File size: 2,221 Bytes
fbd8c55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.530612244897959,
  "eval_steps": 20,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.82,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.7509,
      "step": 10
    },
    {
      "epoch": 1.63,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.6967,
      "step": 20
    },
    {
      "epoch": 1.63,
      "eval_loss": 1.6115258932113647,
      "eval_runtime": 30.6688,
      "eval_samples_per_second": 12.619,
      "eval_steps_per_second": 1.598,
      "step": 20
    },
    {
      "epoch": 2.45,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.5138,
      "step": 30
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.0417,
      "step": 40
    },
    {
      "epoch": 3.27,
      "eval_loss": 0.5990618467330933,
      "eval_runtime": 45.282,
      "eval_samples_per_second": 8.546,
      "eval_steps_per_second": 1.082,
      "step": 40
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00015,
      "loss": 0.4159,
      "step": 50
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.3112,
      "step": 60
    },
    {
      "epoch": 4.9,
      "eval_loss": 0.277026891708374,
      "eval_runtime": 30.7302,
      "eval_samples_per_second": 12.593,
      "eval_steps_per_second": 1.595,
      "step": 60
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.285,
      "step": 70
    },
    {
      "epoch": 6.53,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.27,
      "step": 80
    },
    {
      "epoch": 6.53,
      "eval_loss": 0.24872899055480957,
      "eval_runtime": 30.6498,
      "eval_samples_per_second": 12.627,
      "eval_steps_per_second": 1.599,
      "step": 80
    }
  ],
  "logging_steps": 10,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 34,
  "save_steps": 20,
  "total_flos": 2.0387147098462618e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}