Upload folder using huggingface_hub
Browse files- expdecaybackward_42/epoch0/metadata.json +6 -0
- expdecaybackward_42/epoch0/metrics.json +562 -0
- expdecaybackward_42/epoch0/model.pt +3 -0
- expdecaybackward_42/epoch0/optimizer.pt +3 -0
- expdecaybackward_42/epoch0/scheduler.pt +3 -0
- expdecaybackward_42/epoch0/tokenizer/merges.txt +0 -0
- expdecaybackward_42/epoch0/tokenizer/special_tokens_map.json +6 -0
- expdecaybackward_42/epoch0/tokenizer/tokenizer.json +0 -0
- expdecaybackward_42/epoch0/tokenizer/tokenizer_config.json +21 -0
- expdecaybackward_42/epoch0/tokenizer/vocab.json +0 -0
expdecaybackward_42/epoch0/metadata.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch_num": 0,
|
| 3 |
+
"global_batch_num": 134,
|
| 4 |
+
"device": "cuda",
|
| 5 |
+
"dtype": "bfloat16"
|
| 6 |
+
}
|
expdecaybackward_42/epoch0/metrics.json
ADDED
|
@@ -0,0 +1,562 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"training": {
|
| 3 |
+
"effective_batch_nums": [
|
| 4 |
+
1,
|
| 5 |
+
2,
|
| 6 |
+
3,
|
| 7 |
+
4,
|
| 8 |
+
5,
|
| 9 |
+
6,
|
| 10 |
+
7,
|
| 11 |
+
8,
|
| 12 |
+
9,
|
| 13 |
+
10,
|
| 14 |
+
11,
|
| 15 |
+
12,
|
| 16 |
+
13,
|
| 17 |
+
14,
|
| 18 |
+
15,
|
| 19 |
+
16,
|
| 20 |
+
17,
|
| 21 |
+
18,
|
| 22 |
+
19,
|
| 23 |
+
20,
|
| 24 |
+
21,
|
| 25 |
+
22,
|
| 26 |
+
23,
|
| 27 |
+
24,
|
| 28 |
+
25,
|
| 29 |
+
26,
|
| 30 |
+
27,
|
| 31 |
+
28,
|
| 32 |
+
29,
|
| 33 |
+
30,
|
| 34 |
+
31,
|
| 35 |
+
32,
|
| 36 |
+
33,
|
| 37 |
+
34,
|
| 38 |
+
35,
|
| 39 |
+
36,
|
| 40 |
+
37,
|
| 41 |
+
38,
|
| 42 |
+
39,
|
| 43 |
+
40,
|
| 44 |
+
41,
|
| 45 |
+
42,
|
| 46 |
+
43,
|
| 47 |
+
44,
|
| 48 |
+
45,
|
| 49 |
+
46,
|
| 50 |
+
47,
|
| 51 |
+
48,
|
| 52 |
+
49,
|
| 53 |
+
50,
|
| 54 |
+
51,
|
| 55 |
+
52,
|
| 56 |
+
53,
|
| 57 |
+
54,
|
| 58 |
+
55,
|
| 59 |
+
56,
|
| 60 |
+
57,
|
| 61 |
+
58,
|
| 62 |
+
59,
|
| 63 |
+
60,
|
| 64 |
+
61,
|
| 65 |
+
62,
|
| 66 |
+
63,
|
| 67 |
+
64,
|
| 68 |
+
65,
|
| 69 |
+
66,
|
| 70 |
+
67,
|
| 71 |
+
68,
|
| 72 |
+
69,
|
| 73 |
+
70,
|
| 74 |
+
71,
|
| 75 |
+
72,
|
| 76 |
+
73,
|
| 77 |
+
74,
|
| 78 |
+
75,
|
| 79 |
+
76,
|
| 80 |
+
77,
|
| 81 |
+
78,
|
| 82 |
+
79,
|
| 83 |
+
80,
|
| 84 |
+
81,
|
| 85 |
+
82,
|
| 86 |
+
83,
|
| 87 |
+
84,
|
| 88 |
+
85,
|
| 89 |
+
86,
|
| 90 |
+
87,
|
| 91 |
+
88,
|
| 92 |
+
89,
|
| 93 |
+
90,
|
| 94 |
+
91,
|
| 95 |
+
92,
|
| 96 |
+
93,
|
| 97 |
+
94,
|
| 98 |
+
95,
|
| 99 |
+
96,
|
| 100 |
+
97,
|
| 101 |
+
98,
|
| 102 |
+
99,
|
| 103 |
+
100,
|
| 104 |
+
101,
|
| 105 |
+
102,
|
| 106 |
+
103,
|
| 107 |
+
104,
|
| 108 |
+
105,
|
| 109 |
+
106,
|
| 110 |
+
107,
|
| 111 |
+
108,
|
| 112 |
+
109,
|
| 113 |
+
110,
|
| 114 |
+
111,
|
| 115 |
+
112,
|
| 116 |
+
113,
|
| 117 |
+
114,
|
| 118 |
+
115,
|
| 119 |
+
116,
|
| 120 |
+
117,
|
| 121 |
+
118,
|
| 122 |
+
119,
|
| 123 |
+
120,
|
| 124 |
+
121,
|
| 125 |
+
122,
|
| 126 |
+
123,
|
| 127 |
+
124,
|
| 128 |
+
125,
|
| 129 |
+
126,
|
| 130 |
+
127,
|
| 131 |
+
128,
|
| 132 |
+
129,
|
| 133 |
+
130,
|
| 134 |
+
131,
|
| 135 |
+
132,
|
| 136 |
+
133,
|
| 137 |
+
134
|
| 138 |
+
],
|
| 139 |
+
"losses": [
|
| 140 |
+
11.0,
|
| 141 |
+
10.5,
|
| 142 |
+
9.6875,
|
| 143 |
+
9.1875,
|
| 144 |
+
8.9375,
|
| 145 |
+
8.75,
|
| 146 |
+
8.6875,
|
| 147 |
+
8.625,
|
| 148 |
+
8.5625,
|
| 149 |
+
8.4375,
|
| 150 |
+
8.5,
|
| 151 |
+
8.5,
|
| 152 |
+
8.5,
|
| 153 |
+
8.4375,
|
| 154 |
+
8.375,
|
| 155 |
+
8.375,
|
| 156 |
+
8.4375,
|
| 157 |
+
8.3125,
|
| 158 |
+
8.25,
|
| 159 |
+
8.375,
|
| 160 |
+
8.3125,
|
| 161 |
+
8.25,
|
| 162 |
+
8.3125,
|
| 163 |
+
8.1875,
|
| 164 |
+
8.3125,
|
| 165 |
+
8.1875,
|
| 166 |
+
8.1875,
|
| 167 |
+
8.125,
|
| 168 |
+
8.1875,
|
| 169 |
+
8.1875,
|
| 170 |
+
8.125,
|
| 171 |
+
8.1875,
|
| 172 |
+
8.25,
|
| 173 |
+
8.125,
|
| 174 |
+
8.1875,
|
| 175 |
+
8.125,
|
| 176 |
+
8.0625,
|
| 177 |
+
8.0625,
|
| 178 |
+
8.0625,
|
| 179 |
+
8.0625,
|
| 180 |
+
8.0625,
|
| 181 |
+
7.96875,
|
| 182 |
+
8.0625,
|
| 183 |
+
8.0625,
|
| 184 |
+
8.0,
|
| 185 |
+
8.0625,
|
| 186 |
+
7.96875,
|
| 187 |
+
7.96875,
|
| 188 |
+
8.0,
|
| 189 |
+
7.96875,
|
| 190 |
+
8.0625,
|
| 191 |
+
8.0625,
|
| 192 |
+
7.96875,
|
| 193 |
+
7.96875,
|
| 194 |
+
8.0,
|
| 195 |
+
7.90625,
|
| 196 |
+
7.96875,
|
| 197 |
+
7.90625,
|
| 198 |
+
7.9375,
|
| 199 |
+
7.90625,
|
| 200 |
+
7.9375,
|
| 201 |
+
7.96875,
|
| 202 |
+
7.9375,
|
| 203 |
+
7.90625,
|
| 204 |
+
7.9375,
|
| 205 |
+
7.90625,
|
| 206 |
+
7.875,
|
| 207 |
+
7.90625,
|
| 208 |
+
7.84375,
|
| 209 |
+
7.90625,
|
| 210 |
+
7.84375,
|
| 211 |
+
7.875,
|
| 212 |
+
7.84375,
|
| 213 |
+
7.875,
|
| 214 |
+
7.8125,
|
| 215 |
+
7.8125,
|
| 216 |
+
7.8125,
|
| 217 |
+
7.8125,
|
| 218 |
+
7.84375,
|
| 219 |
+
7.84375,
|
| 220 |
+
7.8125,
|
| 221 |
+
7.8125,
|
| 222 |
+
7.8125,
|
| 223 |
+
7.84375,
|
| 224 |
+
7.84375,
|
| 225 |
+
7.8125,
|
| 226 |
+
7.84375,
|
| 227 |
+
7.75,
|
| 228 |
+
7.75,
|
| 229 |
+
7.75,
|
| 230 |
+
7.75,
|
| 231 |
+
7.71875,
|
| 232 |
+
7.71875,
|
| 233 |
+
7.71875,
|
| 234 |
+
7.75,
|
| 235 |
+
7.65625,
|
| 236 |
+
7.71875,
|
| 237 |
+
7.6875,
|
| 238 |
+
7.71875,
|
| 239 |
+
7.6875,
|
| 240 |
+
7.71875,
|
| 241 |
+
7.65625,
|
| 242 |
+
7.6875,
|
| 243 |
+
7.625,
|
| 244 |
+
7.65625,
|
| 245 |
+
7.65625,
|
| 246 |
+
7.65625,
|
| 247 |
+
7.71875,
|
| 248 |
+
7.59375,
|
| 249 |
+
7.6875,
|
| 250 |
+
7.59375,
|
| 251 |
+
7.6875,
|
| 252 |
+
7.65625,
|
| 253 |
+
7.59375,
|
| 254 |
+
7.59375,
|
| 255 |
+
7.6875,
|
| 256 |
+
7.53125,
|
| 257 |
+
7.625,
|
| 258 |
+
7.625,
|
| 259 |
+
7.5625,
|
| 260 |
+
7.625,
|
| 261 |
+
7.65625,
|
| 262 |
+
7.65625,
|
| 263 |
+
7.5,
|
| 264 |
+
7.625,
|
| 265 |
+
7.53125,
|
| 266 |
+
7.5625,
|
| 267 |
+
7.5625,
|
| 268 |
+
7.5625,
|
| 269 |
+
7.53125,
|
| 270 |
+
7.5625,
|
| 271 |
+
7.59375,
|
| 272 |
+
7.5625,
|
| 273 |
+
7.5
|
| 274 |
+
],
|
| 275 |
+
"accuracies": [
|
| 276 |
+
0.0,
|
| 277 |
+
0.05085149458139812,
|
| 278 |
+
0.04856698223317339,
|
| 279 |
+
0.04240555127216654,
|
| 280 |
+
0.04996124724259226,
|
| 281 |
+
0.0477795861427575,
|
| 282 |
+
0.05124618514750763,
|
| 283 |
+
0.043222955384708515,
|
| 284 |
+
0.03076306141154904,
|
| 285 |
+
0.03304504969665677,
|
| 286 |
+
0.04580896686159844,
|
| 287 |
+
0.06222167243938644,
|
| 288 |
+
0.05796033994334278,
|
| 289 |
+
0.07859154929577465,
|
| 290 |
+
0.08933371461252503,
|
| 291 |
+
0.08567634663125685,
|
| 292 |
+
0.09124295573988477,
|
| 293 |
+
0.10056739231125521,
|
| 294 |
+
0.0984523974022385,
|
| 295 |
+
0.09454139491156942,
|
| 296 |
+
0.10200352411407687,
|
| 297 |
+
0.10664819944598337,
|
| 298 |
+
0.10051464514899294,
|
| 299 |
+
0.103943605772428,
|
| 300 |
+
0.10156933667814014,
|
| 301 |
+
0.10343106674984404,
|
| 302 |
+
0.10701382832938831,
|
| 303 |
+
0.10511932956822737,
|
| 304 |
+
0.10452819164475606,
|
| 305 |
+
0.10800346720600983,
|
| 306 |
+
0.11277915632754343,
|
| 307 |
+
0.11264435889843057,
|
| 308 |
+
0.10788310271573749,
|
| 309 |
+
0.11252536432392547,
|
| 310 |
+
0.11223047013078827,
|
| 311 |
+
0.11455000290883705,
|
| 312 |
+
0.11474489437855288,
|
| 313 |
+
0.1169823036324123,
|
| 314 |
+
0.11985864905572935,
|
| 315 |
+
0.11775801670708703,
|
| 316 |
+
0.11529163825698878,
|
| 317 |
+
0.11487499250554589,
|
| 318 |
+
0.11883422124725791,
|
| 319 |
+
0.10921290031574199,
|
| 320 |
+
0.12061177077955601,
|
| 321 |
+
0.12097526831544564,
|
| 322 |
+
0.11993488750654031,
|
| 323 |
+
0.1202747014786859,
|
| 324 |
+
0.1229905588160245,
|
| 325 |
+
0.12142024897283375,
|
| 326 |
+
0.11663018465510468,
|
| 327 |
+
0.11814345991561181,
|
| 328 |
+
0.1215529102111623,
|
| 329 |
+
0.13023380451530783,
|
| 330 |
+
0.11810982325483821,
|
| 331 |
+
0.12568403521294313,
|
| 332 |
+
0.12310505515248038,
|
| 333 |
+
0.12360916884538213,
|
| 334 |
+
0.12477302204928664,
|
| 335 |
+
0.12646514497223935,
|
| 336 |
+
0.12550735667174023,
|
| 337 |
+
0.12567401960784313,
|
| 338 |
+
0.12542393784300426,
|
| 339 |
+
0.12350290525317206,
|
| 340 |
+
0.12495092815882453,
|
| 341 |
+
0.13060669714568146,
|
| 342 |
+
0.1262027438078093,
|
| 343 |
+
0.12121585794438622,
|
| 344 |
+
0.1301543284301905,
|
| 345 |
+
0.12798634812286688,
|
| 346 |
+
0.1307993966817496,
|
| 347 |
+
0.12905031407425835,
|
| 348 |
+
0.1326709526592636,
|
| 349 |
+
0.1302877450418434,
|
| 350 |
+
0.13194103194103193,
|
| 351 |
+
0.128761447884867,
|
| 352 |
+
0.1345275306564078,
|
| 353 |
+
0.12801769150439216,
|
| 354 |
+
0.13315926892950392,
|
| 355 |
+
0.1291374531224523,
|
| 356 |
+
0.12870275791624106,
|
| 357 |
+
0.13365140343267862,
|
| 358 |
+
0.13199699612962856,
|
| 359 |
+
0.13479501090665025,
|
| 360 |
+
0.13461415714559263,
|
| 361 |
+
0.137320720170888,
|
| 362 |
+
0.13247241421122832,
|
| 363 |
+
0.13982815107869198,
|
| 364 |
+
0.1334387887689961,
|
| 365 |
+
0.1432547782519948,
|
| 366 |
+
0.1406486109496687,
|
| 367 |
+
0.1414382421484852,
|
| 368 |
+
0.13690555927662423,
|
| 369 |
+
0.1370218414383975,
|
| 370 |
+
0.14934622296585487,
|
| 371 |
+
0.1468677494199536,
|
| 372 |
+
0.13908222248436947,
|
| 373 |
+
0.13941404782772004,
|
| 374 |
+
0.13922041272267624,
|
| 375 |
+
0.14304307406259684,
|
| 376 |
+
0.14064657156005522,
|
| 377 |
+
0.14821740966399227,
|
| 378 |
+
0.147179169249845,
|
| 379 |
+
0.14852167376597344,
|
| 380 |
+
0.14393527332064182,
|
| 381 |
+
0.14931005350605464,
|
| 382 |
+
0.14665194518412678,
|
| 383 |
+
0.13979098775143275,
|
| 384 |
+
0.1530809972871722,
|
| 385 |
+
0.14539150534527592,
|
| 386 |
+
0.1499457373688653,
|
| 387 |
+
0.1460943904438459,
|
| 388 |
+
0.14810344827586208,
|
| 389 |
+
0.15103080843178132,
|
| 390 |
+
0.15735267231397404,
|
| 391 |
+
0.1459029338516674,
|
| 392 |
+
0.16078298257524326,
|
| 393 |
+
0.15454322801861375,
|
| 394 |
+
0.15575379125780553,
|
| 395 |
+
0.15684614516311096,
|
| 396 |
+
0.15075935300654403,
|
| 397 |
+
0.15716763351474194,
|
| 398 |
+
0.15491754812430195,
|
| 399 |
+
0.1621891790578533,
|
| 400 |
+
0.15062445541678768,
|
| 401 |
+
0.160730705572243,
|
| 402 |
+
0.1579309912956353,
|
| 403 |
+
0.159550975340449,
|
| 404 |
+
0.1595964363679273,
|
| 405 |
+
0.16722699539285268,
|
| 406 |
+
0.15734518189391836,
|
| 407 |
+
0.15240268796754153,
|
| 408 |
+
0.15341150738197945,
|
| 409 |
+
0.1637468716481945
|
| 410 |
+
],
|
| 411 |
+
"grad_norms": [
|
| 412 |
+
0.23046875,
|
| 413 |
+
0.69140625,
|
| 414 |
+
0.8359375,
|
| 415 |
+
0.76171875,
|
| 416 |
+
0.58203125,
|
| 417 |
+
0.404296875,
|
| 418 |
+
0.333984375,
|
| 419 |
+
0.30859375,
|
| 420 |
+
0.376953125,
|
| 421 |
+
0.31640625,
|
| 422 |
+
0.251953125,
|
| 423 |
+
0.267578125,
|
| 424 |
+
0.50390625,
|
| 425 |
+
0.28125,
|
| 426 |
+
0.27734375,
|
| 427 |
+
0.296875,
|
| 428 |
+
0.2177734375,
|
| 429 |
+
0.1787109375,
|
| 430 |
+
0.1904296875,
|
| 431 |
+
0.1904296875,
|
| 432 |
+
0.177734375,
|
| 433 |
+
0.1513671875,
|
| 434 |
+
0.1552734375,
|
| 435 |
+
0.146484375,
|
| 436 |
+
0.1689453125,
|
| 437 |
+
0.126953125,
|
| 438 |
+
0.140625,
|
| 439 |
+
0.1416015625,
|
| 440 |
+
0.1533203125,
|
| 441 |
+
0.1171875,
|
| 442 |
+
0.1357421875,
|
| 443 |
+
0.1181640625,
|
| 444 |
+
0.1171875,
|
| 445 |
+
0.1533203125,
|
| 446 |
+
0.1171875,
|
| 447 |
+
0.130859375,
|
| 448 |
+
0.111328125,
|
| 449 |
+
0.12158203125,
|
| 450 |
+
0.12353515625,
|
| 451 |
+
0.123046875,
|
| 452 |
+
0.1533203125,
|
| 453 |
+
0.1162109375,
|
| 454 |
+
0.177734375,
|
| 455 |
+
0.173828125,
|
| 456 |
+
0.134765625,
|
| 457 |
+
0.181640625,
|
| 458 |
+
0.0927734375,
|
| 459 |
+
0.134765625,
|
| 460 |
+
0.09375,
|
| 461 |
+
0.1474609375,
|
| 462 |
+
0.1171875,
|
| 463 |
+
0.12255859375,
|
| 464 |
+
0.373046875,
|
| 465 |
+
0.31640625,
|
| 466 |
+
0.12451171875,
|
| 467 |
+
0.146484375,
|
| 468 |
+
0.11962890625,
|
| 469 |
+
0.10205078125,
|
| 470 |
+
0.1005859375,
|
| 471 |
+
0.09814453125,
|
| 472 |
+
0.1083984375,
|
| 473 |
+
0.11572265625,
|
| 474 |
+
0.11376953125,
|
| 475 |
+
0.10546875,
|
| 476 |
+
0.09912109375,
|
| 477 |
+
0.11328125,
|
| 478 |
+
0.091796875,
|
| 479 |
+
0.11669921875,
|
| 480 |
+
0.109375,
|
| 481 |
+
0.119140625,
|
| 482 |
+
0.10400390625,
|
| 483 |
+
0.1025390625,
|
| 484 |
+
0.103515625,
|
| 485 |
+
0.1083984375,
|
| 486 |
+
0.0986328125,
|
| 487 |
+
0.125,
|
| 488 |
+
0.14453125,
|
| 489 |
+
0.12060546875,
|
| 490 |
+
0.140625,
|
| 491 |
+
0.1298828125,
|
| 492 |
+
0.095703125,
|
| 493 |
+
0.201171875,
|
| 494 |
+
0.1494140625,
|
| 495 |
+
0.11376953125,
|
| 496 |
+
0.173828125,
|
| 497 |
+
0.1318359375,
|
| 498 |
+
0.1181640625,
|
| 499 |
+
0.125,
|
| 500 |
+
0.087890625,
|
| 501 |
+
0.1123046875,
|
| 502 |
+
0.09033203125,
|
| 503 |
+
0.1259765625,
|
| 504 |
+
0.1298828125,
|
| 505 |
+
0.10400390625,
|
| 506 |
+
0.1142578125,
|
| 507 |
+
0.11376953125,
|
| 508 |
+
0.11572265625,
|
| 509 |
+
0.1123046875,
|
| 510 |
+
0.10498046875,
|
| 511 |
+
0.11279296875,
|
| 512 |
+
0.1357421875,
|
| 513 |
+
0.1328125,
|
| 514 |
+
0.138671875,
|
| 515 |
+
0.189453125,
|
| 516 |
+
0.1298828125,
|
| 517 |
+
0.1904296875,
|
| 518 |
+
0.1455078125,
|
| 519 |
+
0.1484375,
|
| 520 |
+
0.158203125,
|
| 521 |
+
0.11474609375,
|
| 522 |
+
0.10693359375,
|
| 523 |
+
0.11083984375,
|
| 524 |
+
0.1083984375,
|
| 525 |
+
0.1279296875,
|
| 526 |
+
0.10595703125,
|
| 527 |
+
0.12158203125,
|
| 528 |
+
0.11376953125,
|
| 529 |
+
0.12353515625,
|
| 530 |
+
0.1015625,
|
| 531 |
+
0.1298828125,
|
| 532 |
+
0.0927734375,
|
| 533 |
+
0.1298828125,
|
| 534 |
+
0.12890625,
|
| 535 |
+
0.0947265625,
|
| 536 |
+
0.1513671875,
|
| 537 |
+
0.11376953125,
|
| 538 |
+
0.09814453125,
|
| 539 |
+
0.119140625,
|
| 540 |
+
0.10009765625,
|
| 541 |
+
0.1455078125,
|
| 542 |
+
0.1240234375,
|
| 543 |
+
0.11376953125,
|
| 544 |
+
0.1259765625,
|
| 545 |
+
0.11376953125
|
| 546 |
+
]
|
| 547 |
+
},
|
| 548 |
+
"eval": {
|
| 549 |
+
"effective_batch_nums": [
|
| 550 |
+
133
|
| 551 |
+
],
|
| 552 |
+
"losses": [
|
| 553 |
+
7.615808823529412
|
| 554 |
+
],
|
| 555 |
+
"perplexities": [
|
| 556 |
+
2030.0360358518099
|
| 557 |
+
],
|
| 558 |
+
"accuracies": [
|
| 559 |
+
0.1593664725536041
|
| 560 |
+
]
|
| 561 |
+
}
|
| 562 |
+
}
|
expdecaybackward_42/epoch0/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d352dcd37098c35a6fe969d6b750068829b15ecb564830e63b7b097c6b19c30
|
| 3 |
+
size 32139875
|
expdecaybackward_42/epoch0/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6026e1c57543ee4c8cfa312e0930f27fd574a3fea348e54d24d03e23859fb56b
|
| 3 |
+
size 64342347
|
expdecaybackward_42/epoch0/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83584e23aa395dfc4f5896fb37e28d61ae0d919800f1460f06bf8a354885b5ab
|
| 3 |
+
size 1465
|
expdecaybackward_42/epoch0/tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
expdecaybackward_42/epoch0/tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
expdecaybackward_42/epoch0/tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
expdecaybackward_42/epoch0/tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"pad_token": "<|endoftext|>",
|
| 19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 20 |
+
"unk_token": "<|endoftext|>"
|
| 21 |
+
}
|
expdecaybackward_42/epoch0/tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|