sedrickkeh commited on
Commit
85c9e0b
1 Parent(s): f1859c5

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: mistralai/Mistral-7B-v0.1
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: hp_ablations_mistral_adambeta2_0.95
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # hp_ablations_mistral_adambeta2_0.95
17
 
18
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.0723
21
 
 
4
  base_model: mistralai/Mistral-7B-v0.1
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: hp_ablations_mistral_adambeta2_0.95
 
16
 
17
  # hp_ablations_mistral_adambeta2_0.95
18
 
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.0723
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9954430379746837,
3
+ "eval_loss": 0.07233163714408875,
4
+ "eval_runtime": 515.1886,
5
+ "eval_samples_per_second": 25.824,
6
+ "eval_steps_per_second": 0.404,
7
+ "total_flos": 2477170706350080.0,
8
+ "train_loss": 0.4835145230064366,
9
+ "train_runtime": 85503.9751,
10
+ "train_samples_per_second": 8.868,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9954430379746837,
3
+ "eval_loss": 0.07233163714408875,
4
+ "eval_runtime": 515.1886,
5
+ "eval_samples_per_second": 25.824,
6
+ "eval_steps_per_second": 0.404
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9954430379746837,
3
+ "total_flos": 2477170706350080.0,
4
+ "train_loss": 0.4835145230064366,
5
+ "train_runtime": 85503.9751,
6
+ "train_samples_per_second": 8.868,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1095 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9954430379746837,
5
+ "eval_steps": 500,
6
+ "global_step": 1479,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.020253164556962026,
13
+ "grad_norm": 2.8544461931274934,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.7569,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04050632911392405,
20
+ "grad_norm": 2.7444903942187175,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.6507,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.060759493670886074,
27
+ "grad_norm": 1.3943814336457603,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.6289,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0810126582278481,
34
+ "grad_norm": 1.4159200277827484,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.614,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10126582278481013,
41
+ "grad_norm": 1.8420749848935474,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.6034,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.12151898734177215,
48
+ "grad_norm": 1.447732727495403,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.5973,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.14177215189873418,
55
+ "grad_norm": 1.8401989346240508,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.5925,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1620253164556962,
62
+ "grad_norm": 1.4380019004522187,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.5876,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.18227848101265823,
69
+ "grad_norm": 1.657450409370915,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.5863,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.20253164556962025,
76
+ "grad_norm": 2.311058324506438,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.5895,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.22278481012658227,
83
+ "grad_norm": 1.2759051791468548,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.5816,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2430379746835443,
90
+ "grad_norm": 1.3376976540526444,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.5792,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.26329113924050634,
97
+ "grad_norm": 1.6258428242345302,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.578,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.28354430379746837,
104
+ "grad_norm": 1.5716514169659848,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.5677,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3037974683544304,
111
+ "grad_norm": 1.5695310925399224,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.5779,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3240506329113924,
118
+ "grad_norm": 1.5748942702615565,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.5762,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.34430379746835443,
125
+ "grad_norm": 1.739225496496722,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.577,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.36455696202531646,
132
+ "grad_norm": 1.7585144012617044,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.5731,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.3848101265822785,
139
+ "grad_norm": 1.5833716095990014,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.5717,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4050632911392405,
146
+ "grad_norm": 1.6675521594937952,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.5664,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4253164556962025,
153
+ "grad_norm": 1.5564420443090938,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.5621,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.44556962025316454,
160
+ "grad_norm": 1.4391864660123526,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.5678,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.46582278481012657,
167
+ "grad_norm": 1.3545531998280866,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.5665,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.4860759493670886,
174
+ "grad_norm": 1.2117242731823523,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.5628,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5063291139240507,
181
+ "grad_norm": 1.2967375627557465,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.5668,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5265822784810127,
188
+ "grad_norm": 1.4423833757840236,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.5533,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5468354430379747,
195
+ "grad_norm": 1.2030292390095976,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.5623,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.5670886075949367,
202
+ "grad_norm": 1.340394632932045,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.5577,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.5873417721518988,
209
+ "grad_norm": 1.699090610982426,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.5579,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6075949367088608,
216
+ "grad_norm": 1.2878486189890792,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.5576,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6278481012658228,
223
+ "grad_norm": 1.2077186320339615,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.5629,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6481012658227848,
230
+ "grad_norm": 1.3244718672832188,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.5594,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.6683544303797468,
237
+ "grad_norm": 1.417195710228401,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.559,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.6886075949367089,
244
+ "grad_norm": 1.329383308154249,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.5588,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7088607594936709,
251
+ "grad_norm": 1.3387484647946544,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.56,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7291139240506329,
258
+ "grad_norm": 1.2546659088358711,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.5622,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.7493670886075949,
265
+ "grad_norm": 1.2552138171718579,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.5547,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.769620253164557,
272
+ "grad_norm": 1.343049081695452,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.5514,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.789873417721519,
279
+ "grad_norm": 1.7012223994903535,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.5546,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.810126582278481,
286
+ "grad_norm": 1.1159081764354688,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.5549,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.830379746835443,
293
+ "grad_norm": 1.3266370286884424,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.5495,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.850632911392405,
300
+ "grad_norm": 1.1188079131605666,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.5576,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.8708860759493671,
307
+ "grad_norm": 1.281542150580452,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.5508,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.8911392405063291,
314
+ "grad_norm": 1.1598655378018121,
315
+ "learning_rate": 5e-06,
316
+ "loss": 0.5562,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9113924050632911,
321
+ "grad_norm": 1.2672325826373367,
322
+ "learning_rate": 5e-06,
323
+ "loss": 0.5473,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9316455696202531,
328
+ "grad_norm": 1.0317053256498185,
329
+ "learning_rate": 5e-06,
330
+ "loss": 0.5516,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.9518987341772152,
335
+ "grad_norm": 1.4315894237990952,
336
+ "learning_rate": 5e-06,
337
+ "loss": 0.5526,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.9721518987341772,
342
+ "grad_norm": 1.2047073476573256,
343
+ "learning_rate": 5e-06,
344
+ "loss": 0.5499,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.9924050632911392,
349
+ "grad_norm": 1.1500251693609045,
350
+ "learning_rate": 5e-06,
351
+ "loss": 0.5464,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.9984810126582279,
356
+ "eval_loss": 0.06868810206651688,
357
+ "eval_runtime": 512.3603,
358
+ "eval_samples_per_second": 25.966,
359
+ "eval_steps_per_second": 0.406,
360
+ "step": 493
361
+ },
362
+ {
363
+ "epoch": 1.0126582278481013,
364
+ "grad_norm": 1.8413916260979792,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.5079,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.0329113924050632,
371
+ "grad_norm": 1.4722173755845698,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.4751,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.0531645569620254,
378
+ "grad_norm": 1.3281419836326962,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.4713,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.0734177215189873,
385
+ "grad_norm": 1.9790378457546416,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.4733,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.0936708860759494,
392
+ "grad_norm": 1.3589991519525444,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.4702,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.1139240506329113,
399
+ "grad_norm": 1.4545027920691798,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.4722,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.1341772151898735,
406
+ "grad_norm": 1.3978013602179746,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.4695,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.1544303797468354,
413
+ "grad_norm": 1.085881264218112,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.4762,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.1746835443037975,
420
+ "grad_norm": 1.2222577696921726,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.475,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.1949367088607594,
427
+ "grad_norm": 1.1668742626981172,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.4689,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.2151898734177216,
434
+ "grad_norm": 1.2276792224748574,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.4762,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.2354430379746835,
441
+ "grad_norm": 1.453085671614249,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.4721,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.2556962025316456,
448
+ "grad_norm": 1.502759057117359,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.4763,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.2759493670886077,
455
+ "grad_norm": 1.3654526602741475,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.4758,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.2962025316455696,
462
+ "grad_norm": 1.2900057606104782,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.4751,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.3164556962025316,
469
+ "grad_norm": 1.2304140089136695,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.479,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.3367088607594937,
476
+ "grad_norm": 1.3208086599766524,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.4676,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.3569620253164558,
483
+ "grad_norm": 1.6255671967857097,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.4817,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.3772151898734177,
490
+ "grad_norm": 1.2914422612667809,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.4777,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.3974683544303796,
497
+ "grad_norm": 1.1553498242671723,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.4765,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.4177215189873418,
504
+ "grad_norm": 1.0985630409409104,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.4745,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.437974683544304,
511
+ "grad_norm": 1.1922053458640358,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.4796,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.4582278481012658,
518
+ "grad_norm": 1.3398045780563845,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.48,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.4784810126582277,
525
+ "grad_norm": 1.177617617952355,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.4825,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.4987341772151899,
532
+ "grad_norm": 1.2525034867544784,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.4753,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.518987341772152,
539
+ "grad_norm": 1.2039537283128936,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.4779,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.539240506329114,
546
+ "grad_norm": 1.1297848909075034,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.4789,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.5594936708860758,
553
+ "grad_norm": 1.3174710848931364,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.4776,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.579746835443038,
560
+ "grad_norm": 1.175160970448449,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.478,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.6,
567
+ "grad_norm": 1.2815667975924372,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.4807,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.620253164556962,
574
+ "grad_norm": 1.158977784005594,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.4772,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.640506329113924,
581
+ "grad_norm": 1.1864733415229585,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.4697,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.660759493670886,
588
+ "grad_norm": 1.2895166819237298,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.4797,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.6810126582278482,
595
+ "grad_norm": 1.300938286282075,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.4745,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.70126582278481,
602
+ "grad_norm": 1.1424310626896699,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.476,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.721518987341772,
609
+ "grad_norm": 1.1429559951896378,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.478,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.7417721518987341,
616
+ "grad_norm": 1.1739860272827067,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.4783,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.7620253164556963,
623
+ "grad_norm": 1.191849148804322,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.4814,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.7822784810126582,
630
+ "grad_norm": 1.162039130349595,
631
+ "learning_rate": 5e-06,
632
+ "loss": 0.4823,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.80253164556962,
637
+ "grad_norm": 1.2498690007156736,
638
+ "learning_rate": 5e-06,
639
+ "loss": 0.4791,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.8227848101265822,
644
+ "grad_norm": 1.2554926926315564,
645
+ "learning_rate": 5e-06,
646
+ "loss": 0.4785,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.8430379746835444,
651
+ "grad_norm": 1.1957986226654673,
652
+ "learning_rate": 5e-06,
653
+ "loss": 0.4804,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.8632911392405065,
658
+ "grad_norm": 1.1851282579533418,
659
+ "learning_rate": 5e-06,
660
+ "loss": 0.4792,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.8835443037974684,
665
+ "grad_norm": 1.1068170260766412,
666
+ "learning_rate": 5e-06,
667
+ "loss": 0.4757,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.9037974683544303,
672
+ "grad_norm": 1.2646052261464578,
673
+ "learning_rate": 5e-06,
674
+ "loss": 0.4801,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.9240506329113924,
679
+ "grad_norm": 1.333239155517521,
680
+ "learning_rate": 5e-06,
681
+ "loss": 0.4804,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.9443037974683546,
686
+ "grad_norm": 1.1435808455640823,
687
+ "learning_rate": 5e-06,
688
+ "loss": 0.4845,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.9645569620253165,
693
+ "grad_norm": 1.1466649702197023,
694
+ "learning_rate": 5e-06,
695
+ "loss": 0.4829,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.9848101265822784,
700
+ "grad_norm": 1.268837220918901,
701
+ "learning_rate": 5e-06,
702
+ "loss": 0.4834,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.998987341772152,
707
+ "eval_loss": 0.06870175153017044,
708
+ "eval_runtime": 514.0164,
709
+ "eval_samples_per_second": 25.882,
710
+ "eval_steps_per_second": 0.405,
711
+ "step": 987
712
+ },
713
+ {
714
+ "epoch": 2.0050632911392405,
715
+ "grad_norm": 2.1408625149508023,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.4569,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.0253164556962027,
722
+ "grad_norm": 1.72871232368084,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.3942,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.0455696202531644,
729
+ "grad_norm": 1.8639823449544832,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.391,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.0658227848101265,
736
+ "grad_norm": 1.3817144113711173,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.387,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.0860759493670886,
743
+ "grad_norm": 1.5869361079541535,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.3871,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.1063291139240508,
750
+ "grad_norm": 1.2460624418796462,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.3851,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.1265822784810124,
757
+ "grad_norm": 1.7394900572434608,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.3943,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.1468354430379746,
764
+ "grad_norm": 1.338895486927167,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.3897,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.1670886075949367,
771
+ "grad_norm": 1.247982467499197,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.3931,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.187341772151899,
778
+ "grad_norm": 1.3618812768218835,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.3916,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.207594936708861,
785
+ "grad_norm": 1.3590221552926487,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.389,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.2278481012658227,
792
+ "grad_norm": 1.3797000672458826,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.3983,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.248101265822785,
799
+ "grad_norm": 1.2368742400666088,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.3934,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.268354430379747,
806
+ "grad_norm": 1.2904792214170409,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.3961,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.2886075949367086,
813
+ "grad_norm": 1.5782227405689053,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.3977,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.3088607594936708,
820
+ "grad_norm": 1.4737079360584568,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.3933,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.329113924050633,
827
+ "grad_norm": 1.7303325343844742,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.3993,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.349367088607595,
834
+ "grad_norm": 1.4518621606722086,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.3991,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.369620253164557,
841
+ "grad_norm": 2.017892997447158,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.3994,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.389873417721519,
848
+ "grad_norm": 1.5068146289530309,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.3997,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.410126582278481,
855
+ "grad_norm": 1.353124441993217,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.3992,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.430379746835443,
862
+ "grad_norm": 1.4083869167690402,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.3978,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.4506329113924052,
869
+ "grad_norm": 1.2368765464544949,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.3973,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.470886075949367,
876
+ "grad_norm": 1.2620787369427364,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.4011,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.491139240506329,
883
+ "grad_norm": 1.319762068057727,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.4009,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.511392405063291,
890
+ "grad_norm": 1.508263073515773,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.4048,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.5316455696202533,
897
+ "grad_norm": 1.393725315494752,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.3985,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.5518987341772155,
904
+ "grad_norm": 1.7018393169883637,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.3942,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.572151898734177,
911
+ "grad_norm": 1.6451189563967772,
912
+ "learning_rate": 5e-06,
913
+ "loss": 0.4009,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.5924050632911393,
918
+ "grad_norm": 1.3903269923273418,
919
+ "learning_rate": 5e-06,
920
+ "loss": 0.4023,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.6126582278481014,
925
+ "grad_norm": 1.3438952595757327,
926
+ "learning_rate": 5e-06,
927
+ "loss": 0.4075,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.632911392405063,
932
+ "grad_norm": 1.6369476312471234,
933
+ "learning_rate": 5e-06,
934
+ "loss": 0.4019,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.6531645569620252,
939
+ "grad_norm": 1.4002674708903102,
940
+ "learning_rate": 5e-06,
941
+ "loss": 0.4019,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.6734177215189874,
946
+ "grad_norm": 1.5225886664411385,
947
+ "learning_rate": 5e-06,
948
+ "loss": 0.404,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.6936708860759495,
953
+ "grad_norm": 1.378966215529765,
954
+ "learning_rate": 5e-06,
955
+ "loss": 0.4067,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.7139240506329116,
960
+ "grad_norm": 1.4243714009335353,
961
+ "learning_rate": 5e-06,
962
+ "loss": 0.4051,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.7341772151898733,
967
+ "grad_norm": 1.2628130063930583,
968
+ "learning_rate": 5e-06,
969
+ "loss": 0.4047,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.7544303797468355,
974
+ "grad_norm": 1.4068460224070376,
975
+ "learning_rate": 5e-06,
976
+ "loss": 0.4003,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.7746835443037976,
981
+ "grad_norm": 1.5186731540820997,
982
+ "learning_rate": 5e-06,
983
+ "loss": 0.4064,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.7949367088607593,
988
+ "grad_norm": 1.415787690993235,
989
+ "learning_rate": 5e-06,
990
+ "loss": 0.404,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.8151898734177214,
995
+ "grad_norm": 1.4829742066812814,
996
+ "learning_rate": 5e-06,
997
+ "loss": 0.4067,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.8354430379746836,
1002
+ "grad_norm": 1.3153556553473909,
1003
+ "learning_rate": 5e-06,
1004
+ "loss": 0.4002,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.8556962025316457,
1009
+ "grad_norm": 1.258632308468112,
1010
+ "learning_rate": 5e-06,
1011
+ "loss": 0.4088,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.875949367088608,
1016
+ "grad_norm": 1.3069199594530845,
1017
+ "learning_rate": 5e-06,
1018
+ "loss": 0.4049,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.8962025316455695,
1023
+ "grad_norm": 1.348138135055361,
1024
+ "learning_rate": 5e-06,
1025
+ "loss": 0.4055,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.9164556962025316,
1030
+ "grad_norm": 1.3516104016534718,
1031
+ "learning_rate": 5e-06,
1032
+ "loss": 0.4076,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.9367088607594938,
1037
+ "grad_norm": 1.3482820531763435,
1038
+ "learning_rate": 5e-06,
1039
+ "loss": 0.4162,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.9569620253164555,
1044
+ "grad_norm": 1.4854569589520752,
1045
+ "learning_rate": 5e-06,
1046
+ "loss": 0.4042,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.9772151898734176,
1051
+ "grad_norm": 1.2602327451924493,
1052
+ "learning_rate": 5e-06,
1053
+ "loss": 0.4082,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.9954430379746837,
1058
+ "eval_loss": 0.07233163714408875,
1059
+ "eval_runtime": 515.8273,
1060
+ "eval_samples_per_second": 25.792,
1061
+ "eval_steps_per_second": 0.403,
1062
+ "step": 1479
1063
+ },
1064
+ {
1065
+ "epoch": 2.9954430379746837,
1066
+ "step": 1479,
1067
+ "total_flos": 2477170706350080.0,
1068
+ "train_loss": 0.4835145230064366,
1069
+ "train_runtime": 85503.9751,
1070
+ "train_samples_per_second": 8.868,
1071
+ "train_steps_per_second": 0.017
1072
+ }
1073
+ ],
1074
+ "logging_steps": 10,
1075
+ "max_steps": 1479,
1076
+ "num_input_tokens_seen": 0,
1077
+ "num_train_epochs": 3,
1078
+ "save_steps": 500,
1079
+ "stateful_callbacks": {
1080
+ "TrainerControl": {
1081
+ "args": {
1082
+ "should_epoch_stop": false,
1083
+ "should_evaluate": false,
1084
+ "should_log": false,
1085
+ "should_save": true,
1086
+ "should_training_stop": true
1087
+ },
1088
+ "attributes": {}
1089
+ }
1090
+ },
1091
+ "total_flos": 2477170706350080.0,
1092
+ "train_batch_size": 8,
1093
+ "trial_name": null,
1094
+ "trial_params": null
1095
+ }
training_eval_loss.png ADDED
training_loss.png ADDED