Hugging Face's logo

ModelTC
/
bart-base-cola

Text Classification
Transformers
PyTorch
bart
Model card Files
xet
Community
1
bart-base-cola
File size: 4,508 Bytes 
1290f12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.208955223880597,
  "global_step": 2200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.75,
      "learning_rate": 3.92749244712991e-05,
      "loss": 0.5968,
      "step": 200
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.5482025742530823,
      "eval_matthews_correlation": 0.4044551659076911,
      "eval_runtime": 7.0014,
      "eval_samples_per_second": 148.97,
      "eval_steps_per_second": 4.713,
      "step": 200
    },
    {
      "epoch": 1.49,
      "learning_rate": 3.8066465256797584e-05,
      "loss": 0.4748,
      "step": 400
    },
    {
      "epoch": 1.49,
      "eval_loss": 0.7374169826507568,
      "eval_matthews_correlation": 0.295093127326412,
      "eval_runtime": 4.195,
      "eval_samples_per_second": 248.628,
      "eval_steps_per_second": 7.866,
      "step": 400
    },
    {
      "epoch": 2.24,
      "learning_rate": 3.685800604229608e-05,
      "loss": 0.4165,
      "step": 600
    },
    {
      "epoch": 2.24,
      "eval_loss": 0.7154484391212463,
      "eval_matthews_correlation": 0.4656950548188858,
      "eval_runtime": 4.0204,
      "eval_samples_per_second": 259.424,
      "eval_steps_per_second": 8.208,
      "step": 600
    },
    {
      "epoch": 2.99,
      "learning_rate": 3.564954682779456e-05,
      "loss": 0.3461,
      "step": 800
    },
    {
      "epoch": 2.99,
      "eval_loss": 0.5880667567253113,
      "eval_matthews_correlation": 0.4966579188966687,
      "eval_runtime": 4.1325,
      "eval_samples_per_second": 252.389,
      "eval_steps_per_second": 7.985,
      "step": 800
    },
    {
      "epoch": 3.73,
      "learning_rate": 3.4441087613293056e-05,
      "loss": 0.2666,
      "step": 1000
    },
    {
      "epoch": 3.73,
      "eval_loss": 0.6024960875511169,
      "eval_matthews_correlation": 0.5243351914860497,
      "eval_runtime": 4.2714,
      "eval_samples_per_second": 244.185,
      "eval_steps_per_second": 7.726,
      "step": 1000
    },
    {
      "epoch": 4.48,
      "learning_rate": 3.323262839879154e-05,
      "loss": 0.233,
      "step": 1200
    },
    {
      "epoch": 4.48,
      "eval_loss": 0.7757831811904907,
      "eval_matthews_correlation": 0.5180330680945964,
      "eval_runtime": 5.4027,
      "eval_samples_per_second": 193.052,
      "eval_steps_per_second": 6.108,
      "step": 1200
    },
    {
      "epoch": 5.22,
      "learning_rate": 3.2024169184290035e-05,
      "loss": 0.2067,
      "step": 1400
    },
    {
      "epoch": 5.22,
      "eval_loss": 0.8261585831642151,
      "eval_matthews_correlation": 0.4812305179480984,
      "eval_runtime": 4.5778,
      "eval_samples_per_second": 227.84,
      "eval_steps_per_second": 7.209,
      "step": 1400
    },
    {
      "epoch": 5.97,
      "learning_rate": 3.081570996978852e-05,
      "loss": 0.174,
      "step": 1600
    },
    {
      "epoch": 5.97,
      "eval_loss": 1.0030035972595215,
      "eval_matthews_correlation": 0.4690871215881841,
      "eval_runtime": 4.1699,
      "eval_samples_per_second": 250.124,
      "eval_steps_per_second": 7.914,
      "step": 1600
    },
    {
      "epoch": 6.72,
      "learning_rate": 2.9607250755287014e-05,
      "loss": 0.1504,
      "step": 1800
    },
    {
      "epoch": 6.72,
      "eval_loss": 1.007808804512024,
      "eval_matthews_correlation": 0.505928717066083,
      "eval_runtime": 5.5718,
      "eval_samples_per_second": 187.193,
      "eval_steps_per_second": 5.923,
      "step": 1800
    },
    {
      "epoch": 7.46,
      "learning_rate": 2.83987915407855e-05,
      "loss": 0.1261,
      "step": 2000
    },
    {
      "epoch": 7.46,
      "eval_loss": 1.0862607955932617,
      "eval_matthews_correlation": 0.4929950873963667,
      "eval_runtime": 4.1938,
      "eval_samples_per_second": 248.698,
      "eval_steps_per_second": 7.869,
      "step": 2000
    },
    {
      "epoch": 8.21,
      "learning_rate": 2.719033232628399e-05,
      "loss": 0.1141,
      "step": 2200
    },
    {
      "epoch": 8.21,
      "eval_loss": 0.9651995301246643,
      "eval_matthews_correlation": 0.5632084517291658,
      "eval_runtime": 4.2997,
      "eval_samples_per_second": 242.575,
      "eval_steps_per_second": 7.675,
      "step": 2200
    }
  ],
  "max_steps": 6700,
  "num_train_epochs": 25,
  "total_flos": 5382361281024000.0,
  "trial_name": null,
  "trial_params": null
}