File size: 3,104 Bytes
6cadaa0
 
 
89ca2a5
6cadaa0
89ca2a5
6cadaa0
 
 
 
 
 
 
 
 
 
 
 
 
 
89ca2a5
 
 
6cadaa0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89ca2a5
 
 
6cadaa0
8a20e34
 
 
89ca2a5
8a20e34
 
 
 
 
 
 
 
 
 
 
 
 
89ca2a5
8a20e34
 
 
 
 
 
89ca2a5
 
 
 
8a20e34
96f5052
 
 
 
 
 
 
 
 
 
89ca2a5
96f5052
89ca2a5
96f5052
 
 
 
 
 
89ca2a5
96f5052
 
 
 
89ca2a5
 
 
 
96f5052
89ca2a5
 
 
 
 
 
 
6cadaa0
 
 
 
 
 
 
 
 
 
 
 
 
 
89ca2a5
6cadaa0
 
 
 
89ca2a5
6cadaa0
 
 
 
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": 0.0001396028995522237,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.396028995522237e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 1.6888,
      "step": 1
    },
    {
      "epoch": 1.396028995522237e-05,
      "eval_loss": 1.870382308959961,
      "eval_runtime": 1842.0549,
      "eval_samples_per_second": 8.187,
      "eval_steps_per_second": 8.187,
      "step": 1
    },
    {
      "epoch": 2.792057991044474e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 1.6735,
      "step": 2
    },
    {
      "epoch": 4.188086986566711e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 1.8269,
      "step": 3
    },
    {
      "epoch": 4.188086986566711e-05,
      "eval_loss": 1.870382308959961,
      "eval_runtime": 1823.007,
      "eval_samples_per_second": 8.273,
      "eval_steps_per_second": 8.273,
      "step": 3
    },
    {
      "epoch": 5.584115982088948e-05,
      "grad_norm": 0.45489802956581116,
      "learning_rate": 2e-05,
      "loss": 1.6525,
      "step": 4
    },
    {
      "epoch": 6.980144977611185e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 1.6793,
      "step": 5
    },
    {
      "epoch": 8.376173973133422e-05,
      "grad_norm": 0.6043833494186401,
      "learning_rate": 4e-05,
      "loss": 1.5735,
      "step": 6
    },
    {
      "epoch": 8.376173973133422e-05,
      "eval_loss": 1.8686633110046387,
      "eval_runtime": 1822.7895,
      "eval_samples_per_second": 8.274,
      "eval_steps_per_second": 8.274,
      "step": 6
    },
    {
      "epoch": 9.77220296865566e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 1.7572,
      "step": 7
    },
    {
      "epoch": 0.00011168231964177897,
      "grad_norm": 0.5930614471435547,
      "learning_rate": 6e-05,
      "loss": 1.8795,
      "step": 8
    },
    {
      "epoch": 0.00012564260959700132,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 1.6314,
      "step": 9
    },
    {
      "epoch": 0.00012564260959700132,
      "eval_loss": 1.862870216369629,
      "eval_runtime": 1821.1166,
      "eval_samples_per_second": 8.281,
      "eval_steps_per_second": 8.281,
      "step": 9
    },
    {
      "epoch": 0.0001396028995522237,
      "grad_norm": 0.5115928649902344,
      "learning_rate": 8e-05,
      "loss": 1.7711,
      "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": 1628733135912960.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}