File size: 2,357 Bytes
e859a16
 
 
3e00e68
e859a16
3e00e68
e859a16
 
 
 
 
 
3e00e68
e859a16
 
 
 
 
 
 
3e00e68
 
 
e859a16
 
 
 
3e00e68
e859a16
 
 
 
 
 
3e00e68
e859a16
1d02bcb
e859a16
 
 
 
3e00e68
 
 
 
e859a16
82af8c7
 
 
3e00e68
82af8c7
3e00e68
82af8c7
 
 
 
3e00e68
82af8c7
 
 
 
 
 
3e00e68
82af8c7
3e00e68
82af8c7
 
 
 
3e00e68
 
 
 
82af8c7
e859a16
 
 
 
 
 
 
 
 
 
 
 
 
 
3e00e68
e859a16
 
 
 
3e00e68
e859a16
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011276075925577898,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018793459875963165,
      "grad_norm": 0.4121508002281189,
      "learning_rate": 2e-05,
      "loss": 2.0097,
      "step": 1
    },
    {
      "epoch": 0.00018793459875963165,
      "eval_loss": 2.225860595703125,
      "eval_runtime": 104.6968,
      "eval_samples_per_second": 10.707,
      "eval_steps_per_second": 10.707,
      "step": 1
    },
    {
      "epoch": 0.0003758691975192633,
      "grad_norm": 0.34095901250839233,
      "learning_rate": 4e-05,
      "loss": 2.0424,
      "step": 2
    },
    {
      "epoch": 0.0005638037962788949,
      "grad_norm": 0.4388081431388855,
      "learning_rate": 6e-05,
      "loss": 2.2435,
      "step": 3
    },
    {
      "epoch": 0.0005638037962788949,
      "eval_loss": 2.2231271266937256,
      "eval_runtime": 105.4847,
      "eval_samples_per_second": 10.627,
      "eval_steps_per_second": 10.627,
      "step": 3
    },
    {
      "epoch": 0.0007517383950385266,
      "grad_norm": 0.3048204183578491,
      "learning_rate": 8e-05,
      "loss": 2.1182,
      "step": 4
    },
    {
      "epoch": 0.0009396729937981583,
      "grad_norm": 0.4445512592792511,
      "learning_rate": 0.0001,
      "loss": 2.2092,
      "step": 5
    },
    {
      "epoch": 0.0011276075925577898,
      "grad_norm": 0.3167805075645447,
      "learning_rate": 0.00012,
      "loss": 2.2226,
      "step": 6
    },
    {
      "epoch": 0.0011276075925577898,
      "eval_loss": 2.202314615249634,
      "eval_runtime": 104.9224,
      "eval_samples_per_second": 10.684,
      "eval_steps_per_second": 10.684,
      "step": 6
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 417433827409920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}