Hugging Face's logo

wennycooper
/
hw1

TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
hw1
File size: 2,846 Bytes 
9f340e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.47051816449999595,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-4276",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 4276,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23386342376052385,
      "grad_norm": 4.184101104736328,
      "learning_rate": 1.7853399770993998e-05,
      "loss": 0.593,
      "step": 500
    },
    {
      "epoch": 0.4677268475210477,
      "grad_norm": 2.0551953315734863,
      "learning_rate": 1.548933730131789e-05,
      "loss": 0.5753,
      "step": 1000
    },
    {
      "epoch": 0.7015902712815716,
      "grad_norm": 16.489328384399414,
      "learning_rate": 1.3125274831641774e-05,
      "loss": 0.5518,
      "step": 1500
    },
    {
      "epoch": 0.9354536950420954,
      "grad_norm": 47.566402435302734,
      "learning_rate": 1.0761212361965661e-05,
      "loss": 0.5419,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6548950672149658,
      "eval_matthews_correlation": 0.4413232484146929,
      "eval_runtime": 0.7355,
      "eval_samples_per_second": 1418.114,
      "eval_steps_per_second": 89.737,
      "step": 2138
    },
    {
      "epoch": 1.1693171188026192,
      "grad_norm": 41.39296340942383,
      "learning_rate": 8.39714989228955e-06,
      "loss": 0.457,
      "step": 2500
    },
    {
      "epoch": 1.4031805425631432,
      "grad_norm": 0.10284680873155594,
      "learning_rate": 6.0330874226134376e-06,
      "loss": 0.403,
      "step": 3000
    },
    {
      "epoch": 1.637043966323667,
      "grad_norm": 15.211405754089355,
      "learning_rate": 3.6690249529373256e-06,
      "loss": 0.4216,
      "step": 3500
    },
    {
      "epoch": 1.8709073900841908,
      "grad_norm": 0.4435730576515198,
      "learning_rate": 1.304962483261214e-06,
      "loss": 0.408,
      "step": 4000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8785123229026794,
      "eval_matthews_correlation": 0.47051816449999595,
      "eval_runtime": 0.8593,
      "eval_samples_per_second": 1213.801,
      "eval_steps_per_second": 76.808,
      "step": 4276
    }
  ],
  "logging_steps": 500,
  "max_steps": 4276,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 65141619465252.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.021746224067011e-05,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 4,
    "seed": 21
  }
}