File size: 3,373 Bytes
7f161ba
 
 
80387e9
7f161ba
80387e9
7f161ba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
000cc6b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55eda7f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14d7235
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80387e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f161ba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80387e9
7f161ba
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00031308458762846253,
  "eval_steps": 2,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.130845876284625e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 3.130845876284625e-05,
      "eval_loss": NaN,
      "eval_runtime": 3425.8749,
      "eval_samples_per_second": 3.926,
      "eval_steps_per_second": 3.926,
      "step": 1
    },
    {
      "epoch": 6.26169175256925e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 6.26169175256925e-05,
      "eval_loss": NaN,
      "eval_runtime": 3318.2461,
      "eval_samples_per_second": 4.053,
      "eval_steps_per_second": 4.053,
      "step": 2
    },
    {
      "epoch": 9.392537628853876e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.000125233835051385,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.000125233835051385,
      "eval_loss": NaN,
      "eval_runtime": 3321.6951,
      "eval_samples_per_second": 4.049,
      "eval_steps_per_second": 4.049,
      "step": 4
    },
    {
      "epoch": 0.00015654229381423127,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00018785075257707752,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00018785075257707752,
      "eval_loss": NaN,
      "eval_runtime": 3370.752,
      "eval_samples_per_second": 3.99,
      "eval_steps_per_second": 3.99,
      "step": 6
    },
    {
      "epoch": 0.00021915921133992377,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00025046767010277,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00025046767010277,
      "eval_loss": NaN,
      "eval_runtime": 3267.2262,
      "eval_samples_per_second": 4.116,
      "eval_steps_per_second": 4.116,
      "step": 8
    },
    {
      "epoch": 0.0002817761288656163,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00031308458762846253,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00031308458762846253,
      "eval_loss": NaN,
      "eval_runtime": 3420.2031,
      "eval_samples_per_second": 3.932,
      "eval_steps_per_second": 3.932,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7031294986813440.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}