File size: 2,612 Bytes
9003bbb
 
 
 
 
 
 
 
 
 
 
 
 
00fcad7
9003bbb
00fcad7
9003bbb
 
 
 
00fcad7
9003bbb
00fcad7
9003bbb
 
 
 
00fcad7
9003bbb
00fcad7
9003bbb
 
 
 
00fcad7
9003bbb
00fcad7
9003bbb
 
 
 
00fcad7
9003bbb
00fcad7
9003bbb
 
 
 
00fcad7
9003bbb
00fcad7
9003bbb
 
 
 
00fcad7
9003bbb
00fcad7
9003bbb
 
 
 
00fcad7
9003bbb
00fcad7
9003bbb
 
 
 
00fcad7
9003bbb
00fcad7
9003bbb
 
 
 
00fcad7
9003bbb
00fcad7
9003bbb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
00fcad7
9003bbb
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.4271844660194173,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24271844660194175,
      "grad_norm": 2.8362834453582764,
      "learning_rate": 4.960355987055016e-05,
      "loss": 6.0742,
      "step": 50
    },
    {
      "epoch": 0.4854368932038835,
      "grad_norm": 2.9484496116638184,
      "learning_rate": 4.9199029126213595e-05,
      "loss": 5.7218,
      "step": 100
    },
    {
      "epoch": 0.7281553398058253,
      "grad_norm": 3.542572259902954,
      "learning_rate": 4.879449838187702e-05,
      "loss": 5.4227,
      "step": 150
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 4.634098052978516,
      "learning_rate": 4.8389967637540455e-05,
      "loss": 5.1655,
      "step": 200
    },
    {
      "epoch": 1.2135922330097086,
      "grad_norm": 5.699330806732178,
      "learning_rate": 4.798543689320388e-05,
      "loss": 4.8009,
      "step": 250
    },
    {
      "epoch": 1.4563106796116505,
      "grad_norm": 5.711933135986328,
      "learning_rate": 4.7580906148867315e-05,
      "loss": 4.607,
      "step": 300
    },
    {
      "epoch": 1.6990291262135924,
      "grad_norm": 5.113691806793213,
      "learning_rate": 4.717637540453075e-05,
      "loss": 4.462,
      "step": 350
    },
    {
      "epoch": 1.941747572815534,
      "grad_norm": 5.632521152496338,
      "learning_rate": 4.6771844660194174e-05,
      "loss": 4.3695,
      "step": 400
    },
    {
      "epoch": 2.1844660194174756,
      "grad_norm": 5.428906440734863,
      "learning_rate": 4.636731391585761e-05,
      "loss": 4.1549,
      "step": 450
    },
    {
      "epoch": 2.4271844660194173,
      "grad_norm": 5.037013530731201,
      "learning_rate": 4.596278317152104e-05,
      "loss": 4.0921,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 6180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 232176746496000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}