File size: 2,518 Bytes
9192893
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.3881937785695449,
  "best_model_checkpoint": "esm2_t12_35M_qlora_binding_sites_2023-09-28_20-31-07/checkpoint-2620",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2620,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 0.0003700089891924202,
      "loss": 0.3796,
      "step": 200
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003695657761444924,
      "loss": 0.1708,
      "step": 400
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00036882787439658813,
      "loss": 0.1281,
      "step": 600
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003677964626272417,
      "loss": 0.1085,
      "step": 800
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00036647318834971053,
      "loss": 0.0953,
      "step": 1000
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00036486016528034,
      "loss": 0.0868,
      "step": 1200
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003629599699622435,
      "loss": 0.0815,
      "step": 1400
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00036077563764969246,
      "loss": 0.0768,
      "step": 1600
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003583106574597891,
      "loss": 0.0727,
      "step": 1800
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003555689667991667,
      "loss": 0.0695,
      "step": 2000
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00035255494507462076,
      "loss": 0.0652,
      "step": 2200
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003492734066977151,
      "loss": 0.0643,
      "step": 2400
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00034572959339454007,
      "loss": 0.0629,
      "step": 2600
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9514288298771856,
      "eval_auc": 0.8487674697088246,
      "eval_f1": 0.3881937785695449,
      "eval_loss": 0.47870784997940063,
      "eval_mcc": 0.423561780831004,
      "eval_precision": 0.26289979651663037,
      "eval_recall": 0.7416551821788429,
      "eval_runtime": 1915.3281,
      "eval_samples_per_second": 115.187,
      "eval_steps_per_second": 0.678,
      "step": 2620
    }
  ],
  "logging_steps": 200,
  "max_steps": 15720,
  "num_train_epochs": 6,
  "save_steps": 500,
  "total_flos": 1.7917776880933446e+17,
  "trial_name": null,
  "trial_params": null
}