File size: 3,203 Bytes
7fff264
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9826435246995995,
  "eval_steps": 3,
  "global_step": 46,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06408544726301736,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.3923,
      "step": 3
    },
    {
      "epoch": 0.12817089452603472,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.3677,
      "step": 6
    },
    {
      "epoch": 0.19225634178905207,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.3941,
      "step": 9
    },
    {
      "epoch": 0.25634178905206945,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.3217,
      "step": 12
    },
    {
      "epoch": 0.3204272363150868,
      "grad_norm": 0.2677106559276581,
      "learning_rate": 0.001414213562373095,
      "loss": 1.3414,
      "step": 15
    },
    {
      "epoch": 0.38451268357810414,
      "grad_norm": 0.4557584226131439,
      "learning_rate": 0.0011547005383792518,
      "loss": 1.3506,
      "step": 18
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 0.6809806823730469,
      "learning_rate": 0.0008164965809277262,
      "loss": 1.273,
      "step": 21
    },
    {
      "epoch": 0.5126835781041389,
      "grad_norm": 0.39959588646888733,
      "learning_rate": 0.0006666666666666666,
      "loss": 1.0769,
      "step": 24
    },
    {
      "epoch": 0.5767690253671562,
      "grad_norm": 0.48387882113456726,
      "learning_rate": 0.0005773502691896259,
      "loss": 1.0684,
      "step": 27
    },
    {
      "epoch": 0.6408544726301736,
      "grad_norm": 0.3298889100551605,
      "learning_rate": 0.0005163977794943222,
      "loss": 1.0231,
      "step": 30
    },
    {
      "epoch": 0.7049399198931909,
      "grad_norm": 0.7082661986351013,
      "learning_rate": 0.00047140452079103175,
      "loss": 1.0139,
      "step": 33
    },
    {
      "epoch": 0.7690253671562083,
      "grad_norm": 0.29416364431381226,
      "learning_rate": 0.0004364357804719848,
      "loss": 1.0025,
      "step": 36
    },
    {
      "epoch": 0.8331108144192256,
      "grad_norm": 0.324586421251297,
      "learning_rate": 0.0004170288281141495,
      "loss": 1.0247,
      "step": 39
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 0.26038306951522827,
      "learning_rate": 0.0003922322702763681,
      "loss": 0.9517,
      "step": 42
    },
    {
      "epoch": 0.9612817089452603,
      "grad_norm": 0.2797044813632965,
      "learning_rate": 0.0003713906763541037,
      "loss": 0.9935,
      "step": 45
    }
  ],
  "logging_steps": 3,
  "max_steps": 46,
  "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": 4.671973340489974e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}