Hugging Face's logo

Eva1209
/
HW1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
HW1
File size: 2,750 Bytes 
c5bd888
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.47042279469851556,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-2675",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 2675,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.93,
      "grad_norm": 5.041173934936523,
      "learning_rate": 4.466779044509044e-06,
      "loss": 0.5565,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5430340766906738,
      "eval_matthews_correlation": 0.3453182575293756,
      "eval_runtime": 0.8193,
      "eval_samples_per_second": 1273.053,
      "eval_steps_per_second": 80.557,
      "step": 535
    },
    {
      "epoch": 1.87,
      "grad_norm": 9.476218223571777,
      "learning_rate": 3.4399332871506427e-06,
      "loss": 0.4477,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5347909927368164,
      "eval_matthews_correlation": 0.4329619258860067,
      "eval_runtime": 1.3398,
      "eval_samples_per_second": 778.476,
      "eval_steps_per_second": 49.261,
      "step": 1070
    },
    {
      "epoch": 2.8,
      "grad_norm": 13.160967826843262,
      "learning_rate": 2.413087529792242e-06,
      "loss": 0.3814,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.518277108669281,
      "eval_matthews_correlation": 0.4491418956579208,
      "eval_runtime": 0.952,
      "eval_samples_per_second": 1095.631,
      "eval_steps_per_second": 69.33,
      "step": 1605
    },
    {
      "epoch": 3.74,
      "grad_norm": 10.544774055480957,
      "learning_rate": 1.386241772433841e-06,
      "loss": 0.3476,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5457636713981628,
      "eval_matthews_correlation": 0.4587117762521935,
      "eval_runtime": 2.1058,
      "eval_samples_per_second": 495.294,
      "eval_steps_per_second": 31.342,
      "step": 2140
    },
    {
      "epoch": 4.67,
      "grad_norm": 8.001981735229492,
      "learning_rate": 3.5939601507544025e-07,
      "loss": 0.3086,
      "step": 2500
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.5409175157546997,
      "eval_matthews_correlation": 0.47042279469851556,
      "eval_runtime": 0.7084,
      "eval_samples_per_second": 1472.267,
      "eval_steps_per_second": 93.164,
      "step": 2675
    }
  ],
  "logging_steps": 500,
  "max_steps": 2675,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 214118543854920.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.493624801867445e-06,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 16,
    "seed": 31
  }
}