File size: 2,960 Bytes
86a23d2
 
 
8812c67
86a23d2
8812c67
86a23d2
 
 
 
 
 
 
 
 
 
 
 
 
 
fa14848
 
 
86a23d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fa14848
 
 
86a23d2
d98faad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fa14848
 
 
d98faad
7c89a16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fa14848
7c89a16
fa14848
7c89a16
8812c67
 
 
 
 
 
 
86a23d2
 
 
 
 
 
 
 
 
 
 
 
 
 
8812c67
86a23d2
 
 
 
8812c67
86a23d2
 
 
 
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": 0.0016649323621227888,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016649323621227888,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00016649323621227888,
      "eval_loss": NaN,
      "eval_runtime": 541.5183,
      "eval_samples_per_second": 4.67,
      "eval_steps_per_second": 2.336,
      "step": 1
    },
    {
      "epoch": 0.00033298647242455777,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0004994797086368366,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0004994797086368366,
      "eval_loss": NaN,
      "eval_runtime": 540.5845,
      "eval_samples_per_second": 4.678,
      "eval_steps_per_second": 2.34,
      "step": 3
    },
    {
      "epoch": 0.0006659729448491155,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0008324661810613944,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0009989594172736733,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0009989594172736733,
      "eval_loss": NaN,
      "eval_runtime": 540.514,
      "eval_samples_per_second": 4.679,
      "eval_steps_per_second": 2.34,
      "step": 6
    },
    {
      "epoch": 0.0011654526534859522,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.001331945889698231,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00149843912591051,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00149843912591051,
      "eval_loss": NaN,
      "eval_runtime": 540.6919,
      "eval_samples_per_second": 4.677,
      "eval_steps_per_second": 2.34,
      "step": 9
    },
    {
      "epoch": 0.0016649323621227888,
      "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": 2612537673646080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}