File size: 3,072 Bytes
1a4bf79
 
 
0c0ebc5
1a4bf79
0c0ebc5
1a4bf79
 
 
 
 
 
abf420e
 
 
1a4bf79
 
 
 
abf420e
 
 
1a4bf79
 
 
 
abf420e
 
 
1a4bf79
c7a192b
 
 
 
 
 
 
353bd36
 
 
 
 
 
 
2b9c39e
 
 
 
 
 
 
90b4e54
 
 
 
 
 
 
aaab94f
 
 
 
 
 
 
c3e2378
 
 
 
 
 
 
b0ce398
 
 
 
 
 
 
4f835ac
 
 
 
 
 
 
f877c3a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
da853ab
 
 
 
 
 
 
0c0ebc5
 
 
 
 
 
 
 
 
 
 
 
 
 
1a4bf79
 
 
abf420e
1a4bf79
 
 
0c0ebc5
1a4bf79
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0072,
  "eval_steps": 500,
  "global_step": 360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 79.12922668457031,
      "learning_rate": 1e-06,
      "loss": 4.6771,
      "step": 20
    },
    {
      "epoch": 0.0,
      "grad_norm": 239.7991943359375,
      "learning_rate": 2e-06,
      "loss": 4.5023,
      "step": 40
    },
    {
      "epoch": 0.0,
      "grad_norm": 77.5164794921875,
      "learning_rate": 3e-06,
      "loss": 4.8171,
      "step": 60
    },
    {
      "epoch": 0.0,
      "grad_norm": 207.87796020507812,
      "learning_rate": 4e-06,
      "loss": 4.6765,
      "step": 80
    },
    {
      "epoch": 0.0,
      "grad_norm": 147.12461853027344,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 4.7237,
      "step": 100
    },
    {
      "epoch": 0.0,
      "grad_norm": 115.61023712158203,
      "learning_rate": 6e-06,
      "loss": 4.4426,
      "step": 120
    },
    {
      "epoch": 0.0,
      "grad_norm": 43.68627166748047,
      "learning_rate": 7e-06,
      "loss": 5.0142,
      "step": 140
    },
    {
      "epoch": 0.0,
      "grad_norm": 37.58155059814453,
      "learning_rate": 8e-06,
      "loss": 4.8572,
      "step": 160
    },
    {
      "epoch": 0.0,
      "grad_norm": 86.82076263427734,
      "learning_rate": 9e-06,
      "loss": 4.6848,
      "step": 180
    },
    {
      "epoch": 0.0,
      "grad_norm": 289.0603332519531,
      "learning_rate": 9.999999999999999e-06,
      "loss": 4.6474,
      "step": 200
    },
    {
      "epoch": 0.0,
      "grad_norm": 69.93185424804688,
      "learning_rate": 1.1e-05,
      "loss": 4.9724,
      "step": 220
    },
    {
      "epoch": 0.0,
      "grad_norm": 98.215087890625,
      "learning_rate": 1.2e-05,
      "loss": 4.4447,
      "step": 240
    },
    {
      "epoch": 0.01,
      "grad_norm": 92.3516845703125,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 4.9076,
      "step": 260
    },
    {
      "epoch": 0.01,
      "grad_norm": 150.6816864013672,
      "learning_rate": 1.4e-05,
      "loss": 4.8402,
      "step": 280
    },
    {
      "epoch": 0.01,
      "grad_norm": 162.9401397705078,
      "learning_rate": 1.5e-05,
      "loss": 4.9279,
      "step": 300
    },
    {
      "epoch": 0.01,
      "grad_norm": 38.77900695800781,
      "learning_rate": 1.6e-05,
      "loss": 4.5021,
      "step": 320
    },
    {
      "epoch": 0.01,
      "grad_norm": 91.0234146118164,
      "learning_rate": 1.7e-05,
      "loss": 4.5546,
      "step": 340
    },
    {
      "epoch": 0.01,
      "grad_norm": 78.24981689453125,
      "learning_rate": 1.8e-05,
      "loss": 4.3795,
      "step": 360
    }
  ],
  "logging_steps": 20,
  "max_steps": 20000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "total_flos": 127576999796736.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}