File size: 7,587 Bytes
903b5b6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.0809950828552246,
  "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": 1.1065,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.7750000000000004e-08,
      "loss": 1.1586,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.32954091816367265,
      "eval_loss": 1.1065887212753296,
      "eval_runtime": 54.4372,
      "eval_samples_per_second": 92.033,
      "eval_steps_per_second": 11.518,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.5527777777777784e-08,
      "loss": 1.1259,
      "step": 2000
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.3435129740518962,
      "eval_loss": 1.1045255661010742,
      "eval_runtime": 54.458,
      "eval_samples_per_second": 91.997,
      "eval_steps_per_second": 11.513,
      "step": 2000
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.327777777777778e-08,
      "loss": 1.1229,
      "step": 3000
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.3441117764471058,
      "eval_loss": 1.1050777435302734,
      "eval_runtime": 54.349,
      "eval_samples_per_second": 92.182,
      "eval_steps_per_second": 11.537,
      "step": 3000
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.1105555555555557e-07,
      "loss": 1.1237,
      "step": 4000
    },
    {
      "epoch": 0.16,
      "eval_accuracy": 0.3411177644710579,
      "eval_loss": 1.1015312671661377,
      "eval_runtime": 54.4388,
      "eval_samples_per_second": 92.03,
      "eval_steps_per_second": 11.518,
      "step": 4000
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.3883333333333335e-07,
      "loss": 1.1202,
      "step": 5000
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.3405189620758483,
      "eval_loss": 1.1006112098693848,
      "eval_runtime": 54.4109,
      "eval_samples_per_second": 92.077,
      "eval_steps_per_second": 11.523,
      "step": 5000
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.6658333333333335e-07,
      "loss": 1.1182,
      "step": 6000
    },
    {
      "epoch": 0.24,
      "eval_accuracy": 0.35489021956087824,
      "eval_loss": 1.0982259511947632,
      "eval_runtime": 54.3841,
      "eval_samples_per_second": 92.123,
      "eval_steps_per_second": 11.529,
      "step": 6000
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9436111111111112e-07,
      "loss": 1.1125,
      "step": 7000
    },
    {
      "epoch": 0.29,
      "eval_accuracy": 0.35748502994011977,
      "eval_loss": 1.0954252481460571,
      "eval_runtime": 54.3975,
      "eval_samples_per_second": 92.1,
      "eval_steps_per_second": 11.526,
      "step": 7000
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.2213888888888891e-07,
      "loss": 1.1096,
      "step": 8000
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.3664670658682635,
      "eval_loss": 1.0949230194091797,
      "eval_runtime": 54.3263,
      "eval_samples_per_second": 92.221,
      "eval_steps_per_second": 11.541,
      "step": 8000
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.4988888888888893e-07,
      "loss": 1.1057,
      "step": 9000
    },
    {
      "epoch": 0.37,
      "eval_accuracy": 0.34890219560878244,
      "eval_loss": 1.1037237644195557,
      "eval_runtime": 54.3657,
      "eval_samples_per_second": 92.154,
      "eval_steps_per_second": 11.533,
      "step": 9000
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.776666666666667e-07,
      "loss": 1.1056,
      "step": 10000
    },
    {
      "epoch": 0.41,
      "eval_accuracy": 0.3838323353293413,
      "eval_loss": 1.0928014516830444,
      "eval_runtime": 54.6518,
      "eval_samples_per_second": 91.671,
      "eval_steps_per_second": 11.473,
      "step": 10000
    },
    {
      "epoch": 0.45,
      "learning_rate": 3.054444444444444e-07,
      "loss": 1.1036,
      "step": 11000
    },
    {
      "epoch": 0.45,
      "eval_accuracy": 0.3838323353293413,
      "eval_loss": 1.0908663272857666,
      "eval_runtime": 54.579,
      "eval_samples_per_second": 91.794,
      "eval_steps_per_second": 11.488,
      "step": 11000
    },
    {
      "epoch": 0.49,
      "learning_rate": 3.3322222222222225e-07,
      "loss": 1.1012,
      "step": 12000
    },
    {
      "epoch": 0.49,
      "eval_accuracy": 0.3872255489021956,
      "eval_loss": 1.0890672206878662,
      "eval_runtime": 54.5139,
      "eval_samples_per_second": 91.903,
      "eval_steps_per_second": 11.502,
      "step": 12000
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.609722222222222e-07,
      "loss": 1.103,
      "step": 13000
    },
    {
      "epoch": 0.53,
      "eval_accuracy": 0.34311377245508984,
      "eval_loss": 1.0942790508270264,
      "eval_runtime": 54.3951,
      "eval_samples_per_second": 92.104,
      "eval_steps_per_second": 11.527,
      "step": 13000
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.8875e-07,
      "loss": 1.0997,
      "step": 14000
    },
    {
      "epoch": 0.57,
      "eval_accuracy": 0.3712574850299401,
      "eval_loss": 1.0931994915008545,
      "eval_runtime": 54.3749,
      "eval_samples_per_second": 92.138,
      "eval_steps_per_second": 11.531,
      "step": 14000
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.1650000000000006e-07,
      "loss": 1.0993,
      "step": 15000
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.3872255489021956,
      "eval_loss": 1.0887969732284546,
      "eval_runtime": 54.4149,
      "eval_samples_per_second": 92.07,
      "eval_steps_per_second": 11.523,
      "step": 15000
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.4427777777777783e-07,
      "loss": 1.0983,
      "step": 16000
    },
    {
      "epoch": 0.65,
      "eval_accuracy": 0.3980039920159681,
      "eval_loss": 1.0836474895477295,
      "eval_runtime": 54.3692,
      "eval_samples_per_second": 92.148,
      "eval_steps_per_second": 11.532,
      "step": 16000
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.7202777777777785e-07,
      "loss": 1.0954,
      "step": 17000
    },
    {
      "epoch": 0.69,
      "eval_accuracy": 0.3996007984031936,
      "eval_loss": 1.0822749137878418,
      "eval_runtime": 54.3313,
      "eval_samples_per_second": 92.212,
      "eval_steps_per_second": 11.54,
      "step": 17000
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.998055555555556e-07,
      "loss": 1.097,
      "step": 18000
    },
    {
      "epoch": 0.73,
      "eval_accuracy": 0.4033932135728543,
      "eval_loss": 1.0845097303390503,
      "eval_runtime": 54.3565,
      "eval_samples_per_second": 92.169,
      "eval_steps_per_second": 11.535,
      "step": 18000
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.275555555555556e-07,
      "loss": 1.0942,
      "step": 19000
    },
    {
      "epoch": 0.77,
      "eval_accuracy": 0.4039920159680639,
      "eval_loss": 1.0809950828552246,
      "eval_runtime": 54.3973,
      "eval_samples_per_second": 92.1,
      "eval_steps_per_second": 11.526,
      "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
}