File size: 3,045 Bytes
390e616
 
 
ee192a9
390e616
ee192a9
390e616
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64fe0e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ee192a9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
390e616
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ee192a9
390e616
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011090231354548535,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012322479282831706,
      "grad_norm": 10.543423652648926,
      "learning_rate": 2e-05,
      "loss": 6.768,
      "step": 1
    },
    {
      "epoch": 0.00012322479282831706,
      "eval_loss": 1.7490488290786743,
      "eval_runtime": 168.3289,
      "eval_samples_per_second": 20.3,
      "eval_steps_per_second": 10.153,
      "step": 1
    },
    {
      "epoch": 0.0002464495856566341,
      "grad_norm": 10.224077224731445,
      "learning_rate": 4e-05,
      "loss": 7.1368,
      "step": 2
    },
    {
      "epoch": 0.0003696743784849512,
      "grad_norm": 9.224963188171387,
      "learning_rate": 6e-05,
      "loss": 6.9479,
      "step": 3
    },
    {
      "epoch": 0.0003696743784849512,
      "eval_loss": 1.7335113286972046,
      "eval_runtime": 166.3194,
      "eval_samples_per_second": 20.545,
      "eval_steps_per_second": 10.275,
      "step": 3
    },
    {
      "epoch": 0.0004928991713132682,
      "grad_norm": 8.990937232971191,
      "learning_rate": 8e-05,
      "loss": 7.1099,
      "step": 4
    },
    {
      "epoch": 0.0006161239641415853,
      "grad_norm": 9.329360961914062,
      "learning_rate": 0.0001,
      "loss": 7.2767,
      "step": 5
    },
    {
      "epoch": 0.0007393487569699024,
      "grad_norm": 9.28650951385498,
      "learning_rate": 0.00012,
      "loss": 7.1402,
      "step": 6
    },
    {
      "epoch": 0.0007393487569699024,
      "eval_loss": 1.6262080669403076,
      "eval_runtime": 166.2864,
      "eval_samples_per_second": 20.549,
      "eval_steps_per_second": 10.277,
      "step": 6
    },
    {
      "epoch": 0.0008625735497982194,
      "grad_norm": 7.803596019744873,
      "learning_rate": 0.00014,
      "loss": 6.4454,
      "step": 7
    },
    {
      "epoch": 0.0009857983426265365,
      "grad_norm": 6.894227027893066,
      "learning_rate": 0.00016,
      "loss": 5.9383,
      "step": 8
    },
    {
      "epoch": 0.0011090231354548535,
      "grad_norm": 8.620890617370605,
      "learning_rate": 0.00018,
      "loss": 6.558,
      "step": 9
    },
    {
      "epoch": 0.0011090231354548535,
      "eval_loss": 1.6303293704986572,
      "eval_runtime": 166.3919,
      "eval_samples_per_second": 20.536,
      "eval_steps_per_second": 10.271,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2541374108860416.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}