File size: 6,119 Bytes
5395305
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 1.0879395008087158,
  "best_model_checkpoint": "/kaggle/output/checkpoint-15000",
  "epoch": 0.6111473272490222,
  "eval_steps": 1000,
  "global_step": 15000,
  "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": 1.2076,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.7750000000000004e-08,
      "loss": 1.1301,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.3321357285429142,
      "eval_loss": 1.1047232151031494,
      "eval_runtime": 50.8344,
      "eval_samples_per_second": 98.555,
      "eval_steps_per_second": 12.334,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.5527777777777784e-08,
      "loss": 1.1286,
      "step": 2000
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.3377245508982036,
      "eval_loss": 1.1038333177566528,
      "eval_runtime": 50.8114,
      "eval_samples_per_second": 98.6,
      "eval_steps_per_second": 12.34,
      "step": 2000
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.327777777777778e-08,
      "loss": 1.1214,
      "step": 3000
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.3409181636726547,
      "eval_loss": 1.103529930114746,
      "eval_runtime": 50.8258,
      "eval_samples_per_second": 98.572,
      "eval_steps_per_second": 12.336,
      "step": 3000
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.1105555555555557e-07,
      "loss": 1.1249,
      "step": 4000
    },
    {
      "epoch": 0.16,
      "eval_accuracy": 0.3469061876247505,
      "eval_loss": 1.1000434160232544,
      "eval_runtime": 50.6414,
      "eval_samples_per_second": 98.931,
      "eval_steps_per_second": 12.381,
      "step": 4000
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.3880555555555558e-07,
      "loss": 1.1206,
      "step": 5000
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.34171656686626745,
      "eval_loss": 1.0996097326278687,
      "eval_runtime": 50.6956,
      "eval_samples_per_second": 98.825,
      "eval_steps_per_second": 12.368,
      "step": 5000
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.6658333333333335e-07,
      "loss": 1.1161,
      "step": 6000
    },
    {
      "epoch": 0.24,
      "eval_accuracy": 0.3590818363273453,
      "eval_loss": 1.096977710723877,
      "eval_runtime": 50.5826,
      "eval_samples_per_second": 99.046,
      "eval_steps_per_second": 12.396,
      "step": 6000
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9433333333333334e-07,
      "loss": 1.1138,
      "step": 7000
    },
    {
      "epoch": 0.29,
      "eval_accuracy": 0.3532934131736527,
      "eval_loss": 1.0949815511703491,
      "eval_runtime": 50.5604,
      "eval_samples_per_second": 99.089,
      "eval_steps_per_second": 12.401,
      "step": 7000
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.2211111111111114e-07,
      "loss": 1.1135,
      "step": 8000
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.36327345309381237,
      "eval_loss": 1.093558430671692,
      "eval_runtime": 50.608,
      "eval_samples_per_second": 98.996,
      "eval_steps_per_second": 12.389,
      "step": 8000
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.4986111111111113e-07,
      "loss": 1.1063,
      "step": 9000
    },
    {
      "epoch": 0.37,
      "eval_accuracy": 0.35548902195608784,
      "eval_loss": 1.0992107391357422,
      "eval_runtime": 50.5434,
      "eval_samples_per_second": 99.123,
      "eval_steps_per_second": 12.405,
      "step": 9000
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.776388888888889e-07,
      "loss": 1.1083,
      "step": 10000
    },
    {
      "epoch": 0.41,
      "eval_accuracy": 0.3836327345309381,
      "eval_loss": 1.0920206308364868,
      "eval_runtime": 50.5559,
      "eval_samples_per_second": 99.098,
      "eval_steps_per_second": 12.402,
      "step": 10000
    },
    {
      "epoch": 0.45,
      "learning_rate": 3.053888888888889e-07,
      "loss": 1.1044,
      "step": 11000
    },
    {
      "epoch": 0.45,
      "eval_accuracy": 0.38762475049900197,
      "eval_loss": 1.0904459953308105,
      "eval_runtime": 50.9725,
      "eval_samples_per_second": 98.288,
      "eval_steps_per_second": 12.301,
      "step": 11000
    },
    {
      "epoch": 0.49,
      "learning_rate": 3.331666666666667e-07,
      "loss": 1.1019,
      "step": 12000
    },
    {
      "epoch": 0.49,
      "eval_accuracy": 0.3912175648702595,
      "eval_loss": 1.088543176651001,
      "eval_runtime": 50.8297,
      "eval_samples_per_second": 98.564,
      "eval_steps_per_second": 12.335,
      "step": 12000
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.609166666666667e-07,
      "loss": 1.1032,
      "step": 13000
    },
    {
      "epoch": 0.53,
      "eval_accuracy": 0.3435129740518962,
      "eval_loss": 1.0940682888031006,
      "eval_runtime": 51.0031,
      "eval_samples_per_second": 98.229,
      "eval_steps_per_second": 12.293,
      "step": 13000
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.886944444444445e-07,
      "loss": 1.1006,
      "step": 14000
    },
    {
      "epoch": 0.57,
      "eval_accuracy": 0.36826347305389223,
      "eval_loss": 1.0924910306930542,
      "eval_runtime": 51.2753,
      "eval_samples_per_second": 97.708,
      "eval_steps_per_second": 12.228,
      "step": 14000
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.164444444444445e-07,
      "loss": 1.1,
      "step": 15000
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.38323353293413176,
      "eval_loss": 1.0879395008087158,
      "eval_runtime": 51.3783,
      "eval_samples_per_second": 97.512,
      "eval_steps_per_second": 12.204,
      "step": 15000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 10000000,
  "num_train_epochs": 408,
  "save_steps": 1000,
  "total_flos": 3.135532695552e+16,
  "trial_name": null,
  "trial_params": null
}