File size: 7,576 Bytes
07f3deb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
{
  "best_metric": 1.056412935256958,
  "best_model_checkpoint": "/kaggle/output/checkpoint-19000",
  "epoch": 0.7741199478487614,
  "eval_steps": 1000,
  "global_step": 19000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.7777777777777777e-11,
      "loss": 1.0788,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.7750000000000004e-08,
      "loss": 1.2063,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.32894211576846305,
      "eval_loss": 1.109653115272522,
      "eval_runtime": 50.6057,
      "eval_samples_per_second": 99.001,
      "eval_steps_per_second": 12.39,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.5527777777777784e-08,
      "loss": 1.1293,
      "step": 2000
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.32994011976047904,
      "eval_loss": 1.1056402921676636,
      "eval_runtime": 50.7169,
      "eval_samples_per_second": 98.784,
      "eval_steps_per_second": 12.363,
      "step": 2000
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.327777777777778e-08,
      "loss": 1.1263,
      "step": 3000
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.3347305389221557,
      "eval_loss": 1.1063188314437866,
      "eval_runtime": 50.8081,
      "eval_samples_per_second": 98.606,
      "eval_steps_per_second": 12.341,
      "step": 3000
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.1105555555555557e-07,
      "loss": 1.1211,
      "step": 4000
    },
    {
      "epoch": 0.16,
      "eval_accuracy": 0.34291417165668664,
      "eval_loss": 1.1010773181915283,
      "eval_runtime": 50.6469,
      "eval_samples_per_second": 98.92,
      "eval_steps_per_second": 12.38,
      "step": 4000
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.3883333333333335e-07,
      "loss": 1.1176,
      "step": 5000
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.3395209580838323,
      "eval_loss": 1.099412441253662,
      "eval_runtime": 50.7266,
      "eval_samples_per_second": 98.765,
      "eval_steps_per_second": 12.36,
      "step": 5000
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.6658333333333335e-07,
      "loss": 1.1165,
      "step": 6000
    },
    {
      "epoch": 0.24,
      "eval_accuracy": 0.3596806387225549,
      "eval_loss": 1.0983413457870483,
      "eval_runtime": 50.7493,
      "eval_samples_per_second": 98.721,
      "eval_steps_per_second": 12.355,
      "step": 6000
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9436111111111112e-07,
      "loss": 1.1127,
      "step": 7000
    },
    {
      "epoch": 0.29,
      "eval_accuracy": 0.35768463073852297,
      "eval_loss": 1.094804048538208,
      "eval_runtime": 50.8322,
      "eval_samples_per_second": 98.56,
      "eval_steps_per_second": 12.335,
      "step": 7000
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.2213888888888891e-07,
      "loss": 1.1095,
      "step": 8000
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.36407185628742517,
      "eval_loss": 1.0937609672546387,
      "eval_runtime": 50.8609,
      "eval_samples_per_second": 98.504,
      "eval_steps_per_second": 12.328,
      "step": 8000
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.499166666666667e-07,
      "loss": 1.1074,
      "step": 9000
    },
    {
      "epoch": 0.37,
      "eval_accuracy": 0.34770459081836325,
      "eval_loss": 1.1025313138961792,
      "eval_runtime": 50.8052,
      "eval_samples_per_second": 98.612,
      "eval_steps_per_second": 12.341,
      "step": 9000
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.776666666666667e-07,
      "loss": 1.1065,
      "step": 10000
    },
    {
      "epoch": 0.41,
      "eval_accuracy": 0.38163672654690617,
      "eval_loss": 1.0920748710632324,
      "eval_runtime": 50.8964,
      "eval_samples_per_second": 98.435,
      "eval_steps_per_second": 12.319,
      "step": 10000
    },
    {
      "epoch": 0.45,
      "learning_rate": 3.054444444444444e-07,
      "loss": 1.1026,
      "step": 11000
    },
    {
      "epoch": 0.45,
      "eval_accuracy": 0.37944111776447104,
      "eval_loss": 1.0899525880813599,
      "eval_runtime": 50.6905,
      "eval_samples_per_second": 98.835,
      "eval_steps_per_second": 12.369,
      "step": 11000
    },
    {
      "epoch": 0.49,
      "learning_rate": 3.3319444444444444e-07,
      "loss": 1.1016,
      "step": 12000
    },
    {
      "epoch": 0.49,
      "eval_accuracy": 0.4,
      "eval_loss": 1.0867687463760376,
      "eval_runtime": 50.8282,
      "eval_samples_per_second": 98.567,
      "eval_steps_per_second": 12.336,
      "step": 12000
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.6094444444444446e-07,
      "loss": 1.0999,
      "step": 13000
    },
    {
      "epoch": 0.53,
      "eval_accuracy": 0.3467065868263473,
      "eval_loss": 1.0919947624206543,
      "eval_runtime": 50.7953,
      "eval_samples_per_second": 98.631,
      "eval_steps_per_second": 12.344,
      "step": 13000
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.8872222222222223e-07,
      "loss": 1.0976,
      "step": 14000
    },
    {
      "epoch": 0.57,
      "eval_accuracy": 0.38003992015968063,
      "eval_loss": 1.0882444381713867,
      "eval_runtime": 50.8866,
      "eval_samples_per_second": 98.454,
      "eval_steps_per_second": 12.322,
      "step": 14000
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.1650000000000006e-07,
      "loss": 1.0951,
      "step": 15000
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.4229540918163673,
      "eval_loss": 1.0766451358795166,
      "eval_runtime": 50.7597,
      "eval_samples_per_second": 98.7,
      "eval_steps_per_second": 12.352,
      "step": 15000
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.4425e-07,
      "loss": 1.087,
      "step": 16000
    },
    {
      "epoch": 0.65,
      "eval_accuracy": 0.4339321357285429,
      "eval_loss": 1.0621711015701294,
      "eval_runtime": 50.7559,
      "eval_samples_per_second": 98.708,
      "eval_steps_per_second": 12.353,
      "step": 16000
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.7202777777777785e-07,
      "loss": 1.0769,
      "step": 17000
    },
    {
      "epoch": 0.69,
      "eval_accuracy": 0.4357285429141717,
      "eval_loss": 1.0624364614486694,
      "eval_runtime": 50.8608,
      "eval_samples_per_second": 98.504,
      "eval_steps_per_second": 12.328,
      "step": 17000
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.998055555555556e-07,
      "loss": 1.0798,
      "step": 18000
    },
    {
      "epoch": 0.73,
      "eval_accuracy": 0.4311377245508982,
      "eval_loss": 1.0611094236373901,
      "eval_runtime": 50.7255,
      "eval_samples_per_second": 98.767,
      "eval_steps_per_second": 12.361,
      "step": 18000
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.275555555555556e-07,
      "loss": 1.0717,
      "step": 19000
    },
    {
      "epoch": 0.77,
      "eval_accuracy": 0.43852295409181635,
      "eval_loss": 1.056412935256958,
      "eval_runtime": 50.8955,
      "eval_samples_per_second": 98.437,
      "eval_steps_per_second": 12.319,
      "step": 19000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 10000000,
  "num_train_epochs": 408,
  "save_steps": 1000,
  "total_flos": 3.9716747476992e+16,
  "trial_name": null,
  "trial_params": null
}