Hugging Face's logo

spidyun
/
chatbot-roberta

TensorBoard
Safetensors
roberta
Model card Files
xet
 Metrics Community
chatbot-roberta
File size: 3,016 Bytes
e99fcf5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
119
120
121
122
123
{
  "best_metric": 1.0,
  "best_model_checkpoint": "./roberta-kor-cls-jsonl/checkpoint-96",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 384,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5208333333333334,
      "grad_norm": 0.22559186816215515,
      "learning_rate": 1.990740740740741e-05,
      "loss": 0.908,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 1.0,
      "eval_f1_macro": 1.0,
      "eval_loss": 0.0010595795465633273,
      "eval_runtime": 0.3804,
      "eval_samples_per_second": 1006.958,
      "eval_steps_per_second": 31.55,
      "step": 96
    },
    {
      "epoch": 1.0416666666666667,
      "grad_norm": 0.02184768207371235,
      "learning_rate": 1.7592592592592595e-05,
      "loss": 0.0046,
      "step": 100
    },
    {
      "epoch": 1.5625,
      "grad_norm": 0.013300820253789425,
      "learning_rate": 1.5277777777777777e-05,
      "loss": 0.0015,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 1.0,
      "eval_f1_macro": 1.0,
      "eval_loss": 0.0005370556027628481,
      "eval_runtime": 0.3421,
      "eval_samples_per_second": 1119.696,
      "eval_steps_per_second": 35.082,
      "step": 192
    },
    {
      "epoch": 2.0833333333333335,
      "grad_norm": 0.011498144827783108,
      "learning_rate": 1.2962962962962964e-05,
      "loss": 0.0011,
      "step": 200
    },
    {
      "epoch": 2.6041666666666665,
      "grad_norm": 0.011683397926390171,
      "learning_rate": 1.064814814814815e-05,
      "loss": 0.0009,
      "step": 250
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 1.0,
      "eval_f1_macro": 1.0,
      "eval_loss": 0.0003851001674775034,
      "eval_runtime": 0.3369,
      "eval_samples_per_second": 1136.881,
      "eval_steps_per_second": 35.62,
      "step": 288
    },
    {
      "epoch": 3.125,
      "grad_norm": 0.008904162794351578,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.0008,
      "step": 300
    },
    {
      "epoch": 3.6458333333333335,
      "grad_norm": 0.006881843786686659,
      "learning_rate": 6.018518518518519e-06,
      "loss": 0.0007,
      "step": 350
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 1.0,
      "eval_f1_macro": 1.0,
      "eval_loss": 0.0003235470794606954,
      "eval_runtime": 0.3359,
      "eval_samples_per_second": 1140.255,
      "eval_steps_per_second": 35.726,
      "step": 384
    }
  ],
  "logging_steps": 50,
  "max_steps": 480,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 339568651757064.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}