File size: 5,615 Bytes
c25f08c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.28,
  "eval_steps": 50,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 2.3869346733668342e-05,
      "loss": 1.2058,
      "step": 50
    },
    {
      "epoch": 0.08,
      "eval_loss": 0.9411209225654602,
      "eval_runtime": 405.7571,
      "eval_samples_per_second": 12.323,
      "eval_steps_per_second": 1.54,
      "step": 50
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.2613065326633167e-05,
      "loss": 0.9065,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.8835591673851013,
      "eval_runtime": 405.6798,
      "eval_samples_per_second": 12.325,
      "eval_steps_per_second": 1.541,
      "step": 100
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.135678391959799e-05,
      "loss": 0.8612,
      "step": 150
    },
    {
      "epoch": 0.24,
      "eval_loss": 0.8560027480125427,
      "eval_runtime": 405.7296,
      "eval_samples_per_second": 12.323,
      "eval_steps_per_second": 1.54,
      "step": 150
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.0100502512562815e-05,
      "loss": 0.8536,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_loss": 0.8348749876022339,
      "eval_runtime": 405.5958,
      "eval_samples_per_second": 12.328,
      "eval_steps_per_second": 1.541,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.884422110552764e-05,
      "loss": 0.8195,
      "step": 250
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.8201740384101868,
      "eval_runtime": 405.604,
      "eval_samples_per_second": 12.327,
      "eval_steps_per_second": 1.541,
      "step": 250
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.7587939698492464e-05,
      "loss": 0.8272,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_loss": 0.807165801525116,
      "eval_runtime": 405.5942,
      "eval_samples_per_second": 12.328,
      "eval_steps_per_second": 1.541,
      "step": 300
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.6331658291457288e-05,
      "loss": 0.8132,
      "step": 350
    },
    {
      "epoch": 0.56,
      "eval_loss": 0.7971442341804504,
      "eval_runtime": 405.5887,
      "eval_samples_per_second": 12.328,
      "eval_steps_per_second": 1.541,
      "step": 350
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.507537688442211e-05,
      "loss": 0.8124,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_loss": 0.7893713116645813,
      "eval_runtime": 405.5093,
      "eval_samples_per_second": 12.33,
      "eval_steps_per_second": 1.541,
      "step": 400
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.3819095477386935e-05,
      "loss": 0.7823,
      "step": 450
    },
    {
      "epoch": 0.72,
      "eval_loss": 0.7817508578300476,
      "eval_runtime": 405.5623,
      "eval_samples_per_second": 12.329,
      "eval_steps_per_second": 1.541,
      "step": 450
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.2562814070351759e-05,
      "loss": 0.772,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.7751882672309875,
      "eval_runtime": 405.5365,
      "eval_samples_per_second": 12.329,
      "eval_steps_per_second": 1.541,
      "step": 500
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.1306532663316583e-05,
      "loss": 0.7668,
      "step": 550
    },
    {
      "epoch": 0.88,
      "eval_loss": 0.7704442143440247,
      "eval_runtime": 405.5551,
      "eval_samples_per_second": 12.329,
      "eval_steps_per_second": 1.541,
      "step": 550
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0050251256281408e-05,
      "loss": 0.7827,
      "step": 600
    },
    {
      "epoch": 0.96,
      "eval_loss": 0.7652014493942261,
      "eval_runtime": 405.6401,
      "eval_samples_per_second": 12.326,
      "eval_steps_per_second": 1.541,
      "step": 600
    },
    {
      "epoch": 1.04,
      "learning_rate": 8.793969849246232e-06,
      "loss": 0.7248,
      "step": 650
    },
    {
      "epoch": 1.04,
      "eval_loss": 0.7625133991241455,
      "eval_runtime": 405.4991,
      "eval_samples_per_second": 12.33,
      "eval_steps_per_second": 1.541,
      "step": 650
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.537688442211055e-06,
      "loss": 0.7107,
      "step": 700
    },
    {
      "epoch": 1.12,
      "eval_loss": 0.7591288089752197,
      "eval_runtime": 405.5072,
      "eval_samples_per_second": 12.33,
      "eval_steps_per_second": 1.541,
      "step": 700
    },
    {
      "epoch": 1.2,
      "learning_rate": 6.2814070351758795e-06,
      "loss": 0.7094,
      "step": 750
    },
    {
      "epoch": 1.2,
      "eval_loss": 0.7564280033111572,
      "eval_runtime": 405.5407,
      "eval_samples_per_second": 12.329,
      "eval_steps_per_second": 1.541,
      "step": 750
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.025125628140704e-06,
      "loss": 0.7203,
      "step": 800
    },
    {
      "epoch": 1.28,
      "eval_loss": 0.7533515095710754,
      "eval_runtime": 405.633,
      "eval_samples_per_second": 12.326,
      "eval_steps_per_second": 1.541,
      "step": 800
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "total_flos": 1.402192602857472e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}