Hugging Face's logo

aixk
/
fastplus-125m-a

Safetensors
Model card Files
xet
 Community
aixk commited on
Commit
3ec4ae7
·
1 Parent(s): ee16254

FastPlus125m Backup checkpoint-600 at global step 600

Browse files
Files changed (10) hide show
  1. checkpoint-600/config.json +19 -0
  2. checkpoint-600/generation_config.json +6 -0
  3. checkpoint-600/model.safetensors +3 -0
  4. checkpoint-600/optimizer.pt +3 -0
  5. checkpoint-600/scaler.pt +3 -0
  6. checkpoint-600/scheduler.pt +3 -0
  7. checkpoint-600/tokenizer.json +0 -0
  8. checkpoint-600/tokenizer_config.json +15 -0
  9. checkpoint-600/trainer_state.json +514 -0
  10. checkpoint-600/training_args.bin +3 -0
checkpoint-600/config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FastPlus125mForCausalLM"
4
+ ],
5
+ "dtype": "float32",
6
+ "hidden_size": 768,
7
+ "initializer_range": 0.02,
8
+ "intermediate_size": 2048,
9
+ "kd_alpha": 0.4,
10
+ "kd_temperature": 2.5,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "fastplus_125m",
13
+ "num_attention_heads": 12,
14
+ "num_hidden_layers": 16,
15
+ "tie_word_embeddings": true,
16
+ "transformers_version": "5.12.0",
17
+ "use_cache": false,
18
+ "vocab_size": 32704
19
+ }
checkpoint-600/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": "5.12.0"
6
+ }
checkpoint-600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354c0218f35af759c722e6a16260ca02929c0e3c0a7494158feeaf25154da81f
3
+ size 513378952
checkpoint-600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c07972712827cc8550c9a50221419b9addd3d4409348403037ba319f3716c7
3
+ size 157595069
checkpoint-600/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ed020ad88d2062da03160e606d9215c63c4b583588eb822affaefde77a370a
3
+ size 1383
checkpoint-600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73bd2a466ed9a75daf702df013cd6d3a376f72598dcbc2bd162759bfbbf0cbad
3
+ size 7481
checkpoint-600/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-600/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "extra_special_tokens": [
6
+ "<|user|>",
7
+ "<|assistant|>"
8
+ ],
9
+ "is_local": false,
10
+ "local_files_only": false,
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "<pad>",
13
+ "tokenizer_class": "TokenizersBackend",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-600/trainer_state.json ADDED
@@ -0,0 +1,514 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.009524754439924595,
6
+ "eval_steps": 500,
7
+ "global_step": 600,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00028221482192244734,
14
+ "grad_norm": 11040.888671875,
15
+ "learning_rate": 1.0200000000000002e-06,
16
+ "loss": 168.082373046875,
17
+ "original_ce_loss": 10.4894,
18
+ "step": 10
19
+ },
20
+ {
21
+ "epoch": 0.0005644296438448947,
22
+ "grad_norm": 11032.3466796875,
23
+ "learning_rate": 4.42e-06,
24
+ "loss": 167.87103271484375,
25
+ "original_ce_loss": 10.4761,
26
+ "step": 20
27
+ },
28
+ {
29
+ "epoch": 0.0008466444657673421,
30
+ "grad_norm": 10810.0654296875,
31
+ "learning_rate": 7.82e-06,
32
+ "loss": 167.1998291015625,
33
+ "original_ce_loss": 10.4342,
34
+ "step": 30
35
+ },
36
+ {
37
+ "epoch": 0.0011288592876897894,
38
+ "grad_norm": 12794.1640625,
39
+ "learning_rate": 1.1220000000000001e-05,
40
+ "loss": 165.951806640625,
41
+ "original_ce_loss": 10.3562,
42
+ "step": 40
43
+ },
44
+ {
45
+ "epoch": 0.0014110741096122368,
46
+ "grad_norm": 15282.576171875,
47
+ "learning_rate": 1.4280000000000002e-05,
48
+ "loss": 163.73648681640626,
49
+ "original_ce_loss": 10.2177,
50
+ "step": 50
51
+ },
52
+ {
53
+ "epoch": 0.0016932889315346843,
54
+ "grad_norm": 18930.85546875,
55
+ "learning_rate": 1.768e-05,
56
+ "loss": 159.14381103515626,
57
+ "original_ce_loss": 9.9307,
58
+ "step": 60
59
+ },
60
+ {
61
+ "epoch": 0.0019755037534571317,
62
+ "grad_norm": 19692.8984375,
63
+ "learning_rate": 2.074e-05,
64
+ "loss": 151.24730224609374,
65
+ "original_ce_loss": 9.4372,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.0022577185753795788,
70
+ "grad_norm": 14330.4931640625,
71
+ "learning_rate": 2.3800000000000003e-05,
72
+ "loss": 143.26488037109374,
73
+ "original_ce_loss": 8.9383,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 0.002539933397302026,
78
+ "grad_norm": 8985.2783203125,
79
+ "learning_rate": 2.7200000000000004e-05,
80
+ "loss": 138.16317138671874,
81
+ "original_ce_loss": 8.6194,
82
+ "step": 90
83
+ },
84
+ {
85
+ "epoch": 0.0028221482192244737,
86
+ "grad_norm": 4822.86083984375,
87
+ "learning_rate": 3.06e-05,
88
+ "loss": 135.19945068359374,
89
+ "original_ce_loss": 8.4342,
90
+ "step": 100
91
+ },
92
+ {
93
+ "epoch": 0.003104363041146921,
94
+ "grad_norm": 2672.674072265625,
95
+ "learning_rate": 3.4000000000000007e-05,
96
+ "loss": 133.7376220703125,
97
+ "original_ce_loss": 8.3428,
98
+ "step": 110
99
+ },
100
+ {
101
+ "epoch": 0.0033865778630693686,
102
+ "grad_norm": 1405.0697021484375,
103
+ "learning_rate": 3.74e-05,
104
+ "loss": 132.54332275390624,
105
+ "original_ce_loss": 8.2682,
106
+ "step": 120
107
+ },
108
+ {
109
+ "epoch": 0.0036687926849918156,
110
+ "grad_norm": 1129.05126953125,
111
+ "learning_rate": 4.08e-05,
112
+ "loss": 132.1033203125,
113
+ "original_ce_loss": 8.2407,
114
+ "step": 130
115
+ },
116
+ {
117
+ "epoch": 0.0039510075069142635,
118
+ "grad_norm": 633.3341674804688,
119
+ "learning_rate": 4.4200000000000004e-05,
120
+ "loss": 131.26424560546874,
121
+ "original_ce_loss": 8.1883,
122
+ "step": 140
123
+ },
124
+ {
125
+ "epoch": 0.0042332223288367105,
126
+ "grad_norm": 596.7435913085938,
127
+ "learning_rate": 4.7600000000000005e-05,
128
+ "loss": 131.00443115234376,
129
+ "original_ce_loss": 8.1721,
130
+ "step": 150
131
+ },
132
+ {
133
+ "epoch": 0.0045154371507591575,
134
+ "grad_norm": 865.6416015625,
135
+ "learning_rate": 5.1e-05,
136
+ "loss": 130.4638916015625,
137
+ "original_ce_loss": 8.1383,
138
+ "step": 160
139
+ },
140
+ {
141
+ "epoch": 0.004797651972681605,
142
+ "grad_norm": 531.1111450195312,
143
+ "learning_rate": 5.440000000000001e-05,
144
+ "loss": 129.41580810546876,
145
+ "original_ce_loss": 8.0728,
146
+ "step": 170
147
+ },
148
+ {
149
+ "epoch": 0.005079866794604052,
150
+ "grad_norm": 698.611083984375,
151
+ "learning_rate": 5.780000000000001e-05,
152
+ "loss": 128.7685302734375,
153
+ "original_ce_loss": 8.0324,
154
+ "step": 180
155
+ },
156
+ {
157
+ "epoch": 0.0053620816165265,
158
+ "grad_norm": 954.6569213867188,
159
+ "learning_rate": 6.12e-05,
160
+ "loss": 127.86734619140626,
161
+ "original_ce_loss": 7.9761,
162
+ "step": 190
163
+ },
164
+ {
165
+ "epoch": 0.005644296438448947,
166
+ "grad_norm": 898.2266845703125,
167
+ "learning_rate": 6.460000000000001e-05,
168
+ "loss": 126.53792724609374,
169
+ "original_ce_loss": 7.8931,
170
+ "step": 200
171
+ },
172
+ {
173
+ "epoch": 0.0033336640539736086,
174
+ "grad_norm": 21910.677734375,
175
+ "learning_rate": 6.800000000000001e-05,
176
+ "loss": 124.01259765625,
177
+ "original_ce_loss": 10.3186,
178
+ "step": 210
179
+ },
180
+ {
181
+ "epoch": 0.003492409961305685,
182
+ "grad_norm": 20906.169921875,
183
+ "learning_rate": 7.14e-05,
184
+ "loss": 113.152197265625,
185
+ "original_ce_loss": 9.4136,
186
+ "step": 220
187
+ },
188
+ {
189
+ "epoch": 0.0036511558686377617,
190
+ "grad_norm": 8927.6015625,
191
+ "learning_rate": 7.48e-05,
192
+ "loss": 103.94906005859374,
193
+ "original_ce_loss": 8.6467,
194
+ "step": 230
195
+ },
196
+ {
197
+ "epoch": 0.0038099017759698384,
198
+ "grad_norm": 4062.1162109375,
199
+ "learning_rate": 7.82e-05,
200
+ "loss": 100.55014038085938,
201
+ "original_ce_loss": 8.3634,
202
+ "step": 240
203
+ },
204
+ {
205
+ "epoch": 0.003968647683301915,
206
+ "grad_norm": 1275.5186767578125,
207
+ "learning_rate": 8.16e-05,
208
+ "loss": 98.93700561523437,
209
+ "original_ce_loss": 8.229,
210
+ "step": 250
211
+ },
212
+ {
213
+ "epoch": 0.004127393590633991,
214
+ "grad_norm": 1079.235595703125,
215
+ "learning_rate": 8.5e-05,
216
+ "loss": 97.69930419921874,
217
+ "original_ce_loss": 8.1259,
218
+ "step": 260
219
+ },
220
+ {
221
+ "epoch": 0.004286139497966068,
222
+ "grad_norm": 1457.86181640625,
223
+ "learning_rate": 8.840000000000001e-05,
224
+ "loss": 97.12216796875,
225
+ "original_ce_loss": 8.0778,
226
+ "step": 270
227
+ },
228
+ {
229
+ "epoch": 0.004444885405298145,
230
+ "grad_norm": 1775.441162109375,
231
+ "learning_rate": 9.180000000000001e-05,
232
+ "loss": 96.30513916015624,
233
+ "original_ce_loss": 8.0098,
234
+ "step": 280
235
+ },
236
+ {
237
+ "epoch": 0.004603631312630222,
238
+ "grad_norm": 1287.777099609375,
239
+ "learning_rate": 9.486000000000001e-05,
240
+ "loss": 95.04141845703126,
241
+ "original_ce_loss": 7.9045,
242
+ "step": 290
243
+ },
244
+ {
245
+ "epoch": 0.0047623772199622974,
246
+ "grad_norm": 945.9378051757812,
247
+ "learning_rate": 9.826e-05,
248
+ "loss": 94.0897216796875,
249
+ "original_ce_loss": 7.8252,
250
+ "step": 300
251
+ },
252
+ {
253
+ "epoch": 0.004921123127294374,
254
+ "grad_norm": 745.9630126953125,
255
+ "learning_rate": 0.00010166,
256
+ "loss": 93.84947509765625,
257
+ "original_ce_loss": 7.8053,
258
+ "step": 310
259
+ },
260
+ {
261
+ "epoch": 0.005079869034626451,
262
+ "grad_norm": 685.703125,
263
+ "learning_rate": 0.00010506,
264
+ "loss": 92.92034301757812,
265
+ "original_ce_loss": 7.7279,
266
+ "step": 320
267
+ },
268
+ {
269
+ "epoch": 0.005238614941958528,
270
+ "grad_norm": 658.5245361328125,
271
+ "learning_rate": 0.00010846000000000002,
272
+ "loss": 92.60219116210938,
273
+ "original_ce_loss": 7.7014,
274
+ "step": 330
275
+ },
276
+ {
277
+ "epoch": 0.005397360849290604,
278
+ "grad_norm": 880.1781616210938,
279
+ "learning_rate": 0.00011084000000000002,
280
+ "loss": 92.15060424804688,
281
+ "original_ce_loss": 7.6638,
282
+ "step": 340
283
+ },
284
+ {
285
+ "epoch": 0.005556106756622681,
286
+ "grad_norm": NaN,
287
+ "learning_rate": 0.00011322000000000002,
288
+ "loss": 91.7918701171875,
289
+ "original_ce_loss": 7.634,
290
+ "step": 350
291
+ },
292
+ {
293
+ "epoch": 0.005714852663954758,
294
+ "grad_norm": 929.7158203125,
295
+ "learning_rate": 0.00011458000000000002,
296
+ "loss": 91.731103515625,
297
+ "original_ce_loss": 7.6289,
298
+ "step": 360
299
+ },
300
+ {
301
+ "epoch": 0.005873598571286834,
302
+ "grad_norm": 462.8337707519531,
303
+ "learning_rate": 0.00011798,
304
+ "loss": 94.3677490234375,
305
+ "original_ce_loss": 7.8487,
306
+ "step": 370
307
+ },
308
+ {
309
+ "epoch": 0.00603234447861891,
310
+ "grad_norm": 486.2944030761719,
311
+ "learning_rate": 0.00012138,
312
+ "loss": 100.06838989257812,
313
+ "original_ce_loss": 8.3238,
314
+ "step": 380
315
+ },
316
+ {
317
+ "epoch": 0.006191090385950987,
318
+ "grad_norm": 598.30908203125,
319
+ "learning_rate": 0.00012478,
320
+ "loss": 101.41630859375,
321
+ "original_ce_loss": 8.4362,
322
+ "step": 390
323
+ },
324
+ {
325
+ "epoch": 0.006349836293283064,
326
+ "grad_norm": 184.96176147460938,
327
+ "learning_rate": 0.00012818,
328
+ "loss": 100.233056640625,
329
+ "original_ce_loss": 8.3376,
330
+ "step": 400
331
+ },
332
+ {
333
+ "epoch": 0.0065085822006151406,
334
+ "grad_norm": 160.8466796875,
335
+ "learning_rate": 0.00013158,
336
+ "loss": 99.97171630859376,
337
+ "original_ce_loss": 8.3159,
338
+ "step": 410
339
+ },
340
+ {
341
+ "epoch": 0.006667328107947217,
342
+ "grad_norm": 170.20265197753906,
343
+ "learning_rate": 0.00013498,
344
+ "loss": 98.846923828125,
345
+ "original_ce_loss": 8.2223,
346
+ "step": 420
347
+ },
348
+ {
349
+ "epoch": 0.006826074015279294,
350
+ "grad_norm": 153.3136444091797,
351
+ "learning_rate": 0.00013838,
352
+ "loss": 97.51691284179688,
353
+ "original_ce_loss": 8.1115,
354
+ "step": 430
355
+ },
356
+ {
357
+ "epoch": 0.00698481992261137,
358
+ "grad_norm": 149.3381805419922,
359
+ "learning_rate": 0.00014178000000000001,
360
+ "loss": 96.54814453125,
361
+ "original_ce_loss": 8.0308,
362
+ "step": 440
363
+ },
364
+ {
365
+ "epoch": 0.007143565829943447,
366
+ "grad_norm": 7302.71142578125,
367
+ "learning_rate": 0.00014518000000000002,
368
+ "loss": 95.69666748046875,
369
+ "original_ce_loss": 7.96,
370
+ "step": 450
371
+ },
372
+ {
373
+ "epoch": 0.007302311737275523,
374
+ "grad_norm": 541.3035888671875,
375
+ "learning_rate": 0.00014858000000000002,
376
+ "loss": 95.16091918945312,
377
+ "original_ce_loss": 7.9154,
378
+ "step": 460
379
+ },
380
+ {
381
+ "epoch": 0.0074610576446076,
382
+ "grad_norm": 137.68650817871094,
383
+ "learning_rate": 0.00015198000000000002,
384
+ "loss": 93.91212158203125,
385
+ "original_ce_loss": 7.8114,
386
+ "step": 470
387
+ },
388
+ {
389
+ "epoch": 0.007619803551939677,
390
+ "grad_norm": 130.08709716796875,
391
+ "learning_rate": 0.00015538000000000002,
392
+ "loss": 94.08109130859376,
393
+ "original_ce_loss": 7.8255,
394
+ "step": 480
395
+ },
396
+ {
397
+ "epoch": 0.0077785494592717535,
398
+ "grad_norm": 124.69246673583984,
399
+ "learning_rate": 0.00015878000000000002,
400
+ "loss": 93.34008178710937,
401
+ "original_ce_loss": 7.7639,
402
+ "step": 490
403
+ },
404
+ {
405
+ "epoch": 0.00793729536660383,
406
+ "grad_norm": 131.73631286621094,
407
+ "learning_rate": 0.00016218,
408
+ "loss": 93.37709350585938,
409
+ "original_ce_loss": 7.767,
410
+ "step": 500
411
+ },
412
+ {
413
+ "epoch": 0.008096041273935907,
414
+ "grad_norm": 129.07395935058594,
415
+ "learning_rate": 0.00016558,
416
+ "loss": 93.99864501953125,
417
+ "original_ce_loss": 7.8189,
418
+ "step": 510
419
+ },
420
+ {
421
+ "epoch": 0.008254787181267983,
422
+ "grad_norm": 107.86299896240234,
423
+ "learning_rate": 0.00016898,
424
+ "loss": 93.50586547851563,
425
+ "original_ce_loss": 7.7779,
426
+ "step": 520
427
+ },
428
+ {
429
+ "epoch": 0.008413533088600059,
430
+ "grad_norm": 141.98410034179688,
431
+ "learning_rate": 0.0001699999947373062,
432
+ "loss": 94.15840454101563,
433
+ "original_ce_loss": 7.8324,
434
+ "step": 530
435
+ },
436
+ {
437
+ "epoch": 0.008572278995932136,
438
+ "grad_norm": 105.16947174072266,
439
+ "learning_rate": 0.00016999996896084816,
440
+ "loss": 94.6617919921875,
441
+ "original_ce_loss": 7.8744,
442
+ "step": 540
443
+ },
444
+ {
445
+ "epoch": 0.008731024903264212,
446
+ "grad_norm": 103.89173126220703,
447
+ "learning_rate": 0.00016999992170401522,
448
+ "loss": 94.6985107421875,
449
+ "original_ce_loss": 7.8776,
450
+ "step": 550
451
+ },
452
+ {
453
+ "epoch": 0.00888977081059629,
454
+ "grad_norm": 102.89775085449219,
455
+ "learning_rate": 0.0001699998529668193,
456
+ "loss": 94.39563598632813,
457
+ "original_ce_loss": 7.8524,
458
+ "step": 560
459
+ },
460
+ {
461
+ "epoch": 0.009048516717928366,
462
+ "grad_norm": 105.0541763305664,
463
+ "learning_rate": 0.0001699997627492778,
464
+ "loss": 94.77478637695313,
465
+ "original_ce_loss": 7.8841,
466
+ "step": 570
467
+ },
468
+ {
469
+ "epoch": 0.009207262625260443,
470
+ "grad_norm": 101.42198944091797,
471
+ "learning_rate": 0.0001699996510514135,
472
+ "loss": 94.83777465820313,
473
+ "original_ce_loss": 7.8894,
474
+ "step": 580
475
+ },
476
+ {
477
+ "epoch": 0.009366008532592519,
478
+ "grad_norm": 99.91072845458984,
479
+ "learning_rate": 0.00016999951787325458,
480
+ "loss": 95.25111694335938,
481
+ "original_ce_loss": 7.924,
482
+ "step": 590
483
+ },
484
+ {
485
+ "epoch": 0.009524754439924595,
486
+ "grad_norm": 98.75752258300781,
487
+ "learning_rate": 0.00016999936321483478,
488
+ "loss": 95.43342895507813,
489
+ "original_ce_loss": 7.9392,
490
+ "step": 600
491
+ }
492
+ ],
493
+ "logging_steps": 10,
494
+ "max_steps": 62994,
495
+ "num_input_tokens_seen": 0,
496
+ "num_train_epochs": 1,
497
+ "save_steps": 200,
498
+ "stateful_callbacks": {
499
+ "TrainerControl": {
500
+ "args": {
501
+ "should_epoch_stop": false,
502
+ "should_evaluate": false,
503
+ "should_log": false,
504
+ "should_save": true,
505
+ "should_training_stop": false
506
+ },
507
+ "attributes": {}
508
+ }
509
+ },
510
+ "total_flos": 1.4353393620713472e+16,
511
+ "train_batch_size": 16,
512
+ "trial_name": null,
513
+ "trial_params": null
514
+ }
checkpoint-600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76590a28ae0bf54823fa0ee2dd7b2be69ffd03ca50be00ab138f8aa05f764b31
3
+ size 5201