gsmyrnis commited on
Commit
aa9906e
·
verified ·
1 Parent(s): b0d3cd7

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: mistralai/Mistral-7B-v0.3
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: mistral_7b_0-3_webinstruct_original_750k_uniform
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # mistral_7b_0-3_webinstruct_original_750k_uniform
17
 
18
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.3616
21
 
 
4
  base_model: mistralai/Mistral-7B-v0.3
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: mistral_7b_0-3_webinstruct_original_750k_uniform
 
16
 
17
  # mistral_7b_0-3_webinstruct_original_750k_uniform
18
 
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the mlfoundations-dev/webinstruct_original_750k_uniform dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.3616
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.36160025000572205,
4
+ "eval_runtime": 22.9973,
5
+ "eval_samples_per_second": 291.904,
6
+ "eval_steps_per_second": 1.174,
7
+ "total_flos": 1256277934080000.0,
8
+ "train_loss": 0.38879382991790773,
9
+ "train_runtime": 4686.8691,
10
+ "train_samples_per_second": 81.64,
11
+ "train_steps_per_second": 0.16
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.36160025000572205,
4
+ "eval_runtime": 22.9973,
5
+ "eval_samples_per_second": 291.904,
6
+ "eval_steps_per_second": 1.174
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1256277934080000.0,
4
+ "train_loss": 0.38879382991790773,
5
+ "train_runtime": 4686.8691,
6
+ "train_samples_per_second": 81.64,
7
+ "train_steps_per_second": 0.16
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,591 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "grad_norm": 15.310038127586646,
14
+ "learning_rate": 2.8768699654775607e-08,
15
+ "loss": 0.5928,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.08,
20
+ "grad_norm": 14.307371238653309,
21
+ "learning_rate": 5.7537399309551214e-08,
22
+ "loss": 0.5886,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.12,
27
+ "grad_norm": 11.030093905097976,
28
+ "learning_rate": 8.630609896432682e-08,
29
+ "loss": 0.5803,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.16,
34
+ "grad_norm": 5.993337842833648,
35
+ "learning_rate": 1.1507479861910243e-07,
36
+ "loss": 0.548,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.2,
41
+ "grad_norm": 3.710083568844066,
42
+ "learning_rate": 1.4384349827387802e-07,
43
+ "loss": 0.5181,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.24,
48
+ "grad_norm": 1.9705824009872897,
49
+ "learning_rate": 1.7261219792865363e-07,
50
+ "loss": 0.4924,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.28,
55
+ "grad_norm": 1.2663369930235067,
56
+ "learning_rate": 2.0138089758342927e-07,
57
+ "loss": 0.4774,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.32,
62
+ "grad_norm": 1.3138855186585094,
63
+ "learning_rate": 2.3014959723820486e-07,
64
+ "loss": 0.4606,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.36,
69
+ "grad_norm": 1.1467390567333238,
70
+ "learning_rate": 2.5891829689298047e-07,
71
+ "loss": 0.4512,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.4,
76
+ "grad_norm": 1.0129633422067545,
77
+ "learning_rate": 2.8768699654775605e-07,
78
+ "loss": 0.438,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.44,
83
+ "grad_norm": 1.3367425686963006,
84
+ "learning_rate": 3.164556962025317e-07,
85
+ "loss": 0.4272,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.48,
90
+ "grad_norm": 0.9911516620221612,
91
+ "learning_rate": 3.4522439585730727e-07,
92
+ "loss": 0.4239,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.52,
97
+ "grad_norm": 1.1381388271727326,
98
+ "learning_rate": 3.739930955120829e-07,
99
+ "loss": 0.4188,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.56,
104
+ "grad_norm": 1.494070752193929,
105
+ "learning_rate": 4.0276179516685854e-07,
106
+ "loss": 0.4155,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.6,
111
+ "grad_norm": 1.6657782892459603,
112
+ "learning_rate": 4.315304948216341e-07,
113
+ "loss": 0.4192,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.64,
118
+ "grad_norm": 1.3914607726604022,
119
+ "learning_rate": 4.602991944764097e-07,
120
+ "loss": 0.4118,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.68,
125
+ "grad_norm": 1.0670270762955518,
126
+ "learning_rate": 4.890678941311853e-07,
127
+ "loss": 0.4118,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.72,
132
+ "grad_norm": 1.1607821737201103,
133
+ "learning_rate": 5.178365937859609e-07,
134
+ "loss": 0.406,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.76,
139
+ "grad_norm": 1.0877519040830297,
140
+ "learning_rate": 5.466052934407366e-07,
141
+ "loss": 0.4037,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.8,
146
+ "grad_norm": 1.5122893151477952,
147
+ "learning_rate": 5.753739930955121e-07,
148
+ "loss": 0.3994,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.84,
153
+ "grad_norm": 1.0149081002178446,
154
+ "learning_rate": 6.041426927502877e-07,
155
+ "loss": 0.3965,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.88,
160
+ "grad_norm": 1.054174710975304,
161
+ "learning_rate": 6.329113924050634e-07,
162
+ "loss": 0.4021,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.92,
167
+ "grad_norm": 1.3289995110739046,
168
+ "learning_rate": 6.61680092059839e-07,
169
+ "loss": 0.3966,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.96,
174
+ "grad_norm": 1.2045960771734698,
175
+ "learning_rate": 6.904487917146145e-07,
176
+ "loss": 0.3912,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 1.0,
181
+ "grad_norm": 1.4483752652421882,
182
+ "learning_rate": 7.192174913693902e-07,
183
+ "loss": 0.3957,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 1.0,
188
+ "eval_loss": 0.3906799554824829,
189
+ "eval_runtime": 23.4022,
190
+ "eval_samples_per_second": 286.853,
191
+ "eval_steps_per_second": 1.154,
192
+ "step": 250
193
+ },
194
+ {
195
+ "epoch": 1.04,
196
+ "grad_norm": 1.421137606048492,
197
+ "learning_rate": 7.479861910241658e-07,
198
+ "loss": 0.3822,
199
+ "step": 260
200
+ },
201
+ {
202
+ "epoch": 1.08,
203
+ "grad_norm": 1.1569390486775748,
204
+ "learning_rate": 7.767548906789415e-07,
205
+ "loss": 0.382,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 1.12,
210
+ "grad_norm": 1.2966147842235234,
211
+ "learning_rate": 8.055235903337171e-07,
212
+ "loss": 0.3821,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 1.16,
217
+ "grad_norm": 1.4954076930003743,
218
+ "learning_rate": 8.342922899884925e-07,
219
+ "loss": 0.3828,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.2,
224
+ "grad_norm": 1.175833777681018,
225
+ "learning_rate": 8.630609896432681e-07,
226
+ "loss": 0.3776,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.24,
231
+ "grad_norm": 1.4737420203396732,
232
+ "learning_rate": 8.918296892980438e-07,
233
+ "loss": 0.381,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.28,
238
+ "grad_norm": 1.0411173755000598,
239
+ "learning_rate": 9.205983889528194e-07,
240
+ "loss": 0.373,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.32,
245
+ "grad_norm": 1.4170827896859917,
246
+ "learning_rate": 9.493670886075951e-07,
247
+ "loss": 0.3744,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.3599999999999999,
252
+ "grad_norm": 1.14952148588396,
253
+ "learning_rate": 9.781357882623706e-07,
254
+ "loss": 0.3788,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.4,
259
+ "grad_norm": 1.0100864705742274,
260
+ "learning_rate": 1.0069044879171462e-06,
261
+ "loss": 0.3751,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.44,
266
+ "grad_norm": 1.4380885723117884,
267
+ "learning_rate": 1.0356731875719219e-06,
268
+ "loss": 0.3789,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.48,
273
+ "grad_norm": 1.313223935969843,
274
+ "learning_rate": 1.0644418872266975e-06,
275
+ "loss": 0.3762,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.52,
280
+ "grad_norm": 1.6074162427330996,
281
+ "learning_rate": 1.0932105868814731e-06,
282
+ "loss": 0.3719,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.56,
287
+ "grad_norm": 1.0515537415251632,
288
+ "learning_rate": 1.1219792865362486e-06,
289
+ "loss": 0.3704,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.6,
294
+ "grad_norm": 1.2284758699860527,
295
+ "learning_rate": 1.1507479861910242e-06,
296
+ "loss": 0.3706,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.6400000000000001,
301
+ "grad_norm": 1.3749774043001943,
302
+ "learning_rate": 1.1795166858457998e-06,
303
+ "loss": 0.3692,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.6800000000000002,
308
+ "grad_norm": 1.2659695321385707,
309
+ "learning_rate": 1.2082853855005755e-06,
310
+ "loss": 0.3692,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.72,
315
+ "grad_norm": 1.1440516628585093,
316
+ "learning_rate": 1.2370540851553511e-06,
317
+ "loss": 0.369,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.76,
322
+ "grad_norm": 1.225026971871428,
323
+ "learning_rate": 1.2658227848101267e-06,
324
+ "loss": 0.3699,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.8,
329
+ "grad_norm": 1.403959379498929,
330
+ "learning_rate": 1.2945914844649024e-06,
331
+ "loss": 0.3638,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.8399999999999999,
336
+ "grad_norm": 1.188372333305488,
337
+ "learning_rate": 1.323360184119678e-06,
338
+ "loss": 0.3684,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.88,
343
+ "grad_norm": 1.1033565733049102,
344
+ "learning_rate": 1.3521288837744534e-06,
345
+ "loss": 0.3688,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.92,
350
+ "grad_norm": 1.2385035527511736,
351
+ "learning_rate": 1.380897583429229e-06,
352
+ "loss": 0.3637,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.96,
357
+ "grad_norm": 1.2610897099257767,
358
+ "learning_rate": 1.4096662830840047e-06,
359
+ "loss": 0.3665,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 2.0,
364
+ "grad_norm": 1.31063382710149,
365
+ "learning_rate": 1.4384349827387804e-06,
366
+ "loss": 0.3655,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 2.0,
371
+ "eval_loss": 0.3691079914569855,
372
+ "eval_runtime": 22.9129,
373
+ "eval_samples_per_second": 292.979,
374
+ "eval_steps_per_second": 1.178,
375
+ "step": 500
376
+ },
377
+ {
378
+ "epoch": 2.04,
379
+ "grad_norm": 1.3941491496870813,
380
+ "learning_rate": 1.467203682393556e-06,
381
+ "loss": 0.3444,
382
+ "step": 510
383
+ },
384
+ {
385
+ "epoch": 2.08,
386
+ "grad_norm": 1.1940415585124986,
387
+ "learning_rate": 1.4959723820483316e-06,
388
+ "loss": 0.3396,
389
+ "step": 520
390
+ },
391
+ {
392
+ "epoch": 2.12,
393
+ "grad_norm": 1.6568570915918388,
394
+ "learning_rate": 1.5247410817031073e-06,
395
+ "loss": 0.3464,
396
+ "step": 530
397
+ },
398
+ {
399
+ "epoch": 2.16,
400
+ "grad_norm": 1.213779432504231,
401
+ "learning_rate": 1.553509781357883e-06,
402
+ "loss": 0.3446,
403
+ "step": 540
404
+ },
405
+ {
406
+ "epoch": 2.2,
407
+ "grad_norm": 1.044059581354644,
408
+ "learning_rate": 1.5822784810126585e-06,
409
+ "loss": 0.3435,
410
+ "step": 550
411
+ },
412
+ {
413
+ "epoch": 2.24,
414
+ "grad_norm": 1.2395011495921882,
415
+ "learning_rate": 1.6110471806674342e-06,
416
+ "loss": 0.3477,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 2.2800000000000002,
421
+ "grad_norm": 1.5404260685292859,
422
+ "learning_rate": 1.6398158803222094e-06,
423
+ "loss": 0.3438,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 2.32,
428
+ "grad_norm": 1.1140407297709995,
429
+ "learning_rate": 1.668584579976985e-06,
430
+ "loss": 0.3443,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 2.36,
435
+ "grad_norm": 1.4618040726027104,
436
+ "learning_rate": 1.6973532796317607e-06,
437
+ "loss": 0.3374,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.4,
442
+ "grad_norm": 1.5541271391197082,
443
+ "learning_rate": 1.7261219792865363e-06,
444
+ "loss": 0.3408,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.44,
449
+ "grad_norm": 1.7994149245724862,
450
+ "learning_rate": 1.754890678941312e-06,
451
+ "loss": 0.3425,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.48,
456
+ "grad_norm": 1.1608293525012197,
457
+ "learning_rate": 1.7836593785960876e-06,
458
+ "loss": 0.3452,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.52,
463
+ "grad_norm": 1.4076591063804629,
464
+ "learning_rate": 1.8124280782508632e-06,
465
+ "loss": 0.3421,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.56,
470
+ "grad_norm": 1.2923646133856594,
471
+ "learning_rate": 1.8411967779056388e-06,
472
+ "loss": 0.338,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.6,
477
+ "grad_norm": 1.3157432345374322,
478
+ "learning_rate": 1.8699654775604145e-06,
479
+ "loss": 0.3407,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.64,
484
+ "grad_norm": 1.5572730770590508,
485
+ "learning_rate": 1.8987341772151901e-06,
486
+ "loss": 0.3466,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.68,
491
+ "grad_norm": 1.2136917873100426,
492
+ "learning_rate": 1.9275028768699655e-06,
493
+ "loss": 0.3462,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.7199999999999998,
498
+ "grad_norm": 1.140250439915797,
499
+ "learning_rate": 1.956271576524741e-06,
500
+ "loss": 0.3466,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.76,
505
+ "grad_norm": 1.164019763628723,
506
+ "learning_rate": 1.985040276179517e-06,
507
+ "loss": 0.3389,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.8,
512
+ "grad_norm": 1.1464479853572567,
513
+ "learning_rate": 2.0138089758342925e-06,
514
+ "loss": 0.3395,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.84,
519
+ "grad_norm": 1.2122963375611697,
520
+ "learning_rate": 2.042577675489068e-06,
521
+ "loss": 0.3459,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.88,
526
+ "grad_norm": 1.1460209246944402,
527
+ "learning_rate": 2.0713463751438437e-06,
528
+ "loss": 0.3397,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.92,
533
+ "grad_norm": 1.1775969440835221,
534
+ "learning_rate": 2.1001150747986194e-06,
535
+ "loss": 0.3403,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.96,
540
+ "grad_norm": 1.394530831390625,
541
+ "learning_rate": 2.128883774453395e-06,
542
+ "loss": 0.3418,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 3.0,
547
+ "grad_norm": 1.3333287115682235,
548
+ "learning_rate": 2.1576524741081706e-06,
549
+ "loss": 0.3351,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 3.0,
554
+ "eval_loss": 0.36160025000572205,
555
+ "eval_runtime": 22.6747,
556
+ "eval_samples_per_second": 296.057,
557
+ "eval_steps_per_second": 1.191,
558
+ "step": 750
559
+ },
560
+ {
561
+ "epoch": 3.0,
562
+ "step": 750,
563
+ "total_flos": 1256277934080000.0,
564
+ "train_loss": 0.38879382991790773,
565
+ "train_runtime": 4686.8691,
566
+ "train_samples_per_second": 81.64,
567
+ "train_steps_per_second": 0.16
568
+ }
569
+ ],
570
+ "logging_steps": 10,
571
+ "max_steps": 750,
572
+ "num_input_tokens_seen": 0,
573
+ "num_train_epochs": 3,
574
+ "save_steps": 500,
575
+ "stateful_callbacks": {
576
+ "TrainerControl": {
577
+ "args": {
578
+ "should_epoch_stop": false,
579
+ "should_evaluate": false,
580
+ "should_log": false,
581
+ "should_save": true,
582
+ "should_training_stop": true
583
+ },
584
+ "attributes": {}
585
+ }
586
+ },
587
+ "total_flos": 1256277934080000.0,
588
+ "train_batch_size": 16,
589
+ "trial_name": null,
590
+ "trial_params": null
591
+ }
training_eval_loss.png ADDED
training_loss.png ADDED