Grogros commited on
Commit
c1a4f96
·
verified ·
1 Parent(s): e6ade79

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:fda9ceb4684d2b11f62497da91b1de1920b1a66f928918b6d1536727320f550c
3
+ size 2471645608
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8019cab356c26f2b88d0c1d588e7e4ff2d6d82042273fd565695007931b63d5
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:c54df4eef282ce0ee9c2fecf8ba266cb517dcce0b65a055ec1e2e345cb152743
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:326a92bbc92dd2a708a19036175e7dbffa3c696c33e33685cc4a219f400a23f2
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": 5.232177894048398,
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": 0.052321778940483975,
13
+ "grad_norm": 73.5,
14
+ "learning_rate": 8.000000000000001e-07,
15
+ "loss": 0.4785,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.10464355788096795,
20
+ "grad_norm": 280.0,
21
+ "learning_rate": 1.6000000000000001e-06,
22
+ "loss": 0.4749,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.15696533682145192,
27
+ "grad_norm": 664.0,
28
+ "learning_rate": 2.4000000000000003e-06,
29
+ "loss": 0.5162,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.2092871157619359,
34
+ "grad_norm": 684.0,
35
+ "learning_rate": 3.2000000000000003e-06,
36
+ "loss": 0.7172,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.2616088947024199,
41
+ "grad_norm": 209.0,
42
+ "learning_rate": 4.000000000000001e-06,
43
+ "loss": 0.8219,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.31393067364290383,
48
+ "grad_norm": 122.0,
49
+ "learning_rate": 4.800000000000001e-06,
50
+ "loss": 1.1019,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.36625245258338784,
55
+ "grad_norm": 149.0,
56
+ "learning_rate": 5.600000000000001e-06,
57
+ "loss": 1.145,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.4185742315238718,
62
+ "grad_norm": 123.5,
63
+ "learning_rate": 6.4000000000000006e-06,
64
+ "loss": 1.1876,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.4708960104643558,
69
+ "grad_norm": 89.0,
70
+ "learning_rate": 7.2000000000000005e-06,
71
+ "loss": 1.207,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.5232177894048398,
76
+ "grad_norm": 372.0,
77
+ "learning_rate": 8.000000000000001e-06,
78
+ "loss": 1.0986,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.5755395683453237,
83
+ "grad_norm": 69.0,
84
+ "learning_rate": 8.8e-06,
85
+ "loss": 0.8367,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.6278613472858077,
90
+ "grad_norm": 60.25,
91
+ "learning_rate": 9.600000000000001e-06,
92
+ "loss": 0.8822,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.6801831262262917,
97
+ "grad_norm": 44.75,
98
+ "learning_rate": 1.04e-05,
99
+ "loss": 1.2104,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.7325049051667757,
104
+ "grad_norm": 49.0,
105
+ "learning_rate": 1.1200000000000001e-05,
106
+ "loss": 0.8587,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.7848266841072596,
111
+ "grad_norm": 42.5,
112
+ "learning_rate": 1.2e-05,
113
+ "loss": 0.761,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.8371484630477436,
118
+ "grad_norm": 42.5,
119
+ "learning_rate": 1.2800000000000001e-05,
120
+ "loss": 0.7207,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.8894702419882276,
125
+ "grad_norm": 28.25,
126
+ "learning_rate": 1.3600000000000002e-05,
127
+ "loss": 0.7541,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.9417920209287116,
132
+ "grad_norm": 40.75,
133
+ "learning_rate": 1.4400000000000001e-05,
134
+ "loss": 0.7367,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.9941137998691956,
139
+ "grad_norm": 231.0,
140
+ "learning_rate": 1.5200000000000002e-05,
141
+ "loss": 0.8107,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 1.0464355788096795,
146
+ "grad_norm": 70.0,
147
+ "learning_rate": 1.6000000000000003e-05,
148
+ "loss": 0.7498,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 1.0987573577501635,
153
+ "grad_norm": 33.5,
154
+ "learning_rate": 1.6800000000000002e-05,
155
+ "loss": 0.7138,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 1.1510791366906474,
160
+ "grad_norm": 34.75,
161
+ "learning_rate": 1.76e-05,
162
+ "loss": 0.6399,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 1.2034009156311314,
167
+ "grad_norm": 20.125,
168
+ "learning_rate": 1.8400000000000003e-05,
169
+ "loss": 0.5844,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 1.2557226945716153,
174
+ "grad_norm": 34.25,
175
+ "learning_rate": 1.9200000000000003e-05,
176
+ "loss": 0.6765,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 1.3080444735120995,
181
+ "grad_norm": 37.0,
182
+ "learning_rate": 2e-05,
183
+ "loss": 3.7542,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 1.3603662524525835,
188
+ "grad_norm": 27.25,
189
+ "learning_rate": 1.9999025240093045e-05,
190
+ "loss": 0.7183,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 1.4126880313930674,
195
+ "grad_norm": 20.25,
196
+ "learning_rate": 1.9996101150403543e-05,
197
+ "loss": 0.5714,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 1.4650098103335514,
202
+ "grad_norm": 21.125,
203
+ "learning_rate": 1.9991228300988586e-05,
204
+ "loss": 0.5506,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 1.5173315892740353,
209
+ "grad_norm": 23.625,
210
+ "learning_rate": 1.9984407641819812e-05,
211
+ "loss": 0.5253,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 1.5696533682145193,
216
+ "grad_norm": 20.75,
217
+ "learning_rate": 1.9975640502598243e-05,
218
+ "loss": 0.5671,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 1.6219751471550032,
223
+ "grad_norm": 15.6875,
224
+ "learning_rate": 1.9964928592495046e-05,
225
+ "loss": 0.4991,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 1.6742969260954872,
230
+ "grad_norm": 18.125,
231
+ "learning_rate": 1.9952273999818312e-05,
232
+ "loss": 0.5376,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 1.7266187050359711,
237
+ "grad_norm": 18.125,
238
+ "learning_rate": 1.9937679191605964e-05,
239
+ "loss": 0.5307,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 1.7789404839764553,
244
+ "grad_norm": 17.125,
245
+ "learning_rate": 1.9921147013144782e-05,
246
+ "loss": 0.522,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 1.831262262916939,
251
+ "grad_norm": 11.375,
252
+ "learning_rate": 1.9902680687415704e-05,
253
+ "loss": 0.4873,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 1.8835840418574232,
258
+ "grad_norm": 19.625,
259
+ "learning_rate": 1.988228381446553e-05,
260
+ "loss": 0.4609,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 1.9359058207979072,
265
+ "grad_norm": 15.0625,
266
+ "learning_rate": 1.985996037070505e-05,
267
+ "loss": 0.4225,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 1.9882275997383911,
272
+ "grad_norm": 19.0,
273
+ "learning_rate": 1.983571470813386e-05,
274
+ "loss": 0.4309,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 2.040549378678875,
279
+ "grad_norm": 18.5,
280
+ "learning_rate": 1.9809551553491918e-05,
281
+ "loss": 0.4062,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 2.092871157619359,
286
+ "grad_norm": 10.25,
287
+ "learning_rate": 1.9781476007338058e-05,
288
+ "loss": 0.3827,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 2.145192936559843,
293
+ "grad_norm": 23.75,
294
+ "learning_rate": 1.9751493543055634e-05,
295
+ "loss": 0.3883,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 2.197514715500327,
300
+ "grad_norm": 14.8125,
301
+ "learning_rate": 1.9719610005785466e-05,
302
+ "loss": 0.4069,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 2.249836494440811,
307
+ "grad_norm": 23.125,
308
+ "learning_rate": 1.9685831611286312e-05,
309
+ "loss": 0.3815,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 2.302158273381295,
314
+ "grad_norm": 10.8125,
315
+ "learning_rate": 1.9650164944723116e-05,
316
+ "loss": 0.3719,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 2.354480052321779,
321
+ "grad_norm": 15.6875,
322
+ "learning_rate": 1.961261695938319e-05,
323
+ "loss": 0.4038,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 2.4068018312622628,
328
+ "grad_norm": 18.875,
329
+ "learning_rate": 1.9573194975320672e-05,
330
+ "loss": 0.3864,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 2.459123610202747,
335
+ "grad_norm": 21.375,
336
+ "learning_rate": 1.9531906677929472e-05,
337
+ "loss": 0.3941,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 2.5114453891432307,
342
+ "grad_norm": 24.75,
343
+ "learning_rate": 1.9488760116444966e-05,
344
+ "loss": 0.3661,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 2.563767168083715,
349
+ "grad_norm": 30.0,
350
+ "learning_rate": 1.944376370237481e-05,
351
+ "loss": 0.3604,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 2.616088947024199,
356
+ "grad_norm": 11.6875,
357
+ "learning_rate": 1.9396926207859085e-05,
358
+ "loss": 0.3618,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 2.6684107259646828,
363
+ "grad_norm": 24.875,
364
+ "learning_rate": 1.9348256763960146e-05,
365
+ "loss": 0.3942,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 2.720732504905167,
370
+ "grad_norm": 3.390625,
371
+ "learning_rate": 1.9297764858882516e-05,
372
+ "loss": 0.3458,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 2.7730542838456507,
377
+ "grad_norm": 10.3125,
378
+ "learning_rate": 1.9245460336123136e-05,
379
+ "loss": 0.3533,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 2.825376062786135,
384
+ "grad_norm": 20.875,
385
+ "learning_rate": 1.9191353392552346e-05,
386
+ "loss": 0.3546,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 2.8776978417266186,
391
+ "grad_norm": 14.3125,
392
+ "learning_rate": 1.913545457642601e-05,
393
+ "loss": 0.366,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 2.9300196206671028,
398
+ "grad_norm": 13.875,
399
+ "learning_rate": 1.907777478532909e-05,
400
+ "loss": 0.3353,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 2.982341399607587,
405
+ "grad_norm": 4.25,
406
+ "learning_rate": 1.901832526405114e-05,
407
+ "loss": 0.3564,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 3.0346631785480707,
412
+ "grad_norm": 10.3125,
413
+ "learning_rate": 1.895711760239413e-05,
414
+ "loss": 0.3324,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 3.0869849574885544,
419
+ "grad_norm": 6.15625,
420
+ "learning_rate": 1.889416373291298e-05,
421
+ "loss": 0.3254,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 3.1393067364290386,
426
+ "grad_norm": 9.6875,
427
+ "learning_rate": 1.8829475928589272e-05,
428
+ "loss": 0.3278,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 3.1916285153695227,
433
+ "grad_norm": 10.4375,
434
+ "learning_rate": 1.8763066800438638e-05,
435
+ "loss": 0.2962,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 3.2439502943100065,
440
+ "grad_norm": 15.125,
441
+ "learning_rate": 1.869494929505219e-05,
442
+ "loss": 0.311,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 3.2962720732504907,
447
+ "grad_norm": 13.0625,
448
+ "learning_rate": 1.8625136692072577e-05,
449
+ "loss": 0.2956,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 3.3485938521909744,
454
+ "grad_norm": 12.875,
455
+ "learning_rate": 1.855364260160507e-05,
456
+ "loss": 0.3173,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 3.4009156311314586,
461
+ "grad_norm": 10.1875,
462
+ "learning_rate": 1.848048096156426e-05,
463
+ "loss": 0.298,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 3.4532374100719423,
468
+ "grad_norm": 6.375,
469
+ "learning_rate": 1.8405666034956842e-05,
470
+ "loss": 0.3216,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 3.5055591890124265,
475
+ "grad_norm": 23.25,
476
+ "learning_rate": 1.8329212407100996e-05,
477
+ "loss": 0.3417,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 3.5578809679529106,
482
+ "grad_norm": 11.25,
483
+ "learning_rate": 1.8251134982782952e-05,
484
+ "loss": 0.3169,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 3.6102027468933944,
489
+ "grad_norm": 14.9375,
490
+ "learning_rate": 1.8171448983351284e-05,
491
+ "loss": 0.3221,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 3.662524525833878,
496
+ "grad_norm": 9.375,
497
+ "learning_rate": 1.8090169943749477e-05,
498
+ "loss": 0.2793,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 3.7148463047743623,
503
+ "grad_norm": 3.3125,
504
+ "learning_rate": 1.8007313709487334e-05,
505
+ "loss": 0.3063,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 3.7671680837148465,
510
+ "grad_norm": 13.0625,
511
+ "learning_rate": 1.792289643355191e-05,
512
+ "loss": 0.2723,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 3.81948986265533,
517
+ "grad_norm": 13.0,
518
+ "learning_rate": 1.78369345732584e-05,
519
+ "loss": 0.2924,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 3.8718116415958144,
524
+ "grad_norm": 20.25,
525
+ "learning_rate": 1.7749444887041797e-05,
526
+ "loss": 0.314,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 3.924133420536298,
531
+ "grad_norm": 7.0625,
532
+ "learning_rate": 1.766044443118978e-05,
533
+ "loss": 0.2965,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 3.9764551994767823,
538
+ "grad_norm": 12.25,
539
+ "learning_rate": 1.7569950556517566e-05,
540
+ "loss": 0.2784,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 4.028776978417266,
545
+ "grad_norm": 7.5,
546
+ "learning_rate": 1.747798090498532e-05,
547
+ "loss": 0.2626,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 4.08109875735775,
552
+ "grad_norm": 15.0625,
553
+ "learning_rate": 1.7384553406258842e-05,
554
+ "loss": 0.2629,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 4.133420536298234,
559
+ "grad_norm": 11.625,
560
+ "learning_rate": 1.7289686274214116e-05,
561
+ "loss": 0.252,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 4.185742315238718,
566
+ "grad_norm": 9.75,
567
+ "learning_rate": 1.7193398003386514e-05,
568
+ "loss": 0.2466,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 4.238064094179202,
573
+ "grad_norm": 11.3125,
574
+ "learning_rate": 1.709570736536521e-05,
575
+ "loss": 0.2547,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 4.290385873119686,
580
+ "grad_norm": 7.15625,
581
+ "learning_rate": 1.6996633405133656e-05,
582
+ "loss": 0.272,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 4.34270765206017,
587
+ "grad_norm": 9.1875,
588
+ "learning_rate": 1.68961954373567e-05,
589
+ "loss": 0.2467,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 4.395029431000654,
594
+ "grad_norm": 8.125,
595
+ "learning_rate": 1.6794413042615168e-05,
596
+ "loss": 0.2421,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 4.447351209941138,
601
+ "grad_norm": 9.4375,
602
+ "learning_rate": 1.6691306063588583e-05,
603
+ "loss": 0.2699,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 4.499672988881622,
608
+ "grad_norm": 4.96875,
609
+ "learning_rate": 1.6586894601186804e-05,
610
+ "loss": 0.2446,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 4.551994767822106,
615
+ "grad_norm": 7.46875,
616
+ "learning_rate": 1.6481199010631312e-05,
617
+ "loss": 0.2501,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 4.60431654676259,
622
+ "grad_norm": 12.875,
623
+ "learning_rate": 1.63742398974869e-05,
624
+ "loss": 0.2508,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 4.656638325703074,
629
+ "grad_norm": 10.4375,
630
+ "learning_rate": 1.6266038113644605e-05,
631
+ "loss": 0.2487,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 4.708960104643558,
636
+ "grad_norm": 3.046875,
637
+ "learning_rate": 1.6156614753256583e-05,
638
+ "loss": 0.2384,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 4.761281883584042,
643
+ "grad_norm": 11.1875,
644
+ "learning_rate": 1.6045991148623752e-05,
645
+ "loss": 0.2552,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 4.8136036625245255,
650
+ "grad_norm": 10.6875,
651
+ "learning_rate": 1.5934188866037017e-05,
652
+ "loss": 0.2299,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 4.86592544146501,
657
+ "grad_norm": 10.375,
658
+ "learning_rate": 1.5821229701572897e-05,
659
+ "loss": 0.2443,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 4.918247220405494,
664
+ "grad_norm": 2.109375,
665
+ "learning_rate": 1.570713567684432e-05,
666
+ "loss": 0.2364,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 4.970568999345978,
671
+ "grad_norm": 3.828125,
672
+ "learning_rate": 1.5591929034707468e-05,
673
+ "loss": 0.252,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 5.022890778286461,
678
+ "grad_norm": 3.53125,
679
+ "learning_rate": 1.5475632234925505e-05,
680
+ "loss": 0.2499,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 5.075212557226946,
685
+ "grad_norm": 7.90625,
686
+ "learning_rate": 1.5358267949789968e-05,
687
+ "loss": 0.2217,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 5.12753433616743,
692
+ "grad_norm": 8.125,
693
+ "learning_rate": 1.5239859059700794e-05,
694
+ "loss": 0.2111,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 5.179856115107913,
699
+ "grad_norm": 8.75,
700
+ "learning_rate": 1.5120428648705716e-05,
701
+ "loss": 0.2166,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 5.232177894048398,
706
+ "grad_norm": 10.375,
707
+ "learning_rate": 1.5000000000000002e-05,
708
+ "loss": 0.2056,
709
+ "step": 1000
710
+ }
711
+ ],
712
+ "logging_steps": 10,
713
+ "max_steps": 2500,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 14,
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": 3.8253704138194944e+17,
730
+ "train_batch_size": 4,
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:e10f4c3493d7c03a6772e09fa67dd6af5fe700f25044f5df7816afc8f4ab8195
3
+ size 5432