sedrickkeh commited on
Commit
3617dc9
·
verified ·
1 Parent(s): 45c988a

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_19_ranking_stackexchange
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # top_19_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: 0.8026
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_19_ranking_stackexchange
 
16
 
17
  # top_19_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_19_ranking_stackexchange dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.8026
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9961671837926627,
3
+ "eval_loss": 0.8026307821273804,
4
+ "eval_runtime": 735.7112,
5
+ "eval_samples_per_second": 25.085,
6
+ "eval_steps_per_second": 0.393,
7
+ "total_flos": 3436967047987200.0,
8
+ "train_loss": 0.7862561077286161,
9
+ "train_runtime": 121149.8135,
10
+ "train_samples_per_second": 8.683,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9961671837926627,
3
+ "eval_loss": 0.8026307821273804,
4
+ "eval_runtime": 735.7112,
5
+ "eval_samples_per_second": 25.085,
6
+ "eval_steps_per_second": 0.393
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9961671837926627,
3
+ "total_flos": 3436967047987200.0,
4
+ "train_loss": 0.7862561077286161,
5
+ "train_runtime": 121149.8135,
6
+ "train_samples_per_second": 8.683,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1501 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9961671837926627,
5
+ "eval_steps": 500,
6
+ "global_step": 2052,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.014601204599379448,
13
+ "grad_norm": 31.200588193935076,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0665,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.029202409198758897,
20
+ "grad_norm": 2.1030174817289726,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9851,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.043803613798138345,
27
+ "grad_norm": 1.7889745137305164,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.9413,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.058404818397517794,
34
+ "grad_norm": 0.7798640642359425,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.9234,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.07300602299689725,
41
+ "grad_norm": 2.7003950764835163,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.9077,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.08760722759627669,
48
+ "grad_norm": 6.611494407685939,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.9045,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.10220843219565615,
55
+ "grad_norm": 1.081246334652253,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8965,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.11680963679503559,
62
+ "grad_norm": 0.8101716177472186,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8855,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.13141084139441503,
69
+ "grad_norm": 0.8801376249396373,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8827,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.1460120459937945,
76
+ "grad_norm": 0.6385442821205225,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.8714,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.16061325059317394,
83
+ "grad_norm": 0.6872556086848158,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.8735,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.17521445519255338,
90
+ "grad_norm": 0.6992499417358933,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.8682,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.18981565979193282,
97
+ "grad_norm": 0.6013577080845172,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.8662,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2044168643913123,
104
+ "grad_norm": 0.5988600270173734,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.8649,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.21901806899069173,
111
+ "grad_norm": 0.6460225651419232,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.8647,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.23361927359007117,
118
+ "grad_norm": 0.5603551860244527,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.8533,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.24822047818945062,
125
+ "grad_norm": 0.5553710866489995,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.8544,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.26282168278883006,
132
+ "grad_norm": 0.6554387689230537,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.8592,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.2774228873882095,
139
+ "grad_norm": 0.6786037864304745,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.8518,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.292024091987589,
146
+ "grad_norm": 0.5561181889312125,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.8505,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.3066252965869684,
153
+ "grad_norm": 0.7917259340608006,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.8475,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.3212265011863479,
160
+ "grad_norm": 0.5838972916992158,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.8468,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.33582770578572735,
167
+ "grad_norm": 0.5415756077794452,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.8478,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.35042891038510676,
174
+ "grad_norm": 0.561460816685303,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.8471,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.36503011498448623,
181
+ "grad_norm": 0.5431016015146285,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.845,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.37963131958386565,
188
+ "grad_norm": 0.5777928639036234,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.8427,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3942325241832451,
195
+ "grad_norm": 0.6855206088461627,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.8406,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.4088337287826246,
202
+ "grad_norm": 0.5959537867792327,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.843,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.423434933382004,
209
+ "grad_norm": 0.5787987185587301,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.842,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.43803613798138347,
216
+ "grad_norm": 0.9829016985861171,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.841,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.45263734258076294,
223
+ "grad_norm": 0.7109664833342627,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.8376,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.46723854718014235,
230
+ "grad_norm": 0.5953929615896101,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.8352,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.4818397517795218,
237
+ "grad_norm": 0.6459745420821242,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.8322,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.49644095637890123,
244
+ "grad_norm": 0.7286780710714444,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.833,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.5110421609782807,
251
+ "grad_norm": 0.8624769767543123,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.8326,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.5256433655776601,
258
+ "grad_norm": 0.7489286697832975,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.8344,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.5402445701770396,
265
+ "grad_norm": 0.6965027768353624,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.8329,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.554845774776419,
272
+ "grad_norm": 0.5898605613508874,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.8396,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.5694469793757985,
279
+ "grad_norm": 0.669429389652064,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.8318,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.584048183975178,
286
+ "grad_norm": 0.6580798841963941,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.8314,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.5986493885745574,
293
+ "grad_norm": 0.624128356604639,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.8282,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.6132505931739368,
300
+ "grad_norm": 0.5755522646670556,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.8321,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.6278517977733163,
307
+ "grad_norm": 0.8196980265974857,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.8313,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.6424530023726958,
314
+ "grad_norm": 0.48261475886925087,
315
+ "learning_rate": 5e-06,
316
+ "loss": 0.8238,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.6570542069720752,
321
+ "grad_norm": 0.5343014097762563,
322
+ "learning_rate": 5e-06,
323
+ "loss": 0.8296,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.6716554115714547,
328
+ "grad_norm": 0.8585815714707374,
329
+ "learning_rate": 5e-06,
330
+ "loss": 0.823,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.6862566161708341,
335
+ "grad_norm": 0.7315620836524508,
336
+ "learning_rate": 5e-06,
337
+ "loss": 0.8331,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.7008578207702135,
342
+ "grad_norm": 0.4711661790189355,
343
+ "learning_rate": 5e-06,
344
+ "loss": 0.8245,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.7154590253695929,
349
+ "grad_norm": 0.546263482109446,
350
+ "learning_rate": 5e-06,
351
+ "loss": 0.8212,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.7300602299689725,
356
+ "grad_norm": 0.5757304431326317,
357
+ "learning_rate": 5e-06,
358
+ "loss": 0.8252,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.7446614345683519,
363
+ "grad_norm": 0.5563752904399338,
364
+ "learning_rate": 5e-06,
365
+ "loss": 0.8251,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.7592626391677313,
370
+ "grad_norm": 0.48890029763799747,
371
+ "learning_rate": 5e-06,
372
+ "loss": 0.8244,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.7738638437671108,
377
+ "grad_norm": 0.6121148728397559,
378
+ "learning_rate": 5e-06,
379
+ "loss": 0.8219,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.7884650483664902,
384
+ "grad_norm": 0.651565586948898,
385
+ "learning_rate": 5e-06,
386
+ "loss": 0.8203,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.8030662529658696,
391
+ "grad_norm": 0.5365587518038645,
392
+ "learning_rate": 5e-06,
393
+ "loss": 0.8244,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.8176674575652492,
398
+ "grad_norm": 0.5585874614674294,
399
+ "learning_rate": 5e-06,
400
+ "loss": 0.8261,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.8322686621646286,
405
+ "grad_norm": 0.48225482309598716,
406
+ "learning_rate": 5e-06,
407
+ "loss": 0.828,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.846869866764008,
412
+ "grad_norm": 0.6379018399000604,
413
+ "learning_rate": 5e-06,
414
+ "loss": 0.8187,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.8614710713633875,
419
+ "grad_norm": 0.8248757003628987,
420
+ "learning_rate": 5e-06,
421
+ "loss": 0.8245,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.8760722759627669,
426
+ "grad_norm": 0.7072642911500023,
427
+ "learning_rate": 5e-06,
428
+ "loss": 0.8199,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.8906734805621463,
433
+ "grad_norm": 0.6066965111128374,
434
+ "learning_rate": 5e-06,
435
+ "loss": 0.821,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.9052746851615259,
440
+ "grad_norm": 0.49608072224953953,
441
+ "learning_rate": 5e-06,
442
+ "loss": 0.8263,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.9198758897609053,
447
+ "grad_norm": 0.6053461220096085,
448
+ "learning_rate": 5e-06,
449
+ "loss": 0.8225,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.9344770943602847,
454
+ "grad_norm": 0.5575666035835788,
455
+ "learning_rate": 5e-06,
456
+ "loss": 0.8211,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.9490782989596642,
461
+ "grad_norm": 0.5170427420902555,
462
+ "learning_rate": 5e-06,
463
+ "loss": 0.8202,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.9636795035590436,
468
+ "grad_norm": 0.5652214016440857,
469
+ "learning_rate": 5e-06,
470
+ "loss": 0.8219,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.978280708158423,
475
+ "grad_norm": 0.5065476265832586,
476
+ "learning_rate": 5e-06,
477
+ "loss": 0.8121,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.9928819127578025,
482
+ "grad_norm": 0.5713479763199619,
483
+ "learning_rate": 5e-06,
484
+ "loss": 0.8154,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.9987223945975543,
489
+ "eval_loss": 0.8185040950775146,
490
+ "eval_runtime": 729.2812,
491
+ "eval_samples_per_second": 25.306,
492
+ "eval_steps_per_second": 0.396,
493
+ "step": 684
494
+ },
495
+ {
496
+ "epoch": 1.0074831173571819,
497
+ "grad_norm": 0.5659100587324225,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.8068,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.0220843219565614,
504
+ "grad_norm": 0.5725390345160268,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.7796,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.036685526555941,
511
+ "grad_norm": 0.5067331567131128,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.7784,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.0512867311553202,
518
+ "grad_norm": 0.5633875492368658,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.7789,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.0658879357546998,
525
+ "grad_norm": 0.6503391798526155,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.7785,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.0804891403540793,
532
+ "grad_norm": 0.6157238494098765,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.7788,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.0950903449534586,
539
+ "grad_norm": 0.6692246242398756,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.7791,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.109691549552838,
546
+ "grad_norm": 0.772994893504376,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.7772,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.1242927541522176,
553
+ "grad_norm": 0.5654007018077802,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.778,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.138893958751597,
560
+ "grad_norm": 0.5871850769943243,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.7797,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.1534951633509765,
567
+ "grad_norm": 0.6081431556291285,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.7776,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.168096367950356,
574
+ "grad_norm": 0.5943447291419969,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.7812,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.1826975725497353,
581
+ "grad_norm": 0.5174382592861106,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.7742,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.1972987771491148,
588
+ "grad_norm": 0.5335467085784507,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.7821,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.2118999817484943,
595
+ "grad_norm": 0.5424184832410203,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.7832,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.2265011863478736,
602
+ "grad_norm": 0.5401853269685924,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.7764,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.2411023909472532,
609
+ "grad_norm": 0.5532297607385643,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.776,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.2557035955466325,
616
+ "grad_norm": 0.4600563956098031,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.7746,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.270304800146012,
623
+ "grad_norm": 0.5135474289282321,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.7725,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.2849060047453915,
630
+ "grad_norm": 0.6354802982105713,
631
+ "learning_rate": 5e-06,
632
+ "loss": 0.7787,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.299507209344771,
637
+ "grad_norm": 0.5869839476501474,
638
+ "learning_rate": 5e-06,
639
+ "loss": 0.7712,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.3141084139441503,
644
+ "grad_norm": 0.49495760536344496,
645
+ "learning_rate": 5e-06,
646
+ "loss": 0.777,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.3287096185435299,
651
+ "grad_norm": 0.5322628773610525,
652
+ "learning_rate": 5e-06,
653
+ "loss": 0.7791,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.3433108231429092,
658
+ "grad_norm": 0.6394355119269733,
659
+ "learning_rate": 5e-06,
660
+ "loss": 0.7813,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.3579120277422887,
665
+ "grad_norm": 0.6150475948115007,
666
+ "learning_rate": 5e-06,
667
+ "loss": 0.7718,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.3725132323416682,
672
+ "grad_norm": 0.6284466998832495,
673
+ "learning_rate": 5e-06,
674
+ "loss": 0.7716,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.3871144369410477,
679
+ "grad_norm": 0.4995594773156744,
680
+ "learning_rate": 5e-06,
681
+ "loss": 0.7801,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.401715641540427,
686
+ "grad_norm": 0.5533231758658743,
687
+ "learning_rate": 5e-06,
688
+ "loss": 0.7749,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.4163168461398066,
693
+ "grad_norm": 0.5566318311264558,
694
+ "learning_rate": 5e-06,
695
+ "loss": 0.7809,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.4309180507391859,
700
+ "grad_norm": 0.5996092713965696,
701
+ "learning_rate": 5e-06,
702
+ "loss": 0.7769,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.4455192553385654,
707
+ "grad_norm": 0.4923370749506076,
708
+ "learning_rate": 5e-06,
709
+ "loss": 0.7733,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.460120459937945,
714
+ "grad_norm": 0.5718051545730899,
715
+ "learning_rate": 5e-06,
716
+ "loss": 0.778,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.4747216645373245,
721
+ "grad_norm": 0.4966605100244046,
722
+ "learning_rate": 5e-06,
723
+ "loss": 0.7755,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.4893228691367038,
728
+ "grad_norm": 0.5104108866561695,
729
+ "learning_rate": 5e-06,
730
+ "loss": 0.7762,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.5039240737360833,
735
+ "grad_norm": 0.5790841364965528,
736
+ "learning_rate": 5e-06,
737
+ "loss": 0.775,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.5185252783354626,
742
+ "grad_norm": 0.5079205962955746,
743
+ "learning_rate": 5e-06,
744
+ "loss": 0.7791,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.533126482934842,
749
+ "grad_norm": 0.4897829483446737,
750
+ "learning_rate": 5e-06,
751
+ "loss": 0.7732,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.5477276875342216,
756
+ "grad_norm": 0.5375326427308407,
757
+ "learning_rate": 5e-06,
758
+ "loss": 0.7734,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.5623288921336012,
763
+ "grad_norm": 0.4714533263773857,
764
+ "learning_rate": 5e-06,
765
+ "loss": 0.7786,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.5769300967329805,
770
+ "grad_norm": 0.5170403858384673,
771
+ "learning_rate": 5e-06,
772
+ "loss": 0.772,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.5915313013323598,
777
+ "grad_norm": 0.5584745095875884,
778
+ "learning_rate": 5e-06,
779
+ "loss": 0.7788,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.6061325059317393,
784
+ "grad_norm": 0.5632792125524021,
785
+ "learning_rate": 5e-06,
786
+ "loss": 0.7764,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.6207337105311188,
791
+ "grad_norm": 0.5303585273369582,
792
+ "learning_rate": 5e-06,
793
+ "loss": 0.7698,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.6353349151304983,
798
+ "grad_norm": 0.5292556194617752,
799
+ "learning_rate": 5e-06,
800
+ "loss": 0.7754,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.6499361197298779,
805
+ "grad_norm": 0.5319736770394399,
806
+ "learning_rate": 5e-06,
807
+ "loss": 0.7754,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.6645373243292572,
812
+ "grad_norm": 0.5409862397072692,
813
+ "learning_rate": 5e-06,
814
+ "loss": 0.7732,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.6791385289286365,
819
+ "grad_norm": 0.5347398767131228,
820
+ "learning_rate": 5e-06,
821
+ "loss": 0.775,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.693739733528016,
826
+ "grad_norm": 0.5887598823053857,
827
+ "learning_rate": 5e-06,
828
+ "loss": 0.7734,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.7083409381273955,
833
+ "grad_norm": 0.588980481311897,
834
+ "learning_rate": 5e-06,
835
+ "loss": 0.7776,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.722942142726775,
840
+ "grad_norm": 0.5476017973657227,
841
+ "learning_rate": 5e-06,
842
+ "loss": 0.7718,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.7375433473261546,
847
+ "grad_norm": 0.5548638443373327,
848
+ "learning_rate": 5e-06,
849
+ "loss": 0.778,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 1.7521445519255339,
854
+ "grad_norm": 0.5443995408512653,
855
+ "learning_rate": 5e-06,
856
+ "loss": 0.7731,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 1.7667457565249132,
861
+ "grad_norm": 0.5134399032378028,
862
+ "learning_rate": 5e-06,
863
+ "loss": 0.7762,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 1.7813469611242927,
868
+ "grad_norm": 0.5143443520325698,
869
+ "learning_rate": 5e-06,
870
+ "loss": 0.7737,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 1.7959481657236722,
875
+ "grad_norm": 0.5712512301925389,
876
+ "learning_rate": 5e-06,
877
+ "loss": 0.7752,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 1.8105493703230517,
882
+ "grad_norm": 0.5022436155237929,
883
+ "learning_rate": 5e-06,
884
+ "loss": 0.7746,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 1.825150574922431,
889
+ "grad_norm": 0.5183607046169039,
890
+ "learning_rate": 5e-06,
891
+ "loss": 0.7758,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 1.8397517795218106,
896
+ "grad_norm": 0.5327048894936923,
897
+ "learning_rate": 5e-06,
898
+ "loss": 0.7737,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 1.8543529841211899,
903
+ "grad_norm": 0.4828373941208032,
904
+ "learning_rate": 5e-06,
905
+ "loss": 0.7734,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 1.8689541887205694,
910
+ "grad_norm": 0.4692396568766125,
911
+ "learning_rate": 5e-06,
912
+ "loss": 0.7702,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 1.883555393319949,
917
+ "grad_norm": 0.5272353821412613,
918
+ "learning_rate": 5e-06,
919
+ "loss": 0.7738,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 1.8981565979193284,
924
+ "grad_norm": 0.5974378803453756,
925
+ "learning_rate": 5e-06,
926
+ "loss": 0.7744,
927
+ "step": 1300
928
+ },
929
+ {
930
+ "epoch": 1.9127578025187078,
931
+ "grad_norm": 0.45897414900404526,
932
+ "learning_rate": 5e-06,
933
+ "loss": 0.7707,
934
+ "step": 1310
935
+ },
936
+ {
937
+ "epoch": 1.9273590071180873,
938
+ "grad_norm": 0.5661797189222842,
939
+ "learning_rate": 5e-06,
940
+ "loss": 0.7729,
941
+ "step": 1320
942
+ },
943
+ {
944
+ "epoch": 1.9419602117174666,
945
+ "grad_norm": 0.5291159788169262,
946
+ "learning_rate": 5e-06,
947
+ "loss": 0.7704,
948
+ "step": 1330
949
+ },
950
+ {
951
+ "epoch": 1.956561416316846,
952
+ "grad_norm": 0.5803039839795054,
953
+ "learning_rate": 5e-06,
954
+ "loss": 0.7711,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 1.9711626209162256,
959
+ "grad_norm": 0.5668430658536179,
960
+ "learning_rate": 5e-06,
961
+ "loss": 0.7714,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 1.9857638255156052,
966
+ "grad_norm": 0.5292288364377395,
967
+ "learning_rate": 5e-06,
968
+ "loss": 0.7681,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 1.9989049096550464,
973
+ "eval_loss": 0.8045554161071777,
974
+ "eval_runtime": 732.5889,
975
+ "eval_samples_per_second": 25.191,
976
+ "eval_steps_per_second": 0.394,
977
+ "step": 1369
978
+ },
979
+ {
980
+ "epoch": 2.0003650301149847,
981
+ "grad_norm": 0.5917011918049785,
982
+ "learning_rate": 5e-06,
983
+ "loss": 0.7813,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.0149662347143638,
988
+ "grad_norm": 0.6437888983866474,
989
+ "learning_rate": 5e-06,
990
+ "loss": 0.7275,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.0295674393137433,
995
+ "grad_norm": 0.5993159674827806,
996
+ "learning_rate": 5e-06,
997
+ "loss": 0.7301,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.044168643913123,
1002
+ "grad_norm": 0.6004688564094799,
1003
+ "learning_rate": 5e-06,
1004
+ "loss": 0.7279,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.0587698485125023,
1009
+ "grad_norm": 0.5968765010977406,
1010
+ "learning_rate": 5e-06,
1011
+ "loss": 0.732,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.073371053111882,
1016
+ "grad_norm": 0.6368286520923802,
1017
+ "learning_rate": 5e-06,
1018
+ "loss": 0.7327,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.0879722577112614,
1023
+ "grad_norm": 0.5121224799191383,
1024
+ "learning_rate": 5e-06,
1025
+ "loss": 0.7289,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.1025734623106405,
1030
+ "grad_norm": 0.5426488835411897,
1031
+ "learning_rate": 5e-06,
1032
+ "loss": 0.729,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.11717466691002,
1037
+ "grad_norm": 0.5360711433495,
1038
+ "learning_rate": 5e-06,
1039
+ "loss": 0.7321,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.1317758715093995,
1044
+ "grad_norm": 0.570345866307846,
1045
+ "learning_rate": 5e-06,
1046
+ "loss": 0.7283,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.146377076108779,
1051
+ "grad_norm": 0.5646482286111343,
1052
+ "learning_rate": 5e-06,
1053
+ "loss": 0.7341,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.1609782807081586,
1058
+ "grad_norm": 0.6170916412089019,
1059
+ "learning_rate": 5e-06,
1060
+ "loss": 0.7273,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.175579485307538,
1065
+ "grad_norm": 0.5669820051659463,
1066
+ "learning_rate": 5e-06,
1067
+ "loss": 0.7327,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.190180689906917,
1072
+ "grad_norm": 0.5032603903192315,
1073
+ "learning_rate": 5e-06,
1074
+ "loss": 0.7259,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.2047818945062967,
1079
+ "grad_norm": 0.536250519862031,
1080
+ "learning_rate": 5e-06,
1081
+ "loss": 0.7309,
1082
+ "step": 1510
1083
+ },
1084
+ {
1085
+ "epoch": 2.219383099105676,
1086
+ "grad_norm": 0.4989195000116721,
1087
+ "learning_rate": 5e-06,
1088
+ "loss": 0.7351,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.2339843037050557,
1093
+ "grad_norm": 0.48084465295135953,
1094
+ "learning_rate": 5e-06,
1095
+ "loss": 0.7319,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.2485855083044353,
1100
+ "grad_norm": 0.6041492880249871,
1101
+ "learning_rate": 5e-06,
1102
+ "loss": 0.7331,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.2631867129038143,
1107
+ "grad_norm": 0.48501706414438883,
1108
+ "learning_rate": 5e-06,
1109
+ "loss": 0.7364,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.277787917503194,
1114
+ "grad_norm": 0.486621431249399,
1115
+ "learning_rate": 5e-06,
1116
+ "loss": 0.7336,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.2923891221025734,
1121
+ "grad_norm": 0.6249224122437264,
1122
+ "learning_rate": 5e-06,
1123
+ "loss": 0.7335,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.306990326701953,
1128
+ "grad_norm": 0.6255968466832591,
1129
+ "learning_rate": 5e-06,
1130
+ "loss": 0.7315,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.3215915313013324,
1135
+ "grad_norm": 0.5271636183137467,
1136
+ "learning_rate": 5e-06,
1137
+ "loss": 0.7322,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.336192735900712,
1142
+ "grad_norm": 0.5924207573496902,
1143
+ "learning_rate": 5e-06,
1144
+ "loss": 0.7345,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.3507939405000915,
1149
+ "grad_norm": 0.5587622345452513,
1150
+ "learning_rate": 5e-06,
1151
+ "loss": 0.7344,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.3653951450994706,
1156
+ "grad_norm": 0.6269568570302153,
1157
+ "learning_rate": 5e-06,
1158
+ "loss": 0.7359,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.37999634969885,
1163
+ "grad_norm": 0.6533009549527986,
1164
+ "learning_rate": 5e-06,
1165
+ "loss": 0.7368,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.3945975542982296,
1170
+ "grad_norm": 0.5195452792704209,
1171
+ "learning_rate": 5e-06,
1172
+ "loss": 0.7355,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.409198758897609,
1177
+ "grad_norm": 0.5528537289554203,
1178
+ "learning_rate": 5e-06,
1179
+ "loss": 0.7355,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.4237999634969887,
1184
+ "grad_norm": 0.5434124551027695,
1185
+ "learning_rate": 5e-06,
1186
+ "loss": 0.7343,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.4384011680963678,
1191
+ "grad_norm": 0.5166289013156083,
1192
+ "learning_rate": 5e-06,
1193
+ "loss": 0.7348,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.4530023726957473,
1198
+ "grad_norm": 0.5085481998475664,
1199
+ "learning_rate": 5e-06,
1200
+ "loss": 0.7384,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.467603577295127,
1205
+ "grad_norm": 0.47895714940004425,
1206
+ "learning_rate": 5e-06,
1207
+ "loss": 0.7319,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.4822047818945063,
1212
+ "grad_norm": 0.6790087073589551,
1213
+ "learning_rate": 5e-06,
1214
+ "loss": 0.7344,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.496805986493886,
1219
+ "grad_norm": 0.5337750367727961,
1220
+ "learning_rate": 5e-06,
1221
+ "loss": 0.7348,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.511407191093265,
1226
+ "grad_norm": 0.578024943637955,
1227
+ "learning_rate": 5e-06,
1228
+ "loss": 0.7335,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.526008395692645,
1233
+ "grad_norm": 0.5321237652992599,
1234
+ "learning_rate": 5e-06,
1235
+ "loss": 0.7341,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.540609600292024,
1240
+ "grad_norm": 0.552250362014024,
1241
+ "learning_rate": 5e-06,
1242
+ "loss": 0.7345,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.5552108048914035,
1247
+ "grad_norm": 0.47716769494866995,
1248
+ "learning_rate": 5e-06,
1249
+ "loss": 0.7364,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.569812009490783,
1254
+ "grad_norm": 0.5382810891628738,
1255
+ "learning_rate": 5e-06,
1256
+ "loss": 0.7327,
1257
+ "step": 1760
1258
+ },
1259
+ {
1260
+ "epoch": 2.5844132140901626,
1261
+ "grad_norm": 0.5291652309846363,
1262
+ "learning_rate": 5e-06,
1263
+ "loss": 0.734,
1264
+ "step": 1770
1265
+ },
1266
+ {
1267
+ "epoch": 2.599014418689542,
1268
+ "grad_norm": 0.583404809051004,
1269
+ "learning_rate": 5e-06,
1270
+ "loss": 0.7309,
1271
+ "step": 1780
1272
+ },
1273
+ {
1274
+ "epoch": 2.613615623288921,
1275
+ "grad_norm": 0.607832211058636,
1276
+ "learning_rate": 5e-06,
1277
+ "loss": 0.7352,
1278
+ "step": 1790
1279
+ },
1280
+ {
1281
+ "epoch": 2.6282168278883007,
1282
+ "grad_norm": 0.5598928601891838,
1283
+ "learning_rate": 5e-06,
1284
+ "loss": 0.7356,
1285
+ "step": 1800
1286
+ },
1287
+ {
1288
+ "epoch": 2.64281803248768,
1289
+ "grad_norm": 0.5949750898099526,
1290
+ "learning_rate": 5e-06,
1291
+ "loss": 0.7353,
1292
+ "step": 1810
1293
+ },
1294
+ {
1295
+ "epoch": 2.6574192370870597,
1296
+ "grad_norm": 0.6066820856022053,
1297
+ "learning_rate": 5e-06,
1298
+ "loss": 0.7347,
1299
+ "step": 1820
1300
+ },
1301
+ {
1302
+ "epoch": 2.6720204416864393,
1303
+ "grad_norm": 0.5198033507111653,
1304
+ "learning_rate": 5e-06,
1305
+ "loss": 0.7354,
1306
+ "step": 1830
1307
+ },
1308
+ {
1309
+ "epoch": 2.6866216462858183,
1310
+ "grad_norm": 0.5040452692645214,
1311
+ "learning_rate": 5e-06,
1312
+ "loss": 0.7391,
1313
+ "step": 1840
1314
+ },
1315
+ {
1316
+ "epoch": 2.701222850885198,
1317
+ "grad_norm": 0.5156854247429866,
1318
+ "learning_rate": 5e-06,
1319
+ "loss": 0.7388,
1320
+ "step": 1850
1321
+ },
1322
+ {
1323
+ "epoch": 2.7158240554845774,
1324
+ "grad_norm": 0.5617334329140413,
1325
+ "learning_rate": 5e-06,
1326
+ "loss": 0.737,
1327
+ "step": 1860
1328
+ },
1329
+ {
1330
+ "epoch": 2.730425260083957,
1331
+ "grad_norm": 0.4970472716656489,
1332
+ "learning_rate": 5e-06,
1333
+ "loss": 0.7359,
1334
+ "step": 1870
1335
+ },
1336
+ {
1337
+ "epoch": 2.7450264646833364,
1338
+ "grad_norm": 0.6666729572656519,
1339
+ "learning_rate": 5e-06,
1340
+ "loss": 0.7349,
1341
+ "step": 1880
1342
+ },
1343
+ {
1344
+ "epoch": 2.759627669282716,
1345
+ "grad_norm": 0.660456603270783,
1346
+ "learning_rate": 5e-06,
1347
+ "loss": 0.7363,
1348
+ "step": 1890
1349
+ },
1350
+ {
1351
+ "epoch": 2.7742288738820955,
1352
+ "grad_norm": 0.5479397279932245,
1353
+ "learning_rate": 5e-06,
1354
+ "loss": 0.7359,
1355
+ "step": 1900
1356
+ },
1357
+ {
1358
+ "epoch": 2.7888300784814746,
1359
+ "grad_norm": 0.5184737073351016,
1360
+ "learning_rate": 5e-06,
1361
+ "loss": 0.7383,
1362
+ "step": 1910
1363
+ },
1364
+ {
1365
+ "epoch": 2.803431283080854,
1366
+ "grad_norm": 0.501451603194624,
1367
+ "learning_rate": 5e-06,
1368
+ "loss": 0.7344,
1369
+ "step": 1920
1370
+ },
1371
+ {
1372
+ "epoch": 2.8180324876802336,
1373
+ "grad_norm": 0.5543991291124852,
1374
+ "learning_rate": 5e-06,
1375
+ "loss": 0.7382,
1376
+ "step": 1930
1377
+ },
1378
+ {
1379
+ "epoch": 2.832633692279613,
1380
+ "grad_norm": 0.6053239113120223,
1381
+ "learning_rate": 5e-06,
1382
+ "loss": 0.7356,
1383
+ "step": 1940
1384
+ },
1385
+ {
1386
+ "epoch": 2.8472348968789927,
1387
+ "grad_norm": 0.5618006505391813,
1388
+ "learning_rate": 5e-06,
1389
+ "loss": 0.7377,
1390
+ "step": 1950
1391
+ },
1392
+ {
1393
+ "epoch": 2.8618361014783718,
1394
+ "grad_norm": 0.5815392261505143,
1395
+ "learning_rate": 5e-06,
1396
+ "loss": 0.7337,
1397
+ "step": 1960
1398
+ },
1399
+ {
1400
+ "epoch": 2.8764373060777513,
1401
+ "grad_norm": 0.7488694605510656,
1402
+ "learning_rate": 5e-06,
1403
+ "loss": 0.7362,
1404
+ "step": 1970
1405
+ },
1406
+ {
1407
+ "epoch": 2.891038510677131,
1408
+ "grad_norm": 0.5769073126410138,
1409
+ "learning_rate": 5e-06,
1410
+ "loss": 0.7359,
1411
+ "step": 1980
1412
+ },
1413
+ {
1414
+ "epoch": 2.9056397152765103,
1415
+ "grad_norm": 0.5750570915989177,
1416
+ "learning_rate": 5e-06,
1417
+ "loss": 0.7331,
1418
+ "step": 1990
1419
+ },
1420
+ {
1421
+ "epoch": 2.92024091987589,
1422
+ "grad_norm": 0.5354199731148004,
1423
+ "learning_rate": 5e-06,
1424
+ "loss": 0.7341,
1425
+ "step": 2000
1426
+ },
1427
+ {
1428
+ "epoch": 2.9348421244752694,
1429
+ "grad_norm": 0.5855570342179945,
1430
+ "learning_rate": 5e-06,
1431
+ "loss": 0.7404,
1432
+ "step": 2010
1433
+ },
1434
+ {
1435
+ "epoch": 2.949443329074649,
1436
+ "grad_norm": 0.6261526281235102,
1437
+ "learning_rate": 5e-06,
1438
+ "loss": 0.7337,
1439
+ "step": 2020
1440
+ },
1441
+ {
1442
+ "epoch": 2.964044533674028,
1443
+ "grad_norm": 0.5504549828167312,
1444
+ "learning_rate": 5e-06,
1445
+ "loss": 0.7348,
1446
+ "step": 2030
1447
+ },
1448
+ {
1449
+ "epoch": 2.9786457382734075,
1450
+ "grad_norm": 0.529021801831048,
1451
+ "learning_rate": 5e-06,
1452
+ "loss": 0.7354,
1453
+ "step": 2040
1454
+ },
1455
+ {
1456
+ "epoch": 2.993246942872787,
1457
+ "grad_norm": 0.5245972765419218,
1458
+ "learning_rate": 5e-06,
1459
+ "loss": 0.7372,
1460
+ "step": 2050
1461
+ },
1462
+ {
1463
+ "epoch": 2.9961671837926627,
1464
+ "eval_loss": 0.8026307821273804,
1465
+ "eval_runtime": 732.5471,
1466
+ "eval_samples_per_second": 25.193,
1467
+ "eval_steps_per_second": 0.395,
1468
+ "step": 2052
1469
+ },
1470
+ {
1471
+ "epoch": 2.9961671837926627,
1472
+ "step": 2052,
1473
+ "total_flos": 3436967047987200.0,
1474
+ "train_loss": 0.7862561077286161,
1475
+ "train_runtime": 121149.8135,
1476
+ "train_samples_per_second": 8.683,
1477
+ "train_steps_per_second": 0.017
1478
+ }
1479
+ ],
1480
+ "logging_steps": 10,
1481
+ "max_steps": 2052,
1482
+ "num_input_tokens_seen": 0,
1483
+ "num_train_epochs": 3,
1484
+ "save_steps": 500,
1485
+ "stateful_callbacks": {
1486
+ "TrainerControl": {
1487
+ "args": {
1488
+ "should_epoch_stop": false,
1489
+ "should_evaluate": false,
1490
+ "should_log": false,
1491
+ "should_save": true,
1492
+ "should_training_stop": true
1493
+ },
1494
+ "attributes": {}
1495
+ }
1496
+ },
1497
+ "total_flos": 3436967047987200.0,
1498
+ "train_batch_size": 8,
1499
+ "trial_name": null,
1500
+ "trial_params": null
1501
+ }
training_eval_loss.png ADDED
training_loss.png ADDED