Hugging Face's logo

Riyagarg01
/
practice

Model card Files
xet
Community
practice
File size: 3,864 Bytes
a84b8fb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
192
193
194
195
196
197
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 68.18181818181819,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.27,
      "learning_rate": 3e-06,
      "loss": 6.9841,
      "step": 50
    },
    {
      "epoch": 4.55,
      "learning_rate": 6e-06,
      "loss": 3.6549,
      "step": 100
    },
    {
      "epoch": 6.82,
      "learning_rate": 9e-06,
      "loss": 2.3101,
      "step": 150
    },
    {
      "epoch": 9.09,
      "learning_rate": 1.2e-05,
      "loss": 1.9692,
      "step": 200
    },
    {
      "epoch": 11.36,
      "learning_rate": 1.5e-05,
      "loss": 1.7899,
      "step": 250
    },
    {
      "epoch": 13.64,
      "learning_rate": 1.8e-05,
      "loss": 1.6814,
      "step": 300
    },
    {
      "epoch": 15.91,
      "learning_rate": 2.1e-05,
      "loss": 1.6234,
      "step": 350
    },
    {
      "epoch": 18.18,
      "learning_rate": 2.4e-05,
      "loss": 1.5821,
      "step": 400
    },
    {
      "epoch": 20.45,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 1.5501,
      "step": 450
    },
    {
      "epoch": 22.73,
      "learning_rate": 3e-05,
      "loss": 1.5385,
      "step": 500
    },
    {
      "epoch": 25.0,
      "learning_rate": 2.911764705882353e-05,
      "loss": 1.5289,
      "step": 550
    },
    {
      "epoch": 27.27,
      "learning_rate": 2.823529411764706e-05,
      "loss": 1.5101,
      "step": 600
    },
    {
      "epoch": 29.55,
      "learning_rate": 2.735294117647059e-05,
      "loss": 1.4921,
      "step": 650
    },
    {
      "epoch": 31.82,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.4881,
      "step": 700
    },
    {
      "epoch": 34.09,
      "learning_rate": 2.5588235294117648e-05,
      "loss": 1.4834,
      "step": 750
    },
    {
      "epoch": 36.36,
      "learning_rate": 2.4705882352941174e-05,
      "loss": 1.4783,
      "step": 800
    },
    {
      "epoch": 38.64,
      "learning_rate": 2.3823529411764704e-05,
      "loss": 1.4742,
      "step": 850
    },
    {
      "epoch": 40.91,
      "learning_rate": 2.2941176470588233e-05,
      "loss": 1.4671,
      "step": 900
    },
    {
      "epoch": 43.18,
      "learning_rate": 2.2058823529411766e-05,
      "loss": 1.4711,
      "step": 950
    },
    {
      "epoch": 45.45,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.465,
      "step": 1000
    },
    {
      "epoch": 47.73,
      "learning_rate": 2.0294117647058825e-05,
      "loss": 1.4592,
      "step": 1050
    },
    {
      "epoch": 50.0,
      "learning_rate": 1.9411764705882355e-05,
      "loss": 1.4607,
      "step": 1100
    },
    {
      "epoch": 52.27,
      "learning_rate": 1.8529411764705884e-05,
      "loss": 1.4629,
      "step": 1150
    },
    {
      "epoch": 54.55,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.4577,
      "step": 1200
    },
    {
      "epoch": 56.82,
      "learning_rate": 1.6764705882352943e-05,
      "loss": 1.4557,
      "step": 1250
    },
    {
      "epoch": 59.09,
      "learning_rate": 1.5882352941176473e-05,
      "loss": 1.4525,
      "step": 1300
    },
    {
      "epoch": 61.36,
      "learning_rate": 1.5e-05,
      "loss": 1.4519,
      "step": 1350
    },
    {
      "epoch": 63.64,
      "learning_rate": 1.411764705882353e-05,
      "loss": 1.4513,
      "step": 1400
    },
    {
      "epoch": 65.91,
      "learning_rate": 1.323529411764706e-05,
      "loss": 1.4517,
      "step": 1450
    },
    {
      "epoch": 68.18,
      "learning_rate": 1.2352941176470587e-05,
      "loss": 1.4493,
      "step": 1500
    }
  ],
  "max_steps": 2200,
  "num_train_epochs": 100,
  "total_flos": 3534032511959040.0,
  "trial_name": null,
  "trial_params": null
}