sedrickkeh commited on
Commit
2f6c6a7
·
verified ·
1 Parent(s): 062ea9f

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 +588 -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: distill_r1_code_evol_instruct_baseline
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # distill_r1_code_evol_instruct_baseline
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: distill_r1_code_evol_instruct_baseline
 
16
 
17
  # distill_r1_code_evol_instruct_baseline
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/distill_r1_code_evol_instruct_baseline dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9904153354632586,
3
+ "total_flos": 53089482080256.0,
4
+ "train_loss": 0.8778469868195362,
5
+ "train_runtime": 3457.6659,
6
+ "train_samples_per_second": 2.169,
7
+ "train_steps_per_second": 0.023
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9904153354632586,
3
+ "total_flos": 53089482080256.0,
4
+ "train_loss": 0.8778469868195362,
5
+ "train_runtime": 3457.6659,
6
+ "train_samples_per_second": 2.169,
7
+ "train_steps_per_second": 0.023
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,588 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9904153354632586,
5
+ "eval_steps": 500,
6
+ "global_step": 78,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.038338658146964855,
13
+ "grad_norm": 6.45109748840332,
14
+ "learning_rate": 1.25e-06,
15
+ "loss": 1.2212,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.07667731629392971,
20
+ "grad_norm": 6.449772834777832,
21
+ "learning_rate": 2.5e-06,
22
+ "loss": 1.2011,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.11501597444089456,
27
+ "grad_norm": 6.236454963684082,
28
+ "learning_rate": 3.7500000000000005e-06,
29
+ "loss": 1.1949,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.15335463258785942,
34
+ "grad_norm": 6.070368766784668,
35
+ "learning_rate": 5e-06,
36
+ "loss": 1.2172,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.19169329073482427,
41
+ "grad_norm": 4.3351287841796875,
42
+ "learning_rate": 6.25e-06,
43
+ "loss": 1.1609,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.23003194888178913,
48
+ "grad_norm": 2.6603915691375732,
49
+ "learning_rate": 7.500000000000001e-06,
50
+ "loss": 1.0722,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.268370607028754,
55
+ "grad_norm": 4.560462951660156,
56
+ "learning_rate": 8.750000000000001e-06,
57
+ "loss": 1.0798,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.30670926517571884,
62
+ "grad_norm": 5.290356159210205,
63
+ "learning_rate": 1e-05,
64
+ "loss": 1.1219,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.3450479233226837,
69
+ "grad_norm": 4.381709098815918,
70
+ "learning_rate": 9.994965332706574e-06,
71
+ "loss": 1.0392,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.38338658146964855,
76
+ "grad_norm": 4.178859710693359,
77
+ "learning_rate": 9.979871469976197e-06,
78
+ "loss": 1.0663,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.4217252396166134,
83
+ "grad_norm": 3.180849552154541,
84
+ "learning_rate": 9.954748808839675e-06,
85
+ "loss": 1.031,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.46006389776357826,
90
+ "grad_norm": 2.457411289215088,
91
+ "learning_rate": 9.91964794299315e-06,
92
+ "loss": 1.0179,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.4984025559105431,
97
+ "grad_norm": 2.3789966106414795,
98
+ "learning_rate": 9.874639560909118e-06,
99
+ "loss": 0.967,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.536741214057508,
104
+ "grad_norm": 1.7590055465698242,
105
+ "learning_rate": 9.819814303479268e-06,
106
+ "loss": 0.9176,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.5750798722044729,
111
+ "grad_norm": 1.504982829093933,
112
+ "learning_rate": 9.755282581475769e-06,
113
+ "loss": 0.9332,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.6134185303514377,
118
+ "grad_norm": 1.328847885131836,
119
+ "learning_rate": 9.681174353198687e-06,
120
+ "loss": 0.9285,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.6517571884984026,
125
+ "grad_norm": 1.3487250804901123,
126
+ "learning_rate": 9.597638862757255e-06,
127
+ "loss": 0.9548,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.6900958466453674,
132
+ "grad_norm": 1.309167742729187,
133
+ "learning_rate": 9.504844339512096e-06,
134
+ "loss": 0.8749,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.7284345047923323,
139
+ "grad_norm": 1.07999587059021,
140
+ "learning_rate": 9.40297765928369e-06,
141
+ "loss": 0.906,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.7667731629392971,
146
+ "grad_norm": 0.9898855686187744,
147
+ "learning_rate": 9.292243968009332e-06,
148
+ "loss": 0.8826,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.805111821086262,
153
+ "grad_norm": 1.084998369216919,
154
+ "learning_rate": 9.172866268606514e-06,
155
+ "loss": 0.884,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.8434504792332268,
160
+ "grad_norm": 0.9995360374450684,
161
+ "learning_rate": 9.045084971874738e-06,
162
+ "loss": 0.8734,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.8817891373801917,
167
+ "grad_norm": 0.914259672164917,
168
+ "learning_rate": 8.90915741234015e-06,
169
+ "loss": 0.8466,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.9201277955271565,
174
+ "grad_norm": 0.8691526651382446,
175
+ "learning_rate": 8.765357330018056e-06,
176
+ "loss": 0.9043,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.9584664536741214,
181
+ "grad_norm": 0.8191248774528503,
182
+ "learning_rate": 8.613974319136959e-06,
183
+ "loss": 0.9746,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.9968051118210862,
188
+ "grad_norm": 0.9226800799369812,
189
+ "learning_rate": 8.455313244934324e-06,
190
+ "loss": 0.8703,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.035143769968051,
195
+ "grad_norm": 2.459444046020508,
196
+ "learning_rate": 8.289693629698564e-06,
197
+ "loss": 1.3673,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 1.073482428115016,
202
+ "grad_norm": 0.8009559512138367,
203
+ "learning_rate": 8.117449009293668e-06,
204
+ "loss": 0.8485,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 1.1118210862619808,
209
+ "grad_norm": 0.703082799911499,
210
+ "learning_rate": 7.938926261462366e-06,
211
+ "loss": 0.8098,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 1.1501597444089458,
216
+ "grad_norm": 0.7537962794303894,
217
+ "learning_rate": 7.754484907260513e-06,
218
+ "loss": 0.8444,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 1.1884984025559104,
223
+ "grad_norm": 0.760931134223938,
224
+ "learning_rate": 7.564496387029532e-06,
225
+ "loss": 0.8598,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 1.2268370607028753,
230
+ "grad_norm": 0.7525911331176758,
231
+ "learning_rate": 7.369343312364994e-06,
232
+ "loss": 0.865,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 1.2651757188498403,
237
+ "grad_norm": 0.723669707775116,
238
+ "learning_rate": 7.169418695587791e-06,
239
+ "loss": 0.7959,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 1.3035143769968052,
244
+ "grad_norm": 0.7163628339767456,
245
+ "learning_rate": 6.965125158269619e-06,
246
+ "loss": 0.8051,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.34185303514377,
251
+ "grad_norm": 0.6843879222869873,
252
+ "learning_rate": 6.7568741204067145e-06,
253
+ "loss": 0.828,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.3801916932907348,
258
+ "grad_norm": 0.6427307724952698,
259
+ "learning_rate": 6.545084971874738e-06,
260
+ "loss": 0.854,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.4185303514376997,
265
+ "grad_norm": 0.7232085466384888,
266
+ "learning_rate": 6.330184227833376e-06,
267
+ "loss": 0.8848,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.4568690095846646,
272
+ "grad_norm": 0.7611010074615479,
273
+ "learning_rate": 6.112604669781572e-06,
274
+ "loss": 0.6879,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.4952076677316293,
279
+ "grad_norm": 0.7250047922134399,
280
+ "learning_rate": 5.892784473993184e-06,
281
+ "loss": 0.8684,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.5335463258785942,
286
+ "grad_norm": 0.633452832698822,
287
+ "learning_rate": 5.671166329088278e-06,
288
+ "loss": 0.8257,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.571884984025559,
293
+ "grad_norm": 0.6049233078956604,
294
+ "learning_rate": 5.448196544517168e-06,
295
+ "loss": 0.8012,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.610223642172524,
300
+ "grad_norm": 0.701932430267334,
301
+ "learning_rate": 5.224324151752575e-06,
302
+ "loss": 0.8206,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.648562300319489,
307
+ "grad_norm": 0.626121997833252,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.8031,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.6869009584664538,
314
+ "grad_norm": 0.6095514297485352,
315
+ "learning_rate": 4.775675848247427e-06,
316
+ "loss": 0.8131,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.7252396166134185,
321
+ "grad_norm": 0.6313042044639587,
322
+ "learning_rate": 4.551803455482833e-06,
323
+ "loss": 0.8061,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.7635782747603834,
328
+ "grad_norm": 0.6074307560920715,
329
+ "learning_rate": 4.3288336709117246e-06,
330
+ "loss": 0.8172,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.8019169329073481,
335
+ "grad_norm": 0.6239637732505798,
336
+ "learning_rate": 4.107215526006818e-06,
337
+ "loss": 0.8394,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.840255591054313,
342
+ "grad_norm": 0.6018702983856201,
343
+ "learning_rate": 3.887395330218429e-06,
344
+ "loss": 0.8024,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.878594249201278,
349
+ "grad_norm": 0.6898264288902283,
350
+ "learning_rate": 3.669815772166625e-06,
351
+ "loss": 0.8907,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.9169329073482428,
356
+ "grad_norm": 0.5472529530525208,
357
+ "learning_rate": 3.4549150281252635e-06,
358
+ "loss": 0.7073,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.9552715654952078,
363
+ "grad_norm": 0.5887239575386047,
364
+ "learning_rate": 3.2431258795932863e-06,
365
+ "loss": 0.7974,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.9936102236421727,
370
+ "grad_norm": 0.5762373805046082,
371
+ "learning_rate": 3.0348748417303826e-06,
372
+ "loss": 0.8499,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 2.0319488817891376,
377
+ "grad_norm": 1.788190484046936,
378
+ "learning_rate": 2.83058130441221e-06,
379
+ "loss": 1.4672,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 2.070287539936102,
384
+ "grad_norm": 0.6082499027252197,
385
+ "learning_rate": 2.6306566876350072e-06,
386
+ "loss": 0.7681,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 2.108626198083067,
391
+ "grad_norm": 0.5818493962287903,
392
+ "learning_rate": 2.43550361297047e-06,
393
+ "loss": 0.7296,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 2.146964856230032,
398
+ "grad_norm": 0.4775056540966034,
399
+ "learning_rate": 2.245515092739488e-06,
400
+ "loss": 0.7339,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 2.1853035143769968,
405
+ "grad_norm": 0.48535844683647156,
406
+ "learning_rate": 2.061073738537635e-06,
407
+ "loss": 0.7905,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 2.2236421725239617,
412
+ "grad_norm": 0.5611085295677185,
413
+ "learning_rate": 1.8825509907063328e-06,
414
+ "loss": 0.7852,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 2.2619808306709266,
419
+ "grad_norm": 0.554451048374176,
420
+ "learning_rate": 1.7103063703014372e-06,
421
+ "loss": 0.7263,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 2.3003194888178915,
426
+ "grad_norm": 0.5591139793395996,
427
+ "learning_rate": 1.544686755065677e-06,
428
+ "loss": 0.7394,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 2.3386581469648564,
433
+ "grad_norm": 0.5835963487625122,
434
+ "learning_rate": 1.3860256808630429e-06,
435
+ "loss": 0.7811,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 2.376996805111821,
440
+ "grad_norm": 0.4586201608181,
441
+ "learning_rate": 1.234642669981946e-06,
442
+ "loss": 0.6595,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 2.415335463258786,
447
+ "grad_norm": 0.6206969618797302,
448
+ "learning_rate": 1.0908425876598512e-06,
449
+ "loss": 0.9082,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 2.4536741214057507,
454
+ "grad_norm": 0.5300808548927307,
455
+ "learning_rate": 9.549150281252633e-07,
456
+ "loss": 0.7043,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 2.4920127795527156,
461
+ "grad_norm": 0.5531863570213318,
462
+ "learning_rate": 8.271337313934869e-07,
463
+ "loss": 0.7529,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 2.5303514376996805,
468
+ "grad_norm": 0.5038548111915588,
469
+ "learning_rate": 7.077560319906696e-07,
470
+ "loss": 0.7902,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 2.5686900958466454,
475
+ "grad_norm": 0.4608278274536133,
476
+ "learning_rate": 5.9702234071631e-07,
477
+ "loss": 0.7202,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 2.6070287539936103,
482
+ "grad_norm": 0.5147573351860046,
483
+ "learning_rate": 4.951556604879049e-07,
484
+ "loss": 0.8864,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 2.6453674121405752,
489
+ "grad_norm": 0.5285633206367493,
490
+ "learning_rate": 4.0236113724274716e-07,
491
+ "loss": 0.7205,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.68370607028754,
496
+ "grad_norm": 0.511046290397644,
497
+ "learning_rate": 3.18825646801314e-07,
498
+ "loss": 0.72,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.722044728434505,
503
+ "grad_norm": 0.5221746563911438,
504
+ "learning_rate": 2.447174185242324e-07,
505
+ "loss": 0.7959,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.7603833865814695,
510
+ "grad_norm": 0.504964292049408,
511
+ "learning_rate": 1.801856965207338e-07,
512
+ "loss": 0.7179,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.7987220447284344,
517
+ "grad_norm": 0.4362109899520874,
518
+ "learning_rate": 1.253604390908819e-07,
519
+ "loss": 0.6673,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.8370607028753994,
524
+ "grad_norm": 0.5560856461524963,
525
+ "learning_rate": 8.035205700685167e-08,
526
+ "loss": 0.8126,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.8753993610223643,
531
+ "grad_norm": 0.5098027586936951,
532
+ "learning_rate": 4.52511911603265e-08,
533
+ "loss": 0.7562,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.913738019169329,
538
+ "grad_norm": 0.494514137506485,
539
+ "learning_rate": 2.012853002380466e-08,
540
+ "loss": 0.7857,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.952076677316294,
545
+ "grad_norm": 0.5156562924385071,
546
+ "learning_rate": 5.034667293427053e-09,
547
+ "loss": 0.7503,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 2.9904153354632586,
552
+ "grad_norm": 0.4876989722251892,
553
+ "learning_rate": 0.0,
554
+ "loss": 0.7684,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 2.9904153354632586,
559
+ "step": 78,
560
+ "total_flos": 53089482080256.0,
561
+ "train_loss": 0.8778469868195362,
562
+ "train_runtime": 3457.6659,
563
+ "train_samples_per_second": 2.169,
564
+ "train_steps_per_second": 0.023
565
+ }
566
+ ],
567
+ "logging_steps": 1.0,
568
+ "max_steps": 78,
569
+ "num_input_tokens_seen": 0,
570
+ "num_train_epochs": 3,
571
+ "save_steps": 500,
572
+ "stateful_callbacks": {
573
+ "TrainerControl": {
574
+ "args": {
575
+ "should_epoch_stop": false,
576
+ "should_evaluate": false,
577
+ "should_log": false,
578
+ "should_save": true,
579
+ "should_training_stop": true
580
+ },
581
+ "attributes": {}
582
+ }
583
+ },
584
+ "total_flos": 53089482080256.0,
585
+ "train_batch_size": 1,
586
+ "trial_name": null,
587
+ "trial_params": null
588
+ }
training_loss.png ADDED