File size: 3,136 Bytes
138fecc
 
 
52fde9b
138fecc
52fde9b
138fecc
 
 
 
 
1dbffe2
138fecc
 
1dbffe2
138fecc
 
 
1dbffe2
 
c4ccaa0
 
 
138fecc
 
 
1dbffe2
138fecc
 
1dbffe2
138fecc
 
 
1dbffe2
138fecc
 
1dbffe2
138fecc
 
 
1dbffe2
 
c4ccaa0
 
 
138fecc
b5b730b
 
1dbffe2
c4ccaa0
b5b730b
1dbffe2
b5b730b
 
 
1dbffe2
c4ccaa0
b5b730b
1dbffe2
b5b730b
 
 
1dbffe2
c4ccaa0
b5b730b
c4ccaa0
b5b730b
 
 
1dbffe2
c4ccaa0
 
 
 
b5b730b
ff2be76
 
 
c4ccaa0
ff2be76
c4ccaa0
ff2be76
 
 
 
c4ccaa0
ff2be76
c4ccaa0
ff2be76
 
 
 
c4ccaa0
ff2be76
c4ccaa0
ff2be76
 
 
 
c4ccaa0
 
 
 
ff2be76
52fde9b
 
 
 
 
 
 
138fecc
 
 
 
 
 
 
 
 
 
 
 
 
 
52fde9b
138fecc
 
 
 
52fde9b
138fecc
 
 
 
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": 0.0029942360955161314,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002994236095516131,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.9802,
      "step": 1
    },
    {
      "epoch": 0.0002994236095516131,
      "eval_loss": 11.5775728225708,
      "eval_runtime": 95.8227,
      "eval_samples_per_second": 7.347,
      "eval_steps_per_second": 7.347,
      "step": 1
    },
    {
      "epoch": 0.0005988472191032262,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.7165,
      "step": 2
    },
    {
      "epoch": 0.0008982708286548395,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.434,
      "step": 3
    },
    {
      "epoch": 0.0008982708286548395,
      "eval_loss": 11.5775728225708,
      "eval_runtime": 95.0865,
      "eval_samples_per_second": 7.404,
      "eval_steps_per_second": 7.404,
      "step": 3
    },
    {
      "epoch": 0.0011976944382064525,
      "grad_norm": 10.02202320098877,
      "learning_rate": 2e-05,
      "loss": 9.5838,
      "step": 4
    },
    {
      "epoch": 0.0014971180477580657,
      "grad_norm": 11.54944896697998,
      "learning_rate": 4e-05,
      "loss": 11.0567,
      "step": 5
    },
    {
      "epoch": 0.001796541657309679,
      "grad_norm": 12.557976722717285,
      "learning_rate": 6e-05,
      "loss": 12.2132,
      "step": 6
    },
    {
      "epoch": 0.001796541657309679,
      "eval_loss": 11.523130416870117,
      "eval_runtime": 94.7466,
      "eval_samples_per_second": 7.43,
      "eval_steps_per_second": 7.43,
      "step": 6
    },
    {
      "epoch": 0.002095965266861292,
      "grad_norm": 10.816157341003418,
      "learning_rate": 8e-05,
      "loss": 11.453,
      "step": 7
    },
    {
      "epoch": 0.002395388876412905,
      "grad_norm": 11.840999603271484,
      "learning_rate": 0.0001,
      "loss": 11.202,
      "step": 8
    },
    {
      "epoch": 0.002694812485964518,
      "grad_norm": 8.202712059020996,
      "learning_rate": 0.00012,
      "loss": 9.0586,
      "step": 9
    },
    {
      "epoch": 0.002694812485964518,
      "eval_loss": 11.066697120666504,
      "eval_runtime": 95.5362,
      "eval_samples_per_second": 7.369,
      "eval_steps_per_second": 7.369,
      "step": 9
    },
    {
      "epoch": 0.0029942360955161314,
      "grad_norm": 7.411980152130127,
      "learning_rate": 0.00014,
      "loss": 10.0089,
      "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": 1849564248145920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}