File size: 2,944 Bytes
a4b8e42
 
 
5d95797
a4b8e42
5d95797
a4b8e42
 
 
 
 
 
 
 
 
 
 
 
 
 
f9bea92
 
 
a4b8e42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f9bea92
 
 
a4b8e42
db84e43
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77eb592
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d95797
 
 
 
 
 
 
a4b8e42
 
 
 
 
 
 
 
 
 
 
 
 
 
5d95797
a4b8e42
 
 
 
5d95797
a4b8e42
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01153070049005477,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011530700490054772,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0011530700490054772,
      "eval_loss": NaN,
      "eval_runtime": 55.6229,
      "eval_samples_per_second": 6.58,
      "eval_steps_per_second": 3.29,
      "step": 1
    },
    {
      "epoch": 0.0023061400980109543,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.003459210147016431,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.003459210147016431,
      "eval_loss": NaN,
      "eval_runtime": 54.9395,
      "eval_samples_per_second": 6.662,
      "eval_steps_per_second": 3.331,
      "step": 3
    },
    {
      "epoch": 0.004612280196021909,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.005765350245027385,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.006918420294032862,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.006918420294032862,
      "eval_loss": NaN,
      "eval_runtime": 54.9845,
      "eval_samples_per_second": 6.656,
      "eval_steps_per_second": 3.328,
      "step": 6
    },
    {
      "epoch": 0.00807149034303834,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.009224560392043817,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.010377630441049293,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.010377630441049293,
      "eval_loss": NaN,
      "eval_runtime": 55.135,
      "eval_samples_per_second": 6.638,
      "eval_steps_per_second": 3.319,
      "step": 9
    },
    {
      "epoch": 0.01153070049005477,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 720954300825600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}