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: 2,398 Bytes 
a9e22be
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.47078712112764887,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-3207",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 3207,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47,
      "grad_norm": 4.060019016265869,
      "learning_rate": 4.481496253268653e-05,
      "loss": 0.5778,
      "step": 500
    },
    {
      "epoch": 0.94,
      "grad_norm": 12.268152236938477,
      "learning_rate": 3.6537355858751076e-05,
      "loss": 0.5395,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.4984060525894165,
      "eval_matthews_correlation": 0.39596800444544106,
      "eval_runtime": 0.6991,
      "eval_samples_per_second": 1491.822,
      "eval_steps_per_second": 94.401,
      "step": 1069
    },
    {
      "epoch": 1.4,
      "grad_norm": 4.944720268249512,
      "learning_rate": 2.8259749184815627e-05,
      "loss": 0.3959,
      "step": 1500
    },
    {
      "epoch": 1.87,
      "grad_norm": 9.598797798156738,
      "learning_rate": 1.9982142510880178e-05,
      "loss": 0.3603,
      "step": 2000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5668240785598755,
      "eval_matthews_correlation": 0.43881557658403864,
      "eval_runtime": 1.2379,
      "eval_samples_per_second": 842.559,
      "eval_steps_per_second": 53.316,
      "step": 2138
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.8520996570587158,
      "learning_rate": 1.1704535836944727e-05,
      "loss": 0.2352,
      "step": 2500
    },
    {
      "epoch": 2.81,
      "grad_norm": 1.3932373523712158,
      "learning_rate": 3.426929163009277e-06,
      "loss": 0.2377,
      "step": 3000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.8578255772590637,
      "eval_matthews_correlation": 0.47078712112764887,
      "eval_runtime": 1.3062,
      "eval_samples_per_second": 798.53,
      "eval_steps_per_second": 50.53,
      "step": 3207
    }
  ],
  "logging_steps": 500,
  "max_steps": 3207,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 112923282846480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.309256920662198e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 8,
    "seed": 37
  }
}