aixk commited on
Commit
a51f737
·
verified ·
1 Parent(s): ca838b7

Upload folder using huggingface_hub

Browse files
checkpoint-1100/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-1100/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-1100/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b830d7106a8866355b42bc00a80ad70441b32e4bb03e6aa9f54acbcb7a4850fe
3
+ size 501911880
checkpoint-1100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1995f5090d9a7ecb39ba7330f00d3407ca223bf66ff7043f194c843f92d878a9
3
+ size 254431981
checkpoint-1100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056ac4b0b347dd84d8d238b6e432c72198777efe73c404b8f5e79d83eff06cd7
3
+ size 14645
checkpoint-1100/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60d825ed95e3c68e74d5c466675eb5edcdcbc5813ae44502be945356df89fdf
3
+ size 1383
checkpoint-1100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d3cab6b2c585bd56873c851959a80479ed570a399ab35379c01a4b05c887576
3
+ size 1465
checkpoint-1100/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-1100/trainer_state.json ADDED
@@ -0,0 +1,804 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.047603305785123964,
6
+ "eval_steps": 500,
7
+ "global_step": 1100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0005289256198347108,
14
+ "grad_norm": 641.732177734375,
15
+ "learning_rate": 4.0000000000000003e-07,
16
+ "loss": 8.8563,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0010578512396694215,
21
+ "grad_norm": 167.62478637695312,
22
+ "learning_rate": 1.2000000000000002e-06,
23
+ "loss": 8.669,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0015867768595041322,
28
+ "grad_norm": 132.942138671875,
29
+ "learning_rate": 2.0000000000000003e-06,
30
+ "loss": 8.4099,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.002115702479338843,
35
+ "grad_norm": 87.03181457519531,
36
+ "learning_rate": 2.8000000000000003e-06,
37
+ "loss": 8.3399,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.002644628099173554,
42
+ "grad_norm": 83.94163513183594,
43
+ "learning_rate": 3.6e-06,
44
+ "loss": 8.4131,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0031735537190082643,
49
+ "grad_norm": 224.91473388671875,
50
+ "learning_rate": 4.4e-06,
51
+ "loss": 8.1753,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0037024793388429752,
56
+ "grad_norm": 316.9183044433594,
57
+ "learning_rate": 5.2e-06,
58
+ "loss": 8.411,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.004231404958677686,
63
+ "grad_norm": 344.9347839355469,
64
+ "learning_rate": 6e-06,
65
+ "loss": 8.2236,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.004760330578512397,
70
+ "grad_norm": 131.94554138183594,
71
+ "learning_rate": 6.800000000000001e-06,
72
+ "loss": 8.2993,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.005289256198347108,
77
+ "grad_norm": 187.1765594482422,
78
+ "learning_rate": 7.6e-06,
79
+ "loss": 8.0748,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.005818181818181818,
84
+ "grad_norm": 185.48715209960938,
85
+ "learning_rate": 8.400000000000001e-06,
86
+ "loss": 8.0531,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.006347107438016529,
91
+ "grad_norm": 292.0998840332031,
92
+ "learning_rate": 9.2e-06,
93
+ "loss": 8.1898,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.00687603305785124,
98
+ "grad_norm": 236.91464233398438,
99
+ "learning_rate": 1e-05,
100
+ "loss": 8.0968,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.0074049586776859504,
105
+ "grad_norm": 276.836669921875,
106
+ "learning_rate": 1.08e-05,
107
+ "loss": 8.0387,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.007933884297520661,
112
+ "grad_norm": 226.5710906982422,
113
+ "learning_rate": 1.16e-05,
114
+ "loss": 7.9954,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.008462809917355372,
119
+ "grad_norm": 341.735595703125,
120
+ "learning_rate": 1.232e-05,
121
+ "loss": 7.9396,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.008991735537190083,
126
+ "grad_norm": 215.15040588378906,
127
+ "learning_rate": 1.3120000000000001e-05,
128
+ "loss": 8.0838,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.009520661157024794,
133
+ "grad_norm": 314.2020263671875,
134
+ "learning_rate": 1.3919999999999999e-05,
135
+ "loss": 7.9612,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.010049586776859505,
140
+ "grad_norm": 1104.496826171875,
141
+ "learning_rate": 1.472e-05,
142
+ "loss": 7.8864,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.010578512396694216,
147
+ "grad_norm": 114.84138488769531,
148
+ "learning_rate": 1.552e-05,
149
+ "loss": 7.7783,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.0005289256198347108,
154
+ "grad_norm": 298.0364685058594,
155
+ "learning_rate": 1.6320000000000003e-05,
156
+ "loss": 7.7893,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.0010578512396694215,
161
+ "grad_norm": 215.82244873046875,
162
+ "learning_rate": 1.712e-05,
163
+ "loss": 7.779,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.0015867768595041322,
168
+ "grad_norm": 247.94859313964844,
169
+ "learning_rate": 1.792e-05,
170
+ "loss": 7.6925,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.002115702479338843,
175
+ "grad_norm": 97.73837280273438,
176
+ "learning_rate": 1.872e-05,
177
+ "loss": 7.6725,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.002644628099173554,
182
+ "grad_norm": 141.45123291015625,
183
+ "learning_rate": 1.9520000000000003e-05,
184
+ "loss": 7.7421,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.0031735537190082643,
189
+ "grad_norm": 200.86509704589844,
190
+ "learning_rate": 2.032e-05,
191
+ "loss": 7.5497,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.0037024793388429752,
196
+ "grad_norm": 185.7206268310547,
197
+ "learning_rate": 2.112e-05,
198
+ "loss": 7.7364,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.004231404958677686,
203
+ "grad_norm": 101.28189086914062,
204
+ "learning_rate": 2.192e-05,
205
+ "loss": 7.5938,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.004760330578512397,
210
+ "grad_norm": 330.9864807128906,
211
+ "learning_rate": 2.2720000000000003e-05,
212
+ "loss": 7.6908,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.005289256198347108,
217
+ "grad_norm": 148.31687927246094,
218
+ "learning_rate": 2.3520000000000002e-05,
219
+ "loss": 7.5153,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.005818181818181818,
224
+ "grad_norm": 123.8593521118164,
225
+ "learning_rate": 2.432e-05,
226
+ "loss": 7.5011,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.006347107438016529,
231
+ "grad_norm": 114.53250122070312,
232
+ "learning_rate": 2.512e-05,
233
+ "loss": 7.6091,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.00687603305785124,
238
+ "grad_norm": 112.7503662109375,
239
+ "learning_rate": 2.592e-05,
240
+ "loss": 7.5382,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.0074049586776859504,
245
+ "grad_norm": 97.62100219726562,
246
+ "learning_rate": 2.672e-05,
247
+ "loss": 7.5186,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.007933884297520661,
252
+ "grad_norm": 171.15858459472656,
253
+ "learning_rate": 2.752e-05,
254
+ "loss": 7.4748,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.008462809917355372,
259
+ "grad_norm": 149.8796844482422,
260
+ "learning_rate": 2.8320000000000003e-05,
261
+ "loss": 7.4303,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.008991735537190083,
266
+ "grad_norm": 92.16109466552734,
267
+ "learning_rate": 2.9120000000000002e-05,
268
+ "loss": 7.5469,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.009520661157024794,
273
+ "grad_norm": 94.65399932861328,
274
+ "learning_rate": 2.9920000000000005e-05,
275
+ "loss": 7.477,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.010049586776859505,
280
+ "grad_norm": 100.26766967773438,
281
+ "learning_rate": 3.072e-05,
282
+ "loss": 7.4068,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.010578512396694216,
287
+ "grad_norm": 121.88914489746094,
288
+ "learning_rate": 3.1519999999999996e-05,
289
+ "loss": 7.3082,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.011107438016528925,
294
+ "grad_norm": 129.8812255859375,
295
+ "learning_rate": 3.232e-05,
296
+ "loss": 7.2946,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.011636363636363636,
301
+ "grad_norm": 161.5423126220703,
302
+ "learning_rate": 3.312e-05,
303
+ "loss": 7.2299,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.012165289256198347,
308
+ "grad_norm": 143.5394744873047,
309
+ "learning_rate": 3.392e-05,
310
+ "loss": 7.242,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.012694214876033057,
315
+ "grad_norm": 68.21272277832031,
316
+ "learning_rate": 3.472e-05,
317
+ "loss": 7.191,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.013223140495867768,
322
+ "grad_norm": 103.70673370361328,
323
+ "learning_rate": 3.5520000000000006e-05,
324
+ "loss": 7.2327,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.01375206611570248,
329
+ "grad_norm": 185.54530334472656,
330
+ "learning_rate": 3.6320000000000005e-05,
331
+ "loss": 7.2653,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.01428099173553719,
336
+ "grad_norm": 119.81388092041016,
337
+ "learning_rate": 3.712e-05,
338
+ "loss": 7.1239,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.014809917355371901,
343
+ "grad_norm": 151.85702514648438,
344
+ "learning_rate": 3.792e-05,
345
+ "loss": 7.156,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.015338842975206612,
350
+ "grad_norm": 142.77293395996094,
351
+ "learning_rate": 3.872e-05,
352
+ "loss": 7.1226,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.015867768595041323,
357
+ "grad_norm": 91.57913970947266,
358
+ "learning_rate": 3.952e-05,
359
+ "loss": 7.1236,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.016396694214876033,
364
+ "grad_norm": 105.25820922851562,
365
+ "learning_rate": 4.032e-05,
366
+ "loss": 7.0561,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.016925619834710744,
371
+ "grad_norm": 96.5208740234375,
372
+ "learning_rate": 4.1120000000000006e-05,
373
+ "loss": 7.1003,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.017454545454545455,
378
+ "grad_norm": 101.59559631347656,
379
+ "learning_rate": 4.1920000000000005e-05,
380
+ "loss": 7.0201,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.017983471074380166,
385
+ "grad_norm": 82.07259368896484,
386
+ "learning_rate": 4.2720000000000004e-05,
387
+ "loss": 6.9144,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.018512396694214877,
392
+ "grad_norm": 132.1178436279297,
393
+ "learning_rate": 4.352e-05,
394
+ "loss": 7.0484,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.019041322314049588,
399
+ "grad_norm": 179.69866943359375,
400
+ "learning_rate": 4.432e-05,
401
+ "loss": 6.8724,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.0195702479338843,
406
+ "grad_norm": 108.14857482910156,
407
+ "learning_rate": 4.512e-05,
408
+ "loss": 7.0,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.02009917355371901,
413
+ "grad_norm": 93.1995849609375,
414
+ "learning_rate": 4.592e-05,
415
+ "loss": 7.0588,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.02062809917355372,
420
+ "grad_norm": 78.22120666503906,
421
+ "learning_rate": 4.672e-05,
422
+ "loss": 6.9692,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.02115702479338843,
427
+ "grad_norm": 81.8231201171875,
428
+ "learning_rate": 4.7520000000000006e-05,
429
+ "loss": 6.8607,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.021685950413223142,
434
+ "grad_norm": 81.69812774658203,
435
+ "learning_rate": 4.8320000000000005e-05,
436
+ "loss": 6.8804,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.02221487603305785,
441
+ "grad_norm": 67.32670593261719,
442
+ "learning_rate": 4.9120000000000004e-05,
443
+ "loss": 6.8825,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.02274380165289256,
448
+ "grad_norm": 79.66416931152344,
449
+ "learning_rate": 4.992e-05,
450
+ "loss": 6.8302,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.02327272727272727,
455
+ "grad_norm": 91.50218200683594,
456
+ "learning_rate": 5.072e-05,
457
+ "loss": 6.8396,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.023801652892561982,
462
+ "grad_norm": 68.5249252319336,
463
+ "learning_rate": 5.152e-05,
464
+ "loss": 6.8103,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.024330578512396693,
469
+ "grad_norm": 50.630306243896484,
470
+ "learning_rate": 5.232e-05,
471
+ "loss": 6.8521,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.024859504132231404,
476
+ "grad_norm": 59.39335632324219,
477
+ "learning_rate": 5.3120000000000006e-05,
478
+ "loss": 6.8262,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.025388429752066115,
483
+ "grad_norm": 52.00175094604492,
484
+ "learning_rate": 5.3920000000000006e-05,
485
+ "loss": 6.7173,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.025917355371900826,
490
+ "grad_norm": 59.93027877807617,
491
+ "learning_rate": 5.4720000000000005e-05,
492
+ "loss": 6.6567,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.026446280991735537,
497
+ "grad_norm": 71.15003204345703,
498
+ "learning_rate": 5.5520000000000004e-05,
499
+ "loss": 6.7098,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.026975206611570247,
504
+ "grad_norm": 81.00093841552734,
505
+ "learning_rate": 5.632e-05,
506
+ "loss": 6.7311,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.02750413223140496,
511
+ "grad_norm": 88.47158813476562,
512
+ "learning_rate": 5.712000000000001e-05,
513
+ "loss": 6.6873,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.02803305785123967,
518
+ "grad_norm": 74.94734191894531,
519
+ "learning_rate": 5.792000000000001e-05,
520
+ "loss": 6.6633,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.02856198347107438,
525
+ "grad_norm": 70.46430969238281,
526
+ "learning_rate": 5.872000000000001e-05,
527
+ "loss": 6.6849,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.02909090909090909,
532
+ "grad_norm": 56.99905014038086,
533
+ "learning_rate": 5.952e-05,
534
+ "loss": 6.6271,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.029619834710743802,
539
+ "grad_norm": 63.47657012939453,
540
+ "learning_rate": 6.032e-05,
541
+ "loss": 6.6473,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.030148760330578513,
546
+ "grad_norm": 60.045875549316406,
547
+ "learning_rate": 6.112e-05,
548
+ "loss": 6.5595,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.030677685950413223,
553
+ "grad_norm": 50.319881439208984,
554
+ "learning_rate": 6.192e-05,
555
+ "loss": 6.5524,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.031206611570247934,
560
+ "grad_norm": 47.301361083984375,
561
+ "learning_rate": 6.272e-05,
562
+ "loss": 6.5123,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.031735537190082645,
567
+ "grad_norm": 52.02754211425781,
568
+ "learning_rate": 6.352e-05,
569
+ "loss": 6.4223,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.032264462809917356,
574
+ "grad_norm": 53.97670364379883,
575
+ "learning_rate": 6.432000000000001e-05,
576
+ "loss": 6.5096,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.03279338842975207,
581
+ "grad_norm": 53.95705795288086,
582
+ "learning_rate": 6.512e-05,
583
+ "loss": 6.5743,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.03332231404958678,
588
+ "grad_norm": 51.748600006103516,
589
+ "learning_rate": 6.592e-05,
590
+ "loss": 6.4673,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.03385123966942149,
595
+ "grad_norm": 55.20490646362305,
596
+ "learning_rate": 6.672e-05,
597
+ "loss": 6.592,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.0343801652892562,
602
+ "grad_norm": 74.26447296142578,
603
+ "learning_rate": 6.752e-05,
604
+ "loss": 6.4835,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.03490909090909091,
609
+ "grad_norm": 50.41746520996094,
610
+ "learning_rate": 6.832000000000001e-05,
611
+ "loss": 6.4218,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.03543801652892562,
616
+ "grad_norm": 53.79718017578125,
617
+ "learning_rate": 6.912e-05,
618
+ "loss": 6.3984,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.03596694214876033,
623
+ "grad_norm": 46.21867752075195,
624
+ "learning_rate": 6.992000000000001e-05,
625
+ "loss": 6.396,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.03649586776859504,
630
+ "grad_norm": 54.936363220214844,
631
+ "learning_rate": 7.072000000000001e-05,
632
+ "loss": 6.4731,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.037024793388429754,
637
+ "grad_norm": 52.44757080078125,
638
+ "learning_rate": 7.151999999999999e-05,
639
+ "loss": 6.4272,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.037553719008264465,
644
+ "grad_norm": 53.79771041870117,
645
+ "learning_rate": 7.232e-05,
646
+ "loss": 6.3456,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.038082644628099176,
651
+ "grad_norm": 42.58932876586914,
652
+ "learning_rate": 7.312e-05,
653
+ "loss": 6.3595,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.03861157024793389,
658
+ "grad_norm": 50.45634460449219,
659
+ "learning_rate": 7.392e-05,
660
+ "loss": 6.3012,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.0391404958677686,
665
+ "grad_norm": 45.51393508911133,
666
+ "learning_rate": 7.472e-05,
667
+ "loss": 6.2604,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.03966942148760331,
672
+ "grad_norm": 41.524681091308594,
673
+ "learning_rate": 7.552e-05,
674
+ "loss": 6.2671,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.04019834710743802,
679
+ "grad_norm": 46.48579406738281,
680
+ "learning_rate": 7.632e-05,
681
+ "loss": 6.3011,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.04072727272727273,
686
+ "grad_norm": 50.58343505859375,
687
+ "learning_rate": 7.712000000000001e-05,
688
+ "loss": 6.2522,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.04125619834710744,
693
+ "grad_norm": 45.821868896484375,
694
+ "learning_rate": 7.792e-05,
695
+ "loss": 6.2279,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.04178512396694215,
700
+ "grad_norm": 48.15666198730469,
701
+ "learning_rate": 7.872e-05,
702
+ "loss": 6.1382,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.04231404958677686,
707
+ "grad_norm": 42.253700256347656,
708
+ "learning_rate": 7.952000000000001e-05,
709
+ "loss": 6.296,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.042842975206611573,
714
+ "grad_norm": 49.4371452331543,
715
+ "learning_rate": 8.032e-05,
716
+ "loss": 6.1777,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.043371900826446284,
721
+ "grad_norm": 44.89508819580078,
722
+ "learning_rate": 8.112000000000001e-05,
723
+ "loss": 6.1574,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.04390082644628099,
728
+ "grad_norm": 88.30504608154297,
729
+ "learning_rate": 8.192e-05,
730
+ "loss": 6.1655,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.0444297520661157,
735
+ "grad_norm": 70.42292785644531,
736
+ "learning_rate": 8.272000000000001e-05,
737
+ "loss": 6.1936,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.04495867768595041,
742
+ "grad_norm": 47.895164489746094,
743
+ "learning_rate": 8.352000000000001e-05,
744
+ "loss": 6.0796,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.04548760330578512,
749
+ "grad_norm": 39.77252197265625,
750
+ "learning_rate": 8.431999999999999e-05,
751
+ "loss": 6.1191,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.04601652892561983,
756
+ "grad_norm": 37.6796760559082,
757
+ "learning_rate": 8.512e-05,
758
+ "loss": 6.0384,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.04654545454545454,
763
+ "grad_norm": 83.34986877441406,
764
+ "learning_rate": 8.592e-05,
765
+ "loss": 6.0479,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.047074380165289254,
770
+ "grad_norm": 39.067813873291016,
771
+ "learning_rate": 8.672e-05,
772
+ "loss": 5.9874,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.047603305785123964,
777
+ "grad_norm": 49.67880630493164,
778
+ "learning_rate": 8.752e-05,
779
+ "loss": 6.0286,
780
+ "step": 1100
781
+ }
782
+ ],
783
+ "logging_steps": 10,
784
+ "max_steps": 10000000,
785
+ "num_input_tokens_seen": 0,
786
+ "num_train_epochs": 529,
787
+ "save_steps": 100,
788
+ "stateful_callbacks": {
789
+ "TrainerControl": {
790
+ "args": {
791
+ "should_epoch_stop": false,
792
+ "should_evaluate": false,
793
+ "should_log": false,
794
+ "should_save": true,
795
+ "should_training_stop": false
796
+ },
797
+ "attributes": {}
798
+ }
799
+ },
800
+ "total_flos": 1.8747539755008e+16,
801
+ "train_batch_size": 8,
802
+ "trial_name": null,
803
+ "trial_params": null
804
+ }
checkpoint-1100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05cb5d668e12b91a46e597433b8a814a5107ab9e663d3ff34f9f7bdba2b54572
3
+ size 5201