sedrickkeh commited on
Commit
c442bf7
·
verified ·
1 Parent(s): 59c51ef

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3
4
  base_model: meta-llama/Meta-Llama-3-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: OH_DCFT_V3_wo_caseus_custom
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # OH_DCFT_V3_wo_caseus_custom
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.6464
21
 
 
4
  base_model: meta-llama/Meta-Llama-3-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: OH_DCFT_V3_wo_caseus_custom
 
16
 
17
  # OH_DCFT_V3_wo_caseus_custom
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the mlfoundations-dev/OH_DCFT_V3_wo_caseus_custom dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6464
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9982238010657194,
3
+ "eval_loss": 0.6463779211044312,
4
+ "eval_runtime": 225.177,
5
+ "eval_samples_per_second": 50.525,
6
+ "eval_steps_per_second": 0.395,
7
+ "total_flos": 2120178393415680.0,
8
+ "train_loss": 0.6161920559161459,
9
+ "train_runtime": 37913.0448,
10
+ "train_samples_per_second": 17.103,
11
+ "train_steps_per_second": 0.033
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9982238010657194,
3
+ "eval_loss": 0.6463779211044312,
4
+ "eval_runtime": 225.177,
5
+ "eval_samples_per_second": 50.525,
6
+ "eval_steps_per_second": 0.395
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9982238010657194,
3
+ "total_flos": 2120178393415680.0,
4
+ "train_loss": 0.6161920559161459,
5
+ "train_runtime": 37913.0448,
6
+ "train_samples_per_second": 17.103,
7
+ "train_steps_per_second": 0.033
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,948 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9982238010657194,
5
+ "eval_steps": 500,
6
+ "global_step": 1266,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.023682652457075192,
13
+ "grad_norm": 13.189470730439847,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.9153,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.047365304914150384,
20
+ "grad_norm": 16.705378973618984,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.8006,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.07104795737122557,
27
+ "grad_norm": 1.5387333872556015,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.767,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.09473060982830077,
34
+ "grad_norm": 1.5480037290759114,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.7381,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11841326228537596,
41
+ "grad_norm": 0.7592297796517318,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.7299,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.14209591474245115,
48
+ "grad_norm": 0.7439300906768337,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.7102,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.16577856719952636,
55
+ "grad_norm": 0.9644129830031992,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.7226,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.18946121965660154,
62
+ "grad_norm": 1.083419801070231,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.7016,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.21314387211367672,
69
+ "grad_norm": 0.6505643570843905,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.7007,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.23682652457075193,
76
+ "grad_norm": 0.5502857011017064,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6834,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2605091770278271,
83
+ "grad_norm": 0.5293957463932839,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.6843,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2841918294849023,
90
+ "grad_norm": 0.6629192311799427,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.6876,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.30787448194197753,
97
+ "grad_norm": 0.7092941162121122,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.6789,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3315571343990527,
104
+ "grad_norm": 0.6884868718102479,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.6765,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3552397868561279,
111
+ "grad_norm": 0.5675134967361182,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.6781,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3789224393132031,
118
+ "grad_norm": 0.4872689604652464,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6778,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.40260509177027826,
125
+ "grad_norm": 0.5788634488292149,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.6723,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.42628774422735344,
132
+ "grad_norm": 0.5446139045326359,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.6689,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.4499703966844287,
139
+ "grad_norm": 0.7925779847081673,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.6687,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.47365304914150386,
146
+ "grad_norm": 0.7557946920173058,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.6703,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.49733570159857904,
153
+ "grad_norm": 0.6224256728374598,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6674,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.5210183540556542,
160
+ "grad_norm": 0.7659997074796134,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6775,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5447010065127295,
167
+ "grad_norm": 0.6379584879302997,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.6606,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5683836589698046,
174
+ "grad_norm": 0.6095478409444377,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.6688,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5920663114268798,
181
+ "grad_norm": 0.5271893204607883,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.6674,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.6157489638839551,
188
+ "grad_norm": 0.614025958346404,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.6582,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6394316163410302,
195
+ "grad_norm": 0.7285219514043463,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.6581,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6631142687981054,
202
+ "grad_norm": 0.7190322452172576,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.659,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6867969212551805,
209
+ "grad_norm": 0.6071224570407465,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.6649,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.7104795737122558,
216
+ "grad_norm": 0.49216175819370883,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.6611,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.7341622261693309,
223
+ "grad_norm": 0.5178492184765248,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.6608,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7578448786264061,
230
+ "grad_norm": 0.5029896497256847,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.6568,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7815275310834814,
237
+ "grad_norm": 0.7171925939489323,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.6559,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.8052101835405565,
244
+ "grad_norm": 0.6508752197201968,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.6549,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.8288928359976317,
251
+ "grad_norm": 0.5255741435374958,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.6608,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8525754884547069,
258
+ "grad_norm": 0.547087018654004,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.6557,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8762581409117821,
265
+ "grad_norm": 0.48618214031429924,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.6535,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8999407933688574,
272
+ "grad_norm": 0.5442894464037913,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.6556,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.9236234458259325,
279
+ "grad_norm": 0.6652203100668711,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.6585,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.9473060982830077,
286
+ "grad_norm": 0.5348960345212145,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.6429,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9709887507400828,
293
+ "grad_norm": 0.5696256474721889,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.6552,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9946714031971581,
300
+ "grad_norm": 0.6600709101064473,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.6424,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9994079336885732,
307
+ "eval_loss": 0.6530644297599792,
308
+ "eval_runtime": 226.0947,
309
+ "eval_samples_per_second": 50.32,
310
+ "eval_steps_per_second": 0.394,
311
+ "step": 422
312
+ },
313
+ {
314
+ "epoch": 1.0183540556542332,
315
+ "grad_norm": 0.7026612619443326,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6135,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.0420367081113084,
322
+ "grad_norm": 0.6043811485369807,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.609,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.0657193605683837,
329
+ "grad_norm": 0.5930425944334362,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6002,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.089402013025459,
336
+ "grad_norm": 0.5902568338086035,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6078,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.1130846654825342,
343
+ "grad_norm": 0.49068395029218714,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6075,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.1367673179396092,
350
+ "grad_norm": 0.6080540264952039,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.5968,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.1604499703966844,
357
+ "grad_norm": 0.631498780679762,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6033,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.1841326228537596,
364
+ "grad_norm": 0.6454741753351722,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6113,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.2078152753108349,
371
+ "grad_norm": 0.4832541377171757,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.608,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.2314979277679101,
378
+ "grad_norm": 0.576018646795068,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6153,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.2551805802249851,
385
+ "grad_norm": 0.584703843866035,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.604,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2788632326820604,
392
+ "grad_norm": 0.5216537105860701,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6091,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.3025458851391356,
399
+ "grad_norm": 0.5533381633091111,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.6082,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.3262285375962108,
406
+ "grad_norm": 0.6053695231773084,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.6085,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.349911190053286,
413
+ "grad_norm": 0.49887104712071284,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.6052,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.373593842510361,
420
+ "grad_norm": 0.7914662780125341,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.6051,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3972764949674363,
427
+ "grad_norm": 0.6735579998559209,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.6003,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.4209591474245116,
434
+ "grad_norm": 0.6489668939560808,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.6023,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.4446417998815868,
441
+ "grad_norm": 0.5114004583431452,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.6055,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.468324452338662,
448
+ "grad_norm": 0.5435875766325163,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.6016,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.492007104795737,
455
+ "grad_norm": 0.5201706548652517,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.5993,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.5156897572528123,
462
+ "grad_norm": 0.5829006586321327,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.6064,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.5393724097098875,
469
+ "grad_norm": 0.4715645741265029,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.6015,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.5630550621669625,
476
+ "grad_norm": 0.5490786443724993,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.6065,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.586737714624038,
483
+ "grad_norm": 0.5628955248722177,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.6028,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.610420367081113,
490
+ "grad_norm": 0.5612429021808025,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.6054,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.6341030195381883,
497
+ "grad_norm": 0.5381611425419351,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.6081,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.6577856719952635,
504
+ "grad_norm": 0.6114484557774539,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.6013,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.6814683244523385,
511
+ "grad_norm": 0.7308277575487941,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.6013,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.705150976909414,
518
+ "grad_norm": 0.5543487895907269,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.6034,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.728833629366489,
525
+ "grad_norm": 0.7004280943438956,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.6041,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.7525162818235642,
532
+ "grad_norm": 0.5549471387533644,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.6036,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.7761989342806395,
539
+ "grad_norm": 0.4806128760976835,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.6064,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.7998815867377145,
546
+ "grad_norm": 0.5198713849166644,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.6013,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.82356423919479,
553
+ "grad_norm": 0.4992510602270783,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.6019,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.847246891651865,
560
+ "grad_norm": 0.5736035447222264,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.6027,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.8709295441089402,
567
+ "grad_norm": 0.4838895289542149,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.6105,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.8946121965660154,
574
+ "grad_norm": 0.5587547644562073,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.6027,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.9182948490230904,
581
+ "grad_norm": 0.595674379478466,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.6015,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.941977501480166,
588
+ "grad_norm": 0.578820036510254,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.6093,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.965660153937241,
595
+ "grad_norm": 0.6023612558579958,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.6061,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.9893428063943162,
602
+ "grad_norm": 0.5233076861556437,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.6031,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.9988158673771461,
609
+ "eval_loss": 0.6433995366096497,
610
+ "eval_runtime": 226.6273,
611
+ "eval_samples_per_second": 50.201,
612
+ "eval_steps_per_second": 0.393,
613
+ "step": 844
614
+ },
615
+ {
616
+ "epoch": 2.0130254588513914,
617
+ "grad_norm": 0.6787143504485439,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.5759,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.0367081113084664,
624
+ "grad_norm": 0.5958693467971309,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.5524,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.060390763765542,
631
+ "grad_norm": 0.6686487959774522,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.5564,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.084073416222617,
638
+ "grad_norm": 0.6334086790954905,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.558,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.1077560686796923,
645
+ "grad_norm": 0.5726693373620011,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.5549,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.1314387211367674,
652
+ "grad_norm": 0.7389222692453125,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.5601,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.1551213735938424,
659
+ "grad_norm": 0.5596250429874627,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.5558,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.178804026050918,
666
+ "grad_norm": 0.4980926648118017,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.554,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.202486678507993,
673
+ "grad_norm": 0.5341661818817609,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.5575,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.2261693309650683,
680
+ "grad_norm": 0.5872312499818088,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.5573,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.2498519834221433,
687
+ "grad_norm": 0.5524808246263375,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.5597,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.2735346358792183,
694
+ "grad_norm": 0.6665756455358031,
695
+ "learning_rate": 5e-06,
696
+ "loss": 0.5582,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.297217288336294,
701
+ "grad_norm": 0.6380394178638625,
702
+ "learning_rate": 5e-06,
703
+ "loss": 0.5575,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.320899940793369,
708
+ "grad_norm": 0.6401376648665413,
709
+ "learning_rate": 5e-06,
710
+ "loss": 0.5637,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.3445825932504443,
715
+ "grad_norm": 0.5798343260055008,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.5679,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.3682652457075193,
722
+ "grad_norm": 0.5491726722233458,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.5644,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.3919478981645943,
729
+ "grad_norm": 0.5417761950290281,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.5616,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.4156305506216698,
736
+ "grad_norm": 0.5292463549461751,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.5573,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.4393132030787448,
743
+ "grad_norm": 0.5252209565871296,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.5568,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.4629958555358202,
750
+ "grad_norm": 0.5545040747666857,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.5516,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.4866785079928952,
757
+ "grad_norm": 0.584792726087141,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.5558,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.5103611604499703,
764
+ "grad_norm": 0.5853523679293414,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.5623,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.5340438129070457,
771
+ "grad_norm": 0.6018679654899803,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.5621,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.5577264653641207,
778
+ "grad_norm": 0.5843281213248563,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.5678,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.581409117821196,
785
+ "grad_norm": 0.695068864198405,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.5677,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.605091770278271,
792
+ "grad_norm": 0.5553119611017783,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.5578,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.6287744227353462,
799
+ "grad_norm": 0.5986682054349503,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.5583,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.6524570751924217,
806
+ "grad_norm": 0.5547254396195579,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.56,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.6761397276494967,
813
+ "grad_norm": 0.6846167862474701,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.5706,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.699822380106572,
820
+ "grad_norm": 0.5104743423646483,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.5663,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.723505032563647,
827
+ "grad_norm": 0.5307641334546837,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.564,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.747187685020722,
834
+ "grad_norm": 0.5149548951573419,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.562,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.7708703374777977,
841
+ "grad_norm": 0.6003485422420077,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.5583,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.7945529899348727,
848
+ "grad_norm": 0.6041639812457358,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.5662,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.818235642391948,
855
+ "grad_norm": 0.681355395170715,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.5619,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.841918294849023,
862
+ "grad_norm": 0.5003052671879107,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.5591,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.865600947306098,
869
+ "grad_norm": 0.5184483144480979,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.5595,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.8892835997631736,
876
+ "grad_norm": 0.5244993691156036,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.5583,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.9129662522202486,
883
+ "grad_norm": 0.5251082495659288,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.5606,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.936648904677324,
890
+ "grad_norm": 0.5488470152501833,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.556,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.960331557134399,
897
+ "grad_norm": 0.5568845430294795,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.5596,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.984014209591474,
904
+ "grad_norm": 0.5225267576791486,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.562,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.9982238010657194,
911
+ "eval_loss": 0.6463779211044312,
912
+ "eval_runtime": 227.372,
913
+ "eval_samples_per_second": 50.037,
914
+ "eval_steps_per_second": 0.391,
915
+ "step": 1266
916
+ },
917
+ {
918
+ "epoch": 2.9982238010657194,
919
+ "step": 1266,
920
+ "total_flos": 2120178393415680.0,
921
+ "train_loss": 0.6161920559161459,
922
+ "train_runtime": 37913.0448,
923
+ "train_samples_per_second": 17.103,
924
+ "train_steps_per_second": 0.033
925
+ }
926
+ ],
927
+ "logging_steps": 10,
928
+ "max_steps": 1266,
929
+ "num_input_tokens_seen": 0,
930
+ "num_train_epochs": 3,
931
+ "save_steps": 500,
932
+ "stateful_callbacks": {
933
+ "TrainerControl": {
934
+ "args": {
935
+ "should_epoch_stop": false,
936
+ "should_evaluate": false,
937
+ "should_log": false,
938
+ "should_save": true,
939
+ "should_training_stop": true
940
+ },
941
+ "attributes": {}
942
+ }
943
+ },
944
+ "total_flos": 2120178393415680.0,
945
+ "train_batch_size": 8,
946
+ "trial_name": null,
947
+ "trial_params": null
948
+ }
training_eval_loss.png ADDED
training_loss.png ADDED