Upload training_log.json with huggingface_hub
Browse files- training_log.json +362 -0
training_log.json
ADDED
|
@@ -0,0 +1,362 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"step": 100,
|
| 4 |
+
"loss": 7.657252192497253,
|
| 5 |
+
"perplexity": 2115.935250373028,
|
| 6 |
+
"learning_rate": 0.00015150000000000019,
|
| 7 |
+
"step_time": 9.368009328842163,
|
| 8 |
+
"tokens_per_second": 109.30817466708918,
|
| 9 |
+
"memory_mb": 756.6015625
|
| 10 |
+
},
|
| 11 |
+
{
|
| 12 |
+
"step": 200,
|
| 13 |
+
"loss": 7.487581491470337,
|
| 14 |
+
"perplexity": 1785.7280665447065,
|
| 15 |
+
"learning_rate": 0.0002999999999999999,
|
| 16 |
+
"step_time": 10.94300365447998,
|
| 17 |
+
"tokens_per_second": 93.57577063229641,
|
| 18 |
+
"memory_mb": 730.99609375
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"step": 300,
|
| 22 |
+
"loss": 7.163171410560608,
|
| 23 |
+
"perplexity": 1290.9987344513497,
|
| 24 |
+
"learning_rate": 0.00029794904665665113,
|
| 25 |
+
"step_time": 8.949450016021729,
|
| 26 |
+
"tokens_per_second": 114.42043904002891,
|
| 27 |
+
"memory_mb": 733.89453125
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"step": 400,
|
| 31 |
+
"loss": 6.677380561828613,
|
| 32 |
+
"perplexity": 794.2359329078598,
|
| 33 |
+
"learning_rate": 0.00029185850380610337,
|
| 34 |
+
"step_time": 8.572781324386597,
|
| 35 |
+
"tokens_per_second": 119.44781527169884,
|
| 36 |
+
"memory_mb": 827.69140625
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"step": 500,
|
| 40 |
+
"loss": 6.8126842975616455,
|
| 41 |
+
"perplexity": 909.3083881764071,
|
| 42 |
+
"learning_rate": 0.0002819134295109075,
|
| 43 |
+
"step_time": 8.801953315734863,
|
| 44 |
+
"tokens_per_second": 116.33781312716582,
|
| 45 |
+
"memory_mb": 849.21484375
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"step": 600,
|
| 49 |
+
"loss": 6.901162624359131,
|
| 50 |
+
"perplexity": 993.4290292468936,
|
| 51 |
+
"learning_rate": 0.0002684159998210713,
|
| 52 |
+
"step_time": 8.660848379135132,
|
| 53 |
+
"tokens_per_second": 118.23322094714423,
|
| 54 |
+
"memory_mb": 734.16015625
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"step": 700,
|
| 58 |
+
"loss": 6.6995872259140015,
|
| 59 |
+
"perplexity": 812.0705542959239,
|
| 60 |
+
"learning_rate": 0.0002517763273076916,
|
| 61 |
+
"step_time": 9.10423469543457,
|
| 62 |
+
"tokens_per_second": 112.47513209578146,
|
| 63 |
+
"memory_mb": 734.64453125
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"step": 800,
|
| 67 |
+
"loss": 6.729204297065735,
|
| 68 |
+
"perplexity": 836.4814103649661,
|
| 69 |
+
"learning_rate": 0.00023250000000000793,
|
| 70 |
+
"step_time": 8.646829605102539,
|
| 71 |
+
"tokens_per_second": 118.42490794495734,
|
| 72 |
+
"memory_mb": 733.84765625
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"step": 900,
|
| 76 |
+
"loss": 6.801577568054199,
|
| 77 |
+
"perplexity": 899.2648246887062,
|
| 78 |
+
"learning_rate": 0.00021117271934897237,
|
| 79 |
+
"step_time": 8.66753602027893,
|
| 80 |
+
"tokens_per_second": 118.14199532649263,
|
| 81 |
+
"memory_mb": 839.50390625
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"step": 1000,
|
| 85 |
+
"loss": 6.5149312019348145,
|
| 86 |
+
"perplexity": 675.1475110828569,
|
| 87 |
+
"learning_rate": 0.00018844250398504186,
|
| 88 |
+
"step_time": 9.189276933670044,
|
| 89 |
+
"tokens_per_second": 111.43423006961567,
|
| 90 |
+
"memory_mb": 734.55078125
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"step": 1100,
|
| 94 |
+
"loss": 6.551132082939148,
|
| 95 |
+
"perplexity": 700.0362244642821,
|
| 96 |
+
"learning_rate": 0.00016500000000000537,
|
| 97 |
+
"step_time": 8.517168760299683,
|
| 98 |
+
"tokens_per_second": 120.22774572379963,
|
| 99 |
+
"memory_mb": 913.80078125
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"step": 1200,
|
| 103 |
+
"loss": 6.6684452295303345,
|
| 104 |
+
"perplexity": 787.170782663513,
|
| 105 |
+
"learning_rate": 0.00014155749601496882,
|
| 106 |
+
"step_time": 9.400139570236206,
|
| 107 |
+
"tokens_per_second": 108.93455276369572,
|
| 108 |
+
"memory_mb": 968.5859375
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"step": 1300,
|
| 112 |
+
"loss": 6.406905889511108,
|
| 113 |
+
"perplexity": 606.0156976890383,
|
| 114 |
+
"learning_rate": 0.00011882728065103813,
|
| 115 |
+
"step_time": 8.490540981292725,
|
| 116 |
+
"tokens_per_second": 120.6048003603289,
|
| 117 |
+
"memory_mb": 979.359375
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"step": 1400,
|
| 121 |
+
"loss": 6.3421419858932495,
|
| 122 |
+
"perplexity": 568.011682273887,
|
| 123 |
+
"learning_rate": 9.750000000000261e-05,
|
| 124 |
+
"step_time": 10.675879955291748,
|
| 125 |
+
"tokens_per_second": 95.91715196201983,
|
| 126 |
+
"memory_mb": 733.6328125
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"step": 1500,
|
| 130 |
+
"loss": 6.335531115531921,
|
| 131 |
+
"perplexity": 564.2690154518974,
|
| 132 |
+
"learning_rate": 7.822367269231907e-05,
|
| 133 |
+
"step_time": 8.945564270019531,
|
| 134 |
+
"tokens_per_second": 114.47014062957085,
|
| 135 |
+
"memory_mb": 994.3515625
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"step": 1600,
|
| 139 |
+
"loss": 6.629261136054993,
|
| 140 |
+
"perplexity": 756.9227010883292,
|
| 141 |
+
"learning_rate": 6.158400017893925e-05,
|
| 142 |
+
"step_time": 10.422486782073975,
|
| 143 |
+
"tokens_per_second": 98.2491051714468,
|
| 144 |
+
"memory_mb": 730.56640625
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"step": 1700,
|
| 148 |
+
"loss": 6.302608251571655,
|
| 149 |
+
"perplexity": 545.9941446328027,
|
| 150 |
+
"learning_rate": 4.808657048910149e-05,
|
| 151 |
+
"step_time": 9.476832628250122,
|
| 152 |
+
"tokens_per_second": 108.05297932006208,
|
| 153 |
+
"memory_mb": 745.43359375
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"step": 1800,
|
| 157 |
+
"loss": 6.266754984855652,
|
| 158 |
+
"perplexity": 526.765240241726,
|
| 159 |
+
"learning_rate": 3.8141496193902704e-05,
|
| 160 |
+
"step_time": 8.648972511291504,
|
| 161 |
+
"tokens_per_second": 118.3955664864394,
|
| 162 |
+
"memory_mb": 1009.6484375
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"step": 1900,
|
| 166 |
+
"loss": 6.480456352233887,
|
| 167 |
+
"perplexity": 652.268542568135,
|
| 168 |
+
"learning_rate": 3.2050953343351995e-05,
|
| 169 |
+
"step_time": 8.593879699707031,
|
| 170 |
+
"tokens_per_second": 119.15456531639704,
|
| 171 |
+
"memory_mb": 735.796875
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"step": 2000,
|
| 175 |
+
"loss": 5.975515604019165,
|
| 176 |
+
"perplexity": 393.6710271356782,
|
| 177 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 178 |
+
"step_time": 8.94594669342041,
|
| 179 |
+
"tokens_per_second": 114.46524723349116,
|
| 180 |
+
"memory_mb": 729.84375
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"step": 2100,
|
| 184 |
+
"loss": 6.554613709449768,
|
| 185 |
+
"perplexity": 702.4777368926921,
|
| 186 |
+
"learning_rate": 3.205095334333285e-05,
|
| 187 |
+
"step_time": 9.199656009674072,
|
| 188 |
+
"tokens_per_second": 111.3085096794047,
|
| 189 |
+
"memory_mb": 752.64453125
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"step": 2200,
|
| 193 |
+
"loss": 6.471360206604004,
|
| 194 |
+
"perplexity": 646.3623155888199,
|
| 195 |
+
"learning_rate": 3.814149619382671e-05,
|
| 196 |
+
"step_time": 8.654725313186646,
|
| 197 |
+
"tokens_per_second": 118.3168688715975,
|
| 198 |
+
"memory_mb": 735.9375
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"step": 2300,
|
| 202 |
+
"loss": 6.382450699806213,
|
| 203 |
+
"perplexity": 591.3752163574818,
|
| 204 |
+
"learning_rate": 4.808657048893273e-05,
|
| 205 |
+
"step_time": 8.75070834159851,
|
| 206 |
+
"tokens_per_second": 117.01909834340836,
|
| 207 |
+
"memory_mb": 776.53125
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"step": 2400,
|
| 211 |
+
"loss": 5.957324385643005,
|
| 212 |
+
"perplexity": 386.5744152212925,
|
| 213 |
+
"learning_rate": 6.158400017864459e-05,
|
| 214 |
+
"step_time": 8.642782926559448,
|
| 215 |
+
"tokens_per_second": 118.4803562349376,
|
| 216 |
+
"memory_mb": 923.15234375
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"step": 2500,
|
| 220 |
+
"loss": 6.218142509460449,
|
| 221 |
+
"perplexity": 501.7703322170689,
|
| 222 |
+
"learning_rate": 7.822367269186924e-05,
|
| 223 |
+
"step_time": 9.567925691604614,
|
| 224 |
+
"tokens_per_second": 107.0242425585004,
|
| 225 |
+
"memory_mb": 1050.1875
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"step": 2600,
|
| 229 |
+
"loss": 6.314482092857361,
|
| 230 |
+
"perplexity": 552.515834581567,
|
| 231 |
+
"learning_rate": 9.749999999937299e-05,
|
| 232 |
+
"step_time": 8.212730169296265,
|
| 233 |
+
"tokens_per_second": 124.68448115199003,
|
| 234 |
+
"memory_mb": 738.69921875
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"step": 2700,
|
| 238 |
+
"loss": 6.240906238555908,
|
| 239 |
+
"perplexity": 513.3234937600264,
|
| 240 |
+
"learning_rate": 0.00011882728065020969,
|
| 241 |
+
"step_time": 8.88506555557251,
|
| 242 |
+
"tokens_per_second": 115.24957172181702,
|
| 243 |
+
"memory_mb": 739.125
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"step": 2800,
|
| 247 |
+
"loss": 6.308051347732544,
|
| 248 |
+
"perplexity": 548.9741461252174,
|
| 249 |
+
"learning_rate": 0.0001415574960139285,
|
| 250 |
+
"step_time": 9.43014669418335,
|
| 251 |
+
"tokens_per_second": 108.58791842884247,
|
| 252 |
+
"memory_mb": 732.40234375
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"step": 2900,
|
| 256 |
+
"loss": 6.410398960113525,
|
| 257 |
+
"perplexity": 608.136254778883,
|
| 258 |
+
"learning_rate": 0.00016499999999874617,
|
| 259 |
+
"step_time": 8.674461603164673,
|
| 260 |
+
"tokens_per_second": 118.0476722182294,
|
| 261 |
+
"memory_mb": 733.71484375
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"step": 3000,
|
| 265 |
+
"loss": 6.160744071006775,
|
| 266 |
+
"perplexity": 473.7804700263767,
|
| 267 |
+
"learning_rate": 0.0001884425039835638,
|
| 268 |
+
"step_time": 9.056138277053833,
|
| 269 |
+
"tokens_per_second": 113.07247843096432,
|
| 270 |
+
"memory_mb": 803.75390625
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"step": 3100,
|
| 274 |
+
"loss": 6.270610332489014,
|
| 275 |
+
"perplexity": 528.8000232415734,
|
| 276 |
+
"learning_rate": 0.0002111727193472824,
|
| 277 |
+
"step_time": 9.650378227233887,
|
| 278 |
+
"tokens_per_second": 106.10983071214939,
|
| 279 |
+
"memory_mb": 790.328125
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"step": 3200,
|
| 283 |
+
"loss": 6.4413875341415405,
|
| 284 |
+
"perplexity": 627.2765639068664,
|
| 285 |
+
"learning_rate": 0.00023249999999811922,
|
| 286 |
+
"step_time": 8.436410665512085,
|
| 287 |
+
"tokens_per_second": 121.37863371043517,
|
| 288 |
+
"memory_mb": 940.3671875
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"step": 3300,
|
| 292 |
+
"loss": 6.163665413856506,
|
| 293 |
+
"perplexity": 475.1665688640195,
|
| 294 |
+
"learning_rate": 0.0002517763273056231,
|
| 295 |
+
"step_time": 10.011188507080078,
|
| 296 |
+
"tokens_per_second": 102.28555773131335,
|
| 297 |
+
"memory_mb": 747.43359375
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"step": 3400,
|
| 301 |
+
"loss": 6.067382216453552,
|
| 302 |
+
"perplexity": 431.5494984476535,
|
| 303 |
+
"learning_rate": 0.00026841599981884787,
|
| 304 |
+
"step_time": 8.671327114105225,
|
| 305 |
+
"tokens_per_second": 118.0903437876665,
|
| 306 |
+
"memory_mb": 970.37109375
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"step": 3500,
|
| 310 |
+
"loss": 6.14486300945282,
|
| 311 |
+
"perplexity": 466.3157638357051,
|
| 312 |
+
"learning_rate": 0.0002819134295085615,
|
| 313 |
+
"step_time": 8.194751024246216,
|
| 314 |
+
"tokens_per_second": 124.95803679333764,
|
| 315 |
+
"memory_mb": 736.890625
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"step": 3600,
|
| 319 |
+
"loss": 6.448354721069336,
|
| 320 |
+
"perplexity": 631.6621769355031,
|
| 321 |
+
"learning_rate": 0.00029185850380367053,
|
| 322 |
+
"step_time": 8.76004934310913,
|
| 323 |
+
"tokens_per_second": 116.89431872955184,
|
| 324 |
+
"memory_mb": 781.22265625
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"step": 3700,
|
| 328 |
+
"loss": 6.149544358253479,
|
| 329 |
+
"perplexity": 468.5038682213576,
|
| 330 |
+
"learning_rate": 0.00029794904665416755,
|
| 331 |
+
"step_time": 11.995165824890137,
|
| 332 |
+
"tokens_per_second": 85.36772354369505,
|
| 333 |
+
"memory_mb": 836.3046875
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"step": 3800,
|
| 337 |
+
"loss": 6.083824634552002,
|
| 338 |
+
"perplexity": 438.70387214992155,
|
| 339 |
+
"learning_rate": 0.0002999999999975028,
|
| 340 |
+
"step_time": 8.194983720779419,
|
| 341 |
+
"tokens_per_second": 124.95448861033346,
|
| 342 |
+
"memory_mb": 766.9453125
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"step": 3900,
|
| 346 |
+
"loss": 6.295181512832642,
|
| 347 |
+
"perplexity": 541.954209109435,
|
| 348 |
+
"learning_rate": 0.0002979490466541723,
|
| 349 |
+
"step_time": 9.617033004760742,
|
| 350 |
+
"tokens_per_second": 106.47774625428518,
|
| 351 |
+
"memory_mb": 837.29296875
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"step": 4000,
|
| 355 |
+
"loss": 5.752694249153137,
|
| 356 |
+
"perplexity": 315.038309582537,
|
| 357 |
+
"learning_rate": 0.0002918585038036804,
|
| 358 |
+
"step_time": 10.153574228286743,
|
| 359 |
+
"tokens_per_second": 100.85118569845567,
|
| 360 |
+
"memory_mb": 729.46484375
|
| 361 |
+
}
|
| 362 |
+
]
|