File size: 2,714 Bytes
fed6441
 
 
 
 
 
 
 
 
 
 
 
 
f00bda5
 
 
 
fed6441
 
f00bda5
 
 
 
fed6441
 
f00bda5
 
 
 
fed6441
f00bda5
 
fed6441
f00bda5
 
 
 
fed6441
f00bda5
 
 
fed6441
f00bda5
 
 
 
fed6441
 
 
 
 
 
f00bda5
 
 
 
fed6441
 
f00bda5
 
 
 
fed6441
 
f00bda5
 
 
 
fed6441
f00bda5
 
fed6441
f00bda5
 
 
 
fed6441
f00bda5
 
 
fed6441
f00bda5
 
 
 
fed6441
 
 
 
 
 
 
 
 
f00bda5
fed6441
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 162,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_B": {
        "f1-score": 0.7905866302864938,
        "precision": 0.7768096514745308,
        "recall": 0.8048611111111111,
        "support": 1440.0
      },
      "eval_I": {
        "f1-score": 0.9005331227169513,
        "precision": 0.9637593111099372,
        "recall": 0.8450919534905267,
        "support": 21587.0
      },
      "eval_O": {
        "f1-score": 0.8288892663043479,
        "precision": 0.7463108800367001,
        "recall": 0.9320156593144275,
        "support": 10473.0
      },
      "eval_accuracy": 0.8705373134328358,
      "eval_loss": 0.32930415868759155,
      "eval_macro avg": {
        "f1-score": 0.8400030064359308,
        "precision": 0.8289599475403894,
        "recall": 0.8606562413053552,
        "support": 33500.0
      },
      "eval_runtime": 4.7349,
      "eval_samples_per_second": 17.107,
      "eval_steps_per_second": 2.323,
      "eval_weighted avg": {
        "f1-score": 0.8734092702599646,
        "precision": 0.8877430445874,
        "recall": 0.8705373134328358,
        "support": 33500.0
      },
      "step": 81
    },
    {
      "epoch": 2.0,
      "eval_B": {
        "f1-score": 0.8656218739579861,
        "precision": 0.8325849903784477,
        "recall": 0.9013888888888889,
        "support": 1440.0
      },
      "eval_I": {
        "f1-score": 0.9547168948727912,
        "precision": 0.9423736462093862,
        "recall": 0.9673877796822161,
        "support": 21587.0
      },
      "eval_O": {
        "f1-score": 0.9013528191962081,
        "precision": 0.9332379102341274,
        "recall": 0.8715745249689678,
        "support": 10473.0
      },
      "eval_accuracy": 0.9345970149253732,
      "eval_loss": 0.2162298709154129,
      "eval_macro avg": {
        "f1-score": 0.9072305293423284,
        "precision": 0.902732182273987,
        "recall": 0.9134503978466909,
        "support": 33500.0
      },
      "eval_runtime": 4.753,
      "eval_samples_per_second": 17.042,
      "eval_steps_per_second": 2.314,
      "eval_weighted avg": {
        "f1-score": 0.9342040950316517,
        "precision": 0.9347982961417612,
        "recall": 0.9345970149253732,
        "support": 33500.0
      },
      "step": 162
    }
  ],
  "logging_steps": 500,
  "max_steps": 4050,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 286680220671600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}