File size: 3,199 Bytes
557ec60
 
 
8a67d6a
557ec60
8a67d6a
557ec60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71244c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d530b4e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a67d6a
 
 
 
 
 
 
557ec60
 
 
 
 
 
 
 
 
 
 
 
 
 
8a67d6a
557ec60
 
 
 
8a67d6a
557ec60
 
 
 
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": 0.0016354567012838335,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016354567012838336,
      "grad_norm": 0.8404057025909424,
      "learning_rate": 2e-05,
      "loss": 4.1796,
      "step": 1
    },
    {
      "epoch": 0.00016354567012838336,
      "eval_loss": 3.870612859725952,
      "eval_runtime": 118.1065,
      "eval_samples_per_second": 21.802,
      "eval_steps_per_second": 10.905,
      "step": 1
    },
    {
      "epoch": 0.0003270913402567667,
      "grad_norm": 0.676612138748169,
      "learning_rate": 4e-05,
      "loss": 3.2798,
      "step": 2
    },
    {
      "epoch": 0.00049063701038515,
      "grad_norm": 0.5842409133911133,
      "learning_rate": 6e-05,
      "loss": 2.8715,
      "step": 3
    },
    {
      "epoch": 0.00049063701038515,
      "eval_loss": 3.8622374534606934,
      "eval_runtime": 117.0475,
      "eval_samples_per_second": 22.0,
      "eval_steps_per_second": 11.004,
      "step": 3
    },
    {
      "epoch": 0.0006541826805135334,
      "grad_norm": 0.9987009763717651,
      "learning_rate": 8e-05,
      "loss": 3.5753,
      "step": 4
    },
    {
      "epoch": 0.0008177283506419167,
      "grad_norm": 0.8016535043716431,
      "learning_rate": 0.0001,
      "loss": 3.6414,
      "step": 5
    },
    {
      "epoch": 0.0009812740207703,
      "grad_norm": 1.3895742893218994,
      "learning_rate": 0.00012,
      "loss": 3.7456,
      "step": 6
    },
    {
      "epoch": 0.0009812740207703,
      "eval_loss": 3.7499568462371826,
      "eval_runtime": 117.1053,
      "eval_samples_per_second": 21.989,
      "eval_steps_per_second": 10.999,
      "step": 6
    },
    {
      "epoch": 0.0011448196908986834,
      "grad_norm": 0.9894824028015137,
      "learning_rate": 0.00014,
      "loss": 3.2878,
      "step": 7
    },
    {
      "epoch": 0.0013083653610270669,
      "grad_norm": 1.046766757965088,
      "learning_rate": 0.00016,
      "loss": 3.4432,
      "step": 8
    },
    {
      "epoch": 0.0014719110311554502,
      "grad_norm": 1.1286696195602417,
      "learning_rate": 0.00018,
      "loss": 2.3802,
      "step": 9
    },
    {
      "epoch": 0.0014719110311554502,
      "eval_loss": 3.425133466720581,
      "eval_runtime": 117.0288,
      "eval_samples_per_second": 22.003,
      "eval_steps_per_second": 11.006,
      "step": 9
    },
    {
      "epoch": 0.0016354567012838335,
      "grad_norm": 2.14523983001709,
      "learning_rate": 0.0002,
      "loss": 3.9452,
      "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": 3166204172697600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}