sedrickkeh commited on
Commit
31a9934
·
verified ·
1 Parent(s): f463a12

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: top_8_ranking_stackexchange
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # top_8_ranking_stackexchange
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.7736
21
 
 
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: top_8_ranking_stackexchange
 
16
 
17
  # top_8_ranking_stackexchange
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/top_8_ranking_stackexchange dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7736
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.7735684514045715,
4
+ "eval_runtime": 315.4705,
5
+ "eval_samples_per_second": 25.112,
6
+ "eval_steps_per_second": 0.393,
7
+ "total_flos": 1477173470822400.0,
8
+ "train_loss": 0.7552210683184687,
9
+ "train_runtime": 52264.4132,
10
+ "train_samples_per_second": 8.64,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.7735684514045715,
4
+ "eval_runtime": 315.4705,
5
+ "eval_samples_per_second": 25.112,
6
+ "eval_steps_per_second": 0.393
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1477173470822400.0,
4
+ "train_loss": 0.7552210683184687,
5
+ "train_runtime": 52264.4132,
6
+ "train_samples_per_second": 8.64,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,682 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 882,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.034013605442176874,
13
+ "grad_norm": 5.093772950493088,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0253,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.06802721088435375,
20
+ "grad_norm": 1.582810434950759,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9164,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.10204081632653061,
27
+ "grad_norm": 1.081419957922015,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.8837,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.1360544217687075,
34
+ "grad_norm": 1.334991004257816,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8662,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.17006802721088435,
41
+ "grad_norm": 0.6437293692108047,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.8474,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.20408163265306123,
48
+ "grad_norm": 0.7291088099940165,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8403,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.23809523809523808,
55
+ "grad_norm": 1.2250728318971373,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8324,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.272108843537415,
62
+ "grad_norm": 0.5271316099486635,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8255,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.30612244897959184,
69
+ "grad_norm": 0.657776756921105,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8268,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.3401360544217687,
76
+ "grad_norm": 0.6441066353244067,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.8244,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.3741496598639456,
83
+ "grad_norm": 0.8285320708808935,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.8204,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.40816326530612246,
90
+ "grad_norm": 0.7161434853368004,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.8162,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.4421768707482993,
97
+ "grad_norm": 0.5513713742579371,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.8145,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.47619047619047616,
104
+ "grad_norm": 0.7457252021496298,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.8055,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5102040816326531,
111
+ "grad_norm": 0.5974600771687919,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.8046,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.54421768707483,
118
+ "grad_norm": 0.5106810999294438,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.8038,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.5782312925170068,
125
+ "grad_norm": 0.5233604769586638,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7984,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6122448979591837,
132
+ "grad_norm": 0.6621030752821899,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.8053,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.6462585034013606,
139
+ "grad_norm": 0.6082801478115033,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.7971,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.6802721088435374,
146
+ "grad_norm": 0.6921185518271565,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.7962,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.7142857142857143,
153
+ "grad_norm": 0.7932977516942055,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.7965,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.7482993197278912,
160
+ "grad_norm": 0.6324128246753213,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7934,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.782312925170068,
167
+ "grad_norm": 0.559311808415173,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7989,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8163265306122449,
174
+ "grad_norm": 0.6432666654821662,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7969,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.8503401360544217,
181
+ "grad_norm": 0.744813344130182,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.7919,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.8843537414965986,
188
+ "grad_norm": 0.5433587318374555,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.7902,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9183673469387755,
195
+ "grad_norm": 0.7120343599921604,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.7906,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.9523809523809523,
202
+ "grad_norm": 1.1772393318908365,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.7883,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.9863945578231292,
209
+ "grad_norm": 1.289674010358365,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.7865,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 1.0,
216
+ "eval_loss": 0.787599503993988,
217
+ "eval_runtime": 312.4094,
218
+ "eval_samples_per_second": 25.358,
219
+ "eval_steps_per_second": 0.397,
220
+ "step": 294
221
+ },
222
+ {
223
+ "epoch": 1.0204081632653061,
224
+ "grad_norm": 0.9036542003842971,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.7746,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.054421768707483,
231
+ "grad_norm": 0.8034701067288486,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.7488,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.08843537414966,
238
+ "grad_norm": 0.6023506564223867,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.7475,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.1224489795918366,
245
+ "grad_norm": 0.6504967920737302,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.7431,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.1564625850340136,
252
+ "grad_norm": 0.5813877515629605,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.7462,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.1904761904761905,
259
+ "grad_norm": 0.6259897603352809,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.747,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.2244897959183674,
266
+ "grad_norm": 0.6862271161840088,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.7455,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.2585034013605443,
273
+ "grad_norm": 0.5769690007814378,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.7406,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.2925170068027212,
280
+ "grad_norm": 0.557540098903492,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.7538,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.3265306122448979,
287
+ "grad_norm": 0.7131020070740424,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.7458,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.3605442176870748,
294
+ "grad_norm": 0.5948565780053893,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.7446,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.3945578231292517,
301
+ "grad_norm": 0.6911445705490143,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.7497,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.4285714285714286,
308
+ "grad_norm": 0.6252849135367671,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.7469,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.4625850340136055,
315
+ "grad_norm": 0.6646202868499425,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.7424,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.4965986394557822,
322
+ "grad_norm": 0.6970040399316466,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.7445,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.5306122448979593,
329
+ "grad_norm": 0.6004043771512654,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.7492,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.564625850340136,
336
+ "grad_norm": 0.6563540827889115,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.7423,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.598639455782313,
343
+ "grad_norm": 0.7454418696472762,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.7434,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.6326530612244898,
350
+ "grad_norm": 0.5564890350927186,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.7365,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.6666666666666665,
357
+ "grad_norm": 0.7834978093049169,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.7421,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.7006802721088436,
364
+ "grad_norm": 0.583066628701426,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.7463,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.7346938775510203,
371
+ "grad_norm": 0.5893517422275613,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.7376,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.7687074829931972,
378
+ "grad_norm": 0.5037802702044101,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.7441,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.8027210884353742,
385
+ "grad_norm": 0.5931792416654984,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.7431,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.836734693877551,
392
+ "grad_norm": 0.6402441098113224,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.7438,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.870748299319728,
399
+ "grad_norm": 0.5654472975194821,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.7393,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.9047619047619047,
406
+ "grad_norm": 0.5753064985895123,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.7397,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.9387755102040818,
413
+ "grad_norm": 0.7250548373178971,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.7397,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.9727891156462585,
420
+ "grad_norm": 0.5431763568539679,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.7399,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 2.0,
427
+ "eval_loss": 0.7747776508331299,
428
+ "eval_runtime": 316.2944,
429
+ "eval_samples_per_second": 25.046,
430
+ "eval_steps_per_second": 0.392,
431
+ "step": 588
432
+ },
433
+ {
434
+ "epoch": 2.006802721088435,
435
+ "grad_norm": 1.0710107167046419,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.7322,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.0408163265306123,
442
+ "grad_norm": 0.8179848172880277,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.6959,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.074829931972789,
449
+ "grad_norm": 0.7213840408679012,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.6963,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.108843537414966,
456
+ "grad_norm": 0.842144783291229,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.6919,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.142857142857143,
463
+ "grad_norm": 0.8281153884085551,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.6885,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.17687074829932,
470
+ "grad_norm": 0.6466546656089918,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.696,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.2108843537414966,
477
+ "grad_norm": 0.526364663799012,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.6937,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.2448979591836733,
484
+ "grad_norm": 0.5634674036723205,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.6981,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.2789115646258504,
491
+ "grad_norm": 0.5968432701967212,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.7015,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.312925170068027,
498
+ "grad_norm": 0.5913462184907319,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.7012,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.3469387755102042,
505
+ "grad_norm": 0.7450042075059763,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.6952,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.380952380952381,
512
+ "grad_norm": 0.5383186417121737,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.6953,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.4149659863945576,
519
+ "grad_norm": 0.7331040417967113,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.6997,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.4489795918367347,
526
+ "grad_norm": 0.707608838125245,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.6947,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.4829931972789114,
533
+ "grad_norm": 0.5739038681907664,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.7002,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.5170068027210886,
540
+ "grad_norm": 0.6882559394709682,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.7,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.5510204081632653,
547
+ "grad_norm": 0.5748954947299686,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.6977,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.5850340136054424,
554
+ "grad_norm": 0.5661948160767387,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.6972,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.619047619047619,
561
+ "grad_norm": 0.6170581920248837,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.6988,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.6530612244897958,
568
+ "grad_norm": 0.7539930534954333,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.6977,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.687074829931973,
575
+ "grad_norm": 0.5811347422760094,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.6987,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.7210884353741496,
582
+ "grad_norm": 0.6704654193944088,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.6982,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.7551020408163263,
589
+ "grad_norm": 0.6505538631815906,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.7006,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.7891156462585034,
596
+ "grad_norm": 0.5672733814024299,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.7038,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.8231292517006805,
603
+ "grad_norm": 0.6464062527883608,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.7031,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.857142857142857,
610
+ "grad_norm": 0.6783589732638796,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.7001,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.891156462585034,
617
+ "grad_norm": 0.6780111327853662,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.6999,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.925170068027211,
624
+ "grad_norm": 0.6861118715829543,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.7007,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.9591836734693877,
631
+ "grad_norm": 0.6468827032168267,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.7029,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.9931972789115644,
638
+ "grad_norm": 0.5936344265821127,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.7006,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 3.0,
645
+ "eval_loss": 0.7735684514045715,
646
+ "eval_runtime": 316.0096,
647
+ "eval_samples_per_second": 25.069,
648
+ "eval_steps_per_second": 0.392,
649
+ "step": 882
650
+ },
651
+ {
652
+ "epoch": 3.0,
653
+ "step": 882,
654
+ "total_flos": 1477173470822400.0,
655
+ "train_loss": 0.7552210683184687,
656
+ "train_runtime": 52264.4132,
657
+ "train_samples_per_second": 8.64,
658
+ "train_steps_per_second": 0.017
659
+ }
660
+ ],
661
+ "logging_steps": 10,
662
+ "max_steps": 882,
663
+ "num_input_tokens_seen": 0,
664
+ "num_train_epochs": 3,
665
+ "save_steps": 500,
666
+ "stateful_callbacks": {
667
+ "TrainerControl": {
668
+ "args": {
669
+ "should_epoch_stop": false,
670
+ "should_evaluate": false,
671
+ "should_log": false,
672
+ "should_save": true,
673
+ "should_training_stop": true
674
+ },
675
+ "attributes": {}
676
+ }
677
+ },
678
+ "total_flos": 1477173470822400.0,
679
+ "train_batch_size": 8,
680
+ "trial_name": null,
681
+ "trial_params": null
682
+ }
training_eval_loss.png ADDED
training_loss.png ADDED