sedrickkeh commited on
Commit
d3aa98a
·
verified ·
1 Parent(s): 1559121

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: top_18_ranking_stackexchange
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # top_18_ranking_stackexchange
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.8025
21
 
 
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: top_18_ranking_stackexchange
 
16
 
17
  # top_18_ranking_stackexchange
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/top_18_ranking_stackexchange dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.8025
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9963285024154587,
3
+ "eval_loss": 0.8025317192077637,
4
+ "eval_runtime": 692.9086,
5
+ "eval_samples_per_second": 25.156,
6
+ "eval_steps_per_second": 0.394,
7
+ "total_flos": 3246012802007040.0,
8
+ "train_loss": 0.7871413270263357,
9
+ "train_runtime": 114590.6996,
10
+ "train_samples_per_second": 8.67,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9963285024154587,
3
+ "eval_loss": 0.8025317192077637,
4
+ "eval_runtime": 692.9086,
5
+ "eval_samples_per_second": 25.156,
6
+ "eval_steps_per_second": 0.394
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9963285024154587,
3
+ "total_flos": 3246012802007040.0,
4
+ "train_loss": 0.7871413270263357,
5
+ "train_runtime": 114590.6996,
6
+ "train_samples_per_second": 8.67,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1417 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9963285024154587,
5
+ "eval_steps": 500,
6
+ "global_step": 1938,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.015458937198067632,
13
+ "grad_norm": 16.53294779967864,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0792,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.030917874396135265,
20
+ "grad_norm": 2.649325227711683,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9837,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0463768115942029,
27
+ "grad_norm": 8.284136228811613,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.9474,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.06183574879227053,
34
+ "grad_norm": 2.524509268818302,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.9301,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.07729468599033816,
41
+ "grad_norm": 1.5326850741391629,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.9155,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.0927536231884058,
48
+ "grad_norm": 1.0781869595697948,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.9037,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.10821256038647344,
55
+ "grad_norm": 0.8943372564864077,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8967,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.12367149758454106,
62
+ "grad_norm": 0.8868808075595438,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8867,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.1391304347826087,
69
+ "grad_norm": 0.6755190824568067,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8792,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.15458937198067632,
76
+ "grad_norm": 0.6359486667796315,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.8769,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.17004830917874397,
83
+ "grad_norm": 0.6299873717513695,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.8717,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.1855072463768116,
90
+ "grad_norm": 0.5832655638295026,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.8671,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.20096618357487922,
97
+ "grad_norm": 0.5586732401198556,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.8642,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.21642512077294687,
104
+ "grad_norm": 0.6759403203697444,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.863,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.2318840579710145,
111
+ "grad_norm": 0.5234393167054423,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.861,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.24734299516908212,
118
+ "grad_norm": 0.5405697501688478,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.864,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.26280193236714977,
125
+ "grad_norm": 0.5609477995758988,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.8528,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.2782608695652174,
132
+ "grad_norm": 0.648827500892738,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.857,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.293719806763285,
139
+ "grad_norm": 0.6627079853918527,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.8511,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.30917874396135264,
146
+ "grad_norm": 0.6915034637639949,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.8485,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.32463768115942027,
153
+ "grad_norm": 0.6366893171242987,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.8462,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.34009661835748795,
160
+ "grad_norm": 0.5070708715215638,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.8446,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.35555555555555557,
167
+ "grad_norm": 0.5871716320705027,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.8445,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.3710144927536232,
174
+ "grad_norm": 0.7730510671832644,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.8497,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.3864734299516908,
181
+ "grad_norm": 0.7142598054734569,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.8438,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.40193236714975844,
188
+ "grad_norm": 0.5417070693738956,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.8476,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.41739130434782606,
195
+ "grad_norm": 0.6163533652451042,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.8442,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.43285024154589374,
202
+ "grad_norm": 0.5863440757370957,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.8384,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.44830917874396137,
209
+ "grad_norm": 0.6841438022567938,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.8416,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.463768115942029,
216
+ "grad_norm": 0.5830887688966261,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.8363,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.4792270531400966,
223
+ "grad_norm": 0.7565147804535631,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.8391,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.49468599033816424,
230
+ "grad_norm": 0.5377296055296723,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.8384,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5101449275362319,
237
+ "grad_norm": 0.6313225350990711,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.8344,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5256038647342995,
244
+ "grad_norm": 0.6011085474374273,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.8352,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.5410628019323671,
251
+ "grad_norm": 0.6313718464958992,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.8319,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.5565217391304348,
258
+ "grad_norm": 0.5602186929251594,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.8305,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.5719806763285025,
265
+ "grad_norm": 0.5682159814727703,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.8283,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.58743961352657,
272
+ "grad_norm": 0.5718556832144389,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.8341,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6028985507246377,
279
+ "grad_norm": 0.546768373760242,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.8291,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.6183574879227053,
286
+ "grad_norm": 0.5993423126379529,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.8361,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.633816425120773,
293
+ "grad_norm": 0.5491459229199431,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.8291,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.6492753623188405,
300
+ "grad_norm": 0.5168339143544802,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.83,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.6647342995169082,
307
+ "grad_norm": 0.5210184948415354,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.8237,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.6801932367149759,
314
+ "grad_norm": 0.5424122263787127,
315
+ "learning_rate": 5e-06,
316
+ "loss": 0.8228,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.6956521739130435,
321
+ "grad_norm": 0.5637417843194678,
322
+ "learning_rate": 5e-06,
323
+ "loss": 0.829,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.7111111111111111,
328
+ "grad_norm": 0.4743888435043112,
329
+ "learning_rate": 5e-06,
330
+ "loss": 0.8221,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.7265700483091787,
335
+ "grad_norm": 0.5224626427829437,
336
+ "learning_rate": 5e-06,
337
+ "loss": 0.8254,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.7420289855072464,
342
+ "grad_norm": 0.6508696496425336,
343
+ "learning_rate": 5e-06,
344
+ "loss": 0.8264,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.7574879227053141,
349
+ "grad_norm": 0.5904629481154552,
350
+ "learning_rate": 5e-06,
351
+ "loss": 0.8295,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.7729468599033816,
356
+ "grad_norm": 0.574388340778744,
357
+ "learning_rate": 5e-06,
358
+ "loss": 0.8223,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.7884057971014493,
363
+ "grad_norm": 0.5353158279457252,
364
+ "learning_rate": 5e-06,
365
+ "loss": 0.8257,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.8038647342995169,
370
+ "grad_norm": 0.5821234180105461,
371
+ "learning_rate": 5e-06,
372
+ "loss": 0.8265,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.8193236714975846,
377
+ "grad_norm": 0.5068894400573091,
378
+ "learning_rate": 5e-06,
379
+ "loss": 0.8224,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.8347826086956521,
384
+ "grad_norm": 0.5375828449207095,
385
+ "learning_rate": 5e-06,
386
+ "loss": 0.821,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.8502415458937198,
391
+ "grad_norm": 0.5410980089439529,
392
+ "learning_rate": 5e-06,
393
+ "loss": 0.8271,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.8657004830917875,
398
+ "grad_norm": 0.5953566167479901,
399
+ "learning_rate": 5e-06,
400
+ "loss": 0.8168,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.881159420289855,
405
+ "grad_norm": 0.6599677690788177,
406
+ "learning_rate": 5e-06,
407
+ "loss": 0.8234,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.8966183574879227,
412
+ "grad_norm": 0.6548750016255851,
413
+ "learning_rate": 5e-06,
414
+ "loss": 0.8198,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.9120772946859903,
419
+ "grad_norm": 0.6314610392042965,
420
+ "learning_rate": 5e-06,
421
+ "loss": 0.8169,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.927536231884058,
426
+ "grad_norm": 0.4920135279723095,
427
+ "learning_rate": 5e-06,
428
+ "loss": 0.8225,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.9429951690821256,
433
+ "grad_norm": 0.5279136309564921,
434
+ "learning_rate": 5e-06,
435
+ "loss": 0.8188,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.9584541062801932,
440
+ "grad_norm": 0.5531816471285108,
441
+ "learning_rate": 5e-06,
442
+ "loss": 0.8217,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.9739130434782609,
447
+ "grad_norm": 0.5924801838934433,
448
+ "learning_rate": 5e-06,
449
+ "loss": 0.8221,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.9893719806763285,
454
+ "grad_norm": 0.5117042192273262,
455
+ "learning_rate": 5e-06,
456
+ "loss": 0.8188,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.9986473429951691,
461
+ "eval_loss": 0.8183467984199524,
462
+ "eval_runtime": 686.568,
463
+ "eval_samples_per_second": 25.389,
464
+ "eval_steps_per_second": 0.398,
465
+ "step": 646
466
+ },
467
+ {
468
+ "epoch": 1.0050241545893719,
469
+ "grad_norm": 0.6925909025947767,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.8235,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.0204830917874397,
476
+ "grad_norm": 0.6132973767615294,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.7771,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.0359420289855072,
483
+ "grad_norm": 0.6797848846411009,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.7802,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.0514009661835748,
490
+ "grad_norm": 0.5295735808202817,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.7777,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.0668599033816426,
497
+ "grad_norm": 0.5271721002677758,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.7751,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.0823188405797102,
504
+ "grad_norm": 0.47521281338293253,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.7808,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.0977777777777777,
511
+ "grad_norm": 0.5201403409762577,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.7769,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.1132367149758453,
518
+ "grad_norm": 0.5374055398678584,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.7775,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.128695652173913,
525
+ "grad_norm": 0.520683864449963,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.7787,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.1441545893719807,
532
+ "grad_norm": 0.5406489528118505,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.7816,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.1596135265700482,
539
+ "grad_norm": 0.585881797178412,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.7811,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.175072463768116,
546
+ "grad_norm": 0.5490222258224376,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.7763,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.1905314009661836,
553
+ "grad_norm": 0.6049557272461074,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.7821,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.2059903381642512,
560
+ "grad_norm": 0.6287813068938076,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.7771,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.221449275362319,
567
+ "grad_norm": 0.5791771698431348,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.7832,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.2369082125603865,
574
+ "grad_norm": 0.552647068072239,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.7795,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.252367149758454,
581
+ "grad_norm": 0.48953182542010515,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.7767,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.2678260869565217,
588
+ "grad_norm": 0.5809037976182655,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.7784,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.2832850241545894,
595
+ "grad_norm": 0.49664609280994976,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.7765,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.298743961352657,
602
+ "grad_norm": 0.5514267021897065,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.7791,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.3142028985507246,
609
+ "grad_norm": 0.6174163379347436,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.7775,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.3296618357487922,
616
+ "grad_norm": 0.5893029009867757,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.7743,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.34512077294686,
623
+ "grad_norm": 0.5884521899466931,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.7768,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.3605797101449275,
630
+ "grad_norm": 0.526781782612563,
631
+ "learning_rate": 5e-06,
632
+ "loss": 0.773,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.376038647342995,
637
+ "grad_norm": 0.5133541303046,
638
+ "learning_rate": 5e-06,
639
+ "loss": 0.774,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.3914975845410629,
644
+ "grad_norm": 0.5514217537787884,
645
+ "learning_rate": 5e-06,
646
+ "loss": 0.7802,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.4069565217391304,
651
+ "grad_norm": 0.5829849669974898,
652
+ "learning_rate": 5e-06,
653
+ "loss": 0.7787,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.422415458937198,
658
+ "grad_norm": 0.6099035981973764,
659
+ "learning_rate": 5e-06,
660
+ "loss": 0.7738,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.4378743961352658,
665
+ "grad_norm": 0.4767884324426242,
666
+ "learning_rate": 5e-06,
667
+ "loss": 0.7773,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.4533333333333334,
672
+ "grad_norm": 0.5611337081061908,
673
+ "learning_rate": 5e-06,
674
+ "loss": 0.7767,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.468792270531401,
679
+ "grad_norm": 0.47930773858272085,
680
+ "learning_rate": 5e-06,
681
+ "loss": 0.7765,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.4842512077294687,
686
+ "grad_norm": 0.498168257215718,
687
+ "learning_rate": 5e-06,
688
+ "loss": 0.7728,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.4997101449275363,
693
+ "grad_norm": 0.5576989172567428,
694
+ "learning_rate": 5e-06,
695
+ "loss": 0.7777,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.5151690821256039,
700
+ "grad_norm": 0.5873903650866855,
701
+ "learning_rate": 5e-06,
702
+ "loss": 0.7747,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.5306280193236717,
707
+ "grad_norm": 0.5564865473674926,
708
+ "learning_rate": 5e-06,
709
+ "loss": 0.7786,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.546086956521739,
714
+ "grad_norm": 0.6746662280932265,
715
+ "learning_rate": 5e-06,
716
+ "loss": 0.7823,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.5615458937198068,
721
+ "grad_norm": 0.550553366091711,
722
+ "learning_rate": 5e-06,
723
+ "loss": 0.7704,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.5770048309178744,
728
+ "grad_norm": 0.555996816403915,
729
+ "learning_rate": 5e-06,
730
+ "loss": 0.7758,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.592463768115942,
735
+ "grad_norm": 0.5621088990135378,
736
+ "learning_rate": 5e-06,
737
+ "loss": 0.7751,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.6079227053140097,
742
+ "grad_norm": 0.4672348676970037,
743
+ "learning_rate": 5e-06,
744
+ "loss": 0.7742,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.6233816425120773,
749
+ "grad_norm": 0.49112359521062937,
750
+ "learning_rate": 5e-06,
751
+ "loss": 0.777,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.6388405797101449,
756
+ "grad_norm": 0.5517626252028611,
757
+ "learning_rate": 5e-06,
758
+ "loss": 0.7757,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.6542995169082126,
763
+ "grad_norm": 0.5518129870744243,
764
+ "learning_rate": 5e-06,
765
+ "loss": 0.7744,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.6697584541062802,
770
+ "grad_norm": 0.685405898117341,
771
+ "learning_rate": 5e-06,
772
+ "loss": 0.7753,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.6852173913043478,
777
+ "grad_norm": 0.5720673042328214,
778
+ "learning_rate": 5e-06,
779
+ "loss": 0.7753,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.7006763285024156,
784
+ "grad_norm": 0.4690028175072265,
785
+ "learning_rate": 5e-06,
786
+ "loss": 0.774,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.7161352657004831,
791
+ "grad_norm": 0.55568178811657,
792
+ "learning_rate": 5e-06,
793
+ "loss": 0.7772,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.7315942028985507,
798
+ "grad_norm": 0.5185570493500619,
799
+ "learning_rate": 5e-06,
800
+ "loss": 0.781,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.7470531400966185,
805
+ "grad_norm": 0.5292299708932318,
806
+ "learning_rate": 5e-06,
807
+ "loss": 0.7749,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.7625120772946858,
812
+ "grad_norm": 0.5884058161213621,
813
+ "learning_rate": 5e-06,
814
+ "loss": 0.7719,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.7779710144927536,
819
+ "grad_norm": 0.5072506431239099,
820
+ "learning_rate": 5e-06,
821
+ "loss": 0.7753,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.7934299516908214,
826
+ "grad_norm": 0.5551938392960334,
827
+ "learning_rate": 5e-06,
828
+ "loss": 0.7777,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.8088888888888888,
833
+ "grad_norm": 0.5566487078925049,
834
+ "learning_rate": 5e-06,
835
+ "loss": 0.7774,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.8243478260869566,
840
+ "grad_norm": 0.4749917546235466,
841
+ "learning_rate": 5e-06,
842
+ "loss": 0.7734,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.8398067632850241,
847
+ "grad_norm": 0.5022635709311233,
848
+ "learning_rate": 5e-06,
849
+ "loss": 0.7743,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 1.8552657004830917,
854
+ "grad_norm": 0.5442982810099344,
855
+ "learning_rate": 5e-06,
856
+ "loss": 0.7728,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 1.8707246376811595,
861
+ "grad_norm": 0.5155014433123901,
862
+ "learning_rate": 5e-06,
863
+ "loss": 0.774,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 1.886183574879227,
868
+ "grad_norm": 0.5934285413681538,
869
+ "learning_rate": 5e-06,
870
+ "loss": 0.7746,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 1.9016425120772946,
875
+ "grad_norm": 0.5260175972638601,
876
+ "learning_rate": 5e-06,
877
+ "loss": 0.7693,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 1.9171014492753624,
882
+ "grad_norm": 0.515080447493818,
883
+ "learning_rate": 5e-06,
884
+ "loss": 0.7717,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 1.93256038647343,
889
+ "grad_norm": 0.6011160845737209,
890
+ "learning_rate": 5e-06,
891
+ "loss": 0.7754,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 1.9480193236714975,
896
+ "grad_norm": 0.46061302659355685,
897
+ "learning_rate": 5e-06,
898
+ "loss": 0.7755,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 1.9634782608695653,
903
+ "grad_norm": 0.46039484020056154,
904
+ "learning_rate": 5e-06,
905
+ "loss": 0.7722,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 1.9789371980676327,
910
+ "grad_norm": 0.5658493454639554,
911
+ "learning_rate": 5e-06,
912
+ "loss": 0.7755,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 1.9943961352657005,
917
+ "grad_norm": 0.5908199178180503,
918
+ "learning_rate": 5e-06,
919
+ "loss": 0.7709,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 1.9990338164251207,
924
+ "eval_loss": 0.8051349520683289,
925
+ "eval_runtime": 690.0891,
926
+ "eval_samples_per_second": 25.259,
927
+ "eval_steps_per_second": 0.396,
928
+ "step": 1293
929
+ },
930
+ {
931
+ "epoch": 2.0100483091787438,
932
+ "grad_norm": 0.6943407863572525,
933
+ "learning_rate": 5e-06,
934
+ "loss": 0.7604,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.0255072463768116,
939
+ "grad_norm": 0.5840764739328596,
940
+ "learning_rate": 5e-06,
941
+ "loss": 0.7299,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.0409661835748794,
946
+ "grad_norm": 0.645835170219903,
947
+ "learning_rate": 5e-06,
948
+ "loss": 0.7254,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.0564251207729467,
953
+ "grad_norm": 0.6967100498978297,
954
+ "learning_rate": 5e-06,
955
+ "loss": 0.7312,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.0718840579710145,
960
+ "grad_norm": 0.5424795093750152,
961
+ "learning_rate": 5e-06,
962
+ "loss": 0.7283,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.0873429951690823,
967
+ "grad_norm": 0.5651081335517218,
968
+ "learning_rate": 5e-06,
969
+ "loss": 0.7322,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.1028019323671496,
974
+ "grad_norm": 0.5793019251125064,
975
+ "learning_rate": 5e-06,
976
+ "loss": 0.7317,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.1182608695652174,
981
+ "grad_norm": 0.5653295937261641,
982
+ "learning_rate": 5e-06,
983
+ "loss": 0.7331,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.133719806763285,
988
+ "grad_norm": 0.6945092784765529,
989
+ "learning_rate": 5e-06,
990
+ "loss": 0.7346,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.1491787439613526,
995
+ "grad_norm": 0.5795163218543443,
996
+ "learning_rate": 5e-06,
997
+ "loss": 0.7336,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.1646376811594203,
1002
+ "grad_norm": 0.5922357321216497,
1003
+ "learning_rate": 5e-06,
1004
+ "loss": 0.7299,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.1800966183574877,
1009
+ "grad_norm": 0.5570557796263025,
1010
+ "learning_rate": 5e-06,
1011
+ "loss": 0.7333,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.1955555555555555,
1016
+ "grad_norm": 0.5392312450784695,
1017
+ "learning_rate": 5e-06,
1018
+ "loss": 0.7371,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.2110144927536233,
1023
+ "grad_norm": 0.569063560563541,
1024
+ "learning_rate": 5e-06,
1025
+ "loss": 0.7314,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.2264734299516906,
1030
+ "grad_norm": 0.6107660118171969,
1031
+ "learning_rate": 5e-06,
1032
+ "loss": 0.7322,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.2419323671497584,
1037
+ "grad_norm": 0.6566517138097786,
1038
+ "learning_rate": 5e-06,
1039
+ "loss": 0.7356,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.257391304347826,
1044
+ "grad_norm": 0.5806353609910259,
1045
+ "learning_rate": 5e-06,
1046
+ "loss": 0.7418,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.2728502415458935,
1051
+ "grad_norm": 0.544246667709765,
1052
+ "learning_rate": 5e-06,
1053
+ "loss": 0.7319,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.2883091787439613,
1058
+ "grad_norm": 0.5424208252581,
1059
+ "learning_rate": 5e-06,
1060
+ "loss": 0.7332,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.303768115942029,
1065
+ "grad_norm": 0.5380434193955503,
1066
+ "learning_rate": 5e-06,
1067
+ "loss": 0.7342,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.3192270531400965,
1072
+ "grad_norm": 0.5919093406358342,
1073
+ "learning_rate": 5e-06,
1074
+ "loss": 0.7345,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.3346859903381643,
1079
+ "grad_norm": 0.5815232359700448,
1080
+ "learning_rate": 5e-06,
1081
+ "loss": 0.7357,
1082
+ "step": 1510
1083
+ },
1084
+ {
1085
+ "epoch": 2.350144927536232,
1086
+ "grad_norm": 0.6561512544812266,
1087
+ "learning_rate": 5e-06,
1088
+ "loss": 0.7339,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.3656038647342994,
1093
+ "grad_norm": 0.5328952220385875,
1094
+ "learning_rate": 5e-06,
1095
+ "loss": 0.7297,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.381062801932367,
1100
+ "grad_norm": 0.5216733576185124,
1101
+ "learning_rate": 5e-06,
1102
+ "loss": 0.7298,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.396521739130435,
1107
+ "grad_norm": 0.6063067814678768,
1108
+ "learning_rate": 5e-06,
1109
+ "loss": 0.7368,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.4119806763285023,
1114
+ "grad_norm": 0.5818602690123681,
1115
+ "learning_rate": 5e-06,
1116
+ "loss": 0.7353,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.42743961352657,
1121
+ "grad_norm": 0.5913577701518534,
1122
+ "learning_rate": 5e-06,
1123
+ "loss": 0.7338,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.442898550724638,
1128
+ "grad_norm": 0.5527497540961946,
1129
+ "learning_rate": 5e-06,
1130
+ "loss": 0.7329,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.4583574879227053,
1135
+ "grad_norm": 0.6737570445790982,
1136
+ "learning_rate": 5e-06,
1137
+ "loss": 0.7367,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.473816425120773,
1142
+ "grad_norm": 0.6619470586787684,
1143
+ "learning_rate": 5e-06,
1144
+ "loss": 0.733,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.4892753623188404,
1149
+ "grad_norm": 0.4750068577638755,
1150
+ "learning_rate": 5e-06,
1151
+ "loss": 0.7375,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.504734299516908,
1156
+ "grad_norm": 0.6847743909506772,
1157
+ "learning_rate": 5e-06,
1158
+ "loss": 0.7374,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.520193236714976,
1163
+ "grad_norm": 0.5239840846624293,
1164
+ "learning_rate": 5e-06,
1165
+ "loss": 0.7311,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.5356521739130433,
1170
+ "grad_norm": 0.4721718835375596,
1171
+ "learning_rate": 5e-06,
1172
+ "loss": 0.7308,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.551111111111111,
1177
+ "grad_norm": 0.51093602092176,
1178
+ "learning_rate": 5e-06,
1179
+ "loss": 0.7337,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.566570048309179,
1184
+ "grad_norm": 0.5517386015611798,
1185
+ "learning_rate": 5e-06,
1186
+ "loss": 0.7318,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.5820289855072462,
1191
+ "grad_norm": 0.6326674619813268,
1192
+ "learning_rate": 5e-06,
1193
+ "loss": 0.736,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.597487922705314,
1198
+ "grad_norm": 0.5232840712675151,
1199
+ "learning_rate": 5e-06,
1200
+ "loss": 0.7325,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.6129468599033814,
1205
+ "grad_norm": 0.4969751533645812,
1206
+ "learning_rate": 5e-06,
1207
+ "loss": 0.7375,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.628405797101449,
1212
+ "grad_norm": 0.49538430512331766,
1213
+ "learning_rate": 5e-06,
1214
+ "loss": 0.7366,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.643864734299517,
1219
+ "grad_norm": 0.6208865012276192,
1220
+ "learning_rate": 5e-06,
1221
+ "loss": 0.7372,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.6593236714975843,
1226
+ "grad_norm": 0.5276942120485377,
1227
+ "learning_rate": 5e-06,
1228
+ "loss": 0.7351,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.674782608695652,
1233
+ "grad_norm": 0.570808842039396,
1234
+ "learning_rate": 5e-06,
1235
+ "loss": 0.7384,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.69024154589372,
1240
+ "grad_norm": 0.5214638213365278,
1241
+ "learning_rate": 5e-06,
1242
+ "loss": 0.7361,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.7057004830917872,
1247
+ "grad_norm": 0.5190586781651014,
1248
+ "learning_rate": 5e-06,
1249
+ "loss": 0.7309,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.721159420289855,
1254
+ "grad_norm": 0.5317230869170978,
1255
+ "learning_rate": 5e-06,
1256
+ "loss": 0.7296,
1257
+ "step": 1760
1258
+ },
1259
+ {
1260
+ "epoch": 2.736618357487923,
1261
+ "grad_norm": 0.5917255596181432,
1262
+ "learning_rate": 5e-06,
1263
+ "loss": 0.7406,
1264
+ "step": 1770
1265
+ },
1266
+ {
1267
+ "epoch": 2.75207729468599,
1268
+ "grad_norm": 0.49202576322983876,
1269
+ "learning_rate": 5e-06,
1270
+ "loss": 0.7324,
1271
+ "step": 1780
1272
+ },
1273
+ {
1274
+ "epoch": 2.767536231884058,
1275
+ "grad_norm": 0.5594574654106287,
1276
+ "learning_rate": 5e-06,
1277
+ "loss": 0.7331,
1278
+ "step": 1790
1279
+ },
1280
+ {
1281
+ "epoch": 2.7829951690821257,
1282
+ "grad_norm": 0.6198580773466541,
1283
+ "learning_rate": 5e-06,
1284
+ "loss": 0.7372,
1285
+ "step": 1800
1286
+ },
1287
+ {
1288
+ "epoch": 2.798454106280193,
1289
+ "grad_norm": 0.5740394274550438,
1290
+ "learning_rate": 5e-06,
1291
+ "loss": 0.7359,
1292
+ "step": 1810
1293
+ },
1294
+ {
1295
+ "epoch": 2.813913043478261,
1296
+ "grad_norm": 0.5501912428656768,
1297
+ "learning_rate": 5e-06,
1298
+ "loss": 0.7384,
1299
+ "step": 1820
1300
+ },
1301
+ {
1302
+ "epoch": 2.8293719806763287,
1303
+ "grad_norm": 0.5104778986757859,
1304
+ "learning_rate": 5e-06,
1305
+ "loss": 0.7324,
1306
+ "step": 1830
1307
+ },
1308
+ {
1309
+ "epoch": 2.844830917874396,
1310
+ "grad_norm": 0.5395220598812313,
1311
+ "learning_rate": 5e-06,
1312
+ "loss": 0.736,
1313
+ "step": 1840
1314
+ },
1315
+ {
1316
+ "epoch": 2.860289855072464,
1317
+ "grad_norm": 0.6030104859258091,
1318
+ "learning_rate": 5e-06,
1319
+ "loss": 0.7327,
1320
+ "step": 1850
1321
+ },
1322
+ {
1323
+ "epoch": 2.8757487922705316,
1324
+ "grad_norm": 0.556906171705928,
1325
+ "learning_rate": 5e-06,
1326
+ "loss": 0.7374,
1327
+ "step": 1860
1328
+ },
1329
+ {
1330
+ "epoch": 2.891207729468599,
1331
+ "grad_norm": 0.6174821846225631,
1332
+ "learning_rate": 5e-06,
1333
+ "loss": 0.7351,
1334
+ "step": 1870
1335
+ },
1336
+ {
1337
+ "epoch": 2.9066666666666667,
1338
+ "grad_norm": 0.5078906232420815,
1339
+ "learning_rate": 5e-06,
1340
+ "loss": 0.7326,
1341
+ "step": 1880
1342
+ },
1343
+ {
1344
+ "epoch": 2.9221256038647345,
1345
+ "grad_norm": 0.6177111487230912,
1346
+ "learning_rate": 5e-06,
1347
+ "loss": 0.7321,
1348
+ "step": 1890
1349
+ },
1350
+ {
1351
+ "epoch": 2.937584541062802,
1352
+ "grad_norm": 0.5520929737500946,
1353
+ "learning_rate": 5e-06,
1354
+ "loss": 0.7395,
1355
+ "step": 1900
1356
+ },
1357
+ {
1358
+ "epoch": 2.9530434782608697,
1359
+ "grad_norm": 0.5185834378400617,
1360
+ "learning_rate": 5e-06,
1361
+ "loss": 0.7368,
1362
+ "step": 1910
1363
+ },
1364
+ {
1365
+ "epoch": 2.9685024154589374,
1366
+ "grad_norm": 0.5204851978024219,
1367
+ "learning_rate": 5e-06,
1368
+ "loss": 0.7339,
1369
+ "step": 1920
1370
+ },
1371
+ {
1372
+ "epoch": 2.983961352657005,
1373
+ "grad_norm": 0.5807949438616106,
1374
+ "learning_rate": 5e-06,
1375
+ "loss": 0.7386,
1376
+ "step": 1930
1377
+ },
1378
+ {
1379
+ "epoch": 2.9963285024154587,
1380
+ "eval_loss": 0.8025317192077637,
1381
+ "eval_runtime": 693.9451,
1382
+ "eval_samples_per_second": 25.119,
1383
+ "eval_steps_per_second": 0.393,
1384
+ "step": 1938
1385
+ },
1386
+ {
1387
+ "epoch": 2.9963285024154587,
1388
+ "step": 1938,
1389
+ "total_flos": 3246012802007040.0,
1390
+ "train_loss": 0.7871413270263357,
1391
+ "train_runtime": 114590.6996,
1392
+ "train_samples_per_second": 8.67,
1393
+ "train_steps_per_second": 0.017
1394
+ }
1395
+ ],
1396
+ "logging_steps": 10,
1397
+ "max_steps": 1938,
1398
+ "num_input_tokens_seen": 0,
1399
+ "num_train_epochs": 3,
1400
+ "save_steps": 500,
1401
+ "stateful_callbacks": {
1402
+ "TrainerControl": {
1403
+ "args": {
1404
+ "should_epoch_stop": false,
1405
+ "should_evaluate": false,
1406
+ "should_log": false,
1407
+ "should_save": true,
1408
+ "should_training_stop": true
1409
+ },
1410
+ "attributes": {}
1411
+ }
1412
+ },
1413
+ "total_flos": 3246012802007040.0,
1414
+ "train_batch_size": 8,
1415
+ "trial_name": null,
1416
+ "trial_params": null
1417
+ }
training_eval_loss.png ADDED
training_loss.png ADDED