sedrickkeh commited on
Commit
19f726d
·
verified ·
1 Parent(s): ba3a71e

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 +714 -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: 32k_test_dummy
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # 32k_test_dummy
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: 32k_test_dummy
 
16
 
17
  # 32k_test_dummy
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/s1K_reformat dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 5914053476352.0,
4
+ "train_loss": 0.2707547560178985,
5
+ "train_runtime": 421.6069,
6
+ "train_samples_per_second": 7.116,
7
+ "train_steps_per_second": 0.228
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 5914053476352.0,
4
+ "train_loss": 0.2707547560178985,
5
+ "train_runtime": 421.6069,
6
+ "train_samples_per_second": 7.116,
7
+ "train_steps_per_second": 0.228
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,714 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 96,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03125,
13
+ "grad_norm": 5.212899684906006,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 0.5701,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0625,
20
+ "grad_norm": 5.509668827056885,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 0.6002,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.09375,
27
+ "grad_norm": 5.713456630706787,
28
+ "learning_rate": 3e-06,
29
+ "loss": 0.578,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.125,
34
+ "grad_norm": 4.650047779083252,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 0.5471,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.15625,
41
+ "grad_norm": 4.2114577293396,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.6588,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.1875,
48
+ "grad_norm": 3.0272881984710693,
49
+ "learning_rate": 6e-06,
50
+ "loss": 0.5074,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.21875,
55
+ "grad_norm": 2.395081043243408,
56
+ "learning_rate": 7e-06,
57
+ "loss": 0.484,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.25,
62
+ "grad_norm": 5.17173957824707,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 0.6328,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.28125,
69
+ "grad_norm": 2.2946617603302,
70
+ "learning_rate": 9e-06,
71
+ "loss": 0.47,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.3125,
76
+ "grad_norm": 3.2116971015930176,
77
+ "learning_rate": 1e-05,
78
+ "loss": 0.4675,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.34375,
83
+ "grad_norm": 7.591786861419678,
84
+ "learning_rate": 9.996664241851197e-06,
85
+ "loss": 0.6794,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.375,
90
+ "grad_norm": 2.43316912651062,
91
+ "learning_rate": 9.986661418317759e-06,
92
+ "loss": 0.4242,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.40625,
97
+ "grad_norm": 2.3921120166778564,
98
+ "learning_rate": 9.970004876199731e-06,
99
+ "loss": 0.4481,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.4375,
104
+ "grad_norm": 6.6794328689575195,
105
+ "learning_rate": 9.946716840375552e-06,
106
+ "loss": 0.5388,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.46875,
111
+ "grad_norm": 1.9656387567520142,
112
+ "learning_rate": 9.91682838414733e-06,
113
+ "loss": 0.4292,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.5,
118
+ "grad_norm": 1.9465067386627197,
119
+ "learning_rate": 9.880379387779637e-06,
120
+ "loss": 0.3977,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.53125,
125
+ "grad_norm": 1.9357396364212036,
126
+ "learning_rate": 9.837418485287126e-06,
127
+ "loss": 0.418,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.5625,
132
+ "grad_norm": 1.4802380800247192,
133
+ "learning_rate": 9.78800299954203e-06,
134
+ "loss": 0.382,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.59375,
139
+ "grad_norm": 1.3597159385681152,
140
+ "learning_rate": 9.732198865788047e-06,
141
+ "loss": 0.3844,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.625,
146
+ "grad_norm": 1.699665904045105,
147
+ "learning_rate": 9.670080543662742e-06,
148
+ "loss": 0.3707,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.65625,
153
+ "grad_norm": 2.6564078330993652,
154
+ "learning_rate": 9.601730917845798e-06,
155
+ "loss": 0.5049,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.6875,
160
+ "grad_norm": 1.8858695030212402,
161
+ "learning_rate": 9.527241187465735e-06,
162
+ "loss": 0.3874,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.71875,
167
+ "grad_norm": 1.5440151691436768,
168
+ "learning_rate": 9.446710744412595e-06,
169
+ "loss": 0.3295,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.75,
174
+ "grad_norm": 2.438760280609131,
175
+ "learning_rate": 9.36024704071904e-06,
176
+ "loss": 0.3313,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.78125,
181
+ "grad_norm": 1.462939739227295,
182
+ "learning_rate": 9.267965445186733e-06,
183
+ "loss": 0.3649,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.8125,
188
+ "grad_norm": 3.8231046199798584,
189
+ "learning_rate": 9.16998908944939e-06,
190
+ "loss": 0.4084,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.84375,
195
+ "grad_norm": 1.501857876777649,
196
+ "learning_rate": 9.066448703677828e-06,
197
+ "loss": 0.3463,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.875,
202
+ "grad_norm": 4.742476463317871,
203
+ "learning_rate": 8.957482442146271e-06,
204
+ "loss": 0.4789,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.90625,
209
+ "grad_norm": 2.2912559509277344,
210
+ "learning_rate": 8.843235698892661e-06,
211
+ "loss": 0.4739,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.9375,
216
+ "grad_norm": 1.3147192001342773,
217
+ "learning_rate": 8.72386091371891e-06,
218
+ "loss": 0.3864,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.96875,
223
+ "grad_norm": 1.2147444486618042,
224
+ "learning_rate": 8.599517368789981e-06,
225
+ "loss": 0.3181,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 1.0,
230
+ "grad_norm": 1.0684988498687744,
231
+ "learning_rate": 8.470370976103171e-06,
232
+ "loss": 0.2821,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 1.03125,
237
+ "grad_norm": 2.0786163806915283,
238
+ "learning_rate": 8.336594056111197e-06,
239
+ "loss": 0.288,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 1.0625,
244
+ "grad_norm": 1.4894177913665771,
245
+ "learning_rate": 8.198365107794457e-06,
246
+ "loss": 0.275,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.09375,
251
+ "grad_norm": 1.039533019065857,
252
+ "learning_rate": 8.055868570489247e-06,
253
+ "loss": 0.2725,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.125,
258
+ "grad_norm": 1.105832815170288,
259
+ "learning_rate": 7.909294577789765e-06,
260
+ "loss": 0.2298,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.15625,
265
+ "grad_norm": 0.9874384999275208,
266
+ "learning_rate": 7.75883870385223e-06,
267
+ "loss": 0.2389,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.1875,
272
+ "grad_norm": 1.0676255226135254,
273
+ "learning_rate": 7.604701702439652e-06,
274
+ "loss": 0.2394,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.21875,
279
+ "grad_norm": 1.0422248840332031,
280
+ "learning_rate": 7.447089239055428e-06,
281
+ "loss": 0.2535,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.25,
286
+ "grad_norm": 1.4323464632034302,
287
+ "learning_rate": 7.286211616523193e-06,
288
+ "loss": 0.2704,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.28125,
293
+ "grad_norm": 1.0653886795043945,
294
+ "learning_rate": 7.122283494379076e-06,
295
+ "loss": 0.2416,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.3125,
300
+ "grad_norm": 3.6688082218170166,
301
+ "learning_rate": 6.95552360245078e-06,
302
+ "loss": 0.2793,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.34375,
307
+ "grad_norm": 2.467761993408203,
308
+ "learning_rate": 6.786154449005664e-06,
309
+ "loss": 0.2504,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.375,
314
+ "grad_norm": 1.1717958450317383,
315
+ "learning_rate": 6.614402023857231e-06,
316
+ "loss": 0.2549,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.40625,
321
+ "grad_norm": 2.00671648979187,
322
+ "learning_rate": 6.440495496826189e-06,
323
+ "loss": 0.2179,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.4375,
328
+ "grad_norm": 1.0691853761672974,
329
+ "learning_rate": 6.264666911958404e-06,
330
+ "loss": 0.1993,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.46875,
335
+ "grad_norm": 2.143359661102295,
336
+ "learning_rate": 6.087150877907786e-06,
337
+ "loss": 0.2553,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.5,
342
+ "grad_norm": 3.1730265617370605,
343
+ "learning_rate": 5.908184254897183e-06,
344
+ "loss": 0.2949,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.53125,
349
+ "grad_norm": 1.2100728750228882,
350
+ "learning_rate": 5.728005838675026e-06,
351
+ "loss": 0.2204,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.5625,
356
+ "grad_norm": 1.1710706949234009,
357
+ "learning_rate": 5.546856041889374e-06,
358
+ "loss": 0.2082,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.59375,
363
+ "grad_norm": 1.1728243827819824,
364
+ "learning_rate": 5.364976573304538e-06,
365
+ "loss": 0.2052,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.625,
370
+ "grad_norm": 1.1219596862792969,
371
+ "learning_rate": 5.182610115288296e-06,
372
+ "loss": 0.2308,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 1.65625,
377
+ "grad_norm": 1.3272408246994019,
378
+ "learning_rate": 5e-06,
379
+ "loss": 0.2448,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 1.6875,
384
+ "grad_norm": 1.3118982315063477,
385
+ "learning_rate": 4.817389884711706e-06,
386
+ "loss": 0.2229,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 1.71875,
391
+ "grad_norm": 1.0828900337219238,
392
+ "learning_rate": 4.635023426695462e-06,
393
+ "loss": 0.216,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 1.75,
398
+ "grad_norm": 1.1662155389785767,
399
+ "learning_rate": 4.4531439581106295e-06,
400
+ "loss": 0.1926,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 1.78125,
405
+ "grad_norm": 1.1041769981384277,
406
+ "learning_rate": 4.271994161324977e-06,
407
+ "loss": 0.2045,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 1.8125,
412
+ "grad_norm": 1.1366336345672607,
413
+ "learning_rate": 4.091815745102818e-06,
414
+ "loss": 0.2125,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 1.84375,
419
+ "grad_norm": 1.0897059440612793,
420
+ "learning_rate": 3.912849122092216e-06,
421
+ "loss": 0.2282,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 1.875,
426
+ "grad_norm": 0.9965717196464539,
427
+ "learning_rate": 3.7353330880415963e-06,
428
+ "loss": 0.2317,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.90625,
433
+ "grad_norm": 1.1308876276016235,
434
+ "learning_rate": 3.5595045031738123e-06,
435
+ "loss": 0.2459,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.9375,
440
+ "grad_norm": 1.449512243270874,
441
+ "learning_rate": 3.3855979761427705e-06,
442
+ "loss": 0.2836,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 1.96875,
447
+ "grad_norm": 1.0659527778625488,
448
+ "learning_rate": 3.2138455509943365e-06,
449
+ "loss": 0.2508,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 2.0,
454
+ "grad_norm": 1.1291404962539673,
455
+ "learning_rate": 3.044476397549221e-06,
456
+ "loss": 0.1681,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 2.03125,
461
+ "grad_norm": 0.9167552590370178,
462
+ "learning_rate": 2.8777165056209256e-06,
463
+ "loss": 0.1305,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 2.0625,
468
+ "grad_norm": 0.9367494583129883,
469
+ "learning_rate": 2.7137883834768076e-06,
470
+ "loss": 0.1462,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 2.09375,
475
+ "grad_norm": 0.7913087010383606,
476
+ "learning_rate": 2.5529107609445737e-06,
477
+ "loss": 0.1384,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 2.125,
482
+ "grad_norm": 0.8486475944519043,
483
+ "learning_rate": 2.3952982975603494e-06,
484
+ "loss": 0.1262,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 2.15625,
489
+ "grad_norm": 0.8827183246612549,
490
+ "learning_rate": 2.2411612961477704e-06,
491
+ "loss": 0.1297,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.1875,
496
+ "grad_norm": 0.9331244230270386,
497
+ "learning_rate": 2.0907054222102367e-06,
498
+ "loss": 0.127,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.21875,
503
+ "grad_norm": 0.8335605263710022,
504
+ "learning_rate": 1.944131429510754e-06,
505
+ "loss": 0.131,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.25,
510
+ "grad_norm": 0.7966263890266418,
511
+ "learning_rate": 1.8016348922055448e-06,
512
+ "loss": 0.1119,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.28125,
517
+ "grad_norm": 0.9054017066955566,
518
+ "learning_rate": 1.6634059438888034e-06,
519
+ "loss": 0.1131,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.3125,
524
+ "grad_norm": 1.0144445896148682,
525
+ "learning_rate": 1.5296290238968303e-06,
526
+ "loss": 0.1147,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.34375,
531
+ "grad_norm": 0.9999849796295166,
532
+ "learning_rate": 1.4004826312100218e-06,
533
+ "loss": 0.1219,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.375,
538
+ "grad_norm": 1.117247462272644,
539
+ "learning_rate": 1.2761390862810907e-06,
540
+ "loss": 0.1178,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.40625,
545
+ "grad_norm": 1.0464344024658203,
546
+ "learning_rate": 1.1567643011073393e-06,
547
+ "loss": 0.1102,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 2.4375,
552
+ "grad_norm": 1.0447325706481934,
553
+ "learning_rate": 1.04251755785373e-06,
554
+ "loss": 0.1077,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 2.46875,
559
+ "grad_norm": 1.0977072715759277,
560
+ "learning_rate": 9.335512963221732e-07,
561
+ "loss": 0.1045,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 2.5,
566
+ "grad_norm": 1.6026099920272827,
567
+ "learning_rate": 8.30010910550611e-07,
568
+ "loss": 0.1298,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 2.53125,
573
+ "grad_norm": 0.9658783674240112,
574
+ "learning_rate": 7.320345548132679e-07,
575
+ "loss": 0.1336,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 2.5625,
580
+ "grad_norm": 1.047508716583252,
581
+ "learning_rate": 6.397529592809615e-07,
582
+ "loss": 0.1017,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 2.59375,
587
+ "grad_norm": 1.0574610233306885,
588
+ "learning_rate": 5.532892555874059e-07,
589
+ "loss": 0.1058,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 2.625,
594
+ "grad_norm": 1.155909776687622,
595
+ "learning_rate": 4.727588125342669e-07,
596
+ "loss": 0.1174,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 2.65625,
601
+ "grad_norm": 1.0230557918548584,
602
+ "learning_rate": 3.9826908215420344e-07,
603
+ "loss": 0.1076,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 2.6875,
608
+ "grad_norm": 0.9394001960754395,
609
+ "learning_rate": 3.299194563372604e-07,
610
+ "loss": 0.1411,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 2.71875,
615
+ "grad_norm": 0.9740204811096191,
616
+ "learning_rate": 2.67801134211953e-07,
617
+ "loss": 0.1101,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 2.75,
622
+ "grad_norm": 1.1990844011306763,
623
+ "learning_rate": 2.1199700045797077e-07,
624
+ "loss": 0.1397,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 2.78125,
629
+ "grad_norm": 0.9166547060012817,
630
+ "learning_rate": 1.6258151471287397e-07,
631
+ "loss": 0.1053,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 2.8125,
636
+ "grad_norm": 1.7290699481964111,
637
+ "learning_rate": 1.196206122203647e-07,
638
+ "loss": 0.1197,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 2.84375,
643
+ "grad_norm": 0.9263373017311096,
644
+ "learning_rate": 8.317161585266964e-08,
645
+ "loss": 0.1004,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 2.875,
650
+ "grad_norm": 0.9613826870918274,
651
+ "learning_rate": 5.3283159624448745e-08,
652
+ "loss": 0.1161,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 2.90625,
657
+ "grad_norm": 0.9571884870529175,
658
+ "learning_rate": 2.9995123800270476e-08,
659
+ "loss": 0.1109,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 2.9375,
664
+ "grad_norm": 0.9712323546409607,
665
+ "learning_rate": 1.333858168224178e-08,
666
+ "loss": 0.109,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 2.96875,
671
+ "grad_norm": 0.9421584606170654,
672
+ "learning_rate": 3.3357581488030476e-09,
673
+ "loss": 0.1002,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 3.0,
678
+ "grad_norm": 0.7927206158638,
679
+ "learning_rate": 0.0,
680
+ "loss": 0.0853,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 3.0,
685
+ "step": 96,
686
+ "total_flos": 5914053476352.0,
687
+ "train_loss": 0.2707547560178985,
688
+ "train_runtime": 421.6069,
689
+ "train_samples_per_second": 7.116,
690
+ "train_steps_per_second": 0.228
691
+ }
692
+ ],
693
+ "logging_steps": 1.0,
694
+ "max_steps": 96,
695
+ "num_input_tokens_seen": 0,
696
+ "num_train_epochs": 3,
697
+ "save_steps": 500,
698
+ "stateful_callbacks": {
699
+ "TrainerControl": {
700
+ "args": {
701
+ "should_epoch_stop": false,
702
+ "should_evaluate": false,
703
+ "should_log": false,
704
+ "should_save": true,
705
+ "should_training_stop": true
706
+ },
707
+ "attributes": {}
708
+ }
709
+ },
710
+ "total_flos": 5914053476352.0,
711
+ "train_batch_size": 1,
712
+ "trial_name": null,
713
+ "trial_params": null
714
+ }
training_loss.png ADDED