File size: 3,440 Bytes
7dcffd2
 
 
767a13a
3803e16
767a13a
7dcffd2
 
 
 
 
 
 
3803e16
 
 
7dcffd2
3803e16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5f2366f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81d21de
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
767a13a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7dcffd2
 
 
3803e16
7dcffd2
 
3803e16
7dcffd2
 
 
 
 
 
 
767a13a
7dcffd2
 
 
 
767a13a
7dcffd2
 
 
 
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
149
150
151
152
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16339869281045752,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032679738562091504,
      "eval_loss": NaN,
      "eval_runtime": 6.0824,
      "eval_samples_per_second": 21.209,
      "eval_steps_per_second": 10.687,
      "step": 1
    },
    {
      "epoch": 0.016339869281045753,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.032679738562091505,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.032679738562091505,
      "eval_loss": NaN,
      "eval_runtime": 4.9856,
      "eval_samples_per_second": 25.874,
      "eval_steps_per_second": 13.038,
      "step": 10
    },
    {
      "epoch": 0.049019607843137254,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.06535947712418301,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.06535947712418301,
      "eval_loss": NaN,
      "eval_runtime": 5.0444,
      "eval_samples_per_second": 25.573,
      "eval_steps_per_second": 12.886,
      "step": 20
    },
    {
      "epoch": 0.08169934640522876,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.09803921568627451,
      "eval_loss": NaN,
      "eval_runtime": 4.9802,
      "eval_samples_per_second": 25.903,
      "eval_steps_per_second": 13.052,
      "step": 30
    },
    {
      "epoch": 0.11437908496732026,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.13071895424836602,
      "eval_loss": NaN,
      "eval_runtime": 5.1061,
      "eval_samples_per_second": 25.264,
      "eval_steps_per_second": 12.73,
      "step": 40
    },
    {
      "epoch": 0.14705882352941177,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.16339869281045752,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.16339869281045752,
      "eval_loss": NaN,
      "eval_runtime": 5.0254,
      "eval_samples_per_second": 25.67,
      "eval_steps_per_second": 12.934,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1621491292569600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}