Hugging Face's logo

lizardp1
/
steg_schemes

Safetensors
Model card Files
xet
Community
steg_schemes
File size: 4,213 Bytes
8b32d7f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
 
{
  "best_global_step": 150,
  "best_metric": 0.9,
  "best_model_checkpoint": "./models/punctuation/decoder_model_simple/checkpoint-150",
  "epoch": 1.4047058823529412,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 1.3681155443191528,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.7202,
      "step": 10
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 0.7711533308029175,
      "learning_rate": 5.757575757575758e-05,
      "loss": 0.3185,
      "step": 20
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 1.2256836891174316,
      "learning_rate": 8.787878787878789e-05,
      "loss": 0.1827,
      "step": 30
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 0.888201892375946,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.1346,
      "step": 40
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.853918731212616,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0721,
      "step": 50
    },
    {
      "epoch": 0.47058823529411764,
      "eval_loss": 0.04328128695487976,
      "eval_model_preparation_time": 0.0162,
      "eval_runtime": 2.2686,
      "eval_samples_per_second": 44.081,
      "eval_steps_per_second": 22.04,
      "step": 50
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.48631730675697327,
      "learning_rate": 9.800249271929645e-05,
      "loss": 0.042,
      "step": 60
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.5516029596328735,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0218,
      "step": 70
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.28095027804374695,
      "learning_rate": 9.38363377853754e-05,
      "loss": 0.0127,
      "step": 80
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 0.8756083846092224,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.0124,
      "step": 90
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.5514245629310608,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0119,
      "step": 100
    },
    {
      "epoch": 0.9411764705882353,
      "eval_loss": 0.004549662582576275,
      "eval_model_preparation_time": 0.0162,
      "eval_runtime": 2.2779,
      "eval_samples_per_second": 43.9,
      "eval_steps_per_second": 21.95,
      "step": 100
    },
    {
      "epoch": 1.0282352941176471,
      "grad_norm": 0.48209479451179504,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0074,
      "step": 110
    },
    {
      "epoch": 1.1223529411764706,
      "grad_norm": 0.22237619757652283,
      "learning_rate": 7.956548241817912e-05,
      "loss": 0.0033,
      "step": 120
    },
    {
      "epoch": 1.2164705882352942,
      "grad_norm": 0.22323866188526154,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0019,
      "step": 130
    },
    {
      "epoch": 1.3105882352941176,
      "grad_norm": 0.044407621026039124,
      "learning_rate": 7.013733449293687e-05,
      "loss": 0.0022,
      "step": 140
    },
    {
      "epoch": 1.4047058823529412,
      "grad_norm": 0.1491803228855133,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.0026,
      "step": 150
    },
    {
      "epoch": 1.4047058823529412,
      "eval_loss": 0.00037357292603701353,
      "eval_model_preparation_time": 0.0162,
      "eval_runtime": 2.317,
      "eval_samples_per_second": 43.159,
      "eval_steps_per_second": 21.579,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 321,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0049284593389568e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}