File size: 2,123 Bytes
e291318
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.9306122448979591,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-20\\checkpoint-2200",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 2200,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.91,
      "learning_rate": 3.7993613084244125e-05,
      "loss": 1.279,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8530612244897959,
      "eval_loss": 0.5417793393135071,
      "eval_runtime": 1.382,
      "eval_samples_per_second": 177.279,
      "eval_steps_per_second": 11.577,
      "step": 550
    },
    {
      "epoch": 1.82,
      "learning_rate": 2.681902100064291e-05,
      "loss": 0.483,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9183673469387755,
      "eval_loss": 0.35391971468925476,
      "eval_runtime": 1.762,
      "eval_samples_per_second": 139.046,
      "eval_steps_per_second": 9.081,
      "step": 1100
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.56444289170417e-05,
      "loss": 0.3298,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9224489795918367,
      "eval_loss": 0.31729385256767273,
      "eval_runtime": 1.362,
      "eval_samples_per_second": 179.882,
      "eval_steps_per_second": 11.747,
      "step": 1650
    },
    {
      "epoch": 3.64,
      "learning_rate": 4.469836833440486e-06,
      "loss": 0.2627,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9306122448979591,
      "eval_loss": 0.31183353066444397,
      "eval_runtime": 1.267,
      "eval_samples_per_second": 193.369,
      "eval_steps_per_second": 12.628,
      "step": 2200
    }
  ],
  "logging_steps": 500,
  "max_steps": 2200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 3827667253200.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.916820516784534e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 4,
    "seed": 33
  }
}