rate": 7.829999999999999e-05,
926
+ "loss": 9.0831,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.004563999723393956,
931
+ "grad_norm": 9.669852256774902,
932
+ "learning_rate": 7.89e-05,
933
+ "loss": 9.0847,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.004598575478874213,
938
+ "grad_norm": 4.503360271453857,
939
+ "learning_rate": 7.95e-05,
940
+ "loss": 9.0789,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.004633151234354471,
945
+ "grad_norm": 8.09322452545166,
946
+ "learning_rate": 8.01e-05,
947
+ "loss": 9.096,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.004667726989834728,
952
+ "grad_norm": 7.773679256439209,
953
+ "learning_rate": 8.07e-05,
954
+ "loss": 9.0822,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.004702302745314985,
959
+ "grad_norm": 12.035070419311523,
960
+ "learning_rate": 8.13e-05,
961
+ "loss": 9.0535,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.004736878500795242,
966
+ "grad_norm": 6.7790422439575195,
967
+ "learning_rate": 8.19e-05,
968
+ "loss": 9.0923,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.0047714542562755,
973
+ "grad_norm": 49.749053955078125,
974
+ "learning_rate": 8.25e-05,
975
+ "loss": 9.0877,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.004806030011755757,
980
+ "grad_norm": 8.277181625366211,
981
+ "learning_rate": 8.31e-05,
982
+ "loss": 9.0854,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.004840605767236014,
987
+ "grad_norm": 17.89580726623535,
988
+ "learning_rate": 8.37e-05,
989
+ "loss": 9.0793,
990
+ "step": 1400
991
+ }
992
+ ],
993
+ "logging_steps": 10,
994
+ "max_steps": 1000000,
995
+ "num_input_tokens_seen": 0,
996
+ "num_train_epochs": 4,
997
+ "save_steps": 100,
998
+ "stateful_callbacks": {
999
+ "TrainerControl": {
1000
+ "args": {
1001
+ "should_epoch_stop": false,
1002
+ "should_evaluate": false,
1003
+ "should_log": false,
1004
+ "should_save": true,
1005
+ "should_training_stop": false
1006
+ },
1007
+ "attributes": {}
1008
+ }
1009
+ },
1010
+ "total_flos": 4473101869056000.0,
1011
+ "train_batch_size": 4,
1012
+ "trial_name": null,
1013
+ "trial_params": null
1014
+ }
checkpoint-1400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a746fe2aa9d502223795e2f6a42a0bba1c746d65b90cdeab7a9a789b02ea1695
3
+ size 5201