Hugging Face's logo

tmnam20
/
gpt1_original-pretrain_xnli

Text Classification
Transformers
PyTorch
openai-gpt
Inference Endpoints
Model card Files Community
gpt1_original-pretrain_xnli
File size: 4,629 Bytes 
c861702
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.1149991750717163,
  "best_model_checkpoint": "/kaggle/output/checkpoint-9000",
  "epoch": 176.0,
  "eval_steps": 1000,
  "global_step": 11000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2.7777777777777777e-11,
      "loss": 1.2395,
      "step": 1
    },
    {
      "epoch": 16.0,
      "learning_rate": 2.7638888888888893e-08,
      "loss": 1.1422,
      "step": 1000
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.33073852295409184,
      "eval_loss": 1.1557353734970093,
      "eval_runtime": 54.1805,
      "eval_samples_per_second": 92.469,
      "eval_steps_per_second": 11.572,
      "step": 1000
    },
    {
      "epoch": 32.0,
      "learning_rate": 5.541666666666667e-08,
      "loss": 1.1401,
      "step": 2000
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.3311377245508982,
      "eval_loss": 1.1507551670074463,
      "eval_runtime": 53.98,
      "eval_samples_per_second": 92.812,
      "eval_steps_per_second": 11.615,
      "step": 2000
    },
    {
      "epoch": 48.0,
      "learning_rate": 8.316666666666666e-08,
      "loss": 1.1287,
      "step": 3000
    },
    {
      "epoch": 48.0,
      "eval_accuracy": 0.3321357285429142,
      "eval_loss": 1.1441665887832642,
      "eval_runtime": 53.9873,
      "eval_samples_per_second": 92.8,
      "eval_steps_per_second": 11.614,
      "step": 3000
    },
    {
      "epoch": 64.0,
      "learning_rate": 1.1094444444444445e-07,
      "loss": 1.117,
      "step": 4000
    },
    {
      "epoch": 64.0,
      "eval_accuracy": 0.3287425149700599,
      "eval_loss": 1.134506344795227,
      "eval_runtime": 54.0067,
      "eval_samples_per_second": 92.766,
      "eval_steps_per_second": 11.61,
      "step": 4000
    },
    {
      "epoch": 80.0,
      "learning_rate": 1.3872222222222222e-07,
      "loss": 1.1111,
      "step": 5000
    },
    {
      "epoch": 80.0,
      "eval_accuracy": 0.32954091816367265,
      "eval_loss": 1.1283142566680908,
      "eval_runtime": 54.0921,
      "eval_samples_per_second": 92.62,
      "eval_steps_per_second": 11.591,
      "step": 5000
    },
    {
      "epoch": 96.0,
      "learning_rate": 1.6650000000000002e-07,
      "loss": 1.1053,
      "step": 6000
    },
    {
      "epoch": 96.0,
      "eval_accuracy": 0.32894211576846305,
      "eval_loss": 1.1218452453613281,
      "eval_runtime": 54.0607,
      "eval_samples_per_second": 92.674,
      "eval_steps_per_second": 11.598,
      "step": 6000
    },
    {
      "epoch": 112.0,
      "learning_rate": 1.9422222222222223e-07,
      "loss": 1.0952,
      "step": 7000
    },
    {
      "epoch": 112.0,
      "eval_accuracy": 0.33073852295409184,
      "eval_loss": 1.118302583694458,
      "eval_runtime": 53.9252,
      "eval_samples_per_second": 92.906,
      "eval_steps_per_second": 11.627,
      "step": 7000
    },
    {
      "epoch": 128.0,
      "learning_rate": 2.2197222222222225e-07,
      "loss": 1.0909,
      "step": 8000
    },
    {
      "epoch": 128.0,
      "eval_accuracy": 0.3281437125748503,
      "eval_loss": 1.1167163848876953,
      "eval_runtime": 54.095,
      "eval_samples_per_second": 92.615,
      "eval_steps_per_second": 11.591,
      "step": 8000
    },
    {
      "epoch": 144.0,
      "learning_rate": 2.4975e-07,
      "loss": 1.0838,
      "step": 9000
    },
    {
      "epoch": 144.0,
      "eval_accuracy": 0.3317365269461078,
      "eval_loss": 1.1149991750717163,
      "eval_runtime": 54.0536,
      "eval_samples_per_second": 92.686,
      "eval_steps_per_second": 11.6,
      "step": 9000
    },
    {
      "epoch": 160.0,
      "learning_rate": 2.775277777777778e-07,
      "loss": 1.0746,
      "step": 10000
    },
    {
      "epoch": 160.0,
      "eval_accuracy": 0.3347305389221557,
      "eval_loss": 1.1178398132324219,
      "eval_runtime": 54.1273,
      "eval_samples_per_second": 92.56,
      "eval_steps_per_second": 11.584,
      "step": 10000
    },
    {
      "epoch": 176.0,
      "learning_rate": 3.0530555555555556e-07,
      "loss": 1.0722,
      "step": 11000
    },
    {
      "epoch": 176.0,
      "eval_accuracy": 0.3373253493013972,
      "eval_loss": 1.1214321851730347,
      "eval_runtime": 54.046,
      "eval_samples_per_second": 92.699,
      "eval_steps_per_second": 11.601,
      "step": 11000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 10000000,
  "num_train_epochs": 161291,
  "save_steps": 1000,
  "total_flos": 2.2993906434048e+16,
  "trial_name": null,
  "trial_params": null
}