File size: 2,458 Bytes
e375f00
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 6.289308176100629,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7293548387096774,
      "eval_loss": 3.176466703414917,
      "eval_runtime": 2.372,
      "eval_samples_per_second": 1306.914,
      "eval_steps_per_second": 27.403,
      "step": 318
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.650593990216632e-05,
      "loss": 3.7036,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8590322580645161,
      "eval_loss": 1.5857902765274048,
      "eval_runtime": 2.418,
      "eval_samples_per_second": 1282.05,
      "eval_steps_per_second": 26.882,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9109677419354839,
      "eval_loss": 0.7998820543289185,
      "eval_runtime": 2.461,
      "eval_samples_per_second": 1259.651,
      "eval_steps_per_second": 26.412,
      "step": 954
    },
    {
      "epoch": 3.14,
      "learning_rate": 1.3011879804332637e-05,
      "loss": 1.3611,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9338709677419355,
      "eval_loss": 0.4834734797477722,
      "eval_runtime": 2.399,
      "eval_samples_per_second": 1292.206,
      "eval_steps_per_second": 27.095,
      "step": 1272
    },
    {
      "epoch": 4.72,
      "learning_rate": 9.517819706498952e-06,
      "loss": 0.4625,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9416129032258065,
      "eval_loss": 0.35008904337882996,
      "eval_runtime": 2.439,
      "eval_samples_per_second": 1271.013,
      "eval_steps_per_second": 26.65,
      "step": 1590
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9461290322580646,
      "eval_loss": 0.2929627001285553,
      "eval_runtime": 2.462,
      "eval_samples_per_second": 1259.137,
      "eval_steps_per_second": 26.401,
      "step": 1908
    },
    {
      "epoch": 6.29,
      "learning_rate": 6.02375960866527e-06,
      "loss": 0.1991,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2862,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 602555922515232.0,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.47830413160685104,
    "num_train_epochs": 9,
    "temperature": 3
  }
}