File size: 3,854 Bytes
d0836b0
680a405
 
 
d0836b0
680a405
d0836b0
 
 
 
 
 
 
589441f
d0836b0
 
 
 
589441f
 
 
 
d0836b0
eaf771b
 
 
 
 
 
 
 
 
 
 
 
 
 
f4dd453
 
 
 
 
 
 
 
 
 
 
 
 
 
8c1ab31
 
 
 
 
 
 
 
 
 
 
 
 
 
d8c76e4
 
 
 
 
 
 
 
 
 
 
 
 
 
80b80f9
 
 
 
 
 
 
 
 
 
 
 
 
 
3686ec7
 
 
 
 
 
 
 
 
 
 
 
 
 
98023a1
 
 
 
 
 
 
 
 
 
 
 
 
 
86b4c33
 
 
 
 
 
 
 
 
 
 
 
 
 
5a58ccb
 
 
 
 
 
 
 
 
 
 
 
 
 
680a405
 
 
 
 
 
 
 
 
 
 
 
 
 
d0836b0
 
 
 
 
 
 
680a405
d0836b0
 
 
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
{
  "best_metric": 1.4200090169906616,
  "best_model_checkpoint": "./outputs/checkpoint-1100",
  "epoch": 1.4666666666666668,
  "eval_steps": 100,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.4574,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.5645889043807983,
      "eval_runtime": 93.6488,
      "eval_samples_per_second": 15.494,
      "eval_steps_per_second": 1.943,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.2971,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.5321934223175049,
      "eval_runtime": 93.3383,
      "eval_samples_per_second": 15.546,
      "eval_steps_per_second": 1.95,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.2756,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.5133259296417236,
      "eval_runtime": 93.2652,
      "eval_samples_per_second": 15.558,
      "eval_steps_per_second": 1.951,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.2661,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.500829815864563,
      "eval_runtime": 93.3122,
      "eval_samples_per_second": 15.55,
      "eval_steps_per_second": 1.95,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.2493,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.4804445505142212,
      "eval_runtime": 93.3662,
      "eval_samples_per_second": 15.541,
      "eval_steps_per_second": 1.949,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.2327,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.4673335552215576,
      "eval_runtime": 93.4173,
      "eval_samples_per_second": 15.532,
      "eval_steps_per_second": 1.948,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.2216,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.456375241279602,
      "eval_runtime": 93.4236,
      "eval_samples_per_second": 15.531,
      "eval_steps_per_second": 1.948,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.2086,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.4467251300811768,
      "eval_runtime": 93.3142,
      "eval_samples_per_second": 15.55,
      "eval_steps_per_second": 1.95,
      "step": 800
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.1922,
      "step": 900
    },
    {
      "epoch": 1.2,
      "eval_loss": 1.4370195865631104,
      "eval_runtime": 93.2407,
      "eval_samples_per_second": 15.562,
      "eval_steps_per_second": 1.952,
      "step": 900
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.1859,
      "step": 1000
    },
    {
      "epoch": 1.33,
      "eval_loss": 1.4297349452972412,
      "eval_runtime": 93.4112,
      "eval_samples_per_second": 15.533,
      "eval_steps_per_second": 1.948,
      "step": 1000
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.1846,
      "step": 1100
    },
    {
      "epoch": 1.47,
      "eval_loss": 1.4200090169906616,
      "eval_runtime": 93.3115,
      "eval_samples_per_second": 15.55,
      "eval_steps_per_second": 1.95,
      "step": 1100
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 6.43012944795648e+16,
  "trial_name": null,
  "trial_params": null
}