File size: 2,962 Bytes
16a4f87
 
 
e50efbc
16a4f87
e50efbc
16a4f87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
361728b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66fead0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e50efbc
 
 
 
 
 
 
16a4f87
 
 
 
 
 
 
 
 
 
 
 
 
 
e50efbc
16a4f87
 
 
 
e50efbc
16a4f87
 
 
 
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": 0.018001800180018002,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018001800180018,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 12.5554,
      "step": 1
    },
    {
      "epoch": 0.0018001800180018,
      "eval_loss": NaN,
      "eval_runtime": 12.4601,
      "eval_samples_per_second": 18.78,
      "eval_steps_per_second": 9.39,
      "step": 1
    },
    {
      "epoch": 0.0036003600360036,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0054005400540054005,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0054005400540054005,
      "eval_loss": NaN,
      "eval_runtime": 11.2137,
      "eval_samples_per_second": 20.867,
      "eval_steps_per_second": 10.434,
      "step": 3
    },
    {
      "epoch": 0.0072007200720072,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.009000900090009001,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 10.3744,
      "step": 5
    },
    {
      "epoch": 0.010801080108010801,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.010801080108010801,
      "eval_loss": NaN,
      "eval_runtime": 11.2625,
      "eval_samples_per_second": 20.777,
      "eval_steps_per_second": 10.388,
      "step": 6
    },
    {
      "epoch": 0.012601260126012601,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 11.9441,
      "step": 7
    },
    {
      "epoch": 0.0144014401440144,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 5.9032,
      "step": 8
    },
    {
      "epoch": 0.016201620162016202,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.016201620162016202,
      "eval_loss": NaN,
      "eval_runtime": 11.2555,
      "eval_samples_per_second": 20.79,
      "eval_steps_per_second": 10.395,
      "step": 9
    },
    {
      "epoch": 0.018001800180018002,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 2.8104,
      "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": 2935721891463168.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}