sedrickkeh commited on
Commit
e6ec28e
·
verified ·
1 Parent(s): 2d9cf64

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_10_ranking_stackexchange
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # top_10_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: 0.7844
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_10_ranking_stackexchange
 
16
 
17
  # top_10_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_10_ranking_stackexchange dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7844
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.998994974874372,
3
+ "eval_loss": 0.784430980682373,
4
+ "eval_runtime": 399.5634,
5
+ "eval_samples_per_second": 25.162,
6
+ "eval_steps_per_second": 0.395,
7
+ "total_flos": 1874157297991680.0,
8
+ "train_loss": 0.7673776837946369,
9
+ "train_runtime": 65939.4578,
10
+ "train_samples_per_second": 8.691,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.998994974874372,
3
+ "eval_loss": 0.784430980682373,
4
+ "eval_runtime": 399.5634,
5
+ "eval_samples_per_second": 25.162,
6
+ "eval_steps_per_second": 0.395
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.998994974874372,
3
+ "total_flos": 1874157297991680.0,
4
+ "train_loss": 0.7673776837946369,
5
+ "train_runtime": 65939.4578,
6
+ "train_samples_per_second": 8.691,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,843 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.998994974874372,
5
+ "eval_steps": 500,
6
+ "global_step": 1119,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02680067001675042,
13
+ "grad_norm": 31.10676739208888,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0442,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.05360134003350084,
20
+ "grad_norm": 4.120159718355311,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.955,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.08040201005025126,
27
+ "grad_norm": 2.339286993290118,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.9144,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.10720268006700168,
34
+ "grad_norm": 1.0759658796503169,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8882,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.13400335008375208,
41
+ "grad_norm": 0.6453086287600575,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.8699,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.16080402010050251,
48
+ "grad_norm": 1.1160652028087201,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8652,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.18760469011725292,
55
+ "grad_norm": 0.6258812701119981,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.848,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.21440536013400335,
62
+ "grad_norm": 0.5590720583080133,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8463,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.24120603015075376,
69
+ "grad_norm": 0.6795899721647743,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8393,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.26800670016750416,
76
+ "grad_norm": 1.1809098922748584,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.8335,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2948073701842546,
83
+ "grad_norm": 0.8420170258665194,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.8354,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.32160804020100503,
90
+ "grad_norm": 0.6851931492236875,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.8311,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.34840871021775544,
97
+ "grad_norm": 0.9823271515850558,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.8338,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.37520938023450584,
104
+ "grad_norm": 0.7764734742568185,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.8308,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.4020100502512563,
111
+ "grad_norm": 0.8463569347395117,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.8223,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.4288107202680067,
118
+ "grad_norm": 0.7229327877216101,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.8265,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.4556113902847571,
125
+ "grad_norm": 0.7406267992443841,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.8192,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.4824120603015075,
132
+ "grad_norm": 0.5245160572062765,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.8175,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.509212730318258,
139
+ "grad_norm": 0.5446187756240741,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.8173,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.5360134003350083,
146
+ "grad_norm": 0.5387389341379448,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.8152,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.5628140703517588,
153
+ "grad_norm": 0.5942914061122081,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.8158,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.5896147403685092,
160
+ "grad_norm": 0.7289915117140335,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.8157,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.6164154103852596,
167
+ "grad_norm": 0.6166043522729069,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.8154,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.6432160804020101,
174
+ "grad_norm": 0.5402182876037194,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.81,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.6700167504187605,
181
+ "grad_norm": 0.702136667602188,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.8086,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.6968174204355109,
188
+ "grad_norm": 0.5548041175483877,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.8067,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.7236180904522613,
195
+ "grad_norm": 0.5933880054884063,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.8046,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.7504187604690117,
202
+ "grad_norm": 0.6218650700836093,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.8045,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.7772194304857621,
209
+ "grad_norm": 0.6636079178178366,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.8029,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.8040201005025126,
216
+ "grad_norm": 0.7578337185188113,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.8017,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.830820770519263,
223
+ "grad_norm": 0.5964607129683942,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.8039,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.8576214405360134,
230
+ "grad_norm": 0.5731797399351095,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.8018,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.8844221105527639,
237
+ "grad_norm": 1.2550493135376506,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.7994,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.9112227805695142,
244
+ "grad_norm": 0.9368889967347727,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.8074,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.9380234505862647,
251
+ "grad_norm": 0.5921834072388994,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.8049,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.964824120603015,
258
+ "grad_norm": 0.5216457733637546,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.8019,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.9916247906197655,
265
+ "grad_norm": 0.6220842275028926,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.7989,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.9996649916247906,
272
+ "eval_loss": 0.7980747222900391,
273
+ "eval_runtime": 396.9204,
274
+ "eval_samples_per_second": 25.33,
275
+ "eval_steps_per_second": 0.398,
276
+ "step": 373
277
+ },
278
+ {
279
+ "epoch": 1.018425460636516,
280
+ "grad_norm": 0.8379563173937747,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.846,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.0452261306532664,
287
+ "grad_norm": 0.7007106059150332,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.7553,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.0720268006700167,
294
+ "grad_norm": 0.6985327962246497,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.7609,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.0988274706867671,
301
+ "grad_norm": 0.8231254452075508,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.7594,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.1256281407035176,
308
+ "grad_norm": 0.5396289186374543,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.7555,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.152428810720268,
315
+ "grad_norm": 0.5275185306049085,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.7554,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.1792294807370185,
322
+ "grad_norm": 0.5322161709304825,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.7592,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.2060301507537687,
329
+ "grad_norm": 0.6335605844571386,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.7569,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.2328308207705192,
336
+ "grad_norm": 0.6175137584423412,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.7545,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.2596314907872697,
343
+ "grad_norm": 0.5525760530230355,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.755,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.2864321608040201,
350
+ "grad_norm": 0.8168923150097971,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.7546,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.3132328308207706,
357
+ "grad_norm": 0.576393540227948,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.7613,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.3400335008375208,
364
+ "grad_norm": 0.5454484709306812,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.7558,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.3668341708542713,
371
+ "grad_norm": 0.519519630849878,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.7513,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.3936348408710217,
378
+ "grad_norm": 0.5412825055890007,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.757,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.4204355108877722,
385
+ "grad_norm": 0.6663985833801256,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.7549,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.4472361809045227,
392
+ "grad_norm": 0.5433262572367299,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.7546,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.474036850921273,
399
+ "grad_norm": 0.4990591351939153,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.7483,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.5008375209380236,
406
+ "grad_norm": 0.5826918311899233,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.7554,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.5276381909547738,
413
+ "grad_norm": 0.5498876689910938,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.747,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.5544388609715243,
420
+ "grad_norm": 0.5033534721843692,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.7563,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.5812395309882747,
427
+ "grad_norm": 0.5475928059702524,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.7597,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.608040201005025,
434
+ "grad_norm": 0.5483658876220942,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.7538,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.6348408710217757,
441
+ "grad_norm": 0.550772312369244,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.7552,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.661641541038526,
448
+ "grad_norm": 0.541814614413297,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.7556,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.6884422110552764,
455
+ "grad_norm": 0.5623412222166373,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.7523,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.7152428810720268,
462
+ "grad_norm": 0.5486383001151054,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.7548,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.742043551088777,
469
+ "grad_norm": 0.6450442334835524,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.7506,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.7688442211055277,
476
+ "grad_norm": 0.5093346834442244,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.7526,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.795644891122278,
483
+ "grad_norm": 0.5882959805663536,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.756,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.8224455611390284,
490
+ "grad_norm": 0.6121773592899815,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.7516,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.849246231155779,
497
+ "grad_norm": 0.5053865601023015,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.7552,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.8760469011725294,
504
+ "grad_norm": 0.49653124526114595,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.7506,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.9028475711892798,
511
+ "grad_norm": 0.5356438120020067,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.7512,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.92964824120603,
518
+ "grad_norm": 0.4792312103436412,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.7523,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.9564489112227805,
525
+ "grad_norm": 0.5887442908787863,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.7489,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.983249581239531,
532
+ "grad_norm": 0.6013288648401325,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.7568,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.9993299832495812,
539
+ "eval_loss": 0.7848142385482788,
540
+ "eval_runtime": 399.6688,
541
+ "eval_samples_per_second": 25.156,
542
+ "eval_steps_per_second": 0.395,
543
+ "step": 746
544
+ },
545
+ {
546
+ "epoch": 2.0100502512562812,
547
+ "grad_norm": 0.7899358115042834,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.806,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.036850921273032,
554
+ "grad_norm": 0.5438655957140969,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.7051,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.063651591289782,
561
+ "grad_norm": 0.5954978197528383,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.7054,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.090452261306533,
568
+ "grad_norm": 0.5330734638287157,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.7057,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.117252931323283,
575
+ "grad_norm": 0.5719591031814022,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.7074,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.1440536013400333,
582
+ "grad_norm": 0.5749015032749988,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.7035,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.170854271356784,
589
+ "grad_norm": 0.7000012184675283,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.7045,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.1976549413735342,
596
+ "grad_norm": 0.5221545575547275,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.7085,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.224455611390285,
603
+ "grad_norm": 0.5590282858104586,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.7067,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.251256281407035,
610
+ "grad_norm": 0.680247988597194,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.712,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.2780569514237854,
617
+ "grad_norm": 0.5724224597541392,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.7132,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.304857621440536,
624
+ "grad_norm": 0.5890303699337465,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.7126,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.3316582914572863,
631
+ "grad_norm": 0.7060913656445702,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.71,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.358458961474037,
638
+ "grad_norm": 0.5199319551859399,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.7095,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.3852596314907872,
645
+ "grad_norm": 0.5667231972196302,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.7091,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.4120603015075375,
652
+ "grad_norm": 0.5776579179225979,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.7061,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.438860971524288,
659
+ "grad_norm": 0.5068031699453062,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.709,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.4656616415410384,
666
+ "grad_norm": 0.5622723362640956,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.7092,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.492462311557789,
673
+ "grad_norm": 0.6678938168210493,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.7074,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.5192629815745393,
680
+ "grad_norm": 0.7495016986714225,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.7123,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.5460636515912896,
687
+ "grad_norm": 0.5890832065298138,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.7117,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.5728643216080402,
694
+ "grad_norm": 0.5358789200826624,
695
+ "learning_rate": 5e-06,
696
+ "loss": 0.7123,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.5996649916247905,
701
+ "grad_norm": 0.7046518448288711,
702
+ "learning_rate": 5e-06,
703
+ "loss": 0.7124,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.626465661641541,
708
+ "grad_norm": 0.5598275583119999,
709
+ "learning_rate": 5e-06,
710
+ "loss": 0.7095,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.6532663316582914,
715
+ "grad_norm": 0.6175269384061102,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.7098,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.6800670016750416,
722
+ "grad_norm": 0.5833546621317353,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.7114,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.7068676716917923,
729
+ "grad_norm": 0.5577868241277573,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.7126,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.7336683417085426,
736
+ "grad_norm": 0.5384748297588693,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.7107,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.7604690117252932,
743
+ "grad_norm": 0.6077432046061476,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.708,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.7872696817420435,
750
+ "grad_norm": 0.5845658826184227,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.7166,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.8140703517587937,
757
+ "grad_norm": 0.5139932571124606,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.7112,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.8408710217755444,
764
+ "grad_norm": 0.5214647759988249,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.7083,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.8676716917922946,
771
+ "grad_norm": 0.6459251681734683,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.7165,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.8944723618090453,
778
+ "grad_norm": 0.6289426280816557,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.7126,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.9212730318257956,
785
+ "grad_norm": 0.4931010807851759,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.709,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.948073701842546,
792
+ "grad_norm": 0.5257070901798452,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.7131,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.9748743718592965,
799
+ "grad_norm": 0.5735309103540566,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.7167,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.998994974874372,
806
+ "eval_loss": 0.784430980682373,
807
+ "eval_runtime": 398.3496,
808
+ "eval_samples_per_second": 25.239,
809
+ "eval_steps_per_second": 0.397,
810
+ "step": 1119
811
+ },
812
+ {
813
+ "epoch": 2.998994974874372,
814
+ "step": 1119,
815
+ "total_flos": 1874157297991680.0,
816
+ "train_loss": 0.7673776837946369,
817
+ "train_runtime": 65939.4578,
818
+ "train_samples_per_second": 8.691,
819
+ "train_steps_per_second": 0.017
820
+ }
821
+ ],
822
+ "logging_steps": 10,
823
+ "max_steps": 1119,
824
+ "num_input_tokens_seen": 0,
825
+ "num_train_epochs": 3,
826
+ "save_steps": 500,
827
+ "stateful_callbacks": {
828
+ "TrainerControl": {
829
+ "args": {
830
+ "should_epoch_stop": false,
831
+ "should_evaluate": false,
832
+ "should_log": false,
833
+ "should_save": true,
834
+ "should_training_stop": true
835
+ },
836
+ "attributes": {}
837
+ }
838
+ },
839
+ "total_flos": 1874157297991680.0,
840
+ "train_batch_size": 8,
841
+ "trial_name": null,
842
+ "trial_params": null
843
+ }
training_eval_loss.png ADDED
training_loss.png ADDED