sedrickkeh commited on
Commit
769084d
1 Parent(s): 7fe8e42

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen2.5-7B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: hp_ablations_qwen_adambeta2_0.99
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # hp_ablations_qwen_adambeta2_0.99
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.6187
21
 
 
4
  base_model: Qwen/Qwen2.5-7B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: hp_ablations_qwen_adambeta2_0.99
 
16
 
17
  # hp_ablations_qwen_adambeta2_0.99
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6187
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.996011396011396,
3
+ "eval_loss": 0.6186951398849487,
4
+ "eval_runtime": 442.6339,
5
+ "eval_samples_per_second": 26.711,
6
+ "eval_steps_per_second": 0.418,
7
+ "total_flos": 2755219238682624.0,
8
+ "train_loss": 0.6042390294270973,
9
+ "train_runtime": 70307.8473,
10
+ "train_samples_per_second": 9.584,
11
+ "train_steps_per_second": 0.019
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.996011396011396,
3
+ "eval_loss": 0.6186951398849487,
4
+ "eval_runtime": 442.6339,
5
+ "eval_samples_per_second": 26.711,
6
+ "eval_steps_per_second": 0.418
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.996011396011396,
3
+ "total_flos": 2755219238682624.0,
4
+ "train_loss": 0.6042390294270973,
5
+ "train_runtime": 70307.8473,
6
+ "train_samples_per_second": 9.584,
7
+ "train_steps_per_second": 0.019
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,983 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.996011396011396,
5
+ "eval_steps": 500,
6
+ "global_step": 1314,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.022792022792022793,
13
+ "grad_norm": 2.385259024190774,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.7548,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.045584045584045586,
20
+ "grad_norm": 0.8123529833812405,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.7009,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06837606837606838,
27
+ "grad_norm": 0.9370244246162021,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.6806,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.09116809116809117,
34
+ "grad_norm": 0.8655853560135366,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.6804,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11396011396011396,
41
+ "grad_norm": 0.8180572837688457,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.6765,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13675213675213677,
48
+ "grad_norm": 0.7093860636634242,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.6562,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15954415954415954,
55
+ "grad_norm": 0.4818088804643291,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.6529,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.18233618233618235,
62
+ "grad_norm": 0.3912278847825945,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6556,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.20512820512820512,
69
+ "grad_norm": 0.3215150077404874,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.6402,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.22792022792022792,
76
+ "grad_norm": 0.300655966335076,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6414,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.25071225071225073,
83
+ "grad_norm": 0.34016523750354943,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.6326,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.27350427350427353,
90
+ "grad_norm": 0.3082171859656368,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.6409,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2962962962962963,
97
+ "grad_norm": 0.2871758335134722,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.6418,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3190883190883191,
104
+ "grad_norm": 0.3016573193865793,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.644,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3418803418803419,
111
+ "grad_norm": 0.3245714553050615,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.6365,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3646723646723647,
118
+ "grad_norm": 0.3095587744419788,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6416,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.38746438746438744,
125
+ "grad_norm": 0.3459161982130226,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.6334,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.41025641025641024,
132
+ "grad_norm": 0.2994880078186018,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.639,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.43304843304843305,
139
+ "grad_norm": 0.3040019029032286,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.6315,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.45584045584045585,
146
+ "grad_norm": 0.3643957444928807,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.6396,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.47863247863247865,
153
+ "grad_norm": 0.30480683216487126,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6359,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.5014245014245015,
160
+ "grad_norm": 0.29947146923893814,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6396,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5242165242165242,
167
+ "grad_norm": 0.32582064184580617,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.6352,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5470085470085471,
174
+ "grad_norm": 0.30252410341946956,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.6311,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5698005698005698,
181
+ "grad_norm": 0.3358250403363141,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.636,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5925925925925926,
188
+ "grad_norm": 0.30807735109494233,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.6342,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6153846153846154,
195
+ "grad_norm": 0.3131812728861157,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.6313,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6381766381766382,
202
+ "grad_norm": 0.31985241120653257,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.6421,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6609686609686609,
209
+ "grad_norm": 0.324476247054874,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.6308,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6837606837606838,
216
+ "grad_norm": 0.28883012776471284,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.6288,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.7065527065527065,
223
+ "grad_norm": 0.2970547925823876,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.6287,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7293447293447294,
230
+ "grad_norm": 0.341548316793182,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.6292,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7521367521367521,
237
+ "grad_norm": 0.3033814568485461,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.6259,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7749287749287749,
244
+ "grad_norm": 0.328449831938576,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.6317,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7977207977207977,
251
+ "grad_norm": 0.3371917707440557,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.6388,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8205128205128205,
258
+ "grad_norm": 0.31461587606014585,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.6305,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8433048433048433,
265
+ "grad_norm": 0.33907135118113235,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.6243,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8660968660968661,
272
+ "grad_norm": 0.31120719532837904,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.6366,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8888888888888888,
279
+ "grad_norm": 0.3280827254175563,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.6352,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.9116809116809117,
286
+ "grad_norm": 0.2976231396161992,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.6384,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9344729344729344,
293
+ "grad_norm": 0.28856802825621314,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.6346,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9572649572649573,
300
+ "grad_norm": 0.30274834115512034,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.6215,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.98005698005698,
307
+ "grad_norm": 0.3405357700109309,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.6345,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9982905982905983,
314
+ "eval_loss": 0.6251771450042725,
315
+ "eval_runtime": 441.0835,
316
+ "eval_samples_per_second": 26.804,
317
+ "eval_steps_per_second": 0.419,
318
+ "step": 438
319
+ },
320
+ {
321
+ "epoch": 1.0034188034188034,
322
+ "grad_norm": 0.3526043748031207,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6473,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.0262108262108263,
329
+ "grad_norm": 0.3319043583132696,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6019,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.049002849002849,
336
+ "grad_norm": 0.3007005214276095,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.5956,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.0717948717948718,
343
+ "grad_norm": 0.2919687932138887,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.5965,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0945868945868946,
350
+ "grad_norm": 0.3068988143487303,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.604,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.1173789173789175,
357
+ "grad_norm": 0.32280952438742344,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.609,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.1401709401709401,
364
+ "grad_norm": 0.2954901833336679,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.5988,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.162962962962963,
371
+ "grad_norm": 0.31133600652457694,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.5968,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1857549857549858,
378
+ "grad_norm": 0.29782206144100504,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6025,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.2085470085470085,
385
+ "grad_norm": 0.32243670462431007,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.5954,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2313390313390313,
392
+ "grad_norm": 0.28737683552377413,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6057,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2541310541310542,
399
+ "grad_norm": 0.3449585599543857,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.6024,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2769230769230768,
406
+ "grad_norm": 0.28830841917644784,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.604,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2997150997150997,
413
+ "grad_norm": 0.30612494842503374,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.5978,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.3225071225071225,
420
+ "grad_norm": 0.2724077727638273,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.5963,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3452991452991454,
427
+ "grad_norm": 0.29877934311409626,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.596,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.368091168091168,
434
+ "grad_norm": 0.34680996564801814,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.6016,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.390883190883191,
441
+ "grad_norm": 0.31986987718999754,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.6017,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.4136752136752135,
448
+ "grad_norm": 0.2966866180175517,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.6043,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.4364672364672364,
455
+ "grad_norm": 0.3137779112309709,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.6023,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4592592592592593,
462
+ "grad_norm": 0.3096331947645023,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.5971,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4820512820512821,
469
+ "grad_norm": 0.2966178587528764,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.5951,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.504843304843305,
476
+ "grad_norm": 0.29594439286210916,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.5948,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.5276353276353276,
483
+ "grad_norm": 0.3126484811119376,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.6024,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.5504273504273505,
490
+ "grad_norm": 0.27860775073751143,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.5909,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.573219373219373,
497
+ "grad_norm": 0.3266295092665208,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.5949,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.596011396011396,
504
+ "grad_norm": 0.2842030090288304,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.6104,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.6188034188034188,
511
+ "grad_norm": 0.32121111384458395,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.5975,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.6415954415954417,
518
+ "grad_norm": 0.29063941900587575,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.6021,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6643874643874645,
525
+ "grad_norm": 0.32700601541341673,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.5951,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.6871794871794872,
532
+ "grad_norm": 0.3203353680503934,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.5963,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.7099715099715098,
539
+ "grad_norm": 0.2979570919587926,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.5936,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.7327635327635327,
546
+ "grad_norm": 0.3075332516169518,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.5976,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.7555555555555555,
553
+ "grad_norm": 0.29585676758575824,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.594,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7783475783475784,
560
+ "grad_norm": 0.3089318908749895,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.6011,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.8011396011396013,
567
+ "grad_norm": 0.2973271362521097,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.5986,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.823931623931624,
574
+ "grad_norm": 0.3110764584316045,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.5855,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.8467236467236468,
581
+ "grad_norm": 0.3124880561801754,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.5934,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8695156695156694,
588
+ "grad_norm": 0.30291702147004973,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.5911,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8923076923076922,
595
+ "grad_norm": 0.32631521859125023,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.5949,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.915099715099715,
602
+ "grad_norm": 0.31134842892261755,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.5993,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.937891737891738,
609
+ "grad_norm": 0.2973092874298441,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.5975,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.9606837606837608,
616
+ "grad_norm": 0.3135983174480875,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.5988,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9834757834757835,
623
+ "grad_norm": 0.3588843911614199,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.5962,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9994301994301993,
630
+ "eval_loss": 0.6187435388565063,
631
+ "eval_runtime": 442.4932,
632
+ "eval_samples_per_second": 26.719,
633
+ "eval_steps_per_second": 0.418,
634
+ "step": 877
635
+ },
636
+ {
637
+ "epoch": 2.006837606837607,
638
+ "grad_norm": 0.33146665781755474,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.6157,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.0296296296296297,
645
+ "grad_norm": 0.3417879164889085,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.5552,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.0524216524216525,
652
+ "grad_norm": 0.31311130133402526,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.5703,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.0752136752136754,
659
+ "grad_norm": 0.36299710241549005,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.5684,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.098005698005698,
666
+ "grad_norm": 0.3234011191276784,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.5715,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.1207977207977207,
673
+ "grad_norm": 0.2872017880714933,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.5695,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.1435897435897435,
680
+ "grad_norm": 0.3040973085910502,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.5642,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.1663817663817664,
687
+ "grad_norm": 0.31464737696561895,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.5651,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.1891737891737892,
694
+ "grad_norm": 0.30721153233486376,
695
+ "learning_rate": 5e-06,
696
+ "loss": 0.5702,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.211965811965812,
701
+ "grad_norm": 0.29100570938815024,
702
+ "learning_rate": 5e-06,
703
+ "loss": 0.5696,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.234757834757835,
708
+ "grad_norm": 0.2865330940363621,
709
+ "learning_rate": 5e-06,
710
+ "loss": 0.5592,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.2575498575498574,
715
+ "grad_norm": 0.32262288007644346,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.5683,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.2803418803418802,
722
+ "grad_norm": 0.3105400955944539,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.5686,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.303133903133903,
729
+ "grad_norm": 0.3099166916965722,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.5661,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.325925925925926,
736
+ "grad_norm": 0.3155525112335734,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.5691,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.348717948717949,
743
+ "grad_norm": 0.35065823324178585,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.5704,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.3715099715099717,
750
+ "grad_norm": 0.3040779955508841,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.5683,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.394301994301994,
757
+ "grad_norm": 0.30725601996623925,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.5677,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.417094017094017,
764
+ "grad_norm": 0.3105228961513666,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.576,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.43988603988604,
771
+ "grad_norm": 0.3055210157169179,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.5788,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.4626780626780627,
778
+ "grad_norm": 0.2994955220915457,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.5741,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.4854700854700855,
785
+ "grad_norm": 0.3020646523694022,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.5718,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.5082621082621084,
792
+ "grad_norm": 0.3106622215375145,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.5782,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.5310541310541312,
799
+ "grad_norm": 0.3098804695854211,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.5717,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.5538461538461537,
806
+ "grad_norm": 0.30535958301464405,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.5698,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.5766381766381765,
813
+ "grad_norm": 0.3128065336180961,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.5693,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.5994301994301994,
820
+ "grad_norm": 0.3130918719392634,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.5689,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.6222222222222222,
827
+ "grad_norm": 0.30237657391826733,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.5692,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.645014245014245,
834
+ "grad_norm": 0.3100505807857925,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.5703,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.667806267806268,
841
+ "grad_norm": 0.30792158331270064,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.5731,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.690598290598291,
848
+ "grad_norm": 0.29314623782482024,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.5682,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.7133903133903132,
855
+ "grad_norm": 0.28727948476065146,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.5694,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.736182336182336,
862
+ "grad_norm": 0.28933455870139535,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.5725,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.758974358974359,
869
+ "grad_norm": 0.28963278859483754,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.5759,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.781766381766382,
876
+ "grad_norm": 0.2875749861529812,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.5658,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.8045584045584047,
883
+ "grad_norm": 0.2973063720548093,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.5643,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.827350427350427,
890
+ "grad_norm": 0.3147480931046027,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.5791,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.8501424501424504,
897
+ "grad_norm": 0.2995369698557402,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.5757,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.872934472934473,
904
+ "grad_norm": 0.3004285006684937,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.5729,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.8957264957264957,
911
+ "grad_norm": 0.3037842000082908,
912
+ "learning_rate": 5e-06,
913
+ "loss": 0.5739,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.9185185185185185,
918
+ "grad_norm": 0.2868126060885826,
919
+ "learning_rate": 5e-06,
920
+ "loss": 0.5641,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.9413105413105414,
925
+ "grad_norm": 0.30141853606157404,
926
+ "learning_rate": 5e-06,
927
+ "loss": 0.5643,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.9641025641025642,
932
+ "grad_norm": 0.35584532467341695,
933
+ "learning_rate": 5e-06,
934
+ "loss": 0.5654,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.9868945868945866,
939
+ "grad_norm": 0.3043876172487461,
940
+ "learning_rate": 5e-06,
941
+ "loss": 0.5752,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.996011396011396,
946
+ "eval_loss": 0.6186951398849487,
947
+ "eval_runtime": 441.5424,
948
+ "eval_samples_per_second": 26.777,
949
+ "eval_steps_per_second": 0.419,
950
+ "step": 1314
951
+ },
952
+ {
953
+ "epoch": 2.996011396011396,
954
+ "step": 1314,
955
+ "total_flos": 2755219238682624.0,
956
+ "train_loss": 0.6042390294270973,
957
+ "train_runtime": 70307.8473,
958
+ "train_samples_per_second": 9.584,
959
+ "train_steps_per_second": 0.019
960
+ }
961
+ ],
962
+ "logging_steps": 10,
963
+ "max_steps": 1314,
964
+ "num_input_tokens_seen": 0,
965
+ "num_train_epochs": 3,
966
+ "save_steps": 500,
967
+ "stateful_callbacks": {
968
+ "TrainerControl": {
969
+ "args": {
970
+ "should_epoch_stop": false,
971
+ "should_evaluate": false,
972
+ "should_log": false,
973
+ "should_save": true,
974
+ "should_training_stop": true
975
+ },
976
+ "attributes": {}
977
+ }
978
+ },
979
+ "total_flos": 2755219238682624.0,
980
+ "train_batch_size": 8,
981
+ "trial_name": null,
982
+ "trial_params": null
983
+ }
training_eval_loss.png ADDED
training_loss.png ADDED