File size: 3,157 Bytes
e0ca69a
 
 
6f284e0
e0ca69a
6f284e0
e0ca69a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bab74fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b4d1a16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f284e0
 
 
 
 
 
 
e0ca69a
 
 
 
 
 
 
 
 
 
 
 
 
 
6f284e0
e0ca69a
 
 
 
6f284e0
e0ca69a
 
 
 
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": 0.7843137254901961,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 56.80657958984375,
      "learning_rate": 2e-05,
      "loss": 4.5317,
      "step": 1
    },
    {
      "epoch": 0.0784313725490196,
      "eval_loss": 1.4086369276046753,
      "eval_runtime": 0.2104,
      "eval_samples_per_second": 28.52,
      "eval_steps_per_second": 14.26,
      "step": 1
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 65.0270004272461,
      "learning_rate": 4e-05,
      "loss": 5.4882,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 56.104896545410156,
      "learning_rate": 6e-05,
      "loss": 6.384,
      "step": 3
    },
    {
      "epoch": 0.23529411764705882,
      "eval_loss": 1.095396876335144,
      "eval_runtime": 0.2099,
      "eval_samples_per_second": 28.581,
      "eval_steps_per_second": 14.291,
      "step": 3
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 61.97636413574219,
      "learning_rate": 8e-05,
      "loss": 4.6142,
      "step": 4
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 37.48371887207031,
      "learning_rate": 0.0001,
      "loss": 2.535,
      "step": 5
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 24.155080795288086,
      "learning_rate": 0.00012,
      "loss": 1.4195,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "eval_loss": 0.2841545641422272,
      "eval_runtime": 0.208,
      "eval_samples_per_second": 28.853,
      "eval_steps_per_second": 14.426,
      "step": 6
    },
    {
      "epoch": 0.5490196078431373,
      "grad_norm": 30.342317581176758,
      "learning_rate": 0.00014,
      "loss": 1.3593,
      "step": 7
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 14.366281509399414,
      "learning_rate": 0.00016,
      "loss": 0.8921,
      "step": 8
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 13.949260711669922,
      "learning_rate": 0.00018,
      "loss": 0.5549,
      "step": 9
    },
    {
      "epoch": 0.7058823529411765,
      "eval_loss": 0.22411371767520905,
      "eval_runtime": 0.2091,
      "eval_samples_per_second": 28.693,
      "eval_steps_per_second": 14.346,
      "step": 9
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 19.129446029663086,
      "learning_rate": 0.0002,
      "loss": 0.8281,
      "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": 1796486530596864.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}