neginr commited on
Commit
748d467
·
verified ·
1 Parent(s): 444b370

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -1
  2. all_results.json +8 -0
  3. train_results.json +8 -0
  4. trainer_state.json +952 -0
  5. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: no_pipeline_math_0.3k
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # no_pipeline_math_0.3k
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: no_pipeline_math_0.3k
 
16
 
17
  # no_pipeline_math_0.3k
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/no_pipeline_math_0.3k dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 13.0,
3
+ "total_flos": 2.50173978574848e+16,
4
+ "train_loss": 0.20831933366134764,
5
+ "train_runtime": 2041.6117,
6
+ "train_samples_per_second": 2.012,
7
+ "train_steps_per_second": 0.064
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 13.0,
3
+ "total_flos": 2.50173978574848e+16,
4
+ "train_loss": 0.20831933366134764,
5
+ "train_runtime": 2041.6117,
6
+ "train_samples_per_second": 2.012,
7
+ "train_steps_per_second": 0.064
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,952 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 13.0,
5
+ "eval_steps": 500,
6
+ "global_step": 130,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "grad_norm": 6.779627806351935,
14
+ "learning_rate": 7.692307692307694e-07,
15
+ "loss": 0.8321,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.2,
20
+ "grad_norm": 7.733700169087985,
21
+ "learning_rate": 1.5384615384615387e-06,
22
+ "loss": 0.876,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.3,
27
+ "grad_norm": 7.238197182487587,
28
+ "learning_rate": 2.307692307692308e-06,
29
+ "loss": 0.9343,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.4,
34
+ "grad_norm": 7.603617636922086,
35
+ "learning_rate": 3.0769230769230774e-06,
36
+ "loss": 0.9237,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.5,
41
+ "grad_norm": 5.818599974024641,
42
+ "learning_rate": 3.846153846153847e-06,
43
+ "loss": 0.8329,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.6,
48
+ "grad_norm": 4.828681062053993,
49
+ "learning_rate": 4.615384615384616e-06,
50
+ "loss": 0.7508,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.7,
55
+ "grad_norm": 2.946872126320063,
56
+ "learning_rate": 5.384615384615385e-06,
57
+ "loss": 0.7864,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.8,
62
+ "grad_norm": 3.0446358678116603,
63
+ "learning_rate": 6.153846153846155e-06,
64
+ "loss": 0.724,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.9,
69
+ "grad_norm": 3.739861312910538,
70
+ "learning_rate": 6.923076923076923e-06,
71
+ "loss": 0.7341,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 1.0,
76
+ "grad_norm": 3.4227376657752946,
77
+ "learning_rate": 7.692307692307694e-06,
78
+ "loss": 0.6941,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.1,
83
+ "grad_norm": 3.391771433690599,
84
+ "learning_rate": 8.461538461538462e-06,
85
+ "loss": 0.6809,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.2,
90
+ "grad_norm": 3.2009407499112648,
91
+ "learning_rate": 9.230769230769232e-06,
92
+ "loss": 0.6218,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.3,
97
+ "grad_norm": 2.3765840923942827,
98
+ "learning_rate": 1e-05,
99
+ "loss": 0.5491,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.4,
104
+ "grad_norm": 2.3999756241646164,
105
+ "learning_rate": 9.998197638354428e-06,
106
+ "loss": 0.6052,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.5,
111
+ "grad_norm": 1.8401582850030842,
112
+ "learning_rate": 9.992791852820709e-06,
113
+ "loss": 0.5614,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.6,
118
+ "grad_norm": 2.0515653437541763,
119
+ "learning_rate": 9.983786540671052e-06,
120
+ "loss": 0.5627,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.7,
125
+ "grad_norm": 2.4292668893585168,
126
+ "learning_rate": 9.971188194237141e-06,
127
+ "loss": 0.5473,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.8,
132
+ "grad_norm": 1.948375472471034,
133
+ "learning_rate": 9.955005896229543e-06,
134
+ "loss": 0.5612,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.9,
139
+ "grad_norm": 1.1500236041505767,
140
+ "learning_rate": 9.935251313189564e-06,
141
+ "loss": 0.5184,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 2.0,
146
+ "grad_norm": 1.56511087486709,
147
+ "learning_rate": 9.911938687078324e-06,
148
+ "loss": 0.5239,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 2.1,
153
+ "grad_norm": 1.4550230706327607,
154
+ "learning_rate": 9.885084825009085e-06,
155
+ "loss": 0.4476,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 2.2,
160
+ "grad_norm": 1.4683221764519665,
161
+ "learning_rate": 9.854709087130261e-06,
162
+ "loss": 0.4343,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 2.3,
167
+ "grad_norm": 0.9598764618893638,
168
+ "learning_rate": 9.820833372667813e-06,
169
+ "loss": 0.4513,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 2.4,
174
+ "grad_norm": 0.8748226437296447,
175
+ "learning_rate": 9.783482104137127e-06,
176
+ "loss": 0.4223,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 2.5,
181
+ "grad_norm": 0.9915570304867101,
182
+ "learning_rate": 9.742682209735727e-06,
183
+ "loss": 0.3872,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 2.6,
188
+ "grad_norm": 1.0232047465010423,
189
+ "learning_rate": 9.698463103929542e-06,
190
+ "loss": 0.4575,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 2.7,
195
+ "grad_norm": 1.2242842361295692,
196
+ "learning_rate": 9.650856666246693e-06,
197
+ "loss": 0.4301,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.8,
202
+ "grad_norm": 1.0130665777865844,
203
+ "learning_rate": 9.599897218294122e-06,
204
+ "loss": 0.4214,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.9,
209
+ "grad_norm": 0.9414805063646674,
210
+ "learning_rate": 9.54562149901362e-06,
211
+ "loss": 0.4099,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 3.0,
216
+ "grad_norm": 1.0749237269903371,
217
+ "learning_rate": 9.488068638195072e-06,
218
+ "loss": 0.3338,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 3.1,
223
+ "grad_norm": 1.060179945113561,
224
+ "learning_rate": 9.427280128266049e-06,
225
+ "loss": 0.3138,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 3.2,
230
+ "grad_norm": 0.8224397239963451,
231
+ "learning_rate": 9.363299794378072e-06,
232
+ "loss": 0.3326,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 3.3,
237
+ "grad_norm": 1.4173542158443497,
238
+ "learning_rate": 9.296173762811084e-06,
239
+ "loss": 0.3049,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 3.4,
244
+ "grad_norm": 1.4399741661681684,
245
+ "learning_rate": 9.225950427718974e-06,
246
+ "loss": 0.2553,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 3.5,
251
+ "grad_norm": 0.9425436420467089,
252
+ "learning_rate": 9.152680416240059e-06,
253
+ "loss": 0.2908,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 3.6,
258
+ "grad_norm": 1.4458019448596084,
259
+ "learning_rate": 9.076416551997721e-06,
260
+ "loss": 0.2717,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 3.7,
265
+ "grad_norm": 0.968676737156165,
266
+ "learning_rate": 8.997213817017508e-06,
267
+ "loss": 0.262,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 3.8,
272
+ "grad_norm": 0.8827324918142179,
273
+ "learning_rate": 8.915129312088112e-06,
274
+ "loss": 0.2566,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 3.9,
279
+ "grad_norm": 0.811311364516425,
280
+ "learning_rate": 8.83022221559489e-06,
281
+ "loss": 0.2688,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 4.0,
286
+ "grad_norm": 0.898907543496273,
287
+ "learning_rate": 8.742553740855507e-06,
288
+ "loss": 0.2442,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 4.1,
293
+ "grad_norm": 0.828754132086278,
294
+ "learning_rate": 8.652187091988516e-06,
295
+ "loss": 0.2016,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 4.2,
300
+ "grad_norm": 0.7758159042595095,
301
+ "learning_rate": 8.559187418346703e-06,
302
+ "loss": 0.1948,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 4.3,
307
+ "grad_norm": 0.7488933544212325,
308
+ "learning_rate": 8.463621767547998e-06,
309
+ "loss": 0.1538,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 4.4,
314
+ "grad_norm": 1.0658916255129685,
315
+ "learning_rate": 8.36555903713785e-06,
316
+ "loss": 0.2353,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 4.5,
321
+ "grad_norm": 0.903164330113684,
322
+ "learning_rate": 8.265069924917925e-06,
323
+ "loss": 0.2287,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 4.6,
328
+ "grad_norm": 0.7447429897898407,
329
+ "learning_rate": 8.162226877976886e-06,
330
+ "loss": 0.1544,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 4.7,
335
+ "grad_norm": 0.8077667346749938,
336
+ "learning_rate": 8.057104040460062e-06,
337
+ "loss": 0.2015,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 4.8,
342
+ "grad_norm": 0.7466964986415479,
343
+ "learning_rate": 7.949777200115617e-06,
344
+ "loss": 0.1635,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 4.9,
349
+ "grad_norm": 0.8252912787487685,
350
+ "learning_rate": 7.84032373365578e-06,
351
+ "loss": 0.1652,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 5.0,
356
+ "grad_norm": 0.7489178905315844,
357
+ "learning_rate": 7.728822550972523e-06,
358
+ "loss": 0.1806,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 5.1,
363
+ "grad_norm": 0.5821897945848419,
364
+ "learning_rate": 7.615354038247889e-06,
365
+ "loss": 0.1139,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 5.2,
370
+ "grad_norm": 0.7241098658980318,
371
+ "learning_rate": 7.500000000000001e-06,
372
+ "loss": 0.1273,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 5.3,
377
+ "grad_norm": 0.6255431736720212,
378
+ "learning_rate": 7.382843600106539e-06,
379
+ "loss": 0.1295,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 5.4,
384
+ "grad_norm": 0.691002790072626,
385
+ "learning_rate": 7.263969301848188e-06,
386
+ "loss": 0.1265,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 5.5,
391
+ "grad_norm": 0.8846004437927963,
392
+ "learning_rate": 7.143462807015271e-06,
393
+ "loss": 0.1054,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 5.6,
398
+ "grad_norm": 0.7954288609280562,
399
+ "learning_rate": 7.021410994121525e-06,
400
+ "loss": 0.1334,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 5.7,
405
+ "grad_norm": 0.7354679769808076,
406
+ "learning_rate": 6.897901855769483e-06,
407
+ "loss": 0.1613,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 5.8,
412
+ "grad_norm": 0.6454613491986969,
413
+ "learning_rate": 6.773024435212678e-06,
414
+ "loss": 0.1378,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 5.9,
419
+ "grad_norm": 0.5480281731422116,
420
+ "learning_rate": 6.646868762160399e-06,
421
+ "loss": 0.0912,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 6.0,
426
+ "grad_norm": 0.6713079133136983,
427
+ "learning_rate": 6.519525787871235e-06,
428
+ "loss": 0.1419,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 6.1,
433
+ "grad_norm": 0.5735993174644404,
434
+ "learning_rate": 6.391087319582264e-06,
435
+ "loss": 0.0855,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 6.2,
440
+ "grad_norm": 0.5260788939778733,
441
+ "learning_rate": 6.261645954321109e-06,
442
+ "loss": 0.0776,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 6.3,
447
+ "grad_norm": 0.5086340807856387,
448
+ "learning_rate": 6.131295012148613e-06,
449
+ "loss": 0.0567,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 6.4,
454
+ "grad_norm": 0.6863184640140559,
455
+ "learning_rate": 6.000128468880223e-06,
456
+ "loss": 0.1049,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 6.5,
461
+ "grad_norm": 0.7053508342490321,
462
+ "learning_rate": 5.8682408883346535e-06,
463
+ "loss": 0.1187,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 6.6,
468
+ "grad_norm": 0.6907230517007713,
469
+ "learning_rate": 5.735727354158581e-06,
470
+ "loss": 0.0778,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 6.7,
475
+ "grad_norm": 0.5662192151886665,
476
+ "learning_rate": 5.6026834012766155e-06,
477
+ "loss": 0.1261,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 6.8,
482
+ "grad_norm": 0.5500097783951419,
483
+ "learning_rate": 5.469204947015897e-06,
484
+ "loss": 0.0729,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 6.9,
489
+ "grad_norm": 0.5199610486134152,
490
+ "learning_rate": 5.335388221955012e-06,
491
+ "loss": 0.0639,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 7.0,
496
+ "grad_norm": 0.5703471993073134,
497
+ "learning_rate": 5.201329700547077e-06,
498
+ "loss": 0.0868,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 7.1,
503
+ "grad_norm": 0.48459618363091345,
504
+ "learning_rate": 5.067126031566988e-06,
505
+ "loss": 0.0603,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 7.2,
510
+ "grad_norm": 0.4221018661488874,
511
+ "learning_rate": 4.932873968433014e-06,
512
+ "loss": 0.0564,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 7.3,
517
+ "grad_norm": 0.4479624595473982,
518
+ "learning_rate": 4.798670299452926e-06,
519
+ "loss": 0.0676,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 7.4,
524
+ "grad_norm": 0.6159422075741188,
525
+ "learning_rate": 4.664611778044988e-06,
526
+ "loss": 0.0969,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 7.5,
531
+ "grad_norm": 0.4778532002901978,
532
+ "learning_rate": 4.530795052984104e-06,
533
+ "loss": 0.0515,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 7.6,
538
+ "grad_norm": 0.519918127935992,
539
+ "learning_rate": 4.397316598723385e-06,
540
+ "loss": 0.0989,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 7.7,
545
+ "grad_norm": 0.5518238984180506,
546
+ "learning_rate": 4.264272645841419e-06,
547
+ "loss": 0.0518,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 7.8,
552
+ "grad_norm": 0.6162483926314095,
553
+ "learning_rate": 4.131759111665349e-06,
554
+ "loss": 0.0357,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 7.9,
559
+ "grad_norm": 0.5410786019743518,
560
+ "learning_rate": 3.999871531119779e-06,
561
+ "loss": 0.0759,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 8.0,
566
+ "grad_norm": 0.34043415172692976,
567
+ "learning_rate": 3.86870498785139e-06,
568
+ "loss": 0.0213,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 8.1,
573
+ "grad_norm": 0.45491123612455514,
574
+ "learning_rate": 3.7383540456788915e-06,
575
+ "loss": 0.0563,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 8.2,
580
+ "grad_norm": 0.405793593930519,
581
+ "learning_rate": 3.6089126804177373e-06,
582
+ "loss": 0.0323,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 8.3,
587
+ "grad_norm": 0.4128595719166626,
588
+ "learning_rate": 3.480474212128766e-06,
589
+ "loss": 0.0497,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 8.4,
594
+ "grad_norm": 0.3943040299802371,
595
+ "learning_rate": 3.3531312378396026e-06,
596
+ "loss": 0.0698,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 8.5,
601
+ "grad_norm": 0.40453966325471846,
602
+ "learning_rate": 3.226975564787322e-06,
603
+ "loss": 0.0485,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 8.6,
608
+ "grad_norm": 0.3527227038646973,
609
+ "learning_rate": 3.1020981442305187e-06,
610
+ "loss": 0.0474,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 8.7,
615
+ "grad_norm": 0.3113189499234012,
616
+ "learning_rate": 2.978589005878476e-06,
617
+ "loss": 0.0223,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 8.8,
622
+ "grad_norm": 0.47969508626162477,
623
+ "learning_rate": 2.8565371929847286e-06,
624
+ "loss": 0.052,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 8.9,
629
+ "grad_norm": 0.45232502093737514,
630
+ "learning_rate": 2.736030698151815e-06,
631
+ "loss": 0.0431,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 9.0,
636
+ "grad_norm": 0.42026240894441896,
637
+ "learning_rate": 2.6171563998934605e-06,
638
+ "loss": 0.0395,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 9.1,
643
+ "grad_norm": 0.3105540765776395,
644
+ "learning_rate": 2.5000000000000015e-06,
645
+ "loss": 0.0422,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 9.2,
650
+ "grad_norm": 0.33705487084981545,
651
+ "learning_rate": 2.384645961752113e-06,
652
+ "loss": 0.0131,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 9.3,
657
+ "grad_norm": 0.2651102122483395,
658
+ "learning_rate": 2.2711774490274767e-06,
659
+ "loss": 0.0389,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 9.4,
664
+ "grad_norm": 0.23502236871851126,
665
+ "learning_rate": 2.159676266344222e-06,
666
+ "loss": 0.0203,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 9.5,
671
+ "grad_norm": 0.2852899739737784,
672
+ "learning_rate": 2.050222799884387e-06,
673
+ "loss": 0.0455,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 9.6,
678
+ "grad_norm": 0.5135177571505845,
679
+ "learning_rate": 1.942895959539939e-06,
680
+ "loss": 0.0374,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 9.7,
685
+ "grad_norm": 0.3109771044901478,
686
+ "learning_rate": 1.8377731220231144e-06,
687
+ "loss": 0.0273,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 9.8,
692
+ "grad_norm": 0.2794741292253182,
693
+ "learning_rate": 1.7349300750820758e-06,
694
+ "loss": 0.0498,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 9.9,
699
+ "grad_norm": 0.46775927936415107,
700
+ "learning_rate": 1.6344409628621482e-06,
701
+ "loss": 0.0501,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 10.0,
706
+ "grad_norm": 0.2544518030008082,
707
+ "learning_rate": 1.5363782324520033e-06,
708
+ "loss": 0.0248,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 10.1,
713
+ "grad_norm": 0.21067652452529076,
714
+ "learning_rate": 1.4408125816532981e-06,
715
+ "loss": 0.0311,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 10.2,
720
+ "grad_norm": 0.16891889075081276,
721
+ "learning_rate": 1.347812908011485e-06,
722
+ "loss": 0.0164,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 10.3,
727
+ "grad_norm": 0.19557809712868815,
728
+ "learning_rate": 1.257446259144494e-06,
729
+ "loss": 0.039,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 10.4,
734
+ "grad_norm": 0.21154537490243636,
735
+ "learning_rate": 1.1697777844051105e-06,
736
+ "loss": 0.027,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 10.5,
741
+ "grad_norm": 0.19588171489260067,
742
+ "learning_rate": 1.0848706879118893e-06,
743
+ "loss": 0.0119,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 10.6,
748
+ "grad_norm": 0.4830359892264546,
749
+ "learning_rate": 1.0027861829824953e-06,
750
+ "loss": 0.0232,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 10.7,
755
+ "grad_norm": 0.2483409232485105,
756
+ "learning_rate": 9.235834480022788e-07,
757
+ "loss": 0.0233,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 10.8,
762
+ "grad_norm": 0.2978512584627456,
763
+ "learning_rate": 8.473195837599419e-07,
764
+ "loss": 0.0419,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 10.9,
769
+ "grad_norm": 0.24272181112135727,
770
+ "learning_rate": 7.740495722810271e-07,
771
+ "loss": 0.0517,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 11.0,
776
+ "grad_norm": 0.26268861351063316,
777
+ "learning_rate": 7.03826237188916e-07,
778
+ "loss": 0.0285,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 11.1,
783
+ "grad_norm": 0.1660762052563307,
784
+ "learning_rate": 6.367002056219285e-07,
785
+ "loss": 0.0228,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 11.2,
790
+ "grad_norm": 0.28125815338610055,
791
+ "learning_rate": 5.727198717339511e-07,
792
+ "loss": 0.0436,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 11.3,
797
+ "grad_norm": 0.1085402493742939,
798
+ "learning_rate": 5.119313618049309e-07,
799
+ "loss": 0.0137,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 11.4,
804
+ "grad_norm": 0.19439728399973843,
805
+ "learning_rate": 4.54378500986381e-07,
806
+ "loss": 0.0318,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 11.5,
811
+ "grad_norm": 0.1411492540257263,
812
+ "learning_rate": 4.001027817058789e-07,
813
+ "loss": 0.0132,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 11.6,
818
+ "grad_norm": 0.2552476524426269,
819
+ "learning_rate": 3.49143333753309e-07,
820
+ "loss": 0.0472,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 11.7,
825
+ "grad_norm": 0.18961590990356175,
826
+ "learning_rate": 3.015368960704584e-07,
827
+ "loss": 0.0225,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 11.8,
832
+ "grad_norm": 0.16134959351312292,
833
+ "learning_rate": 2.573177902642726e-07,
834
+ "loss": 0.01,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 11.9,
839
+ "grad_norm": 0.20865845319758783,
840
+ "learning_rate": 2.1651789586287442e-07,
841
+ "loss": 0.0491,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 12.0,
846
+ "grad_norm": 0.15530459393079682,
847
+ "learning_rate": 1.7916662733218848e-07,
848
+ "loss": 0.0155,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 12.1,
853
+ "grad_norm": 0.1555202802598813,
854
+ "learning_rate": 1.4529091286973994e-07,
855
+ "loss": 0.0133,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 12.2,
860
+ "grad_norm": 0.2052351226381838,
861
+ "learning_rate": 1.1491517499091498e-07,
862
+ "loss": 0.0254,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 12.3,
867
+ "grad_norm": 0.17749939068887433,
868
+ "learning_rate": 8.80613129216762e-08,
869
+ "loss": 0.0222,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 12.4,
874
+ "grad_norm": 0.21338816615021317,
875
+ "learning_rate": 6.474868681043578e-08,
876
+ "loss": 0.0349,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 12.5,
881
+ "grad_norm": 0.16918304347541172,
882
+ "learning_rate": 4.499410377045765e-08,
883
+ "loss": 0.0292,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 12.6,
888
+ "grad_norm": 0.18651719491638674,
889
+ "learning_rate": 2.8811805762860578e-08,
890
+ "loss": 0.0331,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 12.7,
895
+ "grad_norm": 0.18264072089250763,
896
+ "learning_rate": 1.6213459328950355e-08,
897
+ "loss": 0.029,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 12.8,
902
+ "grad_norm": 0.18867489235805426,
903
+ "learning_rate": 7.2081471792911914e-09,
904
+ "loss": 0.0284,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 12.9,
909
+ "grad_norm": 0.19979335321317201,
910
+ "learning_rate": 1.8023616455731253e-09,
911
+ "loss": 0.0269,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 13.0,
916
+ "grad_norm": 0.15388280708793917,
917
+ "learning_rate": 0.0,
918
+ "loss": 0.0146,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 13.0,
923
+ "step": 130,
924
+ "total_flos": 2.50173978574848e+16,
925
+ "train_loss": 0.20831933366134764,
926
+ "train_runtime": 2041.6117,
927
+ "train_samples_per_second": 2.012,
928
+ "train_steps_per_second": 0.064
929
+ }
930
+ ],
931
+ "logging_steps": 1,
932
+ "max_steps": 130,
933
+ "num_input_tokens_seen": 0,
934
+ "num_train_epochs": 13,
935
+ "save_steps": 500,
936
+ "stateful_callbacks": {
937
+ "TrainerControl": {
938
+ "args": {
939
+ "should_epoch_stop": false,
940
+ "should_evaluate": false,
941
+ "should_log": false,
942
+ "should_save": true,
943
+ "should_training_stop": true
944
+ },
945
+ "attributes": {}
946
+ }
947
+ },
948
+ "total_flos": 2.50173978574848e+16,
949
+ "train_batch_size": 1,
950
+ "trial_name": null,
951
+ "trial_params": null
952
+ }
training_loss.png ADDED