sedrickkeh commited on
Commit
4a0841f
·
verified ·
1 Parent(s): de9e5ed

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: fasttext_mixing_domains_top_6
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # fasttext_mixing_domains_top_6
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: fasttext_mixing_domains_top_6
 
16
 
17
  # fasttext_mixing_domains_top_6
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/fasttext_mixing_domains_top_6 dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 73738752491520.0,
4
+ "train_loss": 0.7710517148176829,
5
+ "train_runtime": 7635.6931,
6
+ "train_samples_per_second": 0.981,
7
+ "train_steps_per_second": 0.01
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 73738752491520.0,
4
+ "train_loss": 0.7710517148176829,
5
+ "train_runtime": 7635.6931,
6
+ "train_samples_per_second": 0.981,
7
+ "train_steps_per_second": 0.01
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,588 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
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": 0.038461538461538464,
13
+ "grad_norm": 6.870266914367676,
14
+ "learning_rate": 1.25e-06,
15
+ "loss": 1.1223,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.07692307692307693,
20
+ "grad_norm": 6.60228157043457,
21
+ "learning_rate": 2.5e-06,
22
+ "loss": 1.0548,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.11538461538461539,
27
+ "grad_norm": 6.515733242034912,
28
+ "learning_rate": 3.7500000000000005e-06,
29
+ "loss": 1.052,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.15384615384615385,
34
+ "grad_norm": 5.764657497406006,
35
+ "learning_rate": 5e-06,
36
+ "loss": 1.0166,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.19230769230769232,
41
+ "grad_norm": 4.684140205383301,
42
+ "learning_rate": 6.25e-06,
43
+ "loss": 0.9942,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.23076923076923078,
48
+ "grad_norm": 2.8065361976623535,
49
+ "learning_rate": 7.500000000000001e-06,
50
+ "loss": 0.9359,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.2692307692307692,
55
+ "grad_norm": 4.593384742736816,
56
+ "learning_rate": 8.750000000000001e-06,
57
+ "loss": 0.9657,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.3076923076923077,
62
+ "grad_norm": 4.550309181213379,
63
+ "learning_rate": 1e-05,
64
+ "loss": 0.9009,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.34615384615384615,
69
+ "grad_norm": 4.862745761871338,
70
+ "learning_rate": 9.994965332706574e-06,
71
+ "loss": 0.9548,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.38461538461538464,
76
+ "grad_norm": 4.1590962409973145,
77
+ "learning_rate": 9.979871469976197e-06,
78
+ "loss": 0.8451,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.4230769230769231,
83
+ "grad_norm": 3.6216330528259277,
84
+ "learning_rate": 9.954748808839675e-06,
85
+ "loss": 0.9311,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.46153846153846156,
90
+ "grad_norm": 2.3328566551208496,
91
+ "learning_rate": 9.91964794299315e-06,
92
+ "loss": 0.9269,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.5,
97
+ "grad_norm": 1.803200602531433,
98
+ "learning_rate": 9.874639560909118e-06,
99
+ "loss": 0.8337,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.5384615384615384,
104
+ "grad_norm": 1.7843149900436401,
105
+ "learning_rate": 9.819814303479268e-06,
106
+ "loss": 0.8367,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.5769230769230769,
111
+ "grad_norm": 1.253243327140808,
112
+ "learning_rate": 9.755282581475769e-06,
113
+ "loss": 0.769,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.6153846153846154,
118
+ "grad_norm": 1.2718814611434937,
119
+ "learning_rate": 9.681174353198687e-06,
120
+ "loss": 0.8519,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.6538461538461539,
125
+ "grad_norm": 1.3002601861953735,
126
+ "learning_rate": 9.597638862757255e-06,
127
+ "loss": 0.8114,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.6923076923076923,
132
+ "grad_norm": 1.0596836805343628,
133
+ "learning_rate": 9.504844339512096e-06,
134
+ "loss": 0.7983,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.7307692307692307,
139
+ "grad_norm": 1.2702919244766235,
140
+ "learning_rate": 9.40297765928369e-06,
141
+ "loss": 0.854,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.7692307692307693,
146
+ "grad_norm": 0.8957973122596741,
147
+ "learning_rate": 9.292243968009332e-06,
148
+ "loss": 0.7384,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.8076923076923077,
153
+ "grad_norm": 0.8740140199661255,
154
+ "learning_rate": 9.172866268606514e-06,
155
+ "loss": 0.8076,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.8461538461538461,
160
+ "grad_norm": 0.7290602922439575,
161
+ "learning_rate": 9.045084971874738e-06,
162
+ "loss": 0.7851,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.8846153846153846,
167
+ "grad_norm": 0.7917980551719666,
168
+ "learning_rate": 8.90915741234015e-06,
169
+ "loss": 0.8086,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.9230769230769231,
174
+ "grad_norm": 0.8550074696540833,
175
+ "learning_rate": 8.765357330018056e-06,
176
+ "loss": 0.7766,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.9615384615384616,
181
+ "grad_norm": 0.8657763004302979,
182
+ "learning_rate": 8.613974319136959e-06,
183
+ "loss": 0.8419,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.0,
188
+ "grad_norm": 0.7246716618537903,
189
+ "learning_rate": 8.455313244934324e-06,
190
+ "loss": 0.7583,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.0384615384615385,
195
+ "grad_norm": 0.7091710567474365,
196
+ "learning_rate": 8.289693629698564e-06,
197
+ "loss": 0.7392,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 1.0769230769230769,
202
+ "grad_norm": 0.7319567799568176,
203
+ "learning_rate": 8.117449009293668e-06,
204
+ "loss": 0.7661,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 1.1153846153846154,
209
+ "grad_norm": 0.6999830007553101,
210
+ "learning_rate": 7.938926261462366e-06,
211
+ "loss": 0.7241,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 1.1538461538461537,
216
+ "grad_norm": 0.637765109539032,
217
+ "learning_rate": 7.754484907260513e-06,
218
+ "loss": 0.7571,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 1.1923076923076923,
223
+ "grad_norm": 0.7767643928527832,
224
+ "learning_rate": 7.564496387029532e-06,
225
+ "loss": 0.7495,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 1.2307692307692308,
230
+ "grad_norm": 0.6210612654685974,
231
+ "learning_rate": 7.369343312364994e-06,
232
+ "loss": 0.7911,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 1.2692307692307692,
237
+ "grad_norm": 0.600116491317749,
238
+ "learning_rate": 7.169418695587791e-06,
239
+ "loss": 0.7276,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 1.3076923076923077,
244
+ "grad_norm": 0.6836248636245728,
245
+ "learning_rate": 6.965125158269619e-06,
246
+ "loss": 0.778,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.3461538461538463,
251
+ "grad_norm": 0.6598909497261047,
252
+ "learning_rate": 6.7568741204067145e-06,
253
+ "loss": 0.761,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.3846153846153846,
258
+ "grad_norm": 0.6266419887542725,
259
+ "learning_rate": 6.545084971874738e-06,
260
+ "loss": 0.7089,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.4230769230769231,
265
+ "grad_norm": 0.6317741870880127,
266
+ "learning_rate": 6.330184227833376e-06,
267
+ "loss": 0.7458,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.4615384615384617,
272
+ "grad_norm": 0.4944937825202942,
273
+ "learning_rate": 6.112604669781572e-06,
274
+ "loss": 0.7355,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.5,
279
+ "grad_norm": 0.5044434666633606,
280
+ "learning_rate": 5.892784473993184e-06,
281
+ "loss": 0.7276,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.5384615384615383,
286
+ "grad_norm": 0.6830148696899414,
287
+ "learning_rate": 5.671166329088278e-06,
288
+ "loss": 0.7389,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.5769230769230769,
293
+ "grad_norm": 0.5602949857711792,
294
+ "learning_rate": 5.448196544517168e-06,
295
+ "loss": 0.7485,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.6153846153846154,
300
+ "grad_norm": 0.516609787940979,
301
+ "learning_rate": 5.224324151752575e-06,
302
+ "loss": 0.7459,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.6538461538461537,
307
+ "grad_norm": 0.5174584984779358,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.7106,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.6923076923076923,
314
+ "grad_norm": 0.5429850816726685,
315
+ "learning_rate": 4.775675848247427e-06,
316
+ "loss": 0.7344,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.7307692307692308,
321
+ "grad_norm": 0.5647832751274109,
322
+ "learning_rate": 4.551803455482833e-06,
323
+ "loss": 0.6985,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.7692307692307692,
328
+ "grad_norm": 0.4936504662036896,
329
+ "learning_rate": 4.3288336709117246e-06,
330
+ "loss": 0.7706,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.8076923076923077,
335
+ "grad_norm": 0.4863971471786499,
336
+ "learning_rate": 4.107215526006818e-06,
337
+ "loss": 0.7063,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.8461538461538463,
342
+ "grad_norm": 0.4576539993286133,
343
+ "learning_rate": 3.887395330218429e-06,
344
+ "loss": 0.7289,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.8846153846153846,
349
+ "grad_norm": 0.6159549355506897,
350
+ "learning_rate": 3.669815772166625e-06,
351
+ "loss": 0.6677,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.9230769230769231,
356
+ "grad_norm": 0.48231181502342224,
357
+ "learning_rate": 3.4549150281252635e-06,
358
+ "loss": 0.7245,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.9615384615384617,
363
+ "grad_norm": 0.4837266802787781,
364
+ "learning_rate": 3.2431258795932863e-06,
365
+ "loss": 0.6666,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 2.0,
370
+ "grad_norm": 0.5765633583068848,
371
+ "learning_rate": 3.0348748417303826e-06,
372
+ "loss": 0.7458,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 2.0384615384615383,
377
+ "grad_norm": 0.44854843616485596,
378
+ "learning_rate": 2.83058130441221e-06,
379
+ "loss": 0.6414,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 2.076923076923077,
384
+ "grad_norm": 0.4607446789741516,
385
+ "learning_rate": 2.6306566876350072e-06,
386
+ "loss": 0.665,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 2.1153846153846154,
391
+ "grad_norm": 0.49104422330856323,
392
+ "learning_rate": 2.43550361297047e-06,
393
+ "loss": 0.708,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 2.1538461538461537,
398
+ "grad_norm": 0.5487802624702454,
399
+ "learning_rate": 2.245515092739488e-06,
400
+ "loss": 0.6931,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 2.1923076923076925,
405
+ "grad_norm": 0.5082237124443054,
406
+ "learning_rate": 2.061073738537635e-06,
407
+ "loss": 0.7527,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 2.230769230769231,
412
+ "grad_norm": 0.3936366140842438,
413
+ "learning_rate": 1.8825509907063328e-06,
414
+ "loss": 0.6653,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 2.269230769230769,
419
+ "grad_norm": 0.4543362259864807,
420
+ "learning_rate": 1.7103063703014372e-06,
421
+ "loss": 0.731,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 2.3076923076923075,
426
+ "grad_norm": 0.4479061961174011,
427
+ "learning_rate": 1.544686755065677e-06,
428
+ "loss": 0.6771,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 2.3461538461538463,
433
+ "grad_norm": 0.4659906029701233,
434
+ "learning_rate": 1.3860256808630429e-06,
435
+ "loss": 0.7394,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 2.3846153846153846,
440
+ "grad_norm": 0.46474915742874146,
441
+ "learning_rate": 1.234642669981946e-06,
442
+ "loss": 0.6736,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 2.423076923076923,
447
+ "grad_norm": 0.48529791831970215,
448
+ "learning_rate": 1.0908425876598512e-06,
449
+ "loss": 0.7392,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 2.4615384615384617,
454
+ "grad_norm": 0.4053143560886383,
455
+ "learning_rate": 9.549150281252633e-07,
456
+ "loss": 0.7555,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 2.5,
461
+ "grad_norm": 0.5247453451156616,
462
+ "learning_rate": 8.271337313934869e-07,
463
+ "loss": 0.7029,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 2.5384615384615383,
468
+ "grad_norm": 0.3968586027622223,
469
+ "learning_rate": 7.077560319906696e-07,
470
+ "loss": 0.6822,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 2.5769230769230766,
475
+ "grad_norm": 0.375961571931839,
476
+ "learning_rate": 5.9702234071631e-07,
477
+ "loss": 0.7254,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 2.6153846153846154,
482
+ "grad_norm": 0.41553905606269836,
483
+ "learning_rate": 4.951556604879049e-07,
484
+ "loss": 0.7007,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 2.6538461538461537,
489
+ "grad_norm": 0.38777419924736023,
490
+ "learning_rate": 4.0236113724274716e-07,
491
+ "loss": 0.6582,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.6923076923076925,
496
+ "grad_norm": 0.41188523173332214,
497
+ "learning_rate": 3.18825646801314e-07,
498
+ "loss": 0.6747,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.730769230769231,
503
+ "grad_norm": 0.4232975244522095,
504
+ "learning_rate": 2.447174185242324e-07,
505
+ "loss": 0.6905,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.769230769230769,
510
+ "grad_norm": 0.4132767915725708,
511
+ "learning_rate": 1.801856965207338e-07,
512
+ "loss": 0.7099,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.8076923076923075,
517
+ "grad_norm": 0.3853932023048401,
518
+ "learning_rate": 1.253604390908819e-07,
519
+ "loss": 0.6352,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.8461538461538463,
524
+ "grad_norm": 0.4183899462223053,
525
+ "learning_rate": 8.035205700685167e-08,
526
+ "loss": 0.721,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.8846153846153846,
531
+ "grad_norm": 0.4098947048187256,
532
+ "learning_rate": 4.52511911603265e-08,
533
+ "loss": 0.6852,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.9230769230769234,
538
+ "grad_norm": 0.39528220891952515,
539
+ "learning_rate": 2.012853002380466e-08,
540
+ "loss": 0.6431,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.9615384615384617,
545
+ "grad_norm": 0.406534343957901,
546
+ "learning_rate": 5.034667293427053e-09,
547
+ "loss": 0.7168,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 3.0,
552
+ "grad_norm": 0.35006237030029297,
553
+ "learning_rate": 0.0,
554
+ "loss": 0.6841,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 3.0,
559
+ "step": 78,
560
+ "total_flos": 73738752491520.0,
561
+ "train_loss": 0.7710517148176829,
562
+ "train_runtime": 7635.6931,
563
+ "train_samples_per_second": 0.981,
564
+ "train_steps_per_second": 0.01
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": 73738752491520.0,
585
+ "train_batch_size": 1,
586
+ "trial_name": null,
587
+ "trial_params": null
588
+ }
training_loss.png ADDED