File size: 5,893 Bytes
9190022
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.48051948051948,
  "eval_steps": 1000,
  "global_step": 9000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.65,
      "learning_rate": 6.493506493506493e-07,
      "loss": 2.3458,
      "step": 300
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.2987012987012986e-06,
      "loss": 2.3309,
      "step": 600
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.9480519480519483e-06,
      "loss": 2.2872,
      "step": 900
    },
    {
      "epoch": 2.16,
      "eval_loss": 2.2653801441192627,
      "eval_runtime": 40.5821,
      "eval_samples_per_second": 64.166,
      "eval_steps_per_second": 4.017,
      "step": 1000
    },
    {
      "epoch": 2.6,
      "learning_rate": 2.597402597402597e-06,
      "loss": 2.2593,
      "step": 1200
    },
    {
      "epoch": 3.25,
      "learning_rate": 3.246753246753247e-06,
      "loss": 2.2332,
      "step": 1500
    },
    {
      "epoch": 3.9,
      "learning_rate": 3.896103896103897e-06,
      "loss": 2.1927,
      "step": 1800
    },
    {
      "epoch": 4.33,
      "eval_loss": 2.181955575942993,
      "eval_runtime": 40.5637,
      "eval_samples_per_second": 64.195,
      "eval_steps_per_second": 4.018,
      "step": 2000
    },
    {
      "epoch": 4.55,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 2.1735,
      "step": 2100
    },
    {
      "epoch": 5.19,
      "learning_rate": 5.194805194805194e-06,
      "loss": 2.1703,
      "step": 2400
    },
    {
      "epoch": 5.84,
      "learning_rate": 5.844155844155844e-06,
      "loss": 2.1335,
      "step": 2700
    },
    {
      "epoch": 6.49,
      "learning_rate": 6.493506493506494e-06,
      "loss": 2.1158,
      "step": 3000
    },
    {
      "epoch": 6.49,
      "eval_loss": 2.119281530380249,
      "eval_runtime": 40.6723,
      "eval_samples_per_second": 64.024,
      "eval_steps_per_second": 4.008,
      "step": 3000
    },
    {
      "epoch": 7.14,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 2.1031,
      "step": 3300
    },
    {
      "epoch": 7.79,
      "learning_rate": 7.792207792207793e-06,
      "loss": 2.0958,
      "step": 3600
    },
    {
      "epoch": 8.44,
      "learning_rate": 8.441558441558442e-06,
      "loss": 2.0816,
      "step": 3900
    },
    {
      "epoch": 8.66,
      "eval_loss": 2.083141803741455,
      "eval_runtime": 40.6586,
      "eval_samples_per_second": 64.045,
      "eval_steps_per_second": 4.009,
      "step": 4000
    },
    {
      "epoch": 9.09,
      "learning_rate": 9.090909090909091e-06,
      "loss": 2.07,
      "step": 4200
    },
    {
      "epoch": 9.74,
      "learning_rate": 9.740259740259742e-06,
      "loss": 2.0637,
      "step": 4500
    },
    {
      "epoch": 10.39,
      "learning_rate": 9.96259251245514e-06,
      "loss": 2.0616,
      "step": 4800
    },
    {
      "epoch": 10.82,
      "eval_loss": 2.0597293376922607,
      "eval_runtime": 40.7285,
      "eval_samples_per_second": 63.936,
      "eval_steps_per_second": 4.002,
      "step": 5000
    },
    {
      "epoch": 11.04,
      "learning_rate": 9.736015051459551e-06,
      "loss": 2.0349,
      "step": 5100
    },
    {
      "epoch": 11.69,
      "learning_rate": 9.313027078004903e-06,
      "loss": 2.0407,
      "step": 5400
    },
    {
      "epoch": 12.34,
      "learning_rate": 8.71117061502135e-06,
      "loss": 2.0326,
      "step": 5700
    },
    {
      "epoch": 12.99,
      "learning_rate": 7.955405662643384e-06,
      "loss": 2.0234,
      "step": 6000
    },
    {
      "epoch": 12.99,
      "eval_loss": 2.0452144145965576,
      "eval_runtime": 40.7967,
      "eval_samples_per_second": 63.829,
      "eval_steps_per_second": 3.995,
      "step": 6000
    },
    {
      "epoch": 13.64,
      "learning_rate": 7.0770750650094335e-06,
      "loss": 2.019,
      "step": 6300
    },
    {
      "epoch": 14.29,
      "learning_rate": 6.112604669781572e-06,
      "loss": 2.0186,
      "step": 6600
    },
    {
      "epoch": 14.94,
      "learning_rate": 5.101992686957028e-06,
      "loss": 2.0114,
      "step": 6900
    },
    {
      "epoch": 15.15,
      "eval_loss": 2.0369863510131836,
      "eval_runtime": 40.6659,
      "eval_samples_per_second": 64.034,
      "eval_steps_per_second": 4.008,
      "step": 7000
    },
    {
      "epoch": 15.58,
      "learning_rate": 4.087150895803192e-06,
      "loss": 2.0134,
      "step": 7200
    },
    {
      "epoch": 16.23,
      "learning_rate": 3.110166492855468e-06,
      "loss": 2.0014,
      "step": 7500
    },
    {
      "epoch": 16.88,
      "learning_rate": 2.211556665065854e-06,
      "loss": 2.011,
      "step": 7800
    },
    {
      "epoch": 17.32,
      "eval_loss": 2.033980369567871,
      "eval_runtime": 40.7311,
      "eval_samples_per_second": 63.931,
      "eval_steps_per_second": 4.002,
      "step": 8000
    },
    {
      "epoch": 17.53,
      "learning_rate": 1.4285882738904822e-06,
      "loss": 1.9908,
      "step": 8100
    },
    {
      "epoch": 18.18,
      "learning_rate": 7.937323358440935e-07,
      "loss": 2.0066,
      "step": 8400
    },
    {
      "epoch": 18.83,
      "learning_rate": 3.333173948131663e-07,
      "loss": 2.0052,
      "step": 8700
    },
    {
      "epoch": 19.48,
      "learning_rate": 6.643763304355566e-08,
      "loss": 1.9944,
      "step": 9000
    },
    {
      "epoch": 19.48,
      "eval_loss": 2.0332887172698975,
      "eval_runtime": 40.7026,
      "eval_samples_per_second": 63.976,
      "eval_steps_per_second": 4.005,
      "step": 9000
    }
  ],
  "logging_steps": 300,
  "max_steps": 9240,
  "num_train_epochs": 20,
  "save_steps": 1000,
  "total_flos": 6.265759479075963e+17,
  "trial_name": null,
  "trial_params": null
}