Hugging Face's logo

HuggingPanda
/
distilbert-base-uncased-finetuned-clinc-oos-plus

TensorBoard
Safetensors
distilbert
Model card Files
xet
 Metrics Community
distilbert-base-uncased-finetuned-clinc-oos-plus
File size: 3,044 Bytes
4e94a8a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
113
114
115
116
117
118
{
  "best_metric": 0.23660233616828918,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-clinc-oos-plus/run-6/checkpoint-595",
  "epoch": 4.958333333333333,
  "eval_steps": 119,
  "global_step": 595,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9916666666666667,
      "grad_norm": 0.8545851707458496,
      "learning_rate": 1.801666666666667e-05,
      "loss": 0.6857,
      "step": 119
    },
    {
      "epoch": 0.9916666666666667,
      "eval_accuracy": 0.05806451612903226,
      "eval_loss": 0.5795652270317078,
      "eval_runtime": 5.2246,
      "eval_samples_per_second": 593.352,
      "eval_steps_per_second": 4.785,
      "step": 119
    },
    {
      "epoch": 1.9833333333333334,
      "grad_norm": 0.9951759576797485,
      "learning_rate": 1.6033333333333335e-05,
      "loss": 0.5273,
      "step": 238
    },
    {
      "epoch": 1.9833333333333334,
      "eval_accuracy": 0.21548387096774194,
      "eval_loss": 0.4308617413043976,
      "eval_runtime": 5.2594,
      "eval_samples_per_second": 589.426,
      "eval_steps_per_second": 4.753,
      "step": 238
    },
    {
      "epoch": 2.975,
      "grad_norm": 0.9097500443458557,
      "learning_rate": 1.4050000000000001e-05,
      "loss": 0.4101,
      "step": 357
    },
    {
      "epoch": 2.975,
      "eval_accuracy": 0.4467741935483871,
      "eval_loss": 0.33184605836868286,
      "eval_runtime": 5.2618,
      "eval_samples_per_second": 589.152,
      "eval_steps_per_second": 4.751,
      "step": 357
    },
    {
      "epoch": 3.966666666666667,
      "grad_norm": 0.7865796685218811,
      "learning_rate": 1.206666666666667e-05,
      "loss": 0.3292,
      "step": 476
    },
    {
      "epoch": 3.966666666666667,
      "eval_accuracy": 0.59,
      "eval_loss": 0.2733142077922821,
      "eval_runtime": 5.3142,
      "eval_samples_per_second": 583.338,
      "eval_steps_per_second": 4.704,
      "step": 476
    },
    {
      "epoch": 4.958333333333333,
      "grad_norm": 0.8034551739692688,
      "learning_rate": 1.0083333333333334e-05,
      "loss": 0.2819,
      "step": 595
    },
    {
      "epoch": 4.958333333333333,
      "eval_accuracy": 0.6548387096774193,
      "eval_loss": 0.23660233616828918,
      "eval_runtime": 5.2514,
      "eval_samples_per_second": 590.317,
      "eval_steps_per_second": 4.761,
      "step": 595
    }
  ],
  "logging_steps": 119,
  "max_steps": 1200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 119,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 455280489210708.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.11019042244707389,
    "num_train_epochs": 10,
    "temperature": 10
  }
}