File size: 3,015 Bytes
a1a5253
 
 
3566469
a1a5253
3566469
a1a5253
 
 
 
 
 
 
 
 
 
 
 
 
 
4ff396f
 
 
a1a5253
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4ff396f
 
 
a1a5253
45afb33
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4ff396f
 
 
45afb33
87e35a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4ff396f
 
 
87e35a3
3566469
 
 
 
 
 
 
a1a5253
 
 
 
 
 
 
 
 
 
 
 
 
 
3566469
a1a5253
 
 
 
3566469
a1a5253
 
 
 
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": 0.006683375104427736,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006683375104427736,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 5.8583,
      "step": 1
    },
    {
      "epoch": 0.0006683375104427736,
      "eval_loss": 6.567427635192871,
      "eval_runtime": 12.5721,
      "eval_samples_per_second": 25.135,
      "eval_steps_per_second": 25.135,
      "step": 1
    },
    {
      "epoch": 0.0013366750208855473,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 6.9726,
      "step": 2
    },
    {
      "epoch": 0.0020050125313283208,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.0245,
      "step": 3
    },
    {
      "epoch": 0.0020050125313283208,
      "eval_loss": 6.567427635192871,
      "eval_runtime": 12.4056,
      "eval_samples_per_second": 25.472,
      "eval_steps_per_second": 25.472,
      "step": 3
    },
    {
      "epoch": 0.0026733500417710945,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 6.3121,
      "step": 4
    },
    {
      "epoch": 0.003341687552213868,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 6.5075,
      "step": 5
    },
    {
      "epoch": 0.0040100250626566416,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 6.479,
      "step": 6
    },
    {
      "epoch": 0.0040100250626566416,
      "eval_loss": 6.567427635192871,
      "eval_runtime": 12.9457,
      "eval_samples_per_second": 24.41,
      "eval_steps_per_second": 24.41,
      "step": 6
    },
    {
      "epoch": 0.004678362573099415,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 5.702,
      "step": 7
    },
    {
      "epoch": 0.005346700083542189,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 5.4896,
      "step": 8
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 5.3384,
      "step": 9
    },
    {
      "epoch": 0.006015037593984963,
      "eval_loss": 6.567427635192871,
      "eval_runtime": 12.5182,
      "eval_samples_per_second": 25.243,
      "eval_steps_per_second": 25.243,
      "step": 9
    },
    {
      "epoch": 0.006683375104427736,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 6.3319,
      "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": 255791978250240.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}