File size: 3,212 Bytes
e859a16
 
 
1519143
e859a16
1519143
e859a16
 
 
 
 
 
82af8c7
e859a16
 
 
 
 
 
 
82af8c7
 
 
e859a16
 
 
 
82af8c7
e859a16
 
 
 
 
 
82af8c7
e859a16
1d02bcb
e859a16
 
 
 
82af8c7
 
 
 
e859a16
82af8c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1519143
 
 
 
 
 
 
e859a16
 
 
 
 
 
 
 
 
 
 
 
 
 
1519143
e859a16
 
 
 
1519143
e859a16
 
 
 
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": 0.0018793459875963165,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018793459875963165,
      "grad_norm": 0.41265636682510376,
      "learning_rate": 2e-05,
      "loss": 2.0097,
      "step": 1
    },
    {
      "epoch": 0.00018793459875963165,
      "eval_loss": 2.225860595703125,
      "eval_runtime": 59.1454,
      "eval_samples_per_second": 18.953,
      "eval_steps_per_second": 18.953,
      "step": 1
    },
    {
      "epoch": 0.0003758691975192633,
      "grad_norm": 0.34109458327293396,
      "learning_rate": 4e-05,
      "loss": 2.0424,
      "step": 2
    },
    {
      "epoch": 0.0005638037962788949,
      "grad_norm": 0.4408990442752838,
      "learning_rate": 6e-05,
      "loss": 2.2435,
      "step": 3
    },
    {
      "epoch": 0.0005638037962788949,
      "eval_loss": 2.2232234477996826,
      "eval_runtime": 53.5686,
      "eval_samples_per_second": 20.926,
      "eval_steps_per_second": 20.926,
      "step": 3
    },
    {
      "epoch": 0.0007517383950385266,
      "grad_norm": 0.3058125972747803,
      "learning_rate": 8e-05,
      "loss": 2.1183,
      "step": 4
    },
    {
      "epoch": 0.0009396729937981583,
      "grad_norm": 0.44318097829818726,
      "learning_rate": 0.0001,
      "loss": 2.2092,
      "step": 5
    },
    {
      "epoch": 0.0011276075925577898,
      "grad_norm": 0.3183535933494568,
      "learning_rate": 0.00012,
      "loss": 2.2227,
      "step": 6
    },
    {
      "epoch": 0.0011276075925577898,
      "eval_loss": 2.2024617195129395,
      "eval_runtime": 54.1467,
      "eval_samples_per_second": 20.703,
      "eval_steps_per_second": 20.703,
      "step": 6
    },
    {
      "epoch": 0.0013155421913174216,
      "grad_norm": 0.4959358274936676,
      "learning_rate": 0.00014,
      "loss": 2.1984,
      "step": 7
    },
    {
      "epoch": 0.0015034767900770532,
      "grad_norm": 0.3904803693294525,
      "learning_rate": 0.00016,
      "loss": 2.1435,
      "step": 8
    },
    {
      "epoch": 0.001691411388836685,
      "grad_norm": 0.3693416714668274,
      "learning_rate": 0.00018,
      "loss": 2.0586,
      "step": 9
    },
    {
      "epoch": 0.001691411388836685,
      "eval_loss": 2.149339437484741,
      "eval_runtime": 52.9676,
      "eval_samples_per_second": 21.164,
      "eval_steps_per_second": 21.164,
      "step": 9
    },
    {
      "epoch": 0.0018793459875963165,
      "grad_norm": 0.36688560247421265,
      "learning_rate": 0.0002,
      "loss": 2.0788,
      "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": 695723045683200.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}