File size: 3,464 Bytes
bbad7b0
 
 
f1a9a18
139d2aa
f1a9a18
bbad7b0
 
 
 
 
 
 
139d2aa
 
 
bbad7b0
139d2aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ed84b63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a4bbe02
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f1a9a18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bbad7b0
 
 
139d2aa
bbad7b0
 
139d2aa
bbad7b0
 
 
 
 
 
 
f1a9a18
bbad7b0
 
 
 
f1a9a18
bbad7b0
 
 
 
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": 0.002671618065481359,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.3432361309627175e-05,
      "eval_loss": NaN,
      "eval_runtime": 833.7908,
      "eval_samples_per_second": 9.452,
      "eval_steps_per_second": 4.727,
      "step": 1
    },
    {
      "epoch": 0.00026716180654813587,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0005343236130962717,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0005343236130962717,
      "eval_loss": NaN,
      "eval_runtime": 885.8741,
      "eval_samples_per_second": 8.896,
      "eval_steps_per_second": 4.449,
      "step": 10
    },
    {
      "epoch": 0.0008014854196444077,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0010686472261925435,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0010686472261925435,
      "eval_loss": NaN,
      "eval_runtime": 841.6339,
      "eval_samples_per_second": 9.364,
      "eval_steps_per_second": 4.683,
      "step": 20
    },
    {
      "epoch": 0.0013358090327406794,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0016029708392888153,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0016029708392888153,
      "eval_loss": NaN,
      "eval_runtime": 883.3728,
      "eval_samples_per_second": 8.921,
      "eval_steps_per_second": 4.461,
      "step": 30
    },
    {
      "epoch": 0.0018701326458369512,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.002137294452385087,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.002137294452385087,
      "eval_loss": NaN,
      "eval_runtime": 817.4301,
      "eval_samples_per_second": 9.641,
      "eval_steps_per_second": 4.821,
      "step": 40
    },
    {
      "epoch": 0.002404456258933223,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.002671618065481359,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.002671618065481359,
      "eval_loss": NaN,
      "eval_runtime": 927.1486,
      "eval_samples_per_second": 8.5,
      "eval_steps_per_second": 4.251,
      "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
}