File size: 3,059 Bytes
e30beec
 
 
61bd3b5
7aeaae7
61bd3b5
e30beec
 
 
 
 
53ddeb5
 
7aeaae7
53ddeb5
e30beec
 
 
53ddeb5
 
 
 
 
e30beec
7aeaae7
 
53ddeb5
 
7aeaae7
53ddeb5
7aeaae7
 
 
53ddeb5
 
7aeaae7
53ddeb5
7aeaae7
 
8d3381d
 
53ddeb5
 
 
 
 
e2d76a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61bd3b5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e30beec
 
 
7aeaae7
e30beec
 
7aeaae7
e30beec
 
 
 
 
 
 
53ddeb5
e30beec
 
 
 
61bd3b5
7aeaae7
e30beec
 
 
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": 0.010095344924284913,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011217049915872126,
      "grad_norm": 0.010464487597346306,
      "learning_rate": 2e-05,
      "loss": 11.9305,
      "step": 1
    },
    {
      "epoch": 0.0011217049915872126,
      "eval_loss": 11.931302070617676,
      "eval_runtime": 1.6109,
      "eval_samples_per_second": 466.206,
      "eval_steps_per_second": 116.707,
      "step": 1
    },
    {
      "epoch": 0.002243409983174425,
      "grad_norm": 0.012750067748129368,
      "learning_rate": 4e-05,
      "loss": 11.9324,
      "step": 2
    },
    {
      "epoch": 0.0033651149747616375,
      "grad_norm": 0.01111360639333725,
      "learning_rate": 6e-05,
      "loss": 11.9253,
      "step": 3
    },
    {
      "epoch": 0.0033651149747616375,
      "eval_loss": 11.931297302246094,
      "eval_runtime": 1.6294,
      "eval_samples_per_second": 460.916,
      "eval_steps_per_second": 115.382,
      "step": 3
    },
    {
      "epoch": 0.00448681996634885,
      "grad_norm": 0.0054331207647919655,
      "learning_rate": 8e-05,
      "loss": 11.9339,
      "step": 4
    },
    {
      "epoch": 0.005608524957936063,
      "grad_norm": 0.008967204950749874,
      "learning_rate": 0.0001,
      "loss": 11.9314,
      "step": 5
    },
    {
      "epoch": 0.006730229949523275,
      "grad_norm": 0.01504911296069622,
      "learning_rate": 0.00012,
      "loss": 11.9317,
      "step": 6
    },
    {
      "epoch": 0.006730229949523275,
      "eval_loss": 11.931279182434082,
      "eval_runtime": 1.6578,
      "eval_samples_per_second": 453.009,
      "eval_steps_per_second": 113.403,
      "step": 6
    },
    {
      "epoch": 0.007851934941110488,
      "grad_norm": 0.015188493765890598,
      "learning_rate": 0.00014,
      "loss": 11.927,
      "step": 7
    },
    {
      "epoch": 0.0089736399326977,
      "grad_norm": 0.015619461424648762,
      "learning_rate": 0.00016,
      "loss": 11.9367,
      "step": 8
    },
    {
      "epoch": 0.010095344924284913,
      "grad_norm": 0.010902787558734417,
      "learning_rate": 0.00018,
      "loss": 11.9306,
      "step": 9
    },
    {
      "epoch": 0.010095344924284913,
      "eval_loss": 11.93125057220459,
      "eval_runtime": 1.641,
      "eval_samples_per_second": 457.636,
      "eval_steps_per_second": 114.561,
      "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": 2156445696.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}