sedrickkeh commited on
Commit
48d7f83
·
verified ·
1 Parent(s): 1edd3ce

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_11_ranking_stackexchange
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # top_11_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: 0.7963
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_11_ranking_stackexchange
 
16
 
17
  # top_11_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_11_ranking_stackexchange dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7963
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99626400996264,
3
+ "eval_loss": 0.7962795495986938,
4
+ "eval_runtime": 430.9339,
5
+ "eval_samples_per_second": 25.104,
6
+ "eval_steps_per_second": 0.394,
7
+ "total_flos": 2014860426608640.0,
8
+ "train_loss": 0.7768312251676843,
9
+ "train_runtime": 70934.0832,
10
+ "train_samples_per_second": 8.693,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99626400996264,
3
+ "eval_loss": 0.7962795495986938,
4
+ "eval_runtime": 430.9339,
5
+ "eval_samples_per_second": 25.104,
6
+ "eval_steps_per_second": 0.394
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99626400996264,
3
+ "total_flos": 2014860426608640.0,
4
+ "train_loss": 0.7768312251676843,
5
+ "train_runtime": 70934.0832,
6
+ "train_samples_per_second": 8.693,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,906 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.99626400996264,
5
+ "eval_steps": 500,
6
+ "global_step": 1203,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.024906600249066,
13
+ "grad_norm": 44.361316887243134,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0469,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.049813200498132,
20
+ "grad_norm": 1.9340361918852786,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9485,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.074719800747198,
27
+ "grad_norm": 1.5810624474405115,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.9118,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.099626400996264,
34
+ "grad_norm": 1.0226804734735437,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.896,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.12453300124533001,
41
+ "grad_norm": 0.8059494431972822,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.885,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.149439601494396,
48
+ "grad_norm": 1.0759666179613023,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8743,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.17434620174346202,
55
+ "grad_norm": 0.6070805032397537,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.865,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.199252801992528,
62
+ "grad_norm": 0.8206282215157027,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8637,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.22415940224159403,
69
+ "grad_norm": 0.8375312112666434,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8538,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.24906600249066002,
76
+ "grad_norm": 0.8745465775067757,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.8462,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.273972602739726,
83
+ "grad_norm": 0.7671374593440573,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.8516,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.298879202988792,
90
+ "grad_norm": 0.6357492120016651,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.8424,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.32378580323785805,
97
+ "grad_norm": 0.7985944551248969,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.838,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.34869240348692404,
104
+ "grad_norm": 0.6906428387839867,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.8425,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.37359900373599003,
111
+ "grad_norm": 0.63382119448828,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.8394,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.398505603985056,
118
+ "grad_norm": 0.7372274527250459,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.8331,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.42341220423412207,
125
+ "grad_norm": 0.6083911703654408,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.8326,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.44831880448318806,
132
+ "grad_norm": 1.1261618495477859,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.8279,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.47322540473225405,
139
+ "grad_norm": 0.7015056078596724,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.8289,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.49813200498132004,
146
+ "grad_norm": 0.7547586360167027,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.8269,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.523038605230386,
153
+ "grad_norm": 0.729606315703109,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.827,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.547945205479452,
160
+ "grad_norm": 0.576263809426071,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.8278,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.572851805728518,
167
+ "grad_norm": 0.608656960705352,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.8255,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.597758405977584,
174
+ "grad_norm": 0.6942678291488105,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.8247,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.6226650062266501,
181
+ "grad_norm": 0.8474112920696388,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.8211,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.6475716064757161,
188
+ "grad_norm": 0.7436541561484579,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.8205,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6724782067247821,
195
+ "grad_norm": 0.5723501381180358,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.8175,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6973848069738481,
202
+ "grad_norm": 0.7393336592407068,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.8266,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.7222914072229141,
209
+ "grad_norm": 0.8642437433242355,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.8213,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.7471980074719801,
216
+ "grad_norm": 0.6599736959065436,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.8197,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.772104607721046,
223
+ "grad_norm": 0.589894020890247,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.8171,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.797011207970112,
230
+ "grad_norm": 0.6770015328448542,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.8159,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.821917808219178,
237
+ "grad_norm": 0.6953955951335576,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.8156,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.8468244084682441,
244
+ "grad_norm": 0.8401761226093455,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.8136,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.8717310087173101,
251
+ "grad_norm": 0.6479655559695816,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.8091,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8966376089663761,
258
+ "grad_norm": 0.7636033751591921,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.8127,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.9215442092154421,
265
+ "grad_norm": 0.5680882933927079,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.8139,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.9464508094645081,
272
+ "grad_norm": 0.5317095758960971,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.8148,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.9713574097135741,
279
+ "grad_norm": 0.5355215121901621,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.8133,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.9962640099626401,
286
+ "grad_norm": 0.5034767977871308,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.8102,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9987546699875467,
293
+ "eval_loss": 0.8109647631645203,
294
+ "eval_runtime": 429.8587,
295
+ "eval_samples_per_second": 25.166,
296
+ "eval_steps_per_second": 0.395,
297
+ "step": 401
298
+ },
299
+ {
300
+ "epoch": 1.0211706102117062,
301
+ "grad_norm": 0.7772306063471781,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.8079,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.046077210460772,
308
+ "grad_norm": 0.547172758232467,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.7693,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.0709838107098382,
315
+ "grad_norm": 0.6602663338851202,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.7659,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.095890410958904,
322
+ "grad_norm": 0.5563021526867751,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.7669,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.1207970112079702,
329
+ "grad_norm": 0.5764004393923637,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.7676,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.145703611457036,
336
+ "grad_norm": 0.6104368430877777,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.7668,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.1706102117061021,
343
+ "grad_norm": 0.5856299384522291,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.7653,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.195516811955168,
350
+ "grad_norm": 0.5968500894238352,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.7691,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.2204234122042341,
357
+ "grad_norm": 0.6425311166512483,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.7692,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.2453300124533002,
364
+ "grad_norm": 0.5800761501783642,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.77,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.270236612702366,
371
+ "grad_norm": 0.5217881601799819,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.7649,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.2951432129514322,
378
+ "grad_norm": 0.7577819320627684,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.7682,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.320049813200498,
385
+ "grad_norm": 0.7467713696988785,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.7712,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.3449564134495642,
392
+ "grad_norm": 0.6010822997576867,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.7664,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.36986301369863,
399
+ "grad_norm": 0.689181454056687,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.7679,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.3947696139476962,
406
+ "grad_norm": 0.4747660184884877,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.7639,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.419676214196762,
413
+ "grad_norm": 0.5116161932838977,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.7677,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.4445828144458281,
420
+ "grad_norm": 0.6433790988167347,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.7626,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.4694894146948942,
427
+ "grad_norm": 0.6145972003931011,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.7639,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.4943960149439601,
434
+ "grad_norm": 0.5887457741602182,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.7612,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.519302615193026,
441
+ "grad_norm": 0.5628593594779383,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.7685,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.544209215442092,
448
+ "grad_norm": 0.49978624448408865,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.7655,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.5691158156911582,
455
+ "grad_norm": 0.5121970961880906,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.7646,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.5940224159402243,
462
+ "grad_norm": 0.5120901081120943,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.7633,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.6189290161892902,
469
+ "grad_norm": 0.5708046084852306,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.7701,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.643835616438356,
476
+ "grad_norm": 0.559772892922969,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.7671,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.6687422166874222,
483
+ "grad_norm": 0.508876685275154,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.7627,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.6936488169364883,
490
+ "grad_norm": 0.5547904679119214,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.7665,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.7185554171855542,
497
+ "grad_norm": 0.5327048566040764,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.7612,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.74346201743462,
504
+ "grad_norm": 0.5681641331800833,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.7625,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.7683686176836861,
511
+ "grad_norm": 0.5583754277477581,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.7678,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.7932752179327522,
518
+ "grad_norm": 0.5821109954208563,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.7641,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.8181818181818183,
525
+ "grad_norm": 0.6033561880814401,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.7671,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.8430884184308842,
532
+ "grad_norm": 0.6575859282775093,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.7569,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.86799501867995,
539
+ "grad_norm": 0.5332781614516378,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.7617,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.8929016189290162,
546
+ "grad_norm": 0.6171829234250781,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.7628,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.9178082191780823,
553
+ "grad_norm": 0.553381597192015,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.7623,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.9427148194271482,
560
+ "grad_norm": 0.5971496735780886,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.7595,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.967621419676214,
567
+ "grad_norm": 0.566450928468519,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.7613,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.9925280199252802,
574
+ "grad_norm": 0.6533740130175245,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.7613,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 2.0,
581
+ "eval_loss": 0.798328697681427,
582
+ "eval_runtime": 427.8716,
583
+ "eval_samples_per_second": 25.283,
584
+ "eval_steps_per_second": 0.397,
585
+ "step": 803
586
+ },
587
+ {
588
+ "epoch": 2.0174346201743463,
589
+ "grad_norm": 0.9428578537809662,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.764,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.0423412204234124,
596
+ "grad_norm": 0.682790769401012,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.7174,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.067247820672478,
603
+ "grad_norm": 0.732474650025201,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.7136,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.092154420921544,
610
+ "grad_norm": 0.5517924405803882,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.7141,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.1170610211706102,
617
+ "grad_norm": 0.527980258175362,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.7205,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.1419676214196763,
624
+ "grad_norm": 0.5578355324627287,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.7182,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.166874221668742,
631
+ "grad_norm": 0.5384061514408854,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.7174,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.191780821917808,
638
+ "grad_norm": 0.5433323621552549,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.7227,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.216687422166874,
645
+ "grad_norm": 0.5934434020270568,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.7154,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.2415940224159403,
652
+ "grad_norm": 0.5610116690136854,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.7181,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.2665006226650064,
659
+ "grad_norm": 0.5956518936383002,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.7188,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.291407222914072,
666
+ "grad_norm": 0.5700434018521554,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.7189,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.316313823163138,
673
+ "grad_norm": 0.6159365804430498,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.7208,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.3412204234122043,
680
+ "grad_norm": 0.5739840813262334,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.7191,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.3661270236612704,
687
+ "grad_norm": 0.517298472276118,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.7254,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.391033623910336,
694
+ "grad_norm": 0.5309037963536546,
695
+ "learning_rate": 5e-06,
696
+ "loss": 0.7177,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.415940224159402,
701
+ "grad_norm": 0.5464343303315381,
702
+ "learning_rate": 5e-06,
703
+ "loss": 0.7162,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.4408468244084682,
708
+ "grad_norm": 0.5884939657248605,
709
+ "learning_rate": 5e-06,
710
+ "loss": 0.7238,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.4657534246575343,
715
+ "grad_norm": 0.6058278477423068,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.7217,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.4906600249066004,
722
+ "grad_norm": 0.575706246130651,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.7211,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.515566625155666,
729
+ "grad_norm": 0.6210182727077225,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.722,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.540473225404732,
736
+ "grad_norm": 0.6248334338554098,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.7226,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.5653798256537983,
743
+ "grad_norm": 0.6075603863013977,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.7201,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.5902864259028644,
750
+ "grad_norm": 0.6125989005343908,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.7225,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.61519302615193,
757
+ "grad_norm": 0.5723698102141317,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.7184,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.640099626400996,
764
+ "grad_norm": 0.5988876404053375,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.7228,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.6650062266500623,
771
+ "grad_norm": 0.5535541669685047,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.7219,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.6899128268991284,
778
+ "grad_norm": 0.6560134586878092,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.7231,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.7148194271481945,
785
+ "grad_norm": 0.570154529031656,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.7207,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.73972602739726,
792
+ "grad_norm": 0.6903793080558596,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.7225,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.7646326276463262,
799
+ "grad_norm": 0.609309475396782,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.7199,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.7895392278953923,
806
+ "grad_norm": 0.4982077265492007,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.723,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.8144458281444584,
813
+ "grad_norm": 0.5520401600798728,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.7195,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.839352428393524,
820
+ "grad_norm": 0.5678772706098874,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.7241,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.86425902864259,
827
+ "grad_norm": 0.6919987752510048,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.7218,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.8891656288916563,
834
+ "grad_norm": 0.5523800519721218,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.7223,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.9140722291407224,
841
+ "grad_norm": 0.5786175424826561,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.7248,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.9389788293897885,
848
+ "grad_norm": 0.5805260846296417,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.7186,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.963885429638854,
855
+ "grad_norm": 0.6087027130014465,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.7225,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.9887920298879203,
862
+ "grad_norm": 0.6138969910749299,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.7228,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.99626400996264,
869
+ "eval_loss": 0.7962795495986938,
870
+ "eval_runtime": 431.1284,
871
+ "eval_samples_per_second": 25.092,
872
+ "eval_steps_per_second": 0.394,
873
+ "step": 1203
874
+ },
875
+ {
876
+ "epoch": 2.99626400996264,
877
+ "step": 1203,
878
+ "total_flos": 2014860426608640.0,
879
+ "train_loss": 0.7768312251676843,
880
+ "train_runtime": 70934.0832,
881
+ "train_samples_per_second": 8.693,
882
+ "train_steps_per_second": 0.017
883
+ }
884
+ ],
885
+ "logging_steps": 10,
886
+ "max_steps": 1203,
887
+ "num_input_tokens_seen": 0,
888
+ "num_train_epochs": 3,
889
+ "save_steps": 500,
890
+ "stateful_callbacks": {
891
+ "TrainerControl": {
892
+ "args": {
893
+ "should_epoch_stop": false,
894
+ "should_evaluate": false,
895
+ "should_log": false,
896
+ "should_save": true,
897
+ "should_training_stop": true
898
+ },
899
+ "attributes": {}
900
+ }
901
+ },
902
+ "total_flos": 2014860426608640.0,
903
+ "train_batch_size": 8,
904
+ "trial_name": null,
905
+ "trial_params": null
906
+ }
training_eval_loss.png ADDED
training_loss.png ADDED