Grogros commited on
Commit
74c93fd
·
verified ·
1 Parent(s): d2bffbc

Training in progress, step 1000, checkpoint

Browse files
checkpoint-1000/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.46.3",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.46.3"
12
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f30f32b577d0f267a14dc5a240e9eaf03dfef0150cdc47a25d4c5b77d9ddc89
3
+ size 2471645608
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdafbabce419c5ea2dbb03f17ba94fdf0538eba05a3df7b39b6789b1d2147f6d
3
+ size 3724602
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530dffc867086773c32ec2bf04d801073511f7e8d7c701f0d209936db81239cb
3
+ size 1064
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005,
13
+ "grad_norm": 37.0,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 1.5359,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 45.5,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 1.4797,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.015,
27
+ "grad_norm": 21.625,
28
+ "learning_rate": 3e-06,
29
+ "loss": 1.3793,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.02,
34
+ "grad_norm": 19.625,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 1.26,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.025,
41
+ "grad_norm": 12.375,
42
+ "learning_rate": 5e-06,
43
+ "loss": 1.2473,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "grad_norm": 9.75,
49
+ "learning_rate": 6e-06,
50
+ "loss": 1.132,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.035,
55
+ "grad_norm": 8.4375,
56
+ "learning_rate": 7e-06,
57
+ "loss": 1.1854,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.04,
62
+ "grad_norm": 9.25,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 1.1473,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.045,
69
+ "grad_norm": 5.5,
70
+ "learning_rate": 9e-06,
71
+ "loss": 1.1484,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.05,
76
+ "grad_norm": 4.71875,
77
+ "learning_rate": 1e-05,
78
+ "loss": 1.1352,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.055,
83
+ "grad_norm": 5.6875,
84
+ "learning_rate": 1.1000000000000001e-05,
85
+ "loss": 1.0916,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.06,
90
+ "grad_norm": 4.90625,
91
+ "learning_rate": 1.2e-05,
92
+ "loss": 1.0473,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.065,
97
+ "grad_norm": 5.09375,
98
+ "learning_rate": 1.3000000000000001e-05,
99
+ "loss": 1.0576,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.07,
104
+ "grad_norm": 5.6875,
105
+ "learning_rate": 1.4e-05,
106
+ "loss": 1.0014,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.075,
111
+ "grad_norm": 5.4375,
112
+ "learning_rate": 1.5000000000000002e-05,
113
+ "loss": 1.015,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.08,
118
+ "grad_norm": 5.0625,
119
+ "learning_rate": 1.6000000000000003e-05,
120
+ "loss": 0.9674,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.085,
125
+ "grad_norm": 5.125,
126
+ "learning_rate": 1.7e-05,
127
+ "loss": 0.9754,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.09,
132
+ "grad_norm": 4.09375,
133
+ "learning_rate": 1.8e-05,
134
+ "loss": 0.9309,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.095,
139
+ "grad_norm": 4.875,
140
+ "learning_rate": 1.9e-05,
141
+ "loss": 0.9158,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.1,
146
+ "grad_norm": 117.5,
147
+ "learning_rate": 2e-05,
148
+ "loss": 0.9994,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.105,
153
+ "grad_norm": 5.34375,
154
+ "learning_rate": 1.9998476951563914e-05,
155
+ "loss": 1.0623,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.11,
160
+ "grad_norm": 19.0,
161
+ "learning_rate": 1.999390827019096e-05,
162
+ "loss": 1.007,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.115,
167
+ "grad_norm": 5.21875,
168
+ "learning_rate": 1.9986295347545738e-05,
169
+ "loss": 0.867,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.12,
174
+ "grad_norm": 3.640625,
175
+ "learning_rate": 1.9975640502598243e-05,
176
+ "loss": 0.852,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.125,
181
+ "grad_norm": 4.40625,
182
+ "learning_rate": 1.9961946980917457e-05,
183
+ "loss": 0.8018,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.13,
188
+ "grad_norm": 5.125,
189
+ "learning_rate": 1.9945218953682736e-05,
190
+ "loss": 0.9186,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.135,
195
+ "grad_norm": 4.875,
196
+ "learning_rate": 1.9925461516413224e-05,
197
+ "loss": 0.804,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.14,
202
+ "grad_norm": 3.71875,
203
+ "learning_rate": 1.9902680687415704e-05,
204
+ "loss": 0.817,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.145,
209
+ "grad_norm": 4.125,
210
+ "learning_rate": 1.9876883405951378e-05,
211
+ "loss": 0.7372,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.15,
216
+ "grad_norm": 3.5,
217
+ "learning_rate": 1.9848077530122083e-05,
218
+ "loss": 0.7237,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.155,
223
+ "grad_norm": 3.375,
224
+ "learning_rate": 1.9816271834476642e-05,
225
+ "loss": 0.6707,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.16,
230
+ "grad_norm": 4.21875,
231
+ "learning_rate": 1.9781476007338058e-05,
232
+ "loss": 0.7664,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.165,
237
+ "grad_norm": 3.640625,
238
+ "learning_rate": 1.9743700647852356e-05,
239
+ "loss": 0.6838,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.17,
244
+ "grad_norm": 4.25,
245
+ "learning_rate": 1.9702957262759964e-05,
246
+ "loss": 0.7225,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.175,
251
+ "grad_norm": 3.625,
252
+ "learning_rate": 1.9659258262890683e-05,
253
+ "loss": 0.6754,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.18,
258
+ "grad_norm": 3.546875,
259
+ "learning_rate": 1.961261695938319e-05,
260
+ "loss": 0.6344,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.185,
265
+ "grad_norm": 3.546875,
266
+ "learning_rate": 1.9563047559630356e-05,
267
+ "loss": 0.6728,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.19,
272
+ "grad_norm": 4.34375,
273
+ "learning_rate": 1.9510565162951538e-05,
274
+ "loss": 0.7283,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.195,
279
+ "grad_norm": 3.671875,
280
+ "learning_rate": 1.945518575599317e-05,
281
+ "loss": 0.666,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.2,
286
+ "grad_norm": 4.4375,
287
+ "learning_rate": 1.9396926207859085e-05,
288
+ "loss": 0.6756,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.205,
293
+ "grad_norm": 3.71875,
294
+ "learning_rate": 1.9335804264972018e-05,
295
+ "loss": 0.6558,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.21,
300
+ "grad_norm": 3.234375,
301
+ "learning_rate": 1.9271838545667876e-05,
302
+ "loss": 0.6243,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.215,
307
+ "grad_norm": 3.90625,
308
+ "learning_rate": 1.9205048534524405e-05,
309
+ "loss": 0.6519,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.22,
314
+ "grad_norm": 3.375,
315
+ "learning_rate": 1.913545457642601e-05,
316
+ "loss": 0.626,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.225,
321
+ "grad_norm": 3.78125,
322
+ "learning_rate": 1.9063077870366504e-05,
323
+ "loss": 0.6592,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.23,
328
+ "grad_norm": 3.75,
329
+ "learning_rate": 1.8987940462991673e-05,
330
+ "loss": 0.5869,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.235,
335
+ "grad_norm": 4.25,
336
+ "learning_rate": 1.891006524188368e-05,
337
+ "loss": 0.6157,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.24,
342
+ "grad_norm": 2.78125,
343
+ "learning_rate": 1.8829475928589272e-05,
344
+ "loss": 0.5537,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.245,
349
+ "grad_norm": 2.734375,
350
+ "learning_rate": 1.874619707139396e-05,
351
+ "loss": 0.631,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.25,
356
+ "grad_norm": 3.875,
357
+ "learning_rate": 1.866025403784439e-05,
358
+ "loss": 0.5853,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.255,
363
+ "grad_norm": 2.46875,
364
+ "learning_rate": 1.8571673007021124e-05,
365
+ "loss": 0.5669,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.26,
370
+ "grad_norm": 4.75,
371
+ "learning_rate": 1.848048096156426e-05,
372
+ "loss": 0.5251,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.265,
377
+ "grad_norm": 3.40625,
378
+ "learning_rate": 1.8386705679454243e-05,
379
+ "loss": 0.5188,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.27,
384
+ "grad_norm": 3.609375,
385
+ "learning_rate": 1.8290375725550417e-05,
386
+ "loss": 0.5289,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.275,
391
+ "grad_norm": 2.953125,
392
+ "learning_rate": 1.819152044288992e-05,
393
+ "loss": 0.628,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.28,
398
+ "grad_norm": 2.484375,
399
+ "learning_rate": 1.8090169943749477e-05,
400
+ "loss": 0.5611,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.285,
405
+ "grad_norm": 3.125,
406
+ "learning_rate": 1.798635510047293e-05,
407
+ "loss": 0.5497,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.29,
412
+ "grad_norm": 3.21875,
413
+ "learning_rate": 1.788010753606722e-05,
414
+ "loss": 0.5717,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.295,
419
+ "grad_norm": 3.15625,
420
+ "learning_rate": 1.777145961456971e-05,
421
+ "loss": 0.5497,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.3,
426
+ "grad_norm": 3.25,
427
+ "learning_rate": 1.766044443118978e-05,
428
+ "loss": 0.543,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.305,
433
+ "grad_norm": 2.671875,
434
+ "learning_rate": 1.7547095802227723e-05,
435
+ "loss": 0.5547,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.31,
440
+ "grad_norm": 2.671875,
441
+ "learning_rate": 1.7431448254773943e-05,
442
+ "loss": 0.5395,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.315,
447
+ "grad_norm": 3.390625,
448
+ "learning_rate": 1.7313537016191706e-05,
449
+ "loss": 0.5913,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.32,
454
+ "grad_norm": 2.640625,
455
+ "learning_rate": 1.7193398003386514e-05,
456
+ "loss": 0.5385,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.325,
461
+ "grad_norm": 3.5,
462
+ "learning_rate": 1.7071067811865477e-05,
463
+ "loss": 0.5522,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.33,
468
+ "grad_norm": 2.96875,
469
+ "learning_rate": 1.6946583704589973e-05,
470
+ "loss": 0.5241,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.335,
475
+ "grad_norm": 3.40625,
476
+ "learning_rate": 1.6819983600624986e-05,
477
+ "loss": 0.4942,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.34,
482
+ "grad_norm": 2.765625,
483
+ "learning_rate": 1.6691306063588583e-05,
484
+ "loss": 0.484,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.345,
489
+ "grad_norm": 2.671875,
490
+ "learning_rate": 1.6560590289905074e-05,
491
+ "loss": 0.463,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.35,
496
+ "grad_norm": 3.34375,
497
+ "learning_rate": 1.6427876096865394e-05,
498
+ "loss": 0.4791,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.355,
503
+ "grad_norm": 3.1875,
504
+ "learning_rate": 1.6293203910498375e-05,
505
+ "loss": 0.4977,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.36,
510
+ "grad_norm": 2.421875,
511
+ "learning_rate": 1.6156614753256583e-05,
512
+ "loss": 0.5117,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.365,
517
+ "grad_norm": 3.46875,
518
+ "learning_rate": 1.6018150231520486e-05,
519
+ "loss": 0.5095,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.37,
524
+ "grad_norm": 2.53125,
525
+ "learning_rate": 1.5877852522924733e-05,
526
+ "loss": 0.4845,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.375,
531
+ "grad_norm": 2.75,
532
+ "learning_rate": 1.573576436351046e-05,
533
+ "loss": 0.4809,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.38,
538
+ "grad_norm": 3.453125,
539
+ "learning_rate": 1.5591929034707468e-05,
540
+ "loss": 0.4588,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.385,
545
+ "grad_norm": 2.9375,
546
+ "learning_rate": 1.5446390350150272e-05,
547
+ "loss": 0.5021,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.39,
552
+ "grad_norm": 2.421875,
553
+ "learning_rate": 1.529919264233205e-05,
554
+ "loss": 0.5011,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.395,
559
+ "grad_norm": 2.59375,
560
+ "learning_rate": 1.5150380749100545e-05,
561
+ "loss": 0.4935,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.4,
566
+ "grad_norm": 2.4375,
567
+ "learning_rate": 1.5000000000000002e-05,
568
+ "loss": 0.5083,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.405,
573
+ "grad_norm": 2.78125,
574
+ "learning_rate": 1.4848096202463373e-05,
575
+ "loss": 0.4488,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.41,
580
+ "grad_norm": 2.625,
581
+ "learning_rate": 1.469471562785891e-05,
582
+ "loss": 0.4308,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.415,
587
+ "grad_norm": 3.453125,
588
+ "learning_rate": 1.4539904997395468e-05,
589
+ "loss": 0.443,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.42,
594
+ "grad_norm": 3.15625,
595
+ "learning_rate": 1.4383711467890776e-05,
596
+ "loss": 0.4832,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.425,
601
+ "grad_norm": 2.625,
602
+ "learning_rate": 1.4226182617406996e-05,
603
+ "loss": 0.4688,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.43,
608
+ "grad_norm": 3.1875,
609
+ "learning_rate": 1.4067366430758004e-05,
610
+ "loss": 0.4534,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.435,
615
+ "grad_norm": 2.921875,
616
+ "learning_rate": 1.3907311284892737e-05,
617
+ "loss": 0.422,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.44,
622
+ "grad_norm": 3.296875,
623
+ "learning_rate": 1.3746065934159123e-05,
624
+ "loss": 0.4677,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.445,
629
+ "grad_norm": 3.1875,
630
+ "learning_rate": 1.3583679495453e-05,
631
+ "loss": 0.4743,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.45,
636
+ "grad_norm": 2.859375,
637
+ "learning_rate": 1.342020143325669e-05,
638
+ "loss": 0.4639,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.455,
643
+ "grad_norm": 4.28125,
644
+ "learning_rate": 1.3255681544571568e-05,
645
+ "loss": 0.4374,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.46,
650
+ "grad_norm": 2.546875,
651
+ "learning_rate": 1.3090169943749475e-05,
652
+ "loss": 0.4294,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.465,
657
+ "grad_norm": 2.890625,
658
+ "learning_rate": 1.2923717047227368e-05,
659
+ "loss": 0.4604,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.47,
664
+ "grad_norm": 2.90625,
665
+ "learning_rate": 1.2756373558169992e-05,
666
+ "loss": 0.4341,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.475,
671
+ "grad_norm": 3.46875,
672
+ "learning_rate": 1.2588190451025209e-05,
673
+ "loss": 0.4212,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.48,
678
+ "grad_norm": 3.109375,
679
+ "learning_rate": 1.2419218955996677e-05,
680
+ "loss": 0.4391,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.485,
685
+ "grad_norm": 2.609375,
686
+ "learning_rate": 1.2249510543438652e-05,
687
+ "loss": 0.4442,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.49,
692
+ "grad_norm": 3.1875,
693
+ "learning_rate": 1.2079116908177592e-05,
694
+ "loss": 0.4612,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.495,
699
+ "grad_norm": 3.375,
700
+ "learning_rate": 1.190808995376545e-05,
701
+ "loss": 0.4126,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.5,
706
+ "grad_norm": 4.71875,
707
+ "learning_rate": 1.1736481776669307e-05,
708
+ "loss": 0.4042,
709
+ "step": 1000
710
+ }
711
+ ],
712
+ "logging_steps": 10,
713
+ "max_steps": 2000,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 9223372036854775807,
716
+ "save_steps": 500,
717
+ "stateful_callbacks": {
718
+ "TrainerControl": {
719
+ "args": {
720
+ "should_epoch_stop": false,
721
+ "should_evaluate": false,
722
+ "should_log": false,
723
+ "should_save": true,
724
+ "should_training_stop": false
725
+ },
726
+ "attributes": {}
727
+ }
728
+ },
729
+ "total_flos": 9.5664155394048e+16,
730
+ "train_batch_size": 16,
731
+ "trial_name": null,
732
+ "trial_params": null
733
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd6b60903244d2c3807559fcc357810b7e7b4b029b3946e04d0a00137162c24
3
+ size 5304