File size: 2,982 Bytes
cbe1f3b
 
 
1dafd69
cbe1f3b
1dafd69
cbe1f3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ff4c67
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6dd4deb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1dafd69
 
 
 
 
 
 
cbe1f3b
 
 
 
 
 
 
 
 
 
 
 
 
 
1dafd69
cbe1f3b
 
 
 
1dafd69
cbe1f3b
 
 
 
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": 0.0003470715835140998,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.470715835140998e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 3.5797,
      "step": 1
    },
    {
      "epoch": 3.470715835140998e-05,
      "eval_loss": NaN,
      "eval_runtime": 255.3165,
      "eval_samples_per_second": 47.517,
      "eval_steps_per_second": 23.759,
      "step": 1
    },
    {
      "epoch": 6.941431670281996e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00010412147505422994,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00010412147505422994,
      "eval_loss": NaN,
      "eval_runtime": 255.1442,
      "eval_samples_per_second": 47.55,
      "eval_steps_per_second": 23.775,
      "step": 3
    },
    {
      "epoch": 0.00013882863340563992,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0001735357917570499,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00020824295010845987,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00020824295010845987,
      "eval_loss": NaN,
      "eval_runtime": 256.6448,
      "eval_samples_per_second": 47.272,
      "eval_steps_per_second": 23.636,
      "step": 6
    },
    {
      "epoch": 0.00024295010845986985,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00027765726681127983,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0003123644251626898,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0003123644251626898,
      "eval_loss": NaN,
      "eval_runtime": 256.5453,
      "eval_samples_per_second": 47.29,
      "eval_steps_per_second": 23.645,
      "step": 9
    },
    {
      "epoch": 0.0003470715835140998,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 133557245706240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}