Hugging Face's logo

noniewiem
/
cola-pixel-handwritten-mean-vatrpp-256-64-4-2e-5-15000-42

PyTorch
English
pixel
Generated from Trainer
Eval Results
Model card Files Community
cola-pixel-handwritten-mean-vatrpp-256-64-4-2e-5-15000-42
File size: 4,708 Bytes 
5497460
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
 
{
  "best_metric": 0.00286100001416597,
  "best_model_checkpoint": "cola-pixel-handwritten-mean-vatrpp-256-64-4-2e-5-15000-42/checkpoint-100",
  "epoch": 33.32835820895522,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.03,
      "learning_rate": 9.800000000000001e-06,
      "loss": 0.655,
      "step": 100
    },
    {
      "epoch": 3.03,
      "eval_loss": 0.6341390013694763,
      "eval_matthews_correlation": 0.00286100001416597,
      "eval_runtime": 7.8213,
      "eval_samples_per_second": 133.354,
      "eval_steps_per_second": 16.749,
      "step": 100
    },
    {
      "epoch": 6.06,
      "learning_rate": 1.98e-05,
      "loss": 0.6174,
      "step": 200
    },
    {
      "epoch": 6.06,
      "eval_loss": 0.6281591057777405,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.9503,
      "eval_samples_per_second": 131.19,
      "eval_steps_per_second": 16.477,
      "step": 200
    },
    {
      "epoch": 9.09,
      "learning_rate": 1.9867567567567568e-05,
      "loss": 0.6196,
      "step": 300
    },
    {
      "epoch": 9.09,
      "eval_loss": 0.6198328137397766,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.8212,
      "eval_samples_per_second": 133.356,
      "eval_steps_per_second": 16.749,
      "step": 300
    },
    {
      "epoch": 12.12,
      "learning_rate": 1.9733783783783785e-05,
      "loss": 0.6158,
      "step": 400
    },
    {
      "epoch": 12.12,
      "eval_loss": 0.6199322938919067,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.8954,
      "eval_samples_per_second": 132.102,
      "eval_steps_per_second": 16.592,
      "step": 400
    },
    {
      "epoch": 15.15,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.6175,
      "step": 500
    },
    {
      "epoch": 15.15,
      "eval_loss": 0.6180645823478699,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 8.2397,
      "eval_samples_per_second": 126.583,
      "eval_steps_per_second": 15.899,
      "step": 500
    },
    {
      "epoch": 18.18,
      "learning_rate": 1.9464864864864867e-05,
      "loss": 0.6152,
      "step": 600
    },
    {
      "epoch": 18.18,
      "eval_loss": 0.619079053401947,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.8304,
      "eval_samples_per_second": 133.198,
      "eval_steps_per_second": 16.73,
      "step": 600
    },
    {
      "epoch": 21.21,
      "learning_rate": 1.932972972972973e-05,
      "loss": 0.617,
      "step": 700
    },
    {
      "epoch": 21.21,
      "eval_loss": 0.6184842586517334,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 8.2213,
      "eval_samples_per_second": 126.865,
      "eval_steps_per_second": 15.934,
      "step": 700
    },
    {
      "epoch": 24.24,
      "learning_rate": 1.9194594594594596e-05,
      "loss": 0.6191,
      "step": 800
    },
    {
      "epoch": 24.24,
      "eval_loss": 0.6185177564620972,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.887,
      "eval_samples_per_second": 132.243,
      "eval_steps_per_second": 16.61,
      "step": 800
    },
    {
      "epoch": 27.27,
      "learning_rate": 1.905945945945946e-05,
      "loss": 0.6162,
      "step": 900
    },
    {
      "epoch": 27.27,
      "eval_loss": 0.6183082461357117,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.8268,
      "eval_samples_per_second": 133.26,
      "eval_steps_per_second": 16.737,
      "step": 900
    },
    {
      "epoch": 30.3,
      "learning_rate": 1.8924324324324325e-05,
      "loss": 0.6166,
      "step": 1000
    },
    {
      "epoch": 30.3,
      "eval_loss": 0.6183302402496338,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.795,
      "eval_samples_per_second": 133.803,
      "eval_steps_per_second": 16.806,
      "step": 1000
    },
    {
      "epoch": 33.33,
      "learning_rate": 1.878918918918919e-05,
      "loss": 0.6177,
      "step": 1100
    },
    {
      "epoch": 33.33,
      "eval_loss": 0.6182125210762024,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.8695,
      "eval_samples_per_second": 132.537,
      "eval_steps_per_second": 16.647,
      "step": 1100
    },
    {
      "epoch": 33.33,
      "step": 1100,
      "total_flos": 7.341930418964005e+18,
      "train_loss": 0.6206500174782493,
      "train_runtime": 3140.0413,
      "train_samples_per_second": 1222.914,
      "train_steps_per_second": 4.777
    }
  ],
  "max_steps": 15000,
  "num_train_epochs": 455,
  "total_flos": 7.341930418964005e+18,
  "trial_name": null,
  "trial_params": null
}