File size: 2,980 Bytes
442d441
 
 
d934acc
442d441
d934acc
442d441
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d91c05
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c2537d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d934acc
 
 
 
 
 
 
442d441
 
 
 
 
 
 
 
 
 
 
 
 
 
d934acc
442d441
 
 
 
d934acc
442d441
 
 
 
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": 8.480271707905521e-05,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.48027170790552e-06,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 8.48027170790552e-06,
      "eval_loss": NaN,
      "eval_runtime": 1519.2732,
      "eval_samples_per_second": 32.681,
      "eval_steps_per_second": 16.341,
      "step": 1
    },
    {
      "epoch": 1.696054341581104e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 2.5440815123716565e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 2.5440815123716565e-05,
      "eval_loss": NaN,
      "eval_runtime": 1517.5888,
      "eval_samples_per_second": 32.717,
      "eval_steps_per_second": 16.359,
      "step": 3
    },
    {
      "epoch": 3.392108683162208e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 4.2401358539527606e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 5.088163024743313e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 5.088163024743313e-05,
      "eval_loss": NaN,
      "eval_runtime": 1517.9777,
      "eval_samples_per_second": 32.709,
      "eval_steps_per_second": 16.355,
      "step": 6
    },
    {
      "epoch": 5.936190195533865e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 6.784217366324416e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 7.632244537114969e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 7.632244537114969e-05,
      "eval_loss": NaN,
      "eval_runtime": 1518.6794,
      "eval_samples_per_second": 32.694,
      "eval_steps_per_second": 16.347,
      "step": 9
    },
    {
      "epoch": 8.480271707905521e-05,
      "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": 1710169792708608.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}