File size: 3,228 Bytes
378fa98
 
 
b1d92fb
378fa98
b1d92fb
378fa98
 
 
 
 
 
b01ec7a
378fa98
 
 
 
 
 
 
b01ec7a
 
 
378fa98
 
 
 
b01ec7a
378fa98
 
 
 
 
 
b01ec7a
378fa98
 
 
 
 
 
b01ec7a
 
 
 
378fa98
0b09426
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9011748
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1d92fb
 
 
 
 
 
 
378fa98
 
 
 
 
 
 
 
 
 
 
 
 
 
b1d92fb
378fa98
 
 
 
b1d92fb
378fa98
 
 
 
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": 0.005608524957936063,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005608524957936063,
      "grad_norm": 0.01440234761685133,
      "learning_rate": 2e-05,
      "loss": 11.9315,
      "step": 1
    },
    {
      "epoch": 0.0005608524957936063,
      "eval_loss": 11.931306838989258,
      "eval_runtime": 2.6444,
      "eval_samples_per_second": 283.993,
      "eval_steps_per_second": 142.186,
      "step": 1
    },
    {
      "epoch": 0.0011217049915872126,
      "grad_norm": 0.008986671455204487,
      "learning_rate": 4e-05,
      "loss": 11.9304,
      "step": 2
    },
    {
      "epoch": 0.0016825574873808188,
      "grad_norm": 0.013879197649657726,
      "learning_rate": 6e-05,
      "loss": 11.9319,
      "step": 3
    },
    {
      "epoch": 0.0016825574873808188,
      "eval_loss": 11.931303977966309,
      "eval_runtime": 2.6803,
      "eval_samples_per_second": 280.195,
      "eval_steps_per_second": 140.284,
      "step": 3
    },
    {
      "epoch": 0.002243409983174425,
      "grad_norm": 0.01761799305677414,
      "learning_rate": 8e-05,
      "loss": 11.9328,
      "step": 4
    },
    {
      "epoch": 0.0028042624789680315,
      "grad_norm": 0.018328625708818436,
      "learning_rate": 0.0001,
      "loss": 11.9248,
      "step": 5
    },
    {
      "epoch": 0.0033651149747616375,
      "grad_norm": 0.009327949024736881,
      "learning_rate": 0.00012,
      "loss": 11.926,
      "step": 6
    },
    {
      "epoch": 0.0033651149747616375,
      "eval_loss": 11.931290626525879,
      "eval_runtime": 2.7752,
      "eval_samples_per_second": 270.606,
      "eval_steps_per_second": 135.483,
      "step": 6
    },
    {
      "epoch": 0.003925967470555244,
      "grad_norm": 0.011274761520326138,
      "learning_rate": 0.00014,
      "loss": 11.9324,
      "step": 7
    },
    {
      "epoch": 0.00448681996634885,
      "grad_norm": 0.0072128307074308395,
      "learning_rate": 0.00016,
      "loss": 11.935,
      "step": 8
    },
    {
      "epoch": 0.005047672462142457,
      "grad_norm": 0.013769167475402355,
      "learning_rate": 0.00018,
      "loss": 11.9287,
      "step": 9
    },
    {
      "epoch": 0.005047672462142457,
      "eval_loss": 11.931265830993652,
      "eval_runtime": 2.7062,
      "eval_samples_per_second": 277.515,
      "eval_steps_per_second": 138.942,
      "step": 9
    },
    {
      "epoch": 0.005608524957936063,
      "grad_norm": 0.008655436336994171,
      "learning_rate": 0.0002,
      "loss": 11.9335,
      "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": 1211154432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}