File size: 2,942 Bytes
9b6ebab
d718766
9b6ebab
 
 
 
 
 
 
 
 
 
d718766
 
 
9b6ebab
 
 
 
d718766
 
 
 
9b6ebab
 
 
 
d718766
 
 
9b6ebab
 
 
 
d718766
 
 
9b6ebab
 
 
 
 
d718766
 
 
9b6ebab
 
 
 
d718766
 
 
 
9b6ebab
 
 
 
d718766
 
 
9b6ebab
 
 
 
d718766
 
 
 
9b6ebab
 
 
 
d718766
 
 
9b6ebab
 
 
 
d718766
 
 
 
9b6ebab
 
 
 
d718766
9b6ebab
d718766
9b6ebab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 1.3168741464614868,
  "best_model_checkpoint": "/kaggle/working/checkpoint-50",
  "epoch": 5.555555555555555,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.02217627689242363,
      "learning_rate": 0.00017777777777777779,
      "loss": 2.0442,
      "step": 10
    },
    {
      "epoch": 1.1111111111111112,
      "eval_loss": 1.737181544303894,
      "eval_runtime": 35.1318,
      "eval_samples_per_second": 1.025,
      "eval_steps_per_second": 0.142,
      "step": 10
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.0346713550388813,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.6131,
      "step": 20
    },
    {
      "epoch": 2.2222222222222223,
      "eval_loss": 1.5489343404769897,
      "eval_runtime": 34.8402,
      "eval_samples_per_second": 1.033,
      "eval_steps_per_second": 0.144,
      "step": 20
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.02501535415649414,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.4152,
      "step": 30
    },
    {
      "epoch": 3.3333333333333335,
      "eval_loss": 1.4295110702514648,
      "eval_runtime": 34.8537,
      "eval_samples_per_second": 1.033,
      "eval_steps_per_second": 0.143,
      "step": 30
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.02104916237294674,
      "learning_rate": 0.00011111111111111112,
      "loss": 1.3068,
      "step": 40
    },
    {
      "epoch": 4.444444444444445,
      "eval_loss": 1.3598744869232178,
      "eval_runtime": 35.0281,
      "eval_samples_per_second": 1.028,
      "eval_steps_per_second": 0.143,
      "step": 40
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.022395364940166473,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.2049,
      "step": 50
    },
    {
      "epoch": 5.555555555555555,
      "eval_loss": 1.3168741464614868,
      "eval_runtime": 34.692,
      "eval_samples_per_second": 1.038,
      "eval_steps_per_second": 0.144,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 90,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3359632879910912e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}