sedrickkeh commited on
Commit
95c8006
·
verified ·
1 Parent(s): d54e8db

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_scheduler_inverse_sqrt
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # hp_ablations_mistral_scheduler_inverse_sqrt
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: 0.0726
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_scheduler_inverse_sqrt
 
16
 
17
  # hp_ablations_mistral_scheduler_inverse_sqrt
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: 0.0726
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9954430379746837,
3
+ "eval_loss": 0.07256945222616196,
4
+ "eval_runtime": 513.5115,
5
+ "eval_samples_per_second": 25.908,
6
+ "eval_steps_per_second": 0.405,
7
+ "total_flos": 2477170706350080.0,
8
+ "train_loss": 0.4816304181700546,
9
+ "train_runtime": 84877.5943,
10
+ "train_samples_per_second": 8.934,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9954430379746837,
3
+ "eval_loss": 0.07256945222616196,
4
+ "eval_runtime": 513.5115,
5
+ "eval_samples_per_second": 25.908,
6
+ "eval_steps_per_second": 0.405
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9954430379746837,
3
+ "total_flos": 2477170706350080.0,
4
+ "train_loss": 0.4816304181700546,
5
+ "train_runtime": 84877.5943,
6
+ "train_samples_per_second": 8.934,
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": 2.8788035764205353,
14
+ "learning_rate": 4.997501873438867e-06,
15
+ "loss": 0.7568,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04050632911392405,
20
+ "grad_norm": 2.361845721552567,
21
+ "learning_rate": 4.995007487521836e-06,
22
+ "loss": 0.6506,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.060759493670886074,
27
+ "grad_norm": 1.6819050271374236,
28
+ "learning_rate": 4.992516832922945e-06,
29
+ "loss": 0.6289,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0810126582278481,
34
+ "grad_norm": 1.3553267881067168,
35
+ "learning_rate": 4.990029900348746e-06,
36
+ "loss": 0.6131,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10126582278481013,
41
+ "grad_norm": 1.674182079689069,
42
+ "learning_rate": 4.987546680538165e-06,
43
+ "loss": 0.6032,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.12151898734177215,
48
+ "grad_norm": 1.554922293674434,
49
+ "learning_rate": 4.985067164262359e-06,
50
+ "loss": 0.5973,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.14177215189873418,
55
+ "grad_norm": 1.7080682270541627,
56
+ "learning_rate": 4.98259134232457e-06,
57
+ "loss": 0.5926,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1620253164556962,
62
+ "grad_norm": 1.8909068615278344,
63
+ "learning_rate": 4.980119205559974e-06,
64
+ "loss": 0.5876,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.18227848101265823,
69
+ "grad_norm": 1.7897935291434377,
70
+ "learning_rate": 4.977650744835555e-06,
71
+ "loss": 0.5865,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.20253164556962025,
76
+ "grad_norm": 1.4212221114505905,
77
+ "learning_rate": 4.975185951049947e-06,
78
+ "loss": 0.5897,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.22278481012658227,
83
+ "grad_norm": 1.528570509738026,
84
+ "learning_rate": 4.972724815133302e-06,
85
+ "loss": 0.5811,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2430379746835443,
90
+ "grad_norm": 1.5914255034072444,
91
+ "learning_rate": 4.970267328047151e-06,
92
+ "loss": 0.5791,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.26329113924050634,
97
+ "grad_norm": 1.8379447405729261,
98
+ "learning_rate": 4.9678134807842575e-06,
99
+ "loss": 0.5779,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.28354430379746837,
104
+ "grad_norm": 1.550572864034472,
105
+ "learning_rate": 4.965363264368484e-06,
106
+ "loss": 0.5678,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3037974683544304,
111
+ "grad_norm": 1.951539283064557,
112
+ "learning_rate": 4.962916669854652e-06,
113
+ "loss": 0.5777,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3240506329113924,
118
+ "grad_norm": 1.6352937401764855,
119
+ "learning_rate": 4.960473688328407e-06,
120
+ "loss": 0.5761,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.34430379746835443,
125
+ "grad_norm": 1.7905857639942138,
126
+ "learning_rate": 4.95803431090608e-06,
127
+ "loss": 0.5766,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.36455696202531646,
132
+ "grad_norm": 2.7969439928849193,
133
+ "learning_rate": 4.955598528734554e-06,
134
+ "loss": 0.5726,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.3848101265822785,
139
+ "grad_norm": 1.7406434738591292,
140
+ "learning_rate": 4.953166332991125e-06,
141
+ "loss": 0.5721,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4050632911392405,
146
+ "grad_norm": 2.195230967825761,
147
+ "learning_rate": 4.950737714883372e-06,
148
+ "loss": 0.5652,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4253164556962025,
153
+ "grad_norm": 1.5840463798102122,
154
+ "learning_rate": 4.948312665649022e-06,
155
+ "loss": 0.561,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.44556962025316454,
160
+ "grad_norm": 1.400469198350245,
161
+ "learning_rate": 4.945891176555817e-06,
162
+ "loss": 0.5667,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.46582278481012657,
167
+ "grad_norm": 1.8476115052956739,
168
+ "learning_rate": 4.943473238901383e-06,
169
+ "loss": 0.5671,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.4860759493670886,
174
+ "grad_norm": 1.543277779556069,
175
+ "learning_rate": 4.941058844013094e-06,
176
+ "loss": 0.5631,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5063291139240507,
181
+ "grad_norm": 1.666354569302293,
182
+ "learning_rate": 4.938647983247949e-06,
183
+ "loss": 0.5665,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5265822784810127,
188
+ "grad_norm": 1.7040400003645124,
189
+ "learning_rate": 4.936240647992436e-06,
190
+ "loss": 0.5522,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5468354430379747,
195
+ "grad_norm": 1.5405220613374135,
196
+ "learning_rate": 4.933836829662409e-06,
197
+ "loss": 0.5612,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.5670886075949367,
202
+ "grad_norm": 2.196415488244024,
203
+ "learning_rate": 4.9314365197029475e-06,
204
+ "loss": 0.5587,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.5873417721518988,
209
+ "grad_norm": 1.6707632102423908,
210
+ "learning_rate": 4.9290397095882446e-06,
211
+ "loss": 0.5583,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6075949367088608,
216
+ "grad_norm": 1.7229761397120533,
217
+ "learning_rate": 4.9266463908214664e-06,
218
+ "loss": 0.557,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6278481012658228,
223
+ "grad_norm": 1.6427030028851288,
224
+ "learning_rate": 4.924256554934632e-06,
225
+ "loss": 0.5615,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6481012658227848,
230
+ "grad_norm": 1.5712237517522913,
231
+ "learning_rate": 4.9218701934884865e-06,
232
+ "loss": 0.5582,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.6683544303797468,
237
+ "grad_norm": 1.2757196833956246,
238
+ "learning_rate": 4.919487298072377e-06,
239
+ "loss": 0.5571,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.6886075949367089,
244
+ "grad_norm": 1.25880164502425,
245
+ "learning_rate": 4.917107860304125e-06,
246
+ "loss": 0.5575,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7088607594936709,
251
+ "grad_norm": 1.4485433549639972,
252
+ "learning_rate": 4.914731871829905e-06,
253
+ "loss": 0.5598,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7291139240506329,
258
+ "grad_norm": 1.1704225748353716,
259
+ "learning_rate": 4.912359324324121e-06,
260
+ "loss": 0.5629,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.7493670886075949,
265
+ "grad_norm": 1.318488958766272,
266
+ "learning_rate": 4.909990209489284e-06,
267
+ "loss": 0.5559,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.769620253164557,
272
+ "grad_norm": 1.32264874013122,
273
+ "learning_rate": 4.907624519055888e-06,
274
+ "loss": 0.5528,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.789873417721519,
279
+ "grad_norm": 1.0684900305074134,
280
+ "learning_rate": 4.905262244782294e-06,
281
+ "loss": 0.5553,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.810126582278481,
286
+ "grad_norm": 1.3508557119235176,
287
+ "learning_rate": 4.902903378454601e-06,
288
+ "loss": 0.5562,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.830379746835443,
293
+ "grad_norm": 1.2967891648131251,
294
+ "learning_rate": 4.900547911886537e-06,
295
+ "loss": 0.5513,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.850632911392405,
300
+ "grad_norm": 1.1824350725479262,
301
+ "learning_rate": 4.898195836919327e-06,
302
+ "loss": 0.559,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.8708860759493671,
307
+ "grad_norm": 1.0762856617174095,
308
+ "learning_rate": 4.895847145421587e-06,
309
+ "loss": 0.5525,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.8911392405063291,
314
+ "grad_norm": 1.2627694798889133,
315
+ "learning_rate": 4.893501829289195e-06,
316
+ "loss": 0.5578,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9113924050632911,
321
+ "grad_norm": 1.1261225678021216,
322
+ "learning_rate": 4.891159880445185e-06,
323
+ "loss": 0.5487,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9316455696202531,
328
+ "grad_norm": 1.080780228905491,
329
+ "learning_rate": 4.888821290839617e-06,
330
+ "loss": 0.553,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.9518987341772152,
335
+ "grad_norm": 1.4060481654323447,
336
+ "learning_rate": 4.886486052449469e-06,
337
+ "loss": 0.5543,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.9721518987341772,
342
+ "grad_norm": 1.1444239217272811,
343
+ "learning_rate": 4.8841541572785224e-06,
344
+ "loss": 0.5518,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.9924050632911392,
349
+ "grad_norm": 1.126393297654111,
350
+ "learning_rate": 4.881825597357242e-06,
351
+ "loss": 0.5483,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.9984810126582279,
356
+ "eval_loss": 0.06889493763446808,
357
+ "eval_runtime": 511.4476,
358
+ "eval_samples_per_second": 26.012,
359
+ "eval_steps_per_second": 0.407,
360
+ "step": 493
361
+ },
362
+ {
363
+ "epoch": 1.0126582278481013,
364
+ "grad_norm": 1.9364519959584037,
365
+ "learning_rate": 4.8795003647426654e-06,
366
+ "loss": 0.5082,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.0329113924050632,
371
+ "grad_norm": 1.5076411367478302,
372
+ "learning_rate": 4.877178451518289e-06,
373
+ "loss": 0.4744,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.0531645569620254,
378
+ "grad_norm": 1.3797211286348672,
379
+ "learning_rate": 4.8748598497939494e-06,
380
+ "loss": 0.4695,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.0734177215189873,
385
+ "grad_norm": 1.7689956020412856,
386
+ "learning_rate": 4.872544551705718e-06,
387
+ "loss": 0.4707,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.0936708860759494,
392
+ "grad_norm": 1.3573617792126764,
393
+ "learning_rate": 4.870232549415787e-06,
394
+ "loss": 0.4666,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.1139240506329113,
399
+ "grad_norm": 1.5485742622436776,
400
+ "learning_rate": 4.867923835112355e-06,
401
+ "loss": 0.4687,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.1341772151898735,
406
+ "grad_norm": 2.501568485920388,
407
+ "learning_rate": 4.865618401009519e-06,
408
+ "loss": 0.4658,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.1544303797468354,
413
+ "grad_norm": 1.529870751045654,
414
+ "learning_rate": 4.863316239347163e-06,
415
+ "loss": 0.4714,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.1746835443037975,
420
+ "grad_norm": 1.7808839306342492,
421
+ "learning_rate": 4.861017342390847e-06,
422
+ "loss": 0.4701,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.1949367088607594,
427
+ "grad_norm": 1.5070049937503416,
428
+ "learning_rate": 4.858721702431704e-06,
429
+ "loss": 0.4631,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.2151898734177216,
434
+ "grad_norm": 1.4447158783419,
435
+ "learning_rate": 4.856429311786322e-06,
436
+ "loss": 0.4706,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.2354430379746835,
441
+ "grad_norm": 1.5684847782241977,
442
+ "learning_rate": 4.8541401627966426e-06,
443
+ "loss": 0.4668,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.2556962025316456,
448
+ "grad_norm": 1.4448212045732463,
449
+ "learning_rate": 4.85185424782985e-06,
450
+ "loss": 0.4716,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.2759493670886077,
455
+ "grad_norm": 1.1832162854908075,
456
+ "learning_rate": 4.8495715592782715e-06,
457
+ "loss": 0.4719,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.2962025316455696,
462
+ "grad_norm": 1.1614405414065794,
463
+ "learning_rate": 4.847292089559258e-06,
464
+ "loss": 0.4717,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.3164556962025316,
469
+ "grad_norm": 1.1706266068656364,
470
+ "learning_rate": 4.845015831115093e-06,
471
+ "loss": 0.4774,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.3367088607594937,
476
+ "grad_norm": 1.2768047171905699,
477
+ "learning_rate": 4.842742776412874e-06,
478
+ "loss": 0.4665,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.3569620253164558,
483
+ "grad_norm": 1.2566572717450486,
484
+ "learning_rate": 4.840472917944417e-06,
485
+ "loss": 0.4808,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.3772151898734177,
490
+ "grad_norm": 1.374918694567089,
491
+ "learning_rate": 4.838206248226147e-06,
492
+ "loss": 0.4771,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.3974683544303796,
497
+ "grad_norm": 1.255409304035899,
498
+ "learning_rate": 4.835942759799002e-06,
499
+ "loss": 0.476,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.4177215189873418,
504
+ "grad_norm": 1.2826497764888765,
505
+ "learning_rate": 4.833682445228318e-06,
506
+ "loss": 0.4743,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.437974683544304,
511
+ "grad_norm": 1.3472804916490808,
512
+ "learning_rate": 4.831425297103738e-06,
513
+ "loss": 0.4789,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.4582278481012658,
518
+ "grad_norm": 1.408804212949645,
519
+ "learning_rate": 4.829171308039099e-06,
520
+ "loss": 0.4788,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.4784810126582277,
525
+ "grad_norm": 1.9194712290971452,
526
+ "learning_rate": 4.826920470672344e-06,
527
+ "loss": 0.4814,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.4987341772151899,
532
+ "grad_norm": 1.276149878008144,
533
+ "learning_rate": 4.824672777665406e-06,
534
+ "loss": 0.4734,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.518987341772152,
539
+ "grad_norm": 1.2416799732009185,
540
+ "learning_rate": 4.822428221704122e-06,
541
+ "loss": 0.4754,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.539240506329114,
546
+ "grad_norm": 1.2471694212471975,
547
+ "learning_rate": 4.820186795498119e-06,
548
+ "loss": 0.4765,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.5594936708860758,
553
+ "grad_norm": 1.349348015100448,
554
+ "learning_rate": 4.817948491780728e-06,
555
+ "loss": 0.477,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.579746835443038,
560
+ "grad_norm": 1.1310599884354389,
561
+ "learning_rate": 4.815713303308872e-06,
562
+ "loss": 0.4772,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.6,
567
+ "grad_norm": 1.4185285216441772,
568
+ "learning_rate": 4.813481222862981e-06,
569
+ "loss": 0.4801,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.620253164556962,
574
+ "grad_norm": 1.1082527054536842,
575
+ "learning_rate": 4.811252243246881e-06,
576
+ "loss": 0.4762,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.640506329113924,
581
+ "grad_norm": 1.121153109955329,
582
+ "learning_rate": 4.809026357287709e-06,
583
+ "loss": 0.4689,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.660759493670886,
588
+ "grad_norm": 1.3627738343833828,
589
+ "learning_rate": 4.806803557835802e-06,
590
+ "loss": 0.4789,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.6810126582278482,
595
+ "grad_norm": 1.2436684508823281,
596
+ "learning_rate": 4.804583837764616e-06,
597
+ "loss": 0.4742,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.70126582278481,
602
+ "grad_norm": 1.2177733907697486,
603
+ "learning_rate": 4.802367189970616e-06,
604
+ "loss": 0.4761,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.721518987341772,
609
+ "grad_norm": 1.2236231668260802,
610
+ "learning_rate": 4.8001536073731936e-06,
611
+ "loss": 0.4782,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.7417721518987341,
616
+ "grad_norm": 1.3388786337234164,
617
+ "learning_rate": 4.797943082914558e-06,
618
+ "loss": 0.4781,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.7620253164556963,
623
+ "grad_norm": 1.2603766222650008,
624
+ "learning_rate": 4.795735609559657e-06,
625
+ "loss": 0.4814,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.7822784810126582,
630
+ "grad_norm": 1.2451790593562906,
631
+ "learning_rate": 4.793531180296065e-06,
632
+ "loss": 0.4821,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.80253164556962,
637
+ "grad_norm": 1.3037591469416854,
638
+ "learning_rate": 4.7913297881339085e-06,
639
+ "loss": 0.4783,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.8227848101265822,
644
+ "grad_norm": 1.2298415662121125,
645
+ "learning_rate": 4.789131426105757e-06,
646
+ "loss": 0.4781,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.8430379746835444,
651
+ "grad_norm": 1.1798225985896182,
652
+ "learning_rate": 4.786936087266542e-06,
653
+ "loss": 0.4797,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.8632911392405065,
658
+ "grad_norm": 1.289300314249028,
659
+ "learning_rate": 4.784743764693455e-06,
660
+ "loss": 0.4789,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.8835443037974684,
665
+ "grad_norm": 1.1054038318282198,
666
+ "learning_rate": 4.7825544514858655e-06,
667
+ "loss": 0.4762,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.9037974683544303,
672
+ "grad_norm": 1.182720292598694,
673
+ "learning_rate": 4.780368140765222e-06,
674
+ "loss": 0.4796,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.9240506329113924,
679
+ "grad_norm": 1.3583145873588216,
680
+ "learning_rate": 4.778184825674966e-06,
681
+ "loss": 0.4802,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.9443037974683546,
686
+ "grad_norm": 1.5178028890899598,
687
+ "learning_rate": 4.776004499380439e-06,
688
+ "loss": 0.4846,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.9645569620253165,
693
+ "grad_norm": 1.4012464319035813,
694
+ "learning_rate": 4.773827155068793e-06,
695
+ "loss": 0.4827,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.9848101265822784,
700
+ "grad_norm": 1.2154066521956564,
701
+ "learning_rate": 4.771652785948902e-06,
702
+ "loss": 0.4822,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.998987341772152,
707
+ "eval_loss": 0.0687691792845726,
708
+ "eval_runtime": 510.0444,
709
+ "eval_samples_per_second": 26.084,
710
+ "eval_steps_per_second": 0.408,
711
+ "step": 987
712
+ },
713
+ {
714
+ "epoch": 2.0050632911392405,
715
+ "grad_norm": 2.0568853583148536,
716
+ "learning_rate": 4.769481385251275e-06,
717
+ "loss": 0.455,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.0253164556962027,
722
+ "grad_norm": 1.7536383318814304,
723
+ "learning_rate": 4.767312946227961e-06,
724
+ "loss": 0.3902,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.0455696202531644,
729
+ "grad_norm": 1.4204199886539934,
730
+ "learning_rate": 4.765147462152471e-06,
731
+ "loss": 0.3861,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.0658227848101265,
736
+ "grad_norm": 1.3793055257769749,
737
+ "learning_rate": 4.762984926319677e-06,
738
+ "loss": 0.3815,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.0860759493670886,
743
+ "grad_norm": 1.4433428855007544,
744
+ "learning_rate": 4.760825332045738e-06,
745
+ "loss": 0.3818,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.1063291139240508,
750
+ "grad_norm": 1.2777427789829565,
751
+ "learning_rate": 4.758668672668006e-06,
752
+ "loss": 0.3796,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.1265822784810124,
757
+ "grad_norm": 1.5185274939756037,
758
+ "learning_rate": 4.756514941544941e-06,
759
+ "loss": 0.3899,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.1468354430379746,
764
+ "grad_norm": 1.7148538224212886,
765
+ "learning_rate": 4.754364132056025e-06,
766
+ "loss": 0.3847,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.1670886075949367,
771
+ "grad_norm": 1.3254183015272027,
772
+ "learning_rate": 4.752216237601676e-06,
773
+ "loss": 0.3887,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.187341772151899,
778
+ "grad_norm": 1.3067386349024652,
779
+ "learning_rate": 4.750071251603165e-06,
780
+ "loss": 0.386,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.207594936708861,
785
+ "grad_norm": 1.3212961649982318,
786
+ "learning_rate": 4.7479291675025314e-06,
787
+ "loss": 0.384,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.2278481012658227,
792
+ "grad_norm": 1.3513915373954084,
793
+ "learning_rate": 4.745789978762496e-06,
794
+ "loss": 0.3936,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.248101265822785,
799
+ "grad_norm": 1.4754149316576497,
800
+ "learning_rate": 4.7436536788663765e-06,
801
+ "loss": 0.3894,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.268354430379747,
806
+ "grad_norm": 1.3605099369787774,
807
+ "learning_rate": 4.74152026131801e-06,
808
+ "loss": 0.392,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.2886075949367086,
813
+ "grad_norm": 1.3825169572370368,
814
+ "learning_rate": 4.739389719641665e-06,
815
+ "loss": 0.3926,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.3088607594936708,
820
+ "grad_norm": 1.428012893079509,
821
+ "learning_rate": 4.7372620473819615e-06,
822
+ "loss": 0.3892,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.329113924050633,
827
+ "grad_norm": 1.6697053356447942,
828
+ "learning_rate": 4.735137238103785e-06,
829
+ "loss": 0.3952,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.349367088607595,
834
+ "grad_norm": 1.5541921430284718,
835
+ "learning_rate": 4.7330152853922064e-06,
836
+ "loss": 0.395,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.369620253164557,
841
+ "grad_norm": 1.441070207551888,
842
+ "learning_rate": 4.730896182852409e-06,
843
+ "loss": 0.3954,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.389873417721519,
848
+ "grad_norm": 1.482729311585938,
849
+ "learning_rate": 4.72877992410959e-06,
850
+ "loss": 0.3953,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.410126582278481,
855
+ "grad_norm": 1.2718461617028598,
856
+ "learning_rate": 4.7266665028088985e-06,
857
+ "loss": 0.3947,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.430379746835443,
862
+ "grad_norm": 1.4781374345627563,
863
+ "learning_rate": 4.72455591261534e-06,
864
+ "loss": 0.3936,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.4506329113924052,
869
+ "grad_norm": 1.2755014474974025,
870
+ "learning_rate": 4.722448147213712e-06,
871
+ "loss": 0.3931,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.470886075949367,
876
+ "grad_norm": 1.2333792608977998,
877
+ "learning_rate": 4.720343200308507e-06,
878
+ "loss": 0.3969,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.491139240506329,
883
+ "grad_norm": 1.3745710227986492,
884
+ "learning_rate": 4.7182410656238484e-06,
885
+ "loss": 0.3969,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.511392405063291,
890
+ "grad_norm": 1.4770714346471105,
891
+ "learning_rate": 4.716141736903407e-06,
892
+ "loss": 0.401,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.5316455696202533,
897
+ "grad_norm": 1.3529789973486162,
898
+ "learning_rate": 4.714045207910318e-06,
899
+ "loss": 0.3948,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.5518987341772155,
904
+ "grad_norm": 1.529293587519141,
905
+ "learning_rate": 4.71195147242711e-06,
906
+ "loss": 0.3905,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.572151898734177,
911
+ "grad_norm": 1.5079569448046315,
912
+ "learning_rate": 4.709860524255622e-06,
913
+ "loss": 0.3967,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.5924050632911393,
918
+ "grad_norm": 1.334937463693978,
919
+ "learning_rate": 4.707772357216934e-06,
920
+ "loss": 0.3981,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.6126582278481014,
925
+ "grad_norm": 1.312425039073661,
926
+ "learning_rate": 4.705686965151282e-06,
927
+ "loss": 0.4032,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.632911392405063,
932
+ "grad_norm": 1.3368014158627064,
933
+ "learning_rate": 4.703604341917987e-06,
934
+ "loss": 0.3977,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.6531645569620252,
939
+ "grad_norm": 1.263795730257161,
940
+ "learning_rate": 4.701524481395374e-06,
941
+ "loss": 0.3975,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.6734177215189874,
946
+ "grad_norm": 1.3989522285161018,
947
+ "learning_rate": 4.699447377480703e-06,
948
+ "loss": 0.4006,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.6936708860759495,
953
+ "grad_norm": 1.3455649706907329,
954
+ "learning_rate": 4.6973730240900876e-06,
955
+ "loss": 0.4027,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.7139240506329116,
960
+ "grad_norm": 1.3599239257047144,
961
+ "learning_rate": 4.695301415158426e-06,
962
+ "loss": 0.4007,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.7341772151898733,
967
+ "grad_norm": 1.3595743182354967,
968
+ "learning_rate": 4.693232544639321e-06,
969
+ "loss": 0.4006,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.7544303797468355,
974
+ "grad_norm": 1.2431518397236534,
975
+ "learning_rate": 4.691166406505011e-06,
976
+ "loss": 0.3967,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.7746835443037976,
981
+ "grad_norm": 1.4521828992275958,
982
+ "learning_rate": 4.689102994746289e-06,
983
+ "loss": 0.4025,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.7949367088607593,
988
+ "grad_norm": 1.3295438802424044,
989
+ "learning_rate": 4.687042303372439e-06,
990
+ "loss": 0.3999,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.8151898734177214,
995
+ "grad_norm": 1.5584235157388586,
996
+ "learning_rate": 4.684984326411154e-06,
997
+ "loss": 0.4027,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.8354430379746836,
1002
+ "grad_norm": 1.3679425564652627,
1003
+ "learning_rate": 4.68292905790847e-06,
1004
+ "loss": 0.3964,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.8556962025316457,
1009
+ "grad_norm": 1.294051835885274,
1010
+ "learning_rate": 4.6808764919286885e-06,
1011
+ "loss": 0.4045,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.875949367088608,
1016
+ "grad_norm": 1.2632343988872143,
1017
+ "learning_rate": 4.678826622554307e-06,
1018
+ "loss": 0.401,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.8962025316455695,
1023
+ "grad_norm": 1.326763835242954,
1024
+ "learning_rate": 4.676779443885949e-06,
1025
+ "loss": 0.4015,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.9164556962025316,
1030
+ "grad_norm": 1.3123187327652401,
1031
+ "learning_rate": 4.674734950042287e-06,
1032
+ "loss": 0.4033,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.9367088607594938,
1037
+ "grad_norm": 1.3557998510809561,
1038
+ "learning_rate": 4.672693135159978e-06,
1039
+ "loss": 0.4124,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.9569620253164555,
1044
+ "grad_norm": 1.3341090273932297,
1045
+ "learning_rate": 4.67065399339359e-06,
1046
+ "loss": 0.4007,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.9772151898734176,
1051
+ "grad_norm": 1.2762659447018396,
1052
+ "learning_rate": 4.668617518915533e-06,
1053
+ "loss": 0.4045,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.9954430379746837,
1058
+ "eval_loss": 0.07256945222616196,
1059
+ "eval_runtime": 512.92,
1060
+ "eval_samples_per_second": 25.938,
1061
+ "eval_steps_per_second": 0.406,
1062
+ "step": 1479
1063
+ },
1064
+ {
1065
+ "epoch": 2.9954430379746837,
1066
+ "step": 1479,
1067
+ "total_flos": 2477170706350080.0,
1068
+ "train_loss": 0.4816304181700546,
1069
+ "train_runtime": 84877.5943,
1070
+ "train_samples_per_second": 8.934,
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