File size: 3,160 Bytes
61efde9
 
 
a71ba96
61efde9
a71ba96
61efde9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c95942e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
09c4c54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a71ba96
 
 
 
 
 
 
61efde9
 
 
 
 
 
 
 
 
 
 
 
 
 
a71ba96
61efde9
 
 
 
a71ba96
61efde9
 
 
 
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": 0.006351222610352493,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006351222610352493,
      "grad_norm": 1.7062007827917114e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0006351222610352493,
      "eval_loss": 11.5,
      "eval_runtime": 3.4713,
      "eval_samples_per_second": 190.997,
      "eval_steps_per_second": 95.643,
      "step": 1
    },
    {
      "epoch": 0.0012702445220704986,
      "grad_norm": 1.8129745512851514e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.001905366783105748,
      "grad_norm": 1.546772000438068e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.001905366783105748,
      "eval_loss": 11.5,
      "eval_runtime": 3.6127,
      "eval_samples_per_second": 183.52,
      "eval_steps_per_second": 91.898,
      "step": 3
    },
    {
      "epoch": 0.0025404890441409972,
      "grad_norm": 3.256682975916192e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0031756113051762463,
      "grad_norm": 3.3200616599060595e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.003810733566211496,
      "grad_norm": 2.9896031264797784e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.003810733566211496,
      "eval_loss": 11.5,
      "eval_runtime": 3.6001,
      "eval_samples_per_second": 184.163,
      "eval_steps_per_second": 92.22,
      "step": 6
    },
    {
      "epoch": 0.004445855827246745,
      "grad_norm": 1.4344588635140099e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0050809780882819944,
      "grad_norm": 1.4874678527121432e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0057161003493172435,
      "grad_norm": 2.7079668143414892e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0057161003493172435,
      "eval_loss": 11.5,
      "eval_runtime": 3.6694,
      "eval_samples_per_second": 180.685,
      "eval_steps_per_second": 90.479,
      "step": 9
    },
    {
      "epoch": 0.006351222610352493,
      "grad_norm": 3.1126408430282027e-05,
      "learning_rate": 0.0002,
      "loss": 46.0,
      "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": 214170943488.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}