Hugging Face's logo

dannychou
/
Homework01

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
Homework01
File size: 2,664 Bytes
19ed69e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.543909089281463,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-2138",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 4276,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47,
      "learning_rate": 2.0681209971615274e-05,
      "loss": 0.5488,
      "step": 500
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8546926176814934e-05,
      "loss": 0.498,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.48384082317352295,
      "eval_matthews_correlation": 0.4611631351812362,
      "eval_runtime": 0.7492,
      "eval_samples_per_second": 1392.127,
      "eval_steps_per_second": 88.092,
      "step": 1069
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.6412642382014598e-05,
      "loss": 0.3532,
      "step": 1500
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.4278358587214258e-05,
      "loss": 0.354,
      "step": 2000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5868804454803467,
      "eval_matthews_correlation": 0.543909089281463,
      "eval_runtime": 0.7926,
      "eval_samples_per_second": 1315.987,
      "eval_steps_per_second": 83.274,
      "step": 2138
    },
    {
      "epoch": 2.34,
      "learning_rate": 1.214407479241392e-05,
      "loss": 0.2699,
      "step": 2500
    },
    {
      "epoch": 2.81,
      "learning_rate": 1.0009790997613584e-05,
      "loss": 0.2462,
      "step": 3000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7930343747138977,
      "eval_matthews_correlation": 0.5340667882909217,
      "eval_runtime": 0.7474,
      "eval_samples_per_second": 1395.496,
      "eval_steps_per_second": 88.306,
      "step": 3207
    },
    {
      "epoch": 3.27,
      "learning_rate": 7.875507202813246e-06,
      "loss": 0.1931,
      "step": 3500
    },
    {
      "epoch": 3.74,
      "learning_rate": 5.741223408012909e-06,
      "loss": 0.1671,
      "step": 4000
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0090364217758179,
      "eval_matthews_correlation": 0.5279532549901665,
      "eval_runtime": 1.1191,
      "eval_samples_per_second": 931.964,
      "eval_steps_per_second": 58.974,
      "step": 4276
    }
  ],
  "logging_steps": 500,
  "max_steps": 5345,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 150372489132540.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.281549376641561e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 8,
    "seed": 24
  }
}