tangken333 commited on
Commit
5113f05
·
verified ·
1 Parent(s): aea0e7f

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -1
  2. all_results.json +8 -0
  3. train_results.json +8 -0
  4. trainer_state.json +651 -0
  5. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen2.5-Coder-7B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: SWE-BENCH-400-planning-claude_qwen_code_7B_test_swe_claude_planning
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # SWE-BENCH-400-planning-claude_qwen_code_7B_test_swe_claude_planning
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen2.5-Coder-7B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: SWE-BENCH-400-planning-claude_qwen_code_7B_test_swe_claude_planning
 
16
 
17
  # SWE-BENCH-400-planning-claude_qwen_code_7B_test_swe_claude_planning
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the SWE-BENCH-400-planning-claude dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 3.952374498459648e+16,
4
+ "train_loss": 0.17466499442341685,
5
+ "train_runtime": 4967.3247,
6
+ "train_samples_per_second": 0.84,
7
+ "train_steps_per_second": 0.018
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 3.952374498459648e+16,
4
+ "train_loss": 0.17466499442341685,
5
+ "train_runtime": 4967.3247,
6
+ "train_samples_per_second": 0.84,
7
+ "train_steps_per_second": 0.018
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,651 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 87,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.034482758620689655,
13
+ "grad_norm": 1.8968472863706825,
14
+ "learning_rate": 1.111111111111111e-06,
15
+ "loss": 0.435,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.06896551724137931,
20
+ "grad_norm": 1.3787873388390994,
21
+ "learning_rate": 2.222222222222222e-06,
22
+ "loss": 0.3556,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.10344827586206896,
27
+ "grad_norm": 1.500745719809916,
28
+ "learning_rate": 3.3333333333333333e-06,
29
+ "loss": 0.3895,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.13793103448275862,
34
+ "grad_norm": 1.3758212628963946,
35
+ "learning_rate": 4.444444444444444e-06,
36
+ "loss": 0.3798,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.1724137931034483,
41
+ "grad_norm": 1.0725134036871664,
42
+ "learning_rate": 5.555555555555557e-06,
43
+ "loss": 0.3282,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.20689655172413793,
48
+ "grad_norm": 0.7977790045197081,
49
+ "learning_rate": 6.666666666666667e-06,
50
+ "loss": 0.2932,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.2413793103448276,
55
+ "grad_norm": 0.8837691300884692,
56
+ "learning_rate": 7.77777777777778e-06,
57
+ "loss": 0.3141,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.27586206896551724,
62
+ "grad_norm": 0.705940070600187,
63
+ "learning_rate": 8.888888888888888e-06,
64
+ "loss": 0.2514,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.3103448275862069,
69
+ "grad_norm": 0.5506871024791313,
70
+ "learning_rate": 1e-05,
71
+ "loss": 0.2285,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.3448275862068966,
76
+ "grad_norm": 0.9069273874218927,
77
+ "learning_rate": 9.995944990857848e-06,
78
+ "loss": 0.3054,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.3793103448275862,
83
+ "grad_norm": 0.7378234840973698,
84
+ "learning_rate": 9.983786540671052e-06,
85
+ "loss": 0.2962,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.41379310344827586,
90
+ "grad_norm": 0.6054420618930146,
91
+ "learning_rate": 9.96354437049027e-06,
92
+ "loss": 0.2805,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.4482758620689655,
97
+ "grad_norm": 0.5093901922135685,
98
+ "learning_rate": 9.935251313189564e-06,
99
+ "loss": 0.2664,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.4827586206896552,
104
+ "grad_norm": 0.5788307564961488,
105
+ "learning_rate": 9.89895326021134e-06,
106
+ "loss": 0.2748,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.5172413793103449,
111
+ "grad_norm": 0.4070144278077285,
112
+ "learning_rate": 9.854709087130261e-06,
113
+ "loss": 0.1965,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.5517241379310345,
118
+ "grad_norm": 0.44452387037855084,
119
+ "learning_rate": 9.802590558156863e-06,
120
+ "loss": 0.2413,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.5862068965517241,
125
+ "grad_norm": 0.46435536348228057,
126
+ "learning_rate": 9.742682209735727e-06,
127
+ "loss": 0.216,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.6206896551724138,
132
+ "grad_norm": 0.3764221335514055,
133
+ "learning_rate": 9.675081213427076e-06,
134
+ "loss": 0.2056,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.6551724137931034,
139
+ "grad_norm": 0.4301176989354492,
140
+ "learning_rate": 9.599897218294122e-06,
141
+ "loss": 0.2318,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.6896551724137931,
146
+ "grad_norm": 0.47375751198098554,
147
+ "learning_rate": 9.517252173051912e-06,
148
+ "loss": 0.2306,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.7241379310344828,
153
+ "grad_norm": 0.36713668347068407,
154
+ "learning_rate": 9.427280128266049e-06,
155
+ "loss": 0.1925,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.7586206896551724,
160
+ "grad_norm": 0.3605603008015653,
161
+ "learning_rate": 9.330127018922195e-06,
162
+ "loss": 0.2035,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.7931034482758621,
167
+ "grad_norm": 0.4148028274133272,
168
+ "learning_rate": 9.225950427718974e-06,
169
+ "loss": 0.2447,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.8275862068965517,
174
+ "grad_norm": 0.37584064602396255,
175
+ "learning_rate": 9.114919329468283e-06,
176
+ "loss": 0.1961,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.8620689655172413,
181
+ "grad_norm": 0.37162969905754883,
182
+ "learning_rate": 8.997213817017508e-06,
183
+ "loss": 0.2143,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.896551724137931,
188
+ "grad_norm": 0.3768066216380791,
189
+ "learning_rate": 8.873024809138272e-06,
190
+ "loss": 0.2177,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.9310344827586207,
195
+ "grad_norm": 0.3632688725752434,
196
+ "learning_rate": 8.742553740855507e-06,
197
+ "loss": 0.2078,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.9655172413793104,
202
+ "grad_norm": 0.3933393816831956,
203
+ "learning_rate": 8.606012236719073e-06,
204
+ "loss": 0.2053,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 1.0,
209
+ "grad_norm": 0.37560278938859387,
210
+ "learning_rate": 8.463621767547998e-06,
211
+ "loss": 0.2078,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 1.0344827586206897,
216
+ "grad_norm": 0.31034148392401967,
217
+ "learning_rate": 8.315613291203977e-06,
218
+ "loss": 0.1503,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 1.0689655172413792,
223
+ "grad_norm": 0.3472551839526283,
224
+ "learning_rate": 8.162226877976886e-06,
225
+ "loss": 0.1624,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 1.103448275862069,
230
+ "grad_norm": 0.3119751636900065,
231
+ "learning_rate": 8.003711321189895e-06,
232
+ "loss": 0.1525,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 1.1379310344827587,
237
+ "grad_norm": 0.36473590972460807,
238
+ "learning_rate": 7.84032373365578e-06,
239
+ "loss": 0.1743,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 1.1724137931034484,
244
+ "grad_norm": 0.3754222460318716,
245
+ "learning_rate": 7.672329130639007e-06,
246
+ "loss": 0.1839,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.206896551724138,
251
+ "grad_norm": 0.3440125880926874,
252
+ "learning_rate": 7.500000000000001e-06,
253
+ "loss": 0.1691,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.2413793103448276,
258
+ "grad_norm": 0.32158510549152597,
259
+ "learning_rate": 7.323615860218844e-06,
260
+ "loss": 0.1535,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.2758620689655173,
265
+ "grad_norm": 0.3339665959815591,
266
+ "learning_rate": 7.143462807015271e-06,
267
+ "loss": 0.1556,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.3103448275862069,
272
+ "grad_norm": 0.34776270320077474,
273
+ "learning_rate": 6.959833049300376e-06,
274
+ "loss": 0.1635,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.3448275862068966,
279
+ "grad_norm": 0.3664731009524177,
280
+ "learning_rate": 6.773024435212678e-06,
281
+ "loss": 0.1629,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.3793103448275863,
286
+ "grad_norm": 0.35319022882448053,
287
+ "learning_rate": 6.583339969007364e-06,
288
+ "loss": 0.1548,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.4137931034482758,
293
+ "grad_norm": 0.322074992178244,
294
+ "learning_rate": 6.391087319582264e-06,
295
+ "loss": 0.1492,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.4482758620689655,
300
+ "grad_norm": 0.3745066020307014,
301
+ "learning_rate": 6.1965783214377895e-06,
302
+ "loss": 0.1678,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.4827586206896552,
307
+ "grad_norm": 0.3349892745642585,
308
+ "learning_rate": 6.000128468880223e-06,
309
+ "loss": 0.1352,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.5172413793103448,
314
+ "grad_norm": 0.3621146034278814,
315
+ "learning_rate": 5.8020564042888015e-06,
316
+ "loss": 0.1535,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.5517241379310345,
321
+ "grad_norm": 0.3356997566620184,
322
+ "learning_rate": 5.6026834012766155e-06,
323
+ "loss": 0.1389,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.5862068965517242,
328
+ "grad_norm": 0.3393649872853136,
329
+ "learning_rate": 5.402332843583631e-06,
330
+ "loss": 0.1418,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.6206896551724137,
335
+ "grad_norm": 0.3288903512386936,
336
+ "learning_rate": 5.201329700547077e-06,
337
+ "loss": 0.1318,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.6551724137931034,
342
+ "grad_norm": 0.35291058020727184,
343
+ "learning_rate": 5e-06,
344
+ "loss": 0.139,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.6896551724137931,
349
+ "grad_norm": 0.31859428188018823,
350
+ "learning_rate": 4.798670299452926e-06,
351
+ "loss": 0.132,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.7241379310344827,
356
+ "grad_norm": 0.36948885648092306,
357
+ "learning_rate": 4.597667156416371e-06,
358
+ "loss": 0.1459,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.7586206896551724,
363
+ "grad_norm": 0.4140907666360901,
364
+ "learning_rate": 4.397316598723385e-06,
365
+ "loss": 0.1898,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.793103448275862,
370
+ "grad_norm": 0.37454232433271367,
371
+ "learning_rate": 4.1979435957111984e-06,
372
+ "loss": 0.1519,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 1.8275862068965516,
377
+ "grad_norm": 0.36698948317992974,
378
+ "learning_rate": 3.999871531119779e-06,
379
+ "loss": 0.1563,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 1.8620689655172413,
384
+ "grad_norm": 0.3987168791517662,
385
+ "learning_rate": 3.803421678562213e-06,
386
+ "loss": 0.1538,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 1.896551724137931,
391
+ "grad_norm": 0.35639343871652807,
392
+ "learning_rate": 3.6089126804177373e-06,
393
+ "loss": 0.1312,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 1.9310344827586206,
398
+ "grad_norm": 0.3051946271043259,
399
+ "learning_rate": 3.416660030992639e-06,
400
+ "loss": 0.1248,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 1.9655172413793105,
405
+ "grad_norm": 0.32352874901380435,
406
+ "learning_rate": 3.226975564787322e-06,
407
+ "loss": 0.1217,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 2.0,
412
+ "grad_norm": 0.3834889635507212,
413
+ "learning_rate": 3.040166950699626e-06,
414
+ "loss": 0.1601,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 2.0344827586206895,
419
+ "grad_norm": 0.311091599579286,
420
+ "learning_rate": 2.8565371929847286e-06,
421
+ "loss": 0.1127,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 2.0689655172413794,
426
+ "grad_norm": 0.35138772971857607,
427
+ "learning_rate": 2.6763841397811576e-06,
428
+ "loss": 0.1301,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 2.103448275862069,
433
+ "grad_norm": 0.3412886489094977,
434
+ "learning_rate": 2.5000000000000015e-06,
435
+ "loss": 0.1243,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 2.1379310344827585,
440
+ "grad_norm": 0.33728563398551564,
441
+ "learning_rate": 2.3276708693609947e-06,
442
+ "loss": 0.1144,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 2.1724137931034484,
447
+ "grad_norm": 0.3115082544602725,
448
+ "learning_rate": 2.159676266344222e-06,
449
+ "loss": 0.1063,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 2.206896551724138,
454
+ "grad_norm": 0.3525243286834508,
455
+ "learning_rate": 1.996288678810105e-06,
456
+ "loss": 0.1259,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 2.2413793103448274,
461
+ "grad_norm": 0.32371434370720314,
462
+ "learning_rate": 1.8377731220231144e-06,
463
+ "loss": 0.1019,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 2.2758620689655173,
468
+ "grad_norm": 0.30148326256239505,
469
+ "learning_rate": 1.6843867087960252e-06,
470
+ "loss": 0.1049,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 2.310344827586207,
475
+ "grad_norm": 0.3311910822062836,
476
+ "learning_rate": 1.5363782324520033e-06,
477
+ "loss": 0.1106,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 2.344827586206897,
482
+ "grad_norm": 0.3506409615806702,
483
+ "learning_rate": 1.3939877632809279e-06,
484
+ "loss": 0.1123,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 2.3793103448275863,
489
+ "grad_norm": 0.305444065384095,
490
+ "learning_rate": 1.257446259144494e-06,
491
+ "loss": 0.102,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.413793103448276,
496
+ "grad_norm": 0.2776673923244958,
497
+ "learning_rate": 1.1269751908617277e-06,
498
+ "loss": 0.0889,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.4482758620689653,
503
+ "grad_norm": 0.2853344145059976,
504
+ "learning_rate": 1.0027861829824953e-06,
505
+ "loss": 0.0905,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.4827586206896552,
510
+ "grad_norm": 0.3297908783701314,
511
+ "learning_rate": 8.850806705317183e-07,
512
+ "loss": 0.1079,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.5172413793103448,
517
+ "grad_norm": 0.32560370624682045,
518
+ "learning_rate": 7.740495722810271e-07,
519
+ "loss": 0.1079,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.5517241379310347,
524
+ "grad_norm": 0.35586337791264894,
525
+ "learning_rate": 6.698729810778065e-07,
526
+ "loss": 0.1037,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.586206896551724,
531
+ "grad_norm": 0.3315175811831225,
532
+ "learning_rate": 5.727198717339511e-07,
533
+ "loss": 0.1075,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.6206896551724137,
538
+ "grad_norm": 0.35277939107078204,
539
+ "learning_rate": 4.827478269480895e-07,
540
+ "loss": 0.1132,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.655172413793103,
545
+ "grad_norm": 0.3970709020417667,
546
+ "learning_rate": 4.001027817058789e-07,
547
+ "loss": 0.1272,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 2.689655172413793,
552
+ "grad_norm": 0.31343582687046845,
553
+ "learning_rate": 3.2491878657292643e-07,
554
+ "loss": 0.1086,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 2.7241379310344827,
559
+ "grad_norm": 0.36817444381442266,
560
+ "learning_rate": 2.573177902642726e-07,
561
+ "loss": 0.1214,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 2.7586206896551726,
566
+ "grad_norm": 0.3201480217673011,
567
+ "learning_rate": 1.9740944184313882e-07,
568
+ "loss": 0.0993,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 2.793103448275862,
573
+ "grad_norm": 0.3588278131749075,
574
+ "learning_rate": 1.4529091286973994e-07,
575
+ "loss": 0.1071,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 2.8275862068965516,
580
+ "grad_norm": 0.3616467526970753,
581
+ "learning_rate": 1.0104673978866164e-07,
582
+ "loss": 0.1112,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 2.862068965517241,
587
+ "grad_norm": 0.3722334553870228,
588
+ "learning_rate": 6.474868681043578e-08,
589
+ "loss": 0.126,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 2.896551724137931,
594
+ "grad_norm": 0.312011836899645,
595
+ "learning_rate": 3.645562950973014e-08,
596
+ "loss": 0.0979,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 2.9310344827586206,
601
+ "grad_norm": 0.3293502901375024,
602
+ "learning_rate": 1.6213459328950355e-08,
603
+ "loss": 0.1006,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 2.9655172413793105,
608
+ "grad_norm": 0.33847790149852947,
609
+ "learning_rate": 4.055009142152066e-09,
610
+ "loss": 0.1012,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 3.0,
615
+ "grad_norm": 0.3498051357440655,
616
+ "learning_rate": 0.0,
617
+ "loss": 0.1129,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 3.0,
622
+ "step": 87,
623
+ "total_flos": 3.952374498459648e+16,
624
+ "train_loss": 0.17466499442341685,
625
+ "train_runtime": 4967.3247,
626
+ "train_samples_per_second": 0.84,
627
+ "train_steps_per_second": 0.018
628
+ }
629
+ ],
630
+ "logging_steps": 1,
631
+ "max_steps": 87,
632
+ "num_input_tokens_seen": 0,
633
+ "num_train_epochs": 3,
634
+ "save_steps": 200,
635
+ "stateful_callbacks": {
636
+ "TrainerControl": {
637
+ "args": {
638
+ "should_epoch_stop": false,
639
+ "should_evaluate": false,
640
+ "should_log": false,
641
+ "should_save": true,
642
+ "should_training_stop": true
643
+ },
644
+ "attributes": {}
645
+ }
646
+ },
647
+ "total_flos": 3.952374498459648e+16,
648
+ "train_batch_size": 1,
649
+ "trial_name": null,
650
+ "trial_params": null
651
+ }
training_loss.png ADDED