Delete trainer_state.json with huggingface_hub
Browse files- trainer_state.json +0 -3073
trainer_state.json
DELETED
|
@@ -1,3073 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.6776034236804565,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 1900,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.001783166904422254,
|
| 13 |
-
"grad_norm": 2.0930111408233643,
|
| 14 |
-
"learning_rate": 4.999995641358869e-05,
|
| 15 |
-
"loss": 0.7967,
|
| 16 |
-
"num_input_tokens_seen": 63024,
|
| 17 |
-
"step": 5
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.003566333808844508,
|
| 21 |
-
"grad_norm": 1.2970882654190063,
|
| 22 |
-
"learning_rate": 4.999982565450674e-05,
|
| 23 |
-
"loss": 0.7382,
|
| 24 |
-
"num_input_tokens_seen": 126336,
|
| 25 |
-
"step": 10
|
| 26 |
-
},
|
| 27 |
-
{
|
| 28 |
-
"epoch": 0.005349500713266762,
|
| 29 |
-
"grad_norm": 0.8319762349128723,
|
| 30 |
-
"learning_rate": 4.999960772321009e-05,
|
| 31 |
-
"loss": 0.6823,
|
| 32 |
-
"num_input_tokens_seen": 184688,
|
| 33 |
-
"step": 15
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 0.007132667617689016,
|
| 37 |
-
"grad_norm": 0.9985227584838867,
|
| 38 |
-
"learning_rate": 4.999930262045865e-05,
|
| 39 |
-
"loss": 0.6836,
|
| 40 |
-
"num_input_tokens_seen": 245808,
|
| 41 |
-
"step": 20
|
| 42 |
-
},
|
| 43 |
-
{
|
| 44 |
-
"epoch": 0.00891583452211127,
|
| 45 |
-
"grad_norm": 1.065556287765503,
|
| 46 |
-
"learning_rate": 4.9998910347316286e-05,
|
| 47 |
-
"loss": 0.7561,
|
| 48 |
-
"num_input_tokens_seen": 306944,
|
| 49 |
-
"step": 25
|
| 50 |
-
},
|
| 51 |
-
{
|
| 52 |
-
"epoch": 0.010699001426533523,
|
| 53 |
-
"grad_norm": 1.066805362701416,
|
| 54 |
-
"learning_rate": 4.9998430905150826e-05,
|
| 55 |
-
"loss": 0.7299,
|
| 56 |
-
"num_input_tokens_seen": 371616,
|
| 57 |
-
"step": 30
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 0.012482168330955777,
|
| 61 |
-
"grad_norm": 1.2590147256851196,
|
| 62 |
-
"learning_rate": 4.999786429563404e-05,
|
| 63 |
-
"loss": 0.6834,
|
| 64 |
-
"num_input_tokens_seen": 435536,
|
| 65 |
-
"step": 35
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.014265335235378032,
|
| 69 |
-
"grad_norm": 1.0066215991973877,
|
| 70 |
-
"learning_rate": 4.999721052074164e-05,
|
| 71 |
-
"loss": 0.6511,
|
| 72 |
-
"num_input_tokens_seen": 499328,
|
| 73 |
-
"step": 40
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 0.016048502139800285,
|
| 77 |
-
"grad_norm": 1.0162546634674072,
|
| 78 |
-
"learning_rate": 4.99964695827533e-05,
|
| 79 |
-
"loss": 0.5992,
|
| 80 |
-
"num_input_tokens_seen": 557504,
|
| 81 |
-
"step": 45
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 0.01783166904422254,
|
| 85 |
-
"grad_norm": 0.9829245209693909,
|
| 86 |
-
"learning_rate": 4.999564148425258e-05,
|
| 87 |
-
"loss": 0.6245,
|
| 88 |
-
"num_input_tokens_seen": 621440,
|
| 89 |
-
"step": 50
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 0.019614835948644792,
|
| 93 |
-
"grad_norm": 0.9447645545005798,
|
| 94 |
-
"learning_rate": 4.999472622812701e-05,
|
| 95 |
-
"loss": 0.6444,
|
| 96 |
-
"num_input_tokens_seen": 685856,
|
| 97 |
-
"step": 55
|
| 98 |
-
},
|
| 99 |
-
{
|
| 100 |
-
"epoch": 0.021398002853067047,
|
| 101 |
-
"grad_norm": 1.0958608388900757,
|
| 102 |
-
"learning_rate": 4.9993723817567996e-05,
|
| 103 |
-
"loss": 0.5194,
|
| 104 |
-
"num_input_tokens_seen": 748112,
|
| 105 |
-
"step": 60
|
| 106 |
-
},
|
| 107 |
-
{
|
| 108 |
-
"epoch": 0.023181169757489302,
|
| 109 |
-
"grad_norm": 0.9865729808807373,
|
| 110 |
-
"learning_rate": 4.999263425607086e-05,
|
| 111 |
-
"loss": 0.5021,
|
| 112 |
-
"num_input_tokens_seen": 811008,
|
| 113 |
-
"step": 65
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 0.024964336661911554,
|
| 117 |
-
"grad_norm": 1.2535978555679321,
|
| 118 |
-
"learning_rate": 4.9991457547434805e-05,
|
| 119 |
-
"loss": 0.6641,
|
| 120 |
-
"num_input_tokens_seen": 878272,
|
| 121 |
-
"step": 70
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.02674750356633381,
|
| 125 |
-
"grad_norm": 1.6020156145095825,
|
| 126 |
-
"learning_rate": 4.9990193695762914e-05,
|
| 127 |
-
"loss": 0.5479,
|
| 128 |
-
"num_input_tokens_seen": 942608,
|
| 129 |
-
"step": 75
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.028530670470756064,
|
| 133 |
-
"grad_norm": 1.1668367385864258,
|
| 134 |
-
"learning_rate": 4.998884270546214e-05,
|
| 135 |
-
"loss": 0.6181,
|
| 136 |
-
"num_input_tokens_seen": 1005776,
|
| 137 |
-
"step": 80
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 0.030313837375178315,
|
| 141 |
-
"grad_norm": 1.1580744981765747,
|
| 142 |
-
"learning_rate": 4.998740458124324e-05,
|
| 143 |
-
"loss": 0.6266,
|
| 144 |
-
"num_input_tokens_seen": 1068192,
|
| 145 |
-
"step": 85
|
| 146 |
-
},
|
| 147 |
-
{
|
| 148 |
-
"epoch": 0.03209700427960057,
|
| 149 |
-
"grad_norm": 0.9773775339126587,
|
| 150 |
-
"learning_rate": 4.9985879328120846e-05,
|
| 151 |
-
"loss": 0.5088,
|
| 152 |
-
"num_input_tokens_seen": 1128592,
|
| 153 |
-
"step": 90
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 0.033880171184022825,
|
| 157 |
-
"grad_norm": 1.4142199754714966,
|
| 158 |
-
"learning_rate": 4.9984266951413396e-05,
|
| 159 |
-
"loss": 0.5199,
|
| 160 |
-
"num_input_tokens_seen": 1194592,
|
| 161 |
-
"step": 95
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 0.03566333808844508,
|
| 165 |
-
"grad_norm": 1.459350347518921,
|
| 166 |
-
"learning_rate": 4.998256745674308e-05,
|
| 167 |
-
"loss": 0.5855,
|
| 168 |
-
"num_input_tokens_seen": 1257744,
|
| 169 |
-
"step": 100
|
| 170 |
-
},
|
| 171 |
-
{
|
| 172 |
-
"epoch": 0.037446504992867335,
|
| 173 |
-
"grad_norm": 1.118642807006836,
|
| 174 |
-
"learning_rate": 4.99807808500359e-05,
|
| 175 |
-
"loss": 0.6148,
|
| 176 |
-
"num_input_tokens_seen": 1320944,
|
| 177 |
-
"step": 105
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.039229671897289584,
|
| 181 |
-
"grad_norm": 1.1180983781814575,
|
| 182 |
-
"learning_rate": 4.99789071375216e-05,
|
| 183 |
-
"loss": 0.5517,
|
| 184 |
-
"num_input_tokens_seen": 1382928,
|
| 185 |
-
"step": 110
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 0.04101283880171184,
|
| 189 |
-
"grad_norm": 1.2651177644729614,
|
| 190 |
-
"learning_rate": 4.9976946325733654e-05,
|
| 191 |
-
"loss": 0.5959,
|
| 192 |
-
"num_input_tokens_seen": 1449408,
|
| 193 |
-
"step": 115
|
| 194 |
-
},
|
| 195 |
-
{
|
| 196 |
-
"epoch": 0.042796005706134094,
|
| 197 |
-
"grad_norm": 0.9860583543777466,
|
| 198 |
-
"learning_rate": 4.997489842150924e-05,
|
| 199 |
-
"loss": 0.4779,
|
| 200 |
-
"num_input_tokens_seen": 1510752,
|
| 201 |
-
"step": 120
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 0.04457917261055635,
|
| 205 |
-
"grad_norm": 1.0358836650848389,
|
| 206 |
-
"learning_rate": 4.997276343198922e-05,
|
| 207 |
-
"loss": 0.5474,
|
| 208 |
-
"num_input_tokens_seen": 1568928,
|
| 209 |
-
"step": 125
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 0.046362339514978604,
|
| 213 |
-
"grad_norm": 1.3108216524124146,
|
| 214 |
-
"learning_rate": 4.997054136461811e-05,
|
| 215 |
-
"loss": 0.4624,
|
| 216 |
-
"num_input_tokens_seen": 1631872,
|
| 217 |
-
"step": 130
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 0.04814550641940086,
|
| 221 |
-
"grad_norm": 1.0577709674835205,
|
| 222 |
-
"learning_rate": 4.996823222714408e-05,
|
| 223 |
-
"loss": 0.558,
|
| 224 |
-
"num_input_tokens_seen": 1694000,
|
| 225 |
-
"step": 135
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 0.04992867332382311,
|
| 229 |
-
"grad_norm": 0.9583589434623718,
|
| 230 |
-
"learning_rate": 4.996583602761887e-05,
|
| 231 |
-
"loss": 0.535,
|
| 232 |
-
"num_input_tokens_seen": 1752208,
|
| 233 |
-
"step": 140
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 0.05171184022824536,
|
| 237 |
-
"grad_norm": 1.1273239850997925,
|
| 238 |
-
"learning_rate": 4.9963352774397845e-05,
|
| 239 |
-
"loss": 0.581,
|
| 240 |
-
"num_input_tokens_seen": 1809968,
|
| 241 |
-
"step": 145
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 0.05349500713266762,
|
| 245 |
-
"grad_norm": 0.9180589914321899,
|
| 246 |
-
"learning_rate": 4.9960782476139875e-05,
|
| 247 |
-
"loss": 0.5853,
|
| 248 |
-
"num_input_tokens_seen": 1875584,
|
| 249 |
-
"step": 150
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.05527817403708987,
|
| 253 |
-
"grad_norm": 0.9368972778320312,
|
| 254 |
-
"learning_rate": 4.9958125141807376e-05,
|
| 255 |
-
"loss": 0.5655,
|
| 256 |
-
"num_input_tokens_seen": 1936544,
|
| 257 |
-
"step": 155
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 0.05706134094151213,
|
| 261 |
-
"grad_norm": 1.093083143234253,
|
| 262 |
-
"learning_rate": 4.9955380780666233e-05,
|
| 263 |
-
"loss": 0.5248,
|
| 264 |
-
"num_input_tokens_seen": 1997312,
|
| 265 |
-
"step": 160
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"epoch": 0.05884450784593438,
|
| 269 |
-
"grad_norm": 1.0452104806900024,
|
| 270 |
-
"learning_rate": 4.99525494022858e-05,
|
| 271 |
-
"loss": 0.5912,
|
| 272 |
-
"num_input_tokens_seen": 2058400,
|
| 273 |
-
"step": 165
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 0.06062767475035663,
|
| 277 |
-
"grad_norm": 1.655479073524475,
|
| 278 |
-
"learning_rate": 4.9949631016538845e-05,
|
| 279 |
-
"loss": 0.5465,
|
| 280 |
-
"num_input_tokens_seen": 2123584,
|
| 281 |
-
"step": 170
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"epoch": 0.062410841654778886,
|
| 285 |
-
"grad_norm": 1.295340895652771,
|
| 286 |
-
"learning_rate": 4.994662563360152e-05,
|
| 287 |
-
"loss": 0.6319,
|
| 288 |
-
"num_input_tokens_seen": 2187776,
|
| 289 |
-
"step": 175
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 0.06419400855920114,
|
| 293 |
-
"grad_norm": 1.1385325193405151,
|
| 294 |
-
"learning_rate": 4.994353326395334e-05,
|
| 295 |
-
"loss": 0.6121,
|
| 296 |
-
"num_input_tokens_seen": 2248592,
|
| 297 |
-
"step": 180
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 0.06597717546362339,
|
| 301 |
-
"grad_norm": 1.2202588319778442,
|
| 302 |
-
"learning_rate": 4.994035391837713e-05,
|
| 303 |
-
"loss": 0.5926,
|
| 304 |
-
"num_input_tokens_seen": 2311472,
|
| 305 |
-
"step": 185
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"epoch": 0.06776034236804565,
|
| 309 |
-
"grad_norm": 1.1300709247589111,
|
| 310 |
-
"learning_rate": 4.9937087607958987e-05,
|
| 311 |
-
"loss": 0.5075,
|
| 312 |
-
"num_input_tokens_seen": 2374240,
|
| 313 |
-
"step": 190
|
| 314 |
-
},
|
| 315 |
-
{
|
| 316 |
-
"epoch": 0.0695435092724679,
|
| 317 |
-
"grad_norm": 1.0753881931304932,
|
| 318 |
-
"learning_rate": 4.993373434408825e-05,
|
| 319 |
-
"loss": 0.5187,
|
| 320 |
-
"num_input_tokens_seen": 2434864,
|
| 321 |
-
"step": 195
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 0.07132667617689016,
|
| 325 |
-
"grad_norm": 1.0271146297454834,
|
| 326 |
-
"learning_rate": 4.993029413845746e-05,
|
| 327 |
-
"loss": 0.5777,
|
| 328 |
-
"num_input_tokens_seen": 2495712,
|
| 329 |
-
"step": 200
|
| 330 |
-
},
|
| 331 |
-
{
|
| 332 |
-
"epoch": 0.07310984308131241,
|
| 333 |
-
"grad_norm": 1.7475312948226929,
|
| 334 |
-
"learning_rate": 4.9926767003062316e-05,
|
| 335 |
-
"loss": 0.5091,
|
| 336 |
-
"num_input_tokens_seen": 2555184,
|
| 337 |
-
"step": 205
|
| 338 |
-
},
|
| 339 |
-
{
|
| 340 |
-
"epoch": 0.07489300998573467,
|
| 341 |
-
"grad_norm": 1.1732685565948486,
|
| 342 |
-
"learning_rate": 4.992315295020163e-05,
|
| 343 |
-
"loss": 0.5594,
|
| 344 |
-
"num_input_tokens_seen": 2616736,
|
| 345 |
-
"step": 210
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 0.07667617689015692,
|
| 349 |
-
"grad_norm": 1.1418745517730713,
|
| 350 |
-
"learning_rate": 4.991945199247728e-05,
|
| 351 |
-
"loss": 0.633,
|
| 352 |
-
"num_input_tokens_seen": 2679568,
|
| 353 |
-
"step": 215
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 0.07845934379457917,
|
| 357 |
-
"grad_norm": 1.5812561511993408,
|
| 358 |
-
"learning_rate": 4.991566414279421e-05,
|
| 359 |
-
"loss": 0.5361,
|
| 360 |
-
"num_input_tokens_seen": 2741888,
|
| 361 |
-
"step": 220
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"epoch": 0.08024251069900143,
|
| 365 |
-
"grad_norm": 1.2565455436706543,
|
| 366 |
-
"learning_rate": 4.99117894143603e-05,
|
| 367 |
-
"loss": 0.5128,
|
| 368 |
-
"num_input_tokens_seen": 2804736,
|
| 369 |
-
"step": 225
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.08202567760342368,
|
| 373 |
-
"grad_norm": 1.081152081489563,
|
| 374 |
-
"learning_rate": 4.990782782068639e-05,
|
| 375 |
-
"loss": 0.4925,
|
| 376 |
-
"num_input_tokens_seen": 2864768,
|
| 377 |
-
"step": 230
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"epoch": 0.08380884450784594,
|
| 381 |
-
"grad_norm": 1.157086730003357,
|
| 382 |
-
"learning_rate": 4.9903779375586224e-05,
|
| 383 |
-
"loss": 0.5091,
|
| 384 |
-
"num_input_tokens_seen": 2925776,
|
| 385 |
-
"step": 235
|
| 386 |
-
},
|
| 387 |
-
{
|
| 388 |
-
"epoch": 0.08559201141226819,
|
| 389 |
-
"grad_norm": 1.496232032775879,
|
| 390 |
-
"learning_rate": 4.989964409317637e-05,
|
| 391 |
-
"loss": 0.5611,
|
| 392 |
-
"num_input_tokens_seen": 2984032,
|
| 393 |
-
"step": 240
|
| 394 |
-
},
|
| 395 |
-
{
|
| 396 |
-
"epoch": 0.08737517831669044,
|
| 397 |
-
"grad_norm": 1.5581008195877075,
|
| 398 |
-
"learning_rate": 4.989542198787619e-05,
|
| 399 |
-
"loss": 0.4574,
|
| 400 |
-
"num_input_tokens_seen": 3047024,
|
| 401 |
-
"step": 245
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 0.0891583452211127,
|
| 405 |
-
"grad_norm": 1.1673293113708496,
|
| 406 |
-
"learning_rate": 4.9891113074407816e-05,
|
| 407 |
-
"loss": 0.4982,
|
| 408 |
-
"num_input_tokens_seen": 3105552,
|
| 409 |
-
"step": 250
|
| 410 |
-
},
|
| 411 |
-
{
|
| 412 |
-
"epoch": 0.09094151212553495,
|
| 413 |
-
"grad_norm": 1.1178501844406128,
|
| 414 |
-
"learning_rate": 4.988671736779604e-05,
|
| 415 |
-
"loss": 0.5412,
|
| 416 |
-
"num_input_tokens_seen": 3165632,
|
| 417 |
-
"step": 255
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 0.09272467902995721,
|
| 421 |
-
"grad_norm": 1.1773957014083862,
|
| 422 |
-
"learning_rate": 4.988223488336832e-05,
|
| 423 |
-
"loss": 0.5028,
|
| 424 |
-
"num_input_tokens_seen": 3229392,
|
| 425 |
-
"step": 260
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 0.09450784593437946,
|
| 429 |
-
"grad_norm": 1.1285181045532227,
|
| 430 |
-
"learning_rate": 4.987766563675467e-05,
|
| 431 |
-
"loss": 0.5414,
|
| 432 |
-
"num_input_tokens_seen": 3287616,
|
| 433 |
-
"step": 265
|
| 434 |
-
},
|
| 435 |
-
{
|
| 436 |
-
"epoch": 0.09629101283880172,
|
| 437 |
-
"grad_norm": 1.630057454109192,
|
| 438 |
-
"learning_rate": 4.9873009643887666e-05,
|
| 439 |
-
"loss": 0.5512,
|
| 440 |
-
"num_input_tokens_seen": 3346496,
|
| 441 |
-
"step": 270
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 0.09807417974322397,
|
| 445 |
-
"grad_norm": 2.1637048721313477,
|
| 446 |
-
"learning_rate": 4.986826692100236e-05,
|
| 447 |
-
"loss": 0.4881,
|
| 448 |
-
"num_input_tokens_seen": 3409312,
|
| 449 |
-
"step": 275
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"epoch": 0.09985734664764621,
|
| 453 |
-
"grad_norm": 1.9481849670410156,
|
| 454 |
-
"learning_rate": 4.98634374846362e-05,
|
| 455 |
-
"loss": 0.4716,
|
| 456 |
-
"num_input_tokens_seen": 3472752,
|
| 457 |
-
"step": 280
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"epoch": 0.10164051355206848,
|
| 461 |
-
"grad_norm": 1.3725030422210693,
|
| 462 |
-
"learning_rate": 4.9858521351629005e-05,
|
| 463 |
-
"loss": 0.5286,
|
| 464 |
-
"num_input_tokens_seen": 3534032,
|
| 465 |
-
"step": 285
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 0.10342368045649072,
|
| 469 |
-
"grad_norm": 1.5664440393447876,
|
| 470 |
-
"learning_rate": 4.985351853912292e-05,
|
| 471 |
-
"loss": 0.4985,
|
| 472 |
-
"num_input_tokens_seen": 3598336,
|
| 473 |
-
"step": 290
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 0.10520684736091299,
|
| 477 |
-
"grad_norm": 1.3553557395935059,
|
| 478 |
-
"learning_rate": 4.984842906456231e-05,
|
| 479 |
-
"loss": 0.5768,
|
| 480 |
-
"num_input_tokens_seen": 3662144,
|
| 481 |
-
"step": 295
|
| 482 |
-
},
|
| 483 |
-
{
|
| 484 |
-
"epoch": 0.10699001426533523,
|
| 485 |
-
"grad_norm": 1.2202125787734985,
|
| 486 |
-
"learning_rate": 4.984325294569372e-05,
|
| 487 |
-
"loss": 0.4933,
|
| 488 |
-
"num_input_tokens_seen": 3724048,
|
| 489 |
-
"step": 300
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 0.10877318116975748,
|
| 493 |
-
"grad_norm": 1.0455083847045898,
|
| 494 |
-
"learning_rate": 4.9837990200565834e-05,
|
| 495 |
-
"loss": 0.5675,
|
| 496 |
-
"num_input_tokens_seen": 3784320,
|
| 497 |
-
"step": 305
|
| 498 |
-
},
|
| 499 |
-
{
|
| 500 |
-
"epoch": 0.11055634807417974,
|
| 501 |
-
"grad_norm": 1.5656300783157349,
|
| 502 |
-
"learning_rate": 4.983264084752939e-05,
|
| 503 |
-
"loss": 0.5315,
|
| 504 |
-
"num_input_tokens_seen": 3849040,
|
| 505 |
-
"step": 310
|
| 506 |
-
},
|
| 507 |
-
{
|
| 508 |
-
"epoch": 0.11233951497860199,
|
| 509 |
-
"grad_norm": 1.4153857231140137,
|
| 510 |
-
"learning_rate": 4.98272049052371e-05,
|
| 511 |
-
"loss": 0.5444,
|
| 512 |
-
"num_input_tokens_seen": 3909552,
|
| 513 |
-
"step": 315
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 0.11412268188302425,
|
| 517 |
-
"grad_norm": 1.9048830270767212,
|
| 518 |
-
"learning_rate": 4.982168239264364e-05,
|
| 519 |
-
"loss": 0.4808,
|
| 520 |
-
"num_input_tokens_seen": 3969120,
|
| 521 |
-
"step": 320
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 0.1159058487874465,
|
| 525 |
-
"grad_norm": 1.0821411609649658,
|
| 526 |
-
"learning_rate": 4.981607332900552e-05,
|
| 527 |
-
"loss": 0.4829,
|
| 528 |
-
"num_input_tokens_seen": 4029360,
|
| 529 |
-
"step": 325
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 0.11768901569186876,
|
| 533 |
-
"grad_norm": 1.2863287925720215,
|
| 534 |
-
"learning_rate": 4.9810377733881065e-05,
|
| 535 |
-
"loss": 0.5273,
|
| 536 |
-
"num_input_tokens_seen": 4091296,
|
| 537 |
-
"step": 330
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 0.11947218259629101,
|
| 541 |
-
"grad_norm": 1.3957486152648926,
|
| 542 |
-
"learning_rate": 4.98045956271303e-05,
|
| 543 |
-
"loss": 0.5443,
|
| 544 |
-
"num_input_tokens_seen": 4154304,
|
| 545 |
-
"step": 335
|
| 546 |
-
},
|
| 547 |
-
{
|
| 548 |
-
"epoch": 0.12125534950071326,
|
| 549 |
-
"grad_norm": 1.1562933921813965,
|
| 550 |
-
"learning_rate": 4.979872702891495e-05,
|
| 551 |
-
"loss": 0.5046,
|
| 552 |
-
"num_input_tokens_seen": 4220400,
|
| 553 |
-
"step": 340
|
| 554 |
-
},
|
| 555 |
-
{
|
| 556 |
-
"epoch": 0.12303851640513552,
|
| 557 |
-
"grad_norm": 1.1498775482177734,
|
| 558 |
-
"learning_rate": 4.979277195969829e-05,
|
| 559 |
-
"loss": 0.5393,
|
| 560 |
-
"num_input_tokens_seen": 4279408,
|
| 561 |
-
"step": 345
|
| 562 |
-
},
|
| 563 |
-
{
|
| 564 |
-
"epoch": 0.12482168330955777,
|
| 565 |
-
"grad_norm": 1.2570199966430664,
|
| 566 |
-
"learning_rate": 4.978673044024514e-05,
|
| 567 |
-
"loss": 0.451,
|
| 568 |
-
"num_input_tokens_seen": 4339392,
|
| 569 |
-
"step": 350
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 0.12660485021398002,
|
| 573 |
-
"grad_norm": 1.3947458267211914,
|
| 574 |
-
"learning_rate": 4.978060249162175e-05,
|
| 575 |
-
"loss": 0.5715,
|
| 576 |
-
"num_input_tokens_seen": 4399424,
|
| 577 |
-
"step": 355
|
| 578 |
-
},
|
| 579 |
-
{
|
| 580 |
-
"epoch": 0.12838801711840228,
|
| 581 |
-
"grad_norm": 1.1799883842468262,
|
| 582 |
-
"learning_rate": 4.977438813519574e-05,
|
| 583 |
-
"loss": 0.5409,
|
| 584 |
-
"num_input_tokens_seen": 4460992,
|
| 585 |
-
"step": 360
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 0.13017118402282454,
|
| 589 |
-
"grad_norm": 0.9736462831497192,
|
| 590 |
-
"learning_rate": 4.976808739263602e-05,
|
| 591 |
-
"loss": 0.5298,
|
| 592 |
-
"num_input_tokens_seen": 4525664,
|
| 593 |
-
"step": 365
|
| 594 |
-
},
|
| 595 |
-
{
|
| 596 |
-
"epoch": 0.13195435092724678,
|
| 597 |
-
"grad_norm": 1.1682716608047485,
|
| 598 |
-
"learning_rate": 4.976170028591274e-05,
|
| 599 |
-
"loss": 0.481,
|
| 600 |
-
"num_input_tokens_seen": 4582160,
|
| 601 |
-
"step": 370
|
| 602 |
-
},
|
| 603 |
-
{
|
| 604 |
-
"epoch": 0.13373751783166904,
|
| 605 |
-
"grad_norm": 1.3871419429779053,
|
| 606 |
-
"learning_rate": 4.975522683729719e-05,
|
| 607 |
-
"loss": 0.5021,
|
| 608 |
-
"num_input_tokens_seen": 4649328,
|
| 609 |
-
"step": 375
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"epoch": 0.1355206847360913,
|
| 613 |
-
"grad_norm": 1.1554944515228271,
|
| 614 |
-
"learning_rate": 4.9748667069361715e-05,
|
| 615 |
-
"loss": 0.5064,
|
| 616 |
-
"num_input_tokens_seen": 4711088,
|
| 617 |
-
"step": 380
|
| 618 |
-
},
|
| 619 |
-
{
|
| 620 |
-
"epoch": 0.13730385164051356,
|
| 621 |
-
"grad_norm": 1.3844372034072876,
|
| 622 |
-
"learning_rate": 4.9742021004979656e-05,
|
| 623 |
-
"loss": 0.5516,
|
| 624 |
-
"num_input_tokens_seen": 4774864,
|
| 625 |
-
"step": 385
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"epoch": 0.1390870185449358,
|
| 629 |
-
"grad_norm": 1.4874283075332642,
|
| 630 |
-
"learning_rate": 4.9735288667325257e-05,
|
| 631 |
-
"loss": 0.4712,
|
| 632 |
-
"num_input_tokens_seen": 4834944,
|
| 633 |
-
"step": 390
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 0.14087018544935806,
|
| 637 |
-
"grad_norm": 1.195500373840332,
|
| 638 |
-
"learning_rate": 4.97284700798736e-05,
|
| 639 |
-
"loss": 0.5326,
|
| 640 |
-
"num_input_tokens_seen": 4897264,
|
| 641 |
-
"step": 395
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 0.14265335235378032,
|
| 645 |
-
"grad_norm": 1.1240135431289673,
|
| 646 |
-
"learning_rate": 4.97215652664005e-05,
|
| 647 |
-
"loss": 0.5958,
|
| 648 |
-
"num_input_tokens_seen": 4962208,
|
| 649 |
-
"step": 400
|
| 650 |
-
},
|
| 651 |
-
{
|
| 652 |
-
"epoch": 0.14443651925820256,
|
| 653 |
-
"grad_norm": 0.8974002599716187,
|
| 654 |
-
"learning_rate": 4.971457425098244e-05,
|
| 655 |
-
"loss": 0.5536,
|
| 656 |
-
"num_input_tokens_seen": 5027264,
|
| 657 |
-
"step": 405
|
| 658 |
-
},
|
| 659 |
-
{
|
| 660 |
-
"epoch": 0.14621968616262482,
|
| 661 |
-
"grad_norm": 1.0974167585372925,
|
| 662 |
-
"learning_rate": 4.970749705799649e-05,
|
| 663 |
-
"loss": 0.4721,
|
| 664 |
-
"num_input_tokens_seen": 5093216,
|
| 665 |
-
"step": 410
|
| 666 |
-
},
|
| 667 |
-
{
|
| 668 |
-
"epoch": 0.14800285306704708,
|
| 669 |
-
"grad_norm": 1.3087302446365356,
|
| 670 |
-
"learning_rate": 4.9700333712120195e-05,
|
| 671 |
-
"loss": 0.4383,
|
| 672 |
-
"num_input_tokens_seen": 5155296,
|
| 673 |
-
"step": 415
|
| 674 |
-
},
|
| 675 |
-
{
|
| 676 |
-
"epoch": 0.14978601997146934,
|
| 677 |
-
"grad_norm": 5.880493640899658,
|
| 678 |
-
"learning_rate": 4.969308423833152e-05,
|
| 679 |
-
"loss": 0.5098,
|
| 680 |
-
"num_input_tokens_seen": 5216416,
|
| 681 |
-
"step": 420
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"epoch": 0.15156918687589158,
|
| 685 |
-
"grad_norm": 1.2446019649505615,
|
| 686 |
-
"learning_rate": 4.9685748661908756e-05,
|
| 687 |
-
"loss": 0.494,
|
| 688 |
-
"num_input_tokens_seen": 5278816,
|
| 689 |
-
"step": 425
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 0.15335235378031384,
|
| 693 |
-
"grad_norm": 1.1921520233154297,
|
| 694 |
-
"learning_rate": 4.967832700843041e-05,
|
| 695 |
-
"loss": 0.5728,
|
| 696 |
-
"num_input_tokens_seen": 5344896,
|
| 697 |
-
"step": 430
|
| 698 |
-
},
|
| 699 |
-
{
|
| 700 |
-
"epoch": 0.1551355206847361,
|
| 701 |
-
"grad_norm": 1.161622166633606,
|
| 702 |
-
"learning_rate": 4.967081930377515e-05,
|
| 703 |
-
"loss": 0.5036,
|
| 704 |
-
"num_input_tokens_seen": 5400960,
|
| 705 |
-
"step": 435
|
| 706 |
-
},
|
| 707 |
-
{
|
| 708 |
-
"epoch": 0.15691868758915833,
|
| 709 |
-
"grad_norm": 1.0513135194778442,
|
| 710 |
-
"learning_rate": 4.966322557412168e-05,
|
| 711 |
-
"loss": 0.4347,
|
| 712 |
-
"num_input_tokens_seen": 5462928,
|
| 713 |
-
"step": 440
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 0.1587018544935806,
|
| 717 |
-
"grad_norm": 1.2251578569412231,
|
| 718 |
-
"learning_rate": 4.965554584594868e-05,
|
| 719 |
-
"loss": 0.4997,
|
| 720 |
-
"num_input_tokens_seen": 5525296,
|
| 721 |
-
"step": 445
|
| 722 |
-
},
|
| 723 |
-
{
|
| 724 |
-
"epoch": 0.16048502139800286,
|
| 725 |
-
"grad_norm": 1.2554380893707275,
|
| 726 |
-
"learning_rate": 4.9647780146034695e-05,
|
| 727 |
-
"loss": 0.511,
|
| 728 |
-
"num_input_tokens_seen": 5590640,
|
| 729 |
-
"step": 450
|
| 730 |
-
},
|
| 731 |
-
{
|
| 732 |
-
"epoch": 0.16226818830242512,
|
| 733 |
-
"grad_norm": 2.3998403549194336,
|
| 734 |
-
"learning_rate": 4.9639928501458035e-05,
|
| 735 |
-
"loss": 0.5376,
|
| 736 |
-
"num_input_tokens_seen": 5652912,
|
| 737 |
-
"step": 455
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 0.16405135520684735,
|
| 741 |
-
"grad_norm": 1.3643852472305298,
|
| 742 |
-
"learning_rate": 4.963199093959671e-05,
|
| 743 |
-
"loss": 0.5668,
|
| 744 |
-
"num_input_tokens_seen": 5711952,
|
| 745 |
-
"step": 460
|
| 746 |
-
},
|
| 747 |
-
{
|
| 748 |
-
"epoch": 0.16583452211126962,
|
| 749 |
-
"grad_norm": 1.4717122316360474,
|
| 750 |
-
"learning_rate": 4.96239674881283e-05,
|
| 751 |
-
"loss": 0.4877,
|
| 752 |
-
"num_input_tokens_seen": 5773968,
|
| 753 |
-
"step": 465
|
| 754 |
-
},
|
| 755 |
-
{
|
| 756 |
-
"epoch": 0.16761768901569188,
|
| 757 |
-
"grad_norm": 1.8179185390472412,
|
| 758 |
-
"learning_rate": 4.9615858175029884e-05,
|
| 759 |
-
"loss": 0.4669,
|
| 760 |
-
"num_input_tokens_seen": 5836064,
|
| 761 |
-
"step": 470
|
| 762 |
-
},
|
| 763 |
-
{
|
| 764 |
-
"epoch": 0.1694008559201141,
|
| 765 |
-
"grad_norm": 2.963438034057617,
|
| 766 |
-
"learning_rate": 4.960766302857793e-05,
|
| 767 |
-
"loss": 0.4766,
|
| 768 |
-
"num_input_tokens_seen": 5897600,
|
| 769 |
-
"step": 475
|
| 770 |
-
},
|
| 771 |
-
{
|
| 772 |
-
"epoch": 0.17118402282453637,
|
| 773 |
-
"grad_norm": 2.9000422954559326,
|
| 774 |
-
"learning_rate": 4.9599382077348205e-05,
|
| 775 |
-
"loss": 0.542,
|
| 776 |
-
"num_input_tokens_seen": 5959856,
|
| 777 |
-
"step": 480
|
| 778 |
-
},
|
| 779 |
-
{
|
| 780 |
-
"epoch": 0.17296718972895864,
|
| 781 |
-
"grad_norm": 1.1453759670257568,
|
| 782 |
-
"learning_rate": 4.959101535021566e-05,
|
| 783 |
-
"loss": 0.5482,
|
| 784 |
-
"num_input_tokens_seen": 6016128,
|
| 785 |
-
"step": 485
|
| 786 |
-
},
|
| 787 |
-
{
|
| 788 |
-
"epoch": 0.17475035663338087,
|
| 789 |
-
"grad_norm": 1.1614904403686523,
|
| 790 |
-
"learning_rate": 4.9582562876354346e-05,
|
| 791 |
-
"loss": 0.5361,
|
| 792 |
-
"num_input_tokens_seen": 6079664,
|
| 793 |
-
"step": 490
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"epoch": 0.17653352353780313,
|
| 797 |
-
"grad_norm": 1.3136591911315918,
|
| 798 |
-
"learning_rate": 4.95740246852373e-05,
|
| 799 |
-
"loss": 0.5131,
|
| 800 |
-
"num_input_tokens_seen": 6137568,
|
| 801 |
-
"step": 495
|
| 802 |
-
},
|
| 803 |
-
{
|
| 804 |
-
"epoch": 0.1783166904422254,
|
| 805 |
-
"grad_norm": 1.0961729288101196,
|
| 806 |
-
"learning_rate": 4.9565400806636447e-05,
|
| 807 |
-
"loss": 0.431,
|
| 808 |
-
"num_input_tokens_seen": 6199280,
|
| 809 |
-
"step": 500
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"epoch": 0.18009985734664766,
|
| 813 |
-
"grad_norm": 1.3530110120773315,
|
| 814 |
-
"learning_rate": 4.9556691270622515e-05,
|
| 815 |
-
"loss": 0.526,
|
| 816 |
-
"num_input_tokens_seen": 6262272,
|
| 817 |
-
"step": 505
|
| 818 |
-
},
|
| 819 |
-
{
|
| 820 |
-
"epoch": 0.1818830242510699,
|
| 821 |
-
"grad_norm": 1.2133769989013672,
|
| 822 |
-
"learning_rate": 4.9547896107564886e-05,
|
| 823 |
-
"loss": 0.5082,
|
| 824 |
-
"num_input_tokens_seen": 6324144,
|
| 825 |
-
"step": 510
|
| 826 |
-
},
|
| 827 |
-
{
|
| 828 |
-
"epoch": 0.18366619115549215,
|
| 829 |
-
"grad_norm": 1.2528913021087646,
|
| 830 |
-
"learning_rate": 4.9539015348131526e-05,
|
| 831 |
-
"loss": 0.5343,
|
| 832 |
-
"num_input_tokens_seen": 6386096,
|
| 833 |
-
"step": 515
|
| 834 |
-
},
|
| 835 |
-
{
|
| 836 |
-
"epoch": 0.18544935805991442,
|
| 837 |
-
"grad_norm": 1.4908058643341064,
|
| 838 |
-
"learning_rate": 4.953004902328887e-05,
|
| 839 |
-
"loss": 0.5408,
|
| 840 |
-
"num_input_tokens_seen": 6450704,
|
| 841 |
-
"step": 520
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 0.18723252496433665,
|
| 845 |
-
"grad_norm": 1.0931016206741333,
|
| 846 |
-
"learning_rate": 4.9520997164301726e-05,
|
| 847 |
-
"loss": 0.53,
|
| 848 |
-
"num_input_tokens_seen": 6512512,
|
| 849 |
-
"step": 525
|
| 850 |
-
},
|
| 851 |
-
{
|
| 852 |
-
"epoch": 0.1890156918687589,
|
| 853 |
-
"grad_norm": 1.317772626876831,
|
| 854 |
-
"learning_rate": 4.951185980273312e-05,
|
| 855 |
-
"loss": 0.4741,
|
| 856 |
-
"num_input_tokens_seen": 6572848,
|
| 857 |
-
"step": 530
|
| 858 |
-
},
|
| 859 |
-
{
|
| 860 |
-
"epoch": 0.19079885877318117,
|
| 861 |
-
"grad_norm": 1.114240288734436,
|
| 862 |
-
"learning_rate": 4.9502636970444246e-05,
|
| 863 |
-
"loss": 0.5021,
|
| 864 |
-
"num_input_tokens_seen": 6634064,
|
| 865 |
-
"step": 535
|
| 866 |
-
},
|
| 867 |
-
{
|
| 868 |
-
"epoch": 0.19258202567760344,
|
| 869 |
-
"grad_norm": 1.1686744689941406,
|
| 870 |
-
"learning_rate": 4.949332869959432e-05,
|
| 871 |
-
"loss": 0.5557,
|
| 872 |
-
"num_input_tokens_seen": 6698560,
|
| 873 |
-
"step": 540
|
| 874 |
-
},
|
| 875 |
-
{
|
| 876 |
-
"epoch": 0.19436519258202567,
|
| 877 |
-
"grad_norm": 1.2107973098754883,
|
| 878 |
-
"learning_rate": 4.948393502264046e-05,
|
| 879 |
-
"loss": 0.5101,
|
| 880 |
-
"num_input_tokens_seen": 6758000,
|
| 881 |
-
"step": 545
|
| 882 |
-
},
|
| 883 |
-
{
|
| 884 |
-
"epoch": 0.19614835948644793,
|
| 885 |
-
"grad_norm": 1.067867398262024,
|
| 886 |
-
"learning_rate": 4.9474455972337607e-05,
|
| 887 |
-
"loss": 0.4712,
|
| 888 |
-
"num_input_tokens_seen": 6823616,
|
| 889 |
-
"step": 550
|
| 890 |
-
},
|
| 891 |
-
{
|
| 892 |
-
"epoch": 0.1979315263908702,
|
| 893 |
-
"grad_norm": 1.0068106651306152,
|
| 894 |
-
"learning_rate": 4.946489158173838e-05,
|
| 895 |
-
"loss": 0.4854,
|
| 896 |
-
"num_input_tokens_seen": 6883376,
|
| 897 |
-
"step": 555
|
| 898 |
-
},
|
| 899 |
-
{
|
| 900 |
-
"epoch": 0.19971469329529243,
|
| 901 |
-
"grad_norm": 1.490473747253418,
|
| 902 |
-
"learning_rate": 4.945524188419298e-05,
|
| 903 |
-
"loss": 0.5664,
|
| 904 |
-
"num_input_tokens_seen": 6943808,
|
| 905 |
-
"step": 560
|
| 906 |
-
},
|
| 907 |
-
{
|
| 908 |
-
"epoch": 0.2014978601997147,
|
| 909 |
-
"grad_norm": 1.0813665390014648,
|
| 910 |
-
"learning_rate": 4.9445506913349063e-05,
|
| 911 |
-
"loss": 0.6241,
|
| 912 |
-
"num_input_tokens_seen": 7005728,
|
| 913 |
-
"step": 565
|
| 914 |
-
},
|
| 915 |
-
{
|
| 916 |
-
"epoch": 0.20328102710413695,
|
| 917 |
-
"grad_norm": 1.3641761541366577,
|
| 918 |
-
"learning_rate": 4.943568670315162e-05,
|
| 919 |
-
"loss": 0.4916,
|
| 920 |
-
"num_input_tokens_seen": 7068608,
|
| 921 |
-
"step": 570
|
| 922 |
-
},
|
| 923 |
-
{
|
| 924 |
-
"epoch": 0.20506419400855921,
|
| 925 |
-
"grad_norm": 1.0902137756347656,
|
| 926 |
-
"learning_rate": 4.942578128784287e-05,
|
| 927 |
-
"loss": 0.4833,
|
| 928 |
-
"num_input_tokens_seen": 7127008,
|
| 929 |
-
"step": 575
|
| 930 |
-
},
|
| 931 |
-
{
|
| 932 |
-
"epoch": 0.20684736091298145,
|
| 933 |
-
"grad_norm": 1.430445909500122,
|
| 934 |
-
"learning_rate": 4.941579070196214e-05,
|
| 935 |
-
"loss": 0.422,
|
| 936 |
-
"num_input_tokens_seen": 7191776,
|
| 937 |
-
"step": 580
|
| 938 |
-
},
|
| 939 |
-
{
|
| 940 |
-
"epoch": 0.2086305278174037,
|
| 941 |
-
"grad_norm": 1.6088680028915405,
|
| 942 |
-
"learning_rate": 4.940571498034572e-05,
|
| 943 |
-
"loss": 0.4913,
|
| 944 |
-
"num_input_tokens_seen": 7251536,
|
| 945 |
-
"step": 585
|
| 946 |
-
},
|
| 947 |
-
{
|
| 948 |
-
"epoch": 0.21041369472182597,
|
| 949 |
-
"grad_norm": 1.3081697225570679,
|
| 950 |
-
"learning_rate": 4.939555415812678e-05,
|
| 951 |
-
"loss": 0.451,
|
| 952 |
-
"num_input_tokens_seen": 7315696,
|
| 953 |
-
"step": 590
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"epoch": 0.2121968616262482,
|
| 957 |
-
"grad_norm": 1.3625929355621338,
|
| 958 |
-
"learning_rate": 4.938530827073522e-05,
|
| 959 |
-
"loss": 0.5694,
|
| 960 |
-
"num_input_tokens_seen": 7373792,
|
| 961 |
-
"step": 595
|
| 962 |
-
},
|
| 963 |
-
{
|
| 964 |
-
"epoch": 0.21398002853067047,
|
| 965 |
-
"grad_norm": 1.1833407878875732,
|
| 966 |
-
"learning_rate": 4.9374977353897566e-05,
|
| 967 |
-
"loss": 0.5647,
|
| 968 |
-
"num_input_tokens_seen": 7434464,
|
| 969 |
-
"step": 600
|
| 970 |
-
},
|
| 971 |
-
{
|
| 972 |
-
"epoch": 0.21576319543509273,
|
| 973 |
-
"grad_norm": 1.3193016052246094,
|
| 974 |
-
"learning_rate": 4.936456144363681e-05,
|
| 975 |
-
"loss": 0.5739,
|
| 976 |
-
"num_input_tokens_seen": 7497328,
|
| 977 |
-
"step": 605
|
| 978 |
-
},
|
| 979 |
-
{
|
| 980 |
-
"epoch": 0.21754636233951496,
|
| 981 |
-
"grad_norm": 1.4671732187271118,
|
| 982 |
-
"learning_rate": 4.935406057627234e-05,
|
| 983 |
-
"loss": 0.5399,
|
| 984 |
-
"num_input_tokens_seen": 7560816,
|
| 985 |
-
"step": 610
|
| 986 |
-
},
|
| 987 |
-
{
|
| 988 |
-
"epoch": 0.21932952924393723,
|
| 989 |
-
"grad_norm": 1.0455771684646606,
|
| 990 |
-
"learning_rate": 4.9343474788419767e-05,
|
| 991 |
-
"loss": 0.4423,
|
| 992 |
-
"num_input_tokens_seen": 7623280,
|
| 993 |
-
"step": 615
|
| 994 |
-
},
|
| 995 |
-
{
|
| 996 |
-
"epoch": 0.2211126961483595,
|
| 997 |
-
"grad_norm": 1.2360905408859253,
|
| 998 |
-
"learning_rate": 4.9332804116990795e-05,
|
| 999 |
-
"loss": 0.4595,
|
| 1000 |
-
"num_input_tokens_seen": 7685264,
|
| 1001 |
-
"step": 620
|
| 1002 |
-
},
|
| 1003 |
-
{
|
| 1004 |
-
"epoch": 0.22289586305278175,
|
| 1005 |
-
"grad_norm": 1.3082692623138428,
|
| 1006 |
-
"learning_rate": 4.9322048599193124e-05,
|
| 1007 |
-
"loss": 0.5022,
|
| 1008 |
-
"num_input_tokens_seen": 7748000,
|
| 1009 |
-
"step": 625
|
| 1010 |
-
},
|
| 1011 |
-
{
|
| 1012 |
-
"epoch": 0.22467902995720399,
|
| 1013 |
-
"grad_norm": 1.306279182434082,
|
| 1014 |
-
"learning_rate": 4.931120827253033e-05,
|
| 1015 |
-
"loss": 0.4287,
|
| 1016 |
-
"num_input_tokens_seen": 7812992,
|
| 1017 |
-
"step": 630
|
| 1018 |
-
},
|
| 1019 |
-
{
|
| 1020 |
-
"epoch": 0.22646219686162625,
|
| 1021 |
-
"grad_norm": 1.3158313035964966,
|
| 1022 |
-
"learning_rate": 4.930028317480167e-05,
|
| 1023 |
-
"loss": 0.4895,
|
| 1024 |
-
"num_input_tokens_seen": 7876416,
|
| 1025 |
-
"step": 635
|
| 1026 |
-
},
|
| 1027 |
-
{
|
| 1028 |
-
"epoch": 0.2282453637660485,
|
| 1029 |
-
"grad_norm": 1.1636604070663452,
|
| 1030 |
-
"learning_rate": 4.9289273344102014e-05,
|
| 1031 |
-
"loss": 0.4975,
|
| 1032 |
-
"num_input_tokens_seen": 7940544,
|
| 1033 |
-
"step": 640
|
| 1034 |
-
},
|
| 1035 |
-
{
|
| 1036 |
-
"epoch": 0.23002853067047074,
|
| 1037 |
-
"grad_norm": 1.23000168800354,
|
| 1038 |
-
"learning_rate": 4.927817881882169e-05,
|
| 1039 |
-
"loss": 0.4295,
|
| 1040 |
-
"num_input_tokens_seen": 7999472,
|
| 1041 |
-
"step": 645
|
| 1042 |
-
},
|
| 1043 |
-
{
|
| 1044 |
-
"epoch": 0.231811697574893,
|
| 1045 |
-
"grad_norm": 1.54082453250885,
|
| 1046 |
-
"learning_rate": 4.9266999637646326e-05,
|
| 1047 |
-
"loss": 0.5753,
|
| 1048 |
-
"num_input_tokens_seen": 8061168,
|
| 1049 |
-
"step": 650
|
| 1050 |
-
},
|
| 1051 |
-
{
|
| 1052 |
-
"epoch": 0.23359486447931527,
|
| 1053 |
-
"grad_norm": 2.485759973526001,
|
| 1054 |
-
"learning_rate": 4.925573583955676e-05,
|
| 1055 |
-
"loss": 0.443,
|
| 1056 |
-
"num_input_tokens_seen": 8118944,
|
| 1057 |
-
"step": 655
|
| 1058 |
-
},
|
| 1059 |
-
{
|
| 1060 |
-
"epoch": 0.23537803138373753,
|
| 1061 |
-
"grad_norm": 1.284912347793579,
|
| 1062 |
-
"learning_rate": 4.9244387463828876e-05,
|
| 1063 |
-
"loss": 0.5421,
|
| 1064 |
-
"num_input_tokens_seen": 8185072,
|
| 1065 |
-
"step": 660
|
| 1066 |
-
},
|
| 1067 |
-
{
|
| 1068 |
-
"epoch": 0.23716119828815976,
|
| 1069 |
-
"grad_norm": 3.4624996185302734,
|
| 1070 |
-
"learning_rate": 4.9232954550033484e-05,
|
| 1071 |
-
"loss": 0.4099,
|
| 1072 |
-
"num_input_tokens_seen": 8247616,
|
| 1073 |
-
"step": 665
|
| 1074 |
-
},
|
| 1075 |
-
{
|
| 1076 |
-
"epoch": 0.23894436519258203,
|
| 1077 |
-
"grad_norm": 1.1022762060165405,
|
| 1078 |
-
"learning_rate": 4.922143713803613e-05,
|
| 1079 |
-
"loss": 0.4784,
|
| 1080 |
-
"num_input_tokens_seen": 8312240,
|
| 1081 |
-
"step": 670
|
| 1082 |
-
},
|
| 1083 |
-
{
|
| 1084 |
-
"epoch": 0.2407275320970043,
|
| 1085 |
-
"grad_norm": 1.1634345054626465,
|
| 1086 |
-
"learning_rate": 4.920983526799705e-05,
|
| 1087 |
-
"loss": 0.3882,
|
| 1088 |
-
"num_input_tokens_seen": 8371088,
|
| 1089 |
-
"step": 675
|
| 1090 |
-
},
|
| 1091 |
-
{
|
| 1092 |
-
"epoch": 0.24251069900142652,
|
| 1093 |
-
"grad_norm": 1.4921728372573853,
|
| 1094 |
-
"learning_rate": 4.919814898037095e-05,
|
| 1095 |
-
"loss": 0.5662,
|
| 1096 |
-
"num_input_tokens_seen": 8435264,
|
| 1097 |
-
"step": 680
|
| 1098 |
-
},
|
| 1099 |
-
{
|
| 1100 |
-
"epoch": 0.24429386590584878,
|
| 1101 |
-
"grad_norm": 1.2474942207336426,
|
| 1102 |
-
"learning_rate": 4.918637831590689e-05,
|
| 1103 |
-
"loss": 0.4169,
|
| 1104 |
-
"num_input_tokens_seen": 8498960,
|
| 1105 |
-
"step": 685
|
| 1106 |
-
},
|
| 1107 |
-
{
|
| 1108 |
-
"epoch": 0.24607703281027105,
|
| 1109 |
-
"grad_norm": 0.9692139625549316,
|
| 1110 |
-
"learning_rate": 4.917452331564816e-05,
|
| 1111 |
-
"loss": 0.4681,
|
| 1112 |
-
"num_input_tokens_seen": 8561168,
|
| 1113 |
-
"step": 690
|
| 1114 |
-
},
|
| 1115 |
-
{
|
| 1116 |
-
"epoch": 0.2478601997146933,
|
| 1117 |
-
"grad_norm": 1.57968008518219,
|
| 1118 |
-
"learning_rate": 4.9162584020932114e-05,
|
| 1119 |
-
"loss": 0.4668,
|
| 1120 |
-
"num_input_tokens_seen": 8624528,
|
| 1121 |
-
"step": 695
|
| 1122 |
-
},
|
| 1123 |
-
{
|
| 1124 |
-
"epoch": 0.24964336661911554,
|
| 1125 |
-
"grad_norm": 1.7983195781707764,
|
| 1126 |
-
"learning_rate": 4.915056047339002e-05,
|
| 1127 |
-
"loss": 0.5366,
|
| 1128 |
-
"num_input_tokens_seen": 8684608,
|
| 1129 |
-
"step": 700
|
| 1130 |
-
},
|
| 1131 |
-
{
|
| 1132 |
-
"epoch": 0.2514265335235378,
|
| 1133 |
-
"grad_norm": 1.3157538175582886,
|
| 1134 |
-
"learning_rate": 4.913845271494695e-05,
|
| 1135 |
-
"loss": 0.4451,
|
| 1136 |
-
"num_input_tokens_seen": 8747216,
|
| 1137 |
-
"step": 705
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 0.25320970042796004,
|
| 1141 |
-
"grad_norm": 1.193604588508606,
|
| 1142 |
-
"learning_rate": 4.91262607878216e-05,
|
| 1143 |
-
"loss": 0.5626,
|
| 1144 |
-
"num_input_tokens_seen": 8807392,
|
| 1145 |
-
"step": 710
|
| 1146 |
-
},
|
| 1147 |
-
{
|
| 1148 |
-
"epoch": 0.2549928673323823,
|
| 1149 |
-
"grad_norm": 1.0445785522460938,
|
| 1150 |
-
"learning_rate": 4.911398473452616e-05,
|
| 1151 |
-
"loss": 0.4848,
|
| 1152 |
-
"num_input_tokens_seen": 8868496,
|
| 1153 |
-
"step": 715
|
| 1154 |
-
},
|
| 1155 |
-
{
|
| 1156 |
-
"epoch": 0.25677603423680456,
|
| 1157 |
-
"grad_norm": 1.8069995641708374,
|
| 1158 |
-
"learning_rate": 4.910162459786617e-05,
|
| 1159 |
-
"loss": 0.4672,
|
| 1160 |
-
"num_input_tokens_seen": 8929056,
|
| 1161 |
-
"step": 720
|
| 1162 |
-
},
|
| 1163 |
-
{
|
| 1164 |
-
"epoch": 0.2585592011412268,
|
| 1165 |
-
"grad_norm": 1.1339744329452515,
|
| 1166 |
-
"learning_rate": 4.908918042094033e-05,
|
| 1167 |
-
"loss": 0.399,
|
| 1168 |
-
"num_input_tokens_seen": 8991968,
|
| 1169 |
-
"step": 725
|
| 1170 |
-
},
|
| 1171 |
-
{
|
| 1172 |
-
"epoch": 0.2603423680456491,
|
| 1173 |
-
"grad_norm": 1.2230961322784424,
|
| 1174 |
-
"learning_rate": 4.907665224714042e-05,
|
| 1175 |
-
"loss": 0.5477,
|
| 1176 |
-
"num_input_tokens_seen": 9053408,
|
| 1177 |
-
"step": 730
|
| 1178 |
-
},
|
| 1179 |
-
{
|
| 1180 |
-
"epoch": 0.26212553495007135,
|
| 1181 |
-
"grad_norm": 1.2331055402755737,
|
| 1182 |
-
"learning_rate": 4.906404012015108e-05,
|
| 1183 |
-
"loss": 0.4485,
|
| 1184 |
-
"num_input_tokens_seen": 9115920,
|
| 1185 |
-
"step": 735
|
| 1186 |
-
},
|
| 1187 |
-
{
|
| 1188 |
-
"epoch": 0.26390870185449355,
|
| 1189 |
-
"grad_norm": 1.8696657419204712,
|
| 1190 |
-
"learning_rate": 4.905134408394969e-05,
|
| 1191 |
-
"loss": 0.4714,
|
| 1192 |
-
"num_input_tokens_seen": 9184576,
|
| 1193 |
-
"step": 740
|
| 1194 |
-
},
|
| 1195 |
-
{
|
| 1196 |
-
"epoch": 0.2656918687589158,
|
| 1197 |
-
"grad_norm": 1.9693909883499146,
|
| 1198 |
-
"learning_rate": 4.9038564182806234e-05,
|
| 1199 |
-
"loss": 0.516,
|
| 1200 |
-
"num_input_tokens_seen": 9247872,
|
| 1201 |
-
"step": 745
|
| 1202 |
-
},
|
| 1203 |
-
{
|
| 1204 |
-
"epoch": 0.2674750356633381,
|
| 1205 |
-
"grad_norm": 1.0184056758880615,
|
| 1206 |
-
"learning_rate": 4.902570046128312e-05,
|
| 1207 |
-
"loss": 0.4914,
|
| 1208 |
-
"num_input_tokens_seen": 9310976,
|
| 1209 |
-
"step": 750
|
| 1210 |
-
},
|
| 1211 |
-
{
|
| 1212 |
-
"epoch": 0.26925820256776034,
|
| 1213 |
-
"grad_norm": 1.165300726890564,
|
| 1214 |
-
"learning_rate": 4.9012752964235014e-05,
|
| 1215 |
-
"loss": 0.4695,
|
| 1216 |
-
"num_input_tokens_seen": 9372016,
|
| 1217 |
-
"step": 755
|
| 1218 |
-
},
|
| 1219 |
-
{
|
| 1220 |
-
"epoch": 0.2710413694721826,
|
| 1221 |
-
"grad_norm": 1.0303696393966675,
|
| 1222 |
-
"learning_rate": 4.8999721736808714e-05,
|
| 1223 |
-
"loss": 0.4741,
|
| 1224 |
-
"num_input_tokens_seen": 9432624,
|
| 1225 |
-
"step": 760
|
| 1226 |
-
},
|
| 1227 |
-
{
|
| 1228 |
-
"epoch": 0.27282453637660486,
|
| 1229 |
-
"grad_norm": 1.2935962677001953,
|
| 1230 |
-
"learning_rate": 4.898660682444297e-05,
|
| 1231 |
-
"loss": 0.5044,
|
| 1232 |
-
"num_input_tokens_seen": 9493360,
|
| 1233 |
-
"step": 765
|
| 1234 |
-
},
|
| 1235 |
-
{
|
| 1236 |
-
"epoch": 0.2746077032810271,
|
| 1237 |
-
"grad_norm": 1.3259665966033936,
|
| 1238 |
-
"learning_rate": 4.8973408272868347e-05,
|
| 1239 |
-
"loss": 0.4618,
|
| 1240 |
-
"num_input_tokens_seen": 9555136,
|
| 1241 |
-
"step": 770
|
| 1242 |
-
},
|
| 1243 |
-
{
|
| 1244 |
-
"epoch": 0.27639087018544933,
|
| 1245 |
-
"grad_norm": 4.303719520568848,
|
| 1246 |
-
"learning_rate": 4.896012612810704e-05,
|
| 1247 |
-
"loss": 0.3954,
|
| 1248 |
-
"num_input_tokens_seen": 9616896,
|
| 1249 |
-
"step": 775
|
| 1250 |
-
},
|
| 1251 |
-
{
|
| 1252 |
-
"epoch": 0.2781740370898716,
|
| 1253 |
-
"grad_norm": 1.2892228364944458,
|
| 1254 |
-
"learning_rate": 4.894676043647274e-05,
|
| 1255 |
-
"loss": 0.3872,
|
| 1256 |
-
"num_input_tokens_seen": 9674752,
|
| 1257 |
-
"step": 780
|
| 1258 |
-
},
|
| 1259 |
-
{
|
| 1260 |
-
"epoch": 0.27995720399429386,
|
| 1261 |
-
"grad_norm": 1.360479474067688,
|
| 1262 |
-
"learning_rate": 4.8933311244570434e-05,
|
| 1263 |
-
"loss": 0.4713,
|
| 1264 |
-
"num_input_tokens_seen": 9736976,
|
| 1265 |
-
"step": 785
|
| 1266 |
-
},
|
| 1267 |
-
{
|
| 1268 |
-
"epoch": 0.2817403708987161,
|
| 1269 |
-
"grad_norm": 1.3140631914138794,
|
| 1270 |
-
"learning_rate": 4.8919778599296293e-05,
|
| 1271 |
-
"loss": 0.3917,
|
| 1272 |
-
"num_input_tokens_seen": 9797136,
|
| 1273 |
-
"step": 790
|
| 1274 |
-
},
|
| 1275 |
-
{
|
| 1276 |
-
"epoch": 0.2835235378031384,
|
| 1277 |
-
"grad_norm": 1.0723479986190796,
|
| 1278 |
-
"learning_rate": 4.890616254783748e-05,
|
| 1279 |
-
"loss": 0.4911,
|
| 1280 |
-
"num_input_tokens_seen": 9858928,
|
| 1281 |
-
"step": 795
|
| 1282 |
-
},
|
| 1283 |
-
{
|
| 1284 |
-
"epoch": 0.28530670470756064,
|
| 1285 |
-
"grad_norm": 1.4321138858795166,
|
| 1286 |
-
"learning_rate": 4.8892463137671963e-05,
|
| 1287 |
-
"loss": 0.4682,
|
| 1288 |
-
"num_input_tokens_seen": 9917776,
|
| 1289 |
-
"step": 800
|
| 1290 |
-
},
|
| 1291 |
-
{
|
| 1292 |
-
"epoch": 0.2870898716119829,
|
| 1293 |
-
"grad_norm": 1.2900583744049072,
|
| 1294 |
-
"learning_rate": 4.887868041656839e-05,
|
| 1295 |
-
"loss": 0.4978,
|
| 1296 |
-
"num_input_tokens_seen": 9982464,
|
| 1297 |
-
"step": 805
|
| 1298 |
-
},
|
| 1299 |
-
{
|
| 1300 |
-
"epoch": 0.2888730385164051,
|
| 1301 |
-
"grad_norm": 1.1396691799163818,
|
| 1302 |
-
"learning_rate": 4.886481443258594e-05,
|
| 1303 |
-
"loss": 0.4178,
|
| 1304 |
-
"num_input_tokens_seen": 10044208,
|
| 1305 |
-
"step": 810
|
| 1306 |
-
},
|
| 1307 |
-
{
|
| 1308 |
-
"epoch": 0.2906562054208274,
|
| 1309 |
-
"grad_norm": 1.40047025680542,
|
| 1310 |
-
"learning_rate": 4.885086523407405e-05,
|
| 1311 |
-
"loss": 0.455,
|
| 1312 |
-
"num_input_tokens_seen": 10105968,
|
| 1313 |
-
"step": 815
|
| 1314 |
-
},
|
| 1315 |
-
{
|
| 1316 |
-
"epoch": 0.29243937232524964,
|
| 1317 |
-
"grad_norm": 1.263271689414978,
|
| 1318 |
-
"learning_rate": 4.88368328696724e-05,
|
| 1319 |
-
"loss": 0.4933,
|
| 1320 |
-
"num_input_tokens_seen": 10166992,
|
| 1321 |
-
"step": 820
|
| 1322 |
-
},
|
| 1323 |
-
{
|
| 1324 |
-
"epoch": 0.2942225392296719,
|
| 1325 |
-
"grad_norm": 1.3891979455947876,
|
| 1326 |
-
"learning_rate": 4.882271738831059e-05,
|
| 1327 |
-
"loss": 0.5043,
|
| 1328 |
-
"num_input_tokens_seen": 10232144,
|
| 1329 |
-
"step": 825
|
| 1330 |
-
},
|
| 1331 |
-
{
|
| 1332 |
-
"epoch": 0.29600570613409416,
|
| 1333 |
-
"grad_norm": 1.4529082775115967,
|
| 1334 |
-
"learning_rate": 4.880851883920809e-05,
|
| 1335 |
-
"loss": 0.5188,
|
| 1336 |
-
"num_input_tokens_seen": 10292944,
|
| 1337 |
-
"step": 830
|
| 1338 |
-
},
|
| 1339 |
-
{
|
| 1340 |
-
"epoch": 0.2977888730385164,
|
| 1341 |
-
"grad_norm": 1.1358407735824585,
|
| 1342 |
-
"learning_rate": 4.879423727187401e-05,
|
| 1343 |
-
"loss": 0.5159,
|
| 1344 |
-
"num_input_tokens_seen": 10354256,
|
| 1345 |
-
"step": 835
|
| 1346 |
-
},
|
| 1347 |
-
{
|
| 1348 |
-
"epoch": 0.2995720399429387,
|
| 1349 |
-
"grad_norm": 1.7224394083023071,
|
| 1350 |
-
"learning_rate": 4.8779872736106916e-05,
|
| 1351 |
-
"loss": 0.5063,
|
| 1352 |
-
"num_input_tokens_seen": 10416688,
|
| 1353 |
-
"step": 840
|
| 1354 |
-
},
|
| 1355 |
-
{
|
| 1356 |
-
"epoch": 0.3013552068473609,
|
| 1357 |
-
"grad_norm": 1.557830810546875,
|
| 1358 |
-
"learning_rate": 4.8765425281994704e-05,
|
| 1359 |
-
"loss": 0.44,
|
| 1360 |
-
"num_input_tokens_seen": 10477712,
|
| 1361 |
-
"step": 845
|
| 1362 |
-
},
|
| 1363 |
-
{
|
| 1364 |
-
"epoch": 0.30313837375178315,
|
| 1365 |
-
"grad_norm": 1.207537293434143,
|
| 1366 |
-
"learning_rate": 4.8750894959914377e-05,
|
| 1367 |
-
"loss": 0.457,
|
| 1368 |
-
"num_input_tokens_seen": 10539120,
|
| 1369 |
-
"step": 850
|
| 1370 |
-
},
|
| 1371 |
-
{
|
| 1372 |
-
"epoch": 0.3049215406562054,
|
| 1373 |
-
"grad_norm": 1.2876931428909302,
|
| 1374 |
-
"learning_rate": 4.873628182053191e-05,
|
| 1375 |
-
"loss": 0.4583,
|
| 1376 |
-
"num_input_tokens_seen": 10602400,
|
| 1377 |
-
"step": 855
|
| 1378 |
-
},
|
| 1379 |
-
{
|
| 1380 |
-
"epoch": 0.3067047075606277,
|
| 1381 |
-
"grad_norm": 1.5556424856185913,
|
| 1382 |
-
"learning_rate": 4.872158591480206e-05,
|
| 1383 |
-
"loss": 0.4462,
|
| 1384 |
-
"num_input_tokens_seen": 10665920,
|
| 1385 |
-
"step": 860
|
| 1386 |
-
},
|
| 1387 |
-
{
|
| 1388 |
-
"epoch": 0.30848787446504994,
|
| 1389 |
-
"grad_norm": 1.2405084371566772,
|
| 1390 |
-
"learning_rate": 4.870680729396815e-05,
|
| 1391 |
-
"loss": 0.4229,
|
| 1392 |
-
"num_input_tokens_seen": 10732768,
|
| 1393 |
-
"step": 865
|
| 1394 |
-
},
|
| 1395 |
-
{
|
| 1396 |
-
"epoch": 0.3102710413694722,
|
| 1397 |
-
"grad_norm": 1.3671534061431885,
|
| 1398 |
-
"learning_rate": 4.869194600956195e-05,
|
| 1399 |
-
"loss": 0.5017,
|
| 1400 |
-
"num_input_tokens_seen": 10794368,
|
| 1401 |
-
"step": 870
|
| 1402 |
-
},
|
| 1403 |
-
{
|
| 1404 |
-
"epoch": 0.31205420827389446,
|
| 1405 |
-
"grad_norm": 1.0638670921325684,
|
| 1406 |
-
"learning_rate": 4.867700211340347e-05,
|
| 1407 |
-
"loss": 0.4751,
|
| 1408 |
-
"num_input_tokens_seen": 10853408,
|
| 1409 |
-
"step": 875
|
| 1410 |
-
},
|
| 1411 |
-
{
|
| 1412 |
-
"epoch": 0.31383737517831667,
|
| 1413 |
-
"grad_norm": 1.2563133239746094,
|
| 1414 |
-
"learning_rate": 4.8661975657600765e-05,
|
| 1415 |
-
"loss": 0.4873,
|
| 1416 |
-
"num_input_tokens_seen": 10918576,
|
| 1417 |
-
"step": 880
|
| 1418 |
-
},
|
| 1419 |
-
{
|
| 1420 |
-
"epoch": 0.31562054208273893,
|
| 1421 |
-
"grad_norm": 1.0638364553451538,
|
| 1422 |
-
"learning_rate": 4.8646866694549795e-05,
|
| 1423 |
-
"loss": 0.4572,
|
| 1424 |
-
"num_input_tokens_seen": 10980976,
|
| 1425 |
-
"step": 885
|
| 1426 |
-
},
|
| 1427 |
-
{
|
| 1428 |
-
"epoch": 0.3174037089871612,
|
| 1429 |
-
"grad_norm": 1.3460172414779663,
|
| 1430 |
-
"learning_rate": 4.863167527693417e-05,
|
| 1431 |
-
"loss": 0.4758,
|
| 1432 |
-
"num_input_tokens_seen": 11040448,
|
| 1433 |
-
"step": 890
|
| 1434 |
-
},
|
| 1435 |
-
{
|
| 1436 |
-
"epoch": 0.31918687589158345,
|
| 1437 |
-
"grad_norm": 1.210242509841919,
|
| 1438 |
-
"learning_rate": 4.861640145772507e-05,
|
| 1439 |
-
"loss": 0.5092,
|
| 1440 |
-
"num_input_tokens_seen": 11104160,
|
| 1441 |
-
"step": 895
|
| 1442 |
-
},
|
| 1443 |
-
{
|
| 1444 |
-
"epoch": 0.3209700427960057,
|
| 1445 |
-
"grad_norm": 1.0002316236495972,
|
| 1446 |
-
"learning_rate": 4.8601045290180946e-05,
|
| 1447 |
-
"loss": 0.4447,
|
| 1448 |
-
"num_input_tokens_seen": 11164224,
|
| 1449 |
-
"step": 900
|
| 1450 |
-
},
|
| 1451 |
-
{
|
| 1452 |
-
"epoch": 0.322753209700428,
|
| 1453 |
-
"grad_norm": 1.332479476928711,
|
| 1454 |
-
"learning_rate": 4.858560682784744e-05,
|
| 1455 |
-
"loss": 0.4335,
|
| 1456 |
-
"num_input_tokens_seen": 11227376,
|
| 1457 |
-
"step": 905
|
| 1458 |
-
},
|
| 1459 |
-
{
|
| 1460 |
-
"epoch": 0.32453637660485024,
|
| 1461 |
-
"grad_norm": 1.223310112953186,
|
| 1462 |
-
"learning_rate": 4.8570086124557116e-05,
|
| 1463 |
-
"loss": 0.4156,
|
| 1464 |
-
"num_input_tokens_seen": 11284704,
|
| 1465 |
-
"step": 910
|
| 1466 |
-
},
|
| 1467 |
-
{
|
| 1468 |
-
"epoch": 0.32631954350927245,
|
| 1469 |
-
"grad_norm": 1.439526915550232,
|
| 1470 |
-
"learning_rate": 4.85544832344293e-05,
|
| 1471 |
-
"loss": 0.431,
|
| 1472 |
-
"num_input_tokens_seen": 11348448,
|
| 1473 |
-
"step": 915
|
| 1474 |
-
},
|
| 1475 |
-
{
|
| 1476 |
-
"epoch": 0.3281027104136947,
|
| 1477 |
-
"grad_norm": 1.27132248878479,
|
| 1478 |
-
"learning_rate": 4.853879821186993e-05,
|
| 1479 |
-
"loss": 0.4941,
|
| 1480 |
-
"num_input_tokens_seen": 11406160,
|
| 1481 |
-
"step": 920
|
| 1482 |
-
},
|
| 1483 |
-
{
|
| 1484 |
-
"epoch": 0.32988587731811697,
|
| 1485 |
-
"grad_norm": 1.6706770658493042,
|
| 1486 |
-
"learning_rate": 4.8523031111571316e-05,
|
| 1487 |
-
"loss": 0.4718,
|
| 1488 |
-
"num_input_tokens_seen": 11467088,
|
| 1489 |
-
"step": 925
|
| 1490 |
-
},
|
| 1491 |
-
{
|
| 1492 |
-
"epoch": 0.33166904422253923,
|
| 1493 |
-
"grad_norm": 1.131922960281372,
|
| 1494 |
-
"learning_rate": 4.850718198851195e-05,
|
| 1495 |
-
"loss": 0.4172,
|
| 1496 |
-
"num_input_tokens_seen": 11532768,
|
| 1497 |
-
"step": 930
|
| 1498 |
-
},
|
| 1499 |
-
{
|
| 1500 |
-
"epoch": 0.3334522111269615,
|
| 1501 |
-
"grad_norm": 1.1946320533752441,
|
| 1502 |
-
"learning_rate": 4.849125089795634e-05,
|
| 1503 |
-
"loss": 0.3736,
|
| 1504 |
-
"num_input_tokens_seen": 11591984,
|
| 1505 |
-
"step": 935
|
| 1506 |
-
},
|
| 1507 |
-
{
|
| 1508 |
-
"epoch": 0.33523537803138376,
|
| 1509 |
-
"grad_norm": 1.2938627004623413,
|
| 1510 |
-
"learning_rate": 4.8475237895454833e-05,
|
| 1511 |
-
"loss": 0.462,
|
| 1512 |
-
"num_input_tokens_seen": 11656624,
|
| 1513 |
-
"step": 940
|
| 1514 |
-
},
|
| 1515 |
-
{
|
| 1516 |
-
"epoch": 0.33701854493580596,
|
| 1517 |
-
"grad_norm": 1.3345882892608643,
|
| 1518 |
-
"learning_rate": 4.845914303684336e-05,
|
| 1519 |
-
"loss": 0.4584,
|
| 1520 |
-
"num_input_tokens_seen": 11718256,
|
| 1521 |
-
"step": 945
|
| 1522 |
-
},
|
| 1523 |
-
{
|
| 1524 |
-
"epoch": 0.3388017118402282,
|
| 1525 |
-
"grad_norm": 0.8923389315605164,
|
| 1526 |
-
"learning_rate": 4.844296637824329e-05,
|
| 1527 |
-
"loss": 0.5339,
|
| 1528 |
-
"num_input_tokens_seen": 11776080,
|
| 1529 |
-
"step": 950
|
| 1530 |
-
},
|
| 1531 |
-
{
|
| 1532 |
-
"epoch": 0.3405848787446505,
|
| 1533 |
-
"grad_norm": 1.2611216306686401,
|
| 1534 |
-
"learning_rate": 4.8426707976061226e-05,
|
| 1535 |
-
"loss": 0.5625,
|
| 1536 |
-
"num_input_tokens_seen": 11840768,
|
| 1537 |
-
"step": 955
|
| 1538 |
-
},
|
| 1539 |
-
{
|
| 1540 |
-
"epoch": 0.34236804564907275,
|
| 1541 |
-
"grad_norm": 1.1760461330413818,
|
| 1542 |
-
"learning_rate": 4.84103678869888e-05,
|
| 1543 |
-
"loss": 0.5043,
|
| 1544 |
-
"num_input_tokens_seen": 11904208,
|
| 1545 |
-
"step": 960
|
| 1546 |
-
},
|
| 1547 |
-
{
|
| 1548 |
-
"epoch": 0.344151212553495,
|
| 1549 |
-
"grad_norm": 1.19206964969635,
|
| 1550 |
-
"learning_rate": 4.8393946168002477e-05,
|
| 1551 |
-
"loss": 0.4183,
|
| 1552 |
-
"num_input_tokens_seen": 11967952,
|
| 1553 |
-
"step": 965
|
| 1554 |
-
},
|
| 1555 |
-
{
|
| 1556 |
-
"epoch": 0.3459343794579173,
|
| 1557 |
-
"grad_norm": 1.1648989915847778,
|
| 1558 |
-
"learning_rate": 4.8377442876363364e-05,
|
| 1559 |
-
"loss": 0.4095,
|
| 1560 |
-
"num_input_tokens_seen": 12033136,
|
| 1561 |
-
"step": 970
|
| 1562 |
-
},
|
| 1563 |
-
{
|
| 1564 |
-
"epoch": 0.34771754636233954,
|
| 1565 |
-
"grad_norm": 1.2076241970062256,
|
| 1566 |
-
"learning_rate": 4.8360858069617006e-05,
|
| 1567 |
-
"loss": 0.4537,
|
| 1568 |
-
"num_input_tokens_seen": 12097584,
|
| 1569 |
-
"step": 975
|
| 1570 |
-
},
|
| 1571 |
-
{
|
| 1572 |
-
"epoch": 0.34950071326676174,
|
| 1573 |
-
"grad_norm": 1.0648747682571411,
|
| 1574 |
-
"learning_rate": 4.834419180559317e-05,
|
| 1575 |
-
"loss": 0.3932,
|
| 1576 |
-
"num_input_tokens_seen": 12156320,
|
| 1577 |
-
"step": 980
|
| 1578 |
-
},
|
| 1579 |
-
{
|
| 1580 |
-
"epoch": 0.351283880171184,
|
| 1581 |
-
"grad_norm": 1.228440523147583,
|
| 1582 |
-
"learning_rate": 4.832744414240567e-05,
|
| 1583 |
-
"loss": 0.4313,
|
| 1584 |
-
"num_input_tokens_seen": 12218384,
|
| 1585 |
-
"step": 985
|
| 1586 |
-
},
|
| 1587 |
-
{
|
| 1588 |
-
"epoch": 0.35306704707560627,
|
| 1589 |
-
"grad_norm": 1.4440958499908447,
|
| 1590 |
-
"learning_rate": 4.8310615138452156e-05,
|
| 1591 |
-
"loss": 0.4685,
|
| 1592 |
-
"num_input_tokens_seen": 12281856,
|
| 1593 |
-
"step": 990
|
| 1594 |
-
},
|
| 1595 |
-
{
|
| 1596 |
-
"epoch": 0.35485021398002853,
|
| 1597 |
-
"grad_norm": 1.0754982233047485,
|
| 1598 |
-
"learning_rate": 4.829370485241388e-05,
|
| 1599 |
-
"loss": 0.4623,
|
| 1600 |
-
"num_input_tokens_seen": 12343904,
|
| 1601 |
-
"step": 995
|
| 1602 |
-
},
|
| 1603 |
-
{
|
| 1604 |
-
"epoch": 0.3566333808844508,
|
| 1605 |
-
"grad_norm": 1.3745994567871094,
|
| 1606 |
-
"learning_rate": 4.827671334325556e-05,
|
| 1607 |
-
"loss": 0.4334,
|
| 1608 |
-
"num_input_tokens_seen": 12402256,
|
| 1609 |
-
"step": 1000
|
| 1610 |
-
},
|
| 1611 |
-
{
|
| 1612 |
-
"epoch": 0.35841654778887305,
|
| 1613 |
-
"grad_norm": 1.0649508237838745,
|
| 1614 |
-
"learning_rate": 4.82596406702251e-05,
|
| 1615 |
-
"loss": 0.4728,
|
| 1616 |
-
"num_input_tokens_seen": 12465536,
|
| 1617 |
-
"step": 1005
|
| 1618 |
-
},
|
| 1619 |
-
{
|
| 1620 |
-
"epoch": 0.3601997146932953,
|
| 1621 |
-
"grad_norm": 1.061046838760376,
|
| 1622 |
-
"learning_rate": 4.8242486892853424e-05,
|
| 1623 |
-
"loss": 0.421,
|
| 1624 |
-
"num_input_tokens_seen": 12530464,
|
| 1625 |
-
"step": 1010
|
| 1626 |
-
},
|
| 1627 |
-
{
|
| 1628 |
-
"epoch": 0.3619828815977175,
|
| 1629 |
-
"grad_norm": 1.7068672180175781,
|
| 1630 |
-
"learning_rate": 4.822525207095425e-05,
|
| 1631 |
-
"loss": 0.4843,
|
| 1632 |
-
"num_input_tokens_seen": 12593216,
|
| 1633 |
-
"step": 1015
|
| 1634 |
-
},
|
| 1635 |
-
{
|
| 1636 |
-
"epoch": 0.3637660485021398,
|
| 1637 |
-
"grad_norm": 1.2018966674804688,
|
| 1638 |
-
"learning_rate": 4.820793626462391e-05,
|
| 1639 |
-
"loss": 0.4604,
|
| 1640 |
-
"num_input_tokens_seen": 12655248,
|
| 1641 |
-
"step": 1020
|
| 1642 |
-
},
|
| 1643 |
-
{
|
| 1644 |
-
"epoch": 0.36554921540656204,
|
| 1645 |
-
"grad_norm": 1.2888667583465576,
|
| 1646 |
-
"learning_rate": 4.819053953424112e-05,
|
| 1647 |
-
"loss": 0.427,
|
| 1648 |
-
"num_input_tokens_seen": 12718048,
|
| 1649 |
-
"step": 1025
|
| 1650 |
-
},
|
| 1651 |
-
{
|
| 1652 |
-
"epoch": 0.3673323823109843,
|
| 1653 |
-
"grad_norm": 1.3183050155639648,
|
| 1654 |
-
"learning_rate": 4.817306194046675e-05,
|
| 1655 |
-
"loss": 0.4415,
|
| 1656 |
-
"num_input_tokens_seen": 12781536,
|
| 1657 |
-
"step": 1030
|
| 1658 |
-
},
|
| 1659 |
-
{
|
| 1660 |
-
"epoch": 0.36911554921540657,
|
| 1661 |
-
"grad_norm": 1.7154110670089722,
|
| 1662 |
-
"learning_rate": 4.815550354424365e-05,
|
| 1663 |
-
"loss": 0.5193,
|
| 1664 |
-
"num_input_tokens_seen": 12844336,
|
| 1665 |
-
"step": 1035
|
| 1666 |
-
},
|
| 1667 |
-
{
|
| 1668 |
-
"epoch": 0.37089871611982883,
|
| 1669 |
-
"grad_norm": 1.3131228685379028,
|
| 1670 |
-
"learning_rate": 4.813786440679642e-05,
|
| 1671 |
-
"loss": 0.4078,
|
| 1672 |
-
"num_input_tokens_seen": 12906288,
|
| 1673 |
-
"step": 1040
|
| 1674 |
-
},
|
| 1675 |
-
{
|
| 1676 |
-
"epoch": 0.3726818830242511,
|
| 1677 |
-
"grad_norm": 1.1588881015777588,
|
| 1678 |
-
"learning_rate": 4.81201445896312e-05,
|
| 1679 |
-
"loss": 0.3672,
|
| 1680 |
-
"num_input_tokens_seen": 12965200,
|
| 1681 |
-
"step": 1045
|
| 1682 |
-
},
|
| 1683 |
-
{
|
| 1684 |
-
"epoch": 0.3744650499286733,
|
| 1685 |
-
"grad_norm": 1.5113669633865356,
|
| 1686 |
-
"learning_rate": 4.810234415453545e-05,
|
| 1687 |
-
"loss": 0.4896,
|
| 1688 |
-
"num_input_tokens_seen": 13033248,
|
| 1689 |
-
"step": 1050
|
| 1690 |
-
},
|
| 1691 |
-
{
|
| 1692 |
-
"epoch": 0.37624821683309556,
|
| 1693 |
-
"grad_norm": 1.4646553993225098,
|
| 1694 |
-
"learning_rate": 4.808446316357773e-05,
|
| 1695 |
-
"loss": 0.4772,
|
| 1696 |
-
"num_input_tokens_seen": 13096752,
|
| 1697 |
-
"step": 1055
|
| 1698 |
-
},
|
| 1699 |
-
{
|
| 1700 |
-
"epoch": 0.3780313837375178,
|
| 1701 |
-
"grad_norm": 1.9652795791625977,
|
| 1702 |
-
"learning_rate": 4.80665016791075e-05,
|
| 1703 |
-
"loss": 0.4468,
|
| 1704 |
-
"num_input_tokens_seen": 13158992,
|
| 1705 |
-
"step": 1060
|
| 1706 |
-
},
|
| 1707 |
-
{
|
| 1708 |
-
"epoch": 0.3798145506419401,
|
| 1709 |
-
"grad_norm": 3.033592700958252,
|
| 1710 |
-
"learning_rate": 4.804845976375489e-05,
|
| 1711 |
-
"loss": 0.3997,
|
| 1712 |
-
"num_input_tokens_seen": 13222064,
|
| 1713 |
-
"step": 1065
|
| 1714 |
-
},
|
| 1715 |
-
{
|
| 1716 |
-
"epoch": 0.38159771754636235,
|
| 1717 |
-
"grad_norm": 1.2086786031723022,
|
| 1718 |
-
"learning_rate": 4.8030337480430496e-05,
|
| 1719 |
-
"loss": 0.4966,
|
| 1720 |
-
"num_input_tokens_seen": 13286112,
|
| 1721 |
-
"step": 1070
|
| 1722 |
-
},
|
| 1723 |
-
{
|
| 1724 |
-
"epoch": 0.3833808844507846,
|
| 1725 |
-
"grad_norm": 1.7219619750976562,
|
| 1726 |
-
"learning_rate": 4.801213489232514e-05,
|
| 1727 |
-
"loss": 0.4918,
|
| 1728 |
-
"num_input_tokens_seen": 13346832,
|
| 1729 |
-
"step": 1075
|
| 1730 |
-
},
|
| 1731 |
-
{
|
| 1732 |
-
"epoch": 0.38516405135520687,
|
| 1733 |
-
"grad_norm": 1.256044864654541,
|
| 1734 |
-
"learning_rate": 4.799385206290965e-05,
|
| 1735 |
-
"loss": 0.4734,
|
| 1736 |
-
"num_input_tokens_seen": 13408992,
|
| 1737 |
-
"step": 1080
|
| 1738 |
-
},
|
| 1739 |
-
{
|
| 1740 |
-
"epoch": 0.3869472182596291,
|
| 1741 |
-
"grad_norm": 1.150932788848877,
|
| 1742 |
-
"learning_rate": 4.7975489055934666e-05,
|
| 1743 |
-
"loss": 0.3703,
|
| 1744 |
-
"num_input_tokens_seen": 13469280,
|
| 1745 |
-
"step": 1085
|
| 1746 |
-
},
|
| 1747 |
-
{
|
| 1748 |
-
"epoch": 0.38873038516405134,
|
| 1749 |
-
"grad_norm": 1.4256497621536255,
|
| 1750 |
-
"learning_rate": 4.79570459354304e-05,
|
| 1751 |
-
"loss": 0.5076,
|
| 1752 |
-
"num_input_tokens_seen": 13533536,
|
| 1753 |
-
"step": 1090
|
| 1754 |
-
},
|
| 1755 |
-
{
|
| 1756 |
-
"epoch": 0.3905135520684736,
|
| 1757 |
-
"grad_norm": 1.1593137979507446,
|
| 1758 |
-
"learning_rate": 4.79385227657064e-05,
|
| 1759 |
-
"loss": 0.4351,
|
| 1760 |
-
"num_input_tokens_seen": 13594304,
|
| 1761 |
-
"step": 1095
|
| 1762 |
-
},
|
| 1763 |
-
{
|
| 1764 |
-
"epoch": 0.39229671897289586,
|
| 1765 |
-
"grad_norm": 0.9239110350608826,
|
| 1766 |
-
"learning_rate": 4.791991961135135e-05,
|
| 1767 |
-
"loss": 0.4984,
|
| 1768 |
-
"num_input_tokens_seen": 13657328,
|
| 1769 |
-
"step": 1100
|
| 1770 |
-
},
|
| 1771 |
-
{
|
| 1772 |
-
"epoch": 0.3940798858773181,
|
| 1773 |
-
"grad_norm": 0.999727189540863,
|
| 1774 |
-
"learning_rate": 4.790123653723282e-05,
|
| 1775 |
-
"loss": 0.4598,
|
| 1776 |
-
"num_input_tokens_seen": 13720224,
|
| 1777 |
-
"step": 1105
|
| 1778 |
-
},
|
| 1779 |
-
{
|
| 1780 |
-
"epoch": 0.3958630527817404,
|
| 1781 |
-
"grad_norm": 1.0658410787582397,
|
| 1782 |
-
"learning_rate": 4.788247360849708e-05,
|
| 1783 |
-
"loss": 0.4409,
|
| 1784 |
-
"num_input_tokens_seen": 13782656,
|
| 1785 |
-
"step": 1110
|
| 1786 |
-
},
|
| 1787 |
-
{
|
| 1788 |
-
"epoch": 0.39764621968616265,
|
| 1789 |
-
"grad_norm": 1.2038542032241821,
|
| 1790 |
-
"learning_rate": 4.786363089056881e-05,
|
| 1791 |
-
"loss": 0.4719,
|
| 1792 |
-
"num_input_tokens_seen": 13849120,
|
| 1793 |
-
"step": 1115
|
| 1794 |
-
},
|
| 1795 |
-
{
|
| 1796 |
-
"epoch": 0.39942938659058486,
|
| 1797 |
-
"grad_norm": 1.1782008409500122,
|
| 1798 |
-
"learning_rate": 4.784470844915093e-05,
|
| 1799 |
-
"loss": 0.4147,
|
| 1800 |
-
"num_input_tokens_seen": 13910944,
|
| 1801 |
-
"step": 1120
|
| 1802 |
-
},
|
| 1803 |
-
{
|
| 1804 |
-
"epoch": 0.4012125534950071,
|
| 1805 |
-
"grad_norm": 0.9827120304107666,
|
| 1806 |
-
"learning_rate": 4.782570635022436e-05,
|
| 1807 |
-
"loss": 0.3883,
|
| 1808 |
-
"num_input_tokens_seen": 13969248,
|
| 1809 |
-
"step": 1125
|
| 1810 |
-
},
|
| 1811 |
-
{
|
| 1812 |
-
"epoch": 0.4029957203994294,
|
| 1813 |
-
"grad_norm": 1.0276070833206177,
|
| 1814 |
-
"learning_rate": 4.7806624660047744e-05,
|
| 1815 |
-
"loss": 0.4337,
|
| 1816 |
-
"num_input_tokens_seen": 14028112,
|
| 1817 |
-
"step": 1130
|
| 1818 |
-
},
|
| 1819 |
-
{
|
| 1820 |
-
"epoch": 0.40477888730385164,
|
| 1821 |
-
"grad_norm": 1.923315167427063,
|
| 1822 |
-
"learning_rate": 4.7787463445157286e-05,
|
| 1823 |
-
"loss": 0.5135,
|
| 1824 |
-
"num_input_tokens_seen": 14090320,
|
| 1825 |
-
"step": 1135
|
| 1826 |
-
},
|
| 1827 |
-
{
|
| 1828 |
-
"epoch": 0.4065620542082739,
|
| 1829 |
-
"grad_norm": 1.3430618047714233,
|
| 1830 |
-
"learning_rate": 4.7768222772366466e-05,
|
| 1831 |
-
"loss": 0.5111,
|
| 1832 |
-
"num_input_tokens_seen": 14151840,
|
| 1833 |
-
"step": 1140
|
| 1834 |
-
},
|
| 1835 |
-
{
|
| 1836 |
-
"epoch": 0.40834522111269617,
|
| 1837 |
-
"grad_norm": 1.5225883722305298,
|
| 1838 |
-
"learning_rate": 4.774890270876584e-05,
|
| 1839 |
-
"loss": 0.5005,
|
| 1840 |
-
"num_input_tokens_seen": 14213824,
|
| 1841 |
-
"step": 1145
|
| 1842 |
-
},
|
| 1843 |
-
{
|
| 1844 |
-
"epoch": 0.41012838801711843,
|
| 1845 |
-
"grad_norm": 1.0013866424560547,
|
| 1846 |
-
"learning_rate": 4.772950332172279e-05,
|
| 1847 |
-
"loss": 0.6018,
|
| 1848 |
-
"num_input_tokens_seen": 14278736,
|
| 1849 |
-
"step": 1150
|
| 1850 |
-
},
|
| 1851 |
-
{
|
| 1852 |
-
"epoch": 0.41191155492154063,
|
| 1853 |
-
"grad_norm": 1.0078413486480713,
|
| 1854 |
-
"learning_rate": 4.771002467888128e-05,
|
| 1855 |
-
"loss": 0.3879,
|
| 1856 |
-
"num_input_tokens_seen": 14339408,
|
| 1857 |
-
"step": 1155
|
| 1858 |
-
},
|
| 1859 |
-
{
|
| 1860 |
-
"epoch": 0.4136947218259629,
|
| 1861 |
-
"grad_norm": 1.1650017499923706,
|
| 1862 |
-
"learning_rate": 4.769046684816165e-05,
|
| 1863 |
-
"loss": 0.4924,
|
| 1864 |
-
"num_input_tokens_seen": 14399008,
|
| 1865 |
-
"step": 1160
|
| 1866 |
-
},
|
| 1867 |
-
{
|
| 1868 |
-
"epoch": 0.41547788873038516,
|
| 1869 |
-
"grad_norm": 1.351217269897461,
|
| 1870 |
-
"learning_rate": 4.767082989776034e-05,
|
| 1871 |
-
"loss": 0.4104,
|
| 1872 |
-
"num_input_tokens_seen": 14462656,
|
| 1873 |
-
"step": 1165
|
| 1874 |
-
},
|
| 1875 |
-
{
|
| 1876 |
-
"epoch": 0.4172610556348074,
|
| 1877 |
-
"grad_norm": 1.3392795324325562,
|
| 1878 |
-
"learning_rate": 4.76511138961497e-05,
|
| 1879 |
-
"loss": 0.4629,
|
| 1880 |
-
"num_input_tokens_seen": 14527568,
|
| 1881 |
-
"step": 1170
|
| 1882 |
-
},
|
| 1883 |
-
{
|
| 1884 |
-
"epoch": 0.4190442225392297,
|
| 1885 |
-
"grad_norm": 1.3544095754623413,
|
| 1886 |
-
"learning_rate": 4.763131891207771e-05,
|
| 1887 |
-
"loss": 0.486,
|
| 1888 |
-
"num_input_tokens_seen": 14590944,
|
| 1889 |
-
"step": 1175
|
| 1890 |
-
},
|
| 1891 |
-
{
|
| 1892 |
-
"epoch": 0.42082738944365194,
|
| 1893 |
-
"grad_norm": 1.1842771768569946,
|
| 1894 |
-
"learning_rate": 4.761144501456773e-05,
|
| 1895 |
-
"loss": 0.4529,
|
| 1896 |
-
"num_input_tokens_seen": 14651104,
|
| 1897 |
-
"step": 1180
|
| 1898 |
-
},
|
| 1899 |
-
{
|
| 1900 |
-
"epoch": 0.4226105563480742,
|
| 1901 |
-
"grad_norm": 0.9588406085968018,
|
| 1902 |
-
"learning_rate": 4.7591492272918344e-05,
|
| 1903 |
-
"loss": 0.3739,
|
| 1904 |
-
"num_input_tokens_seen": 14711344,
|
| 1905 |
-
"step": 1185
|
| 1906 |
-
},
|
| 1907 |
-
{
|
| 1908 |
-
"epoch": 0.4243937232524964,
|
| 1909 |
-
"grad_norm": 1.1637108325958252,
|
| 1910 |
-
"learning_rate": 4.7571460756703e-05,
|
| 1911 |
-
"loss": 0.4772,
|
| 1912 |
-
"num_input_tokens_seen": 14772656,
|
| 1913 |
-
"step": 1190
|
| 1914 |
-
},
|
| 1915 |
-
{
|
| 1916 |
-
"epoch": 0.4261768901569187,
|
| 1917 |
-
"grad_norm": 1.225539207458496,
|
| 1918 |
-
"learning_rate": 4.755135053576987e-05,
|
| 1919 |
-
"loss": 0.4606,
|
| 1920 |
-
"num_input_tokens_seen": 14833840,
|
| 1921 |
-
"step": 1195
|
| 1922 |
-
},
|
| 1923 |
-
{
|
| 1924 |
-
"epoch": 0.42796005706134094,
|
| 1925 |
-
"grad_norm": 1.4021525382995605,
|
| 1926 |
-
"learning_rate": 4.753116168024153e-05,
|
| 1927 |
-
"loss": 0.4168,
|
| 1928 |
-
"num_input_tokens_seen": 14896544,
|
| 1929 |
-
"step": 1200
|
| 1930 |
-
},
|
| 1931 |
-
{
|
| 1932 |
-
"epoch": 0.4297432239657632,
|
| 1933 |
-
"grad_norm": 1.615051507949829,
|
| 1934 |
-
"learning_rate": 4.751089426051476e-05,
|
| 1935 |
-
"loss": 0.4156,
|
| 1936 |
-
"num_input_tokens_seen": 14956432,
|
| 1937 |
-
"step": 1205
|
| 1938 |
-
},
|
| 1939 |
-
{
|
| 1940 |
-
"epoch": 0.43152639087018546,
|
| 1941 |
-
"grad_norm": 3.979645252227783,
|
| 1942 |
-
"learning_rate": 4.749054834726029e-05,
|
| 1943 |
-
"loss": 0.5188,
|
| 1944 |
-
"num_input_tokens_seen": 15021296,
|
| 1945 |
-
"step": 1210
|
| 1946 |
-
},
|
| 1947 |
-
{
|
| 1948 |
-
"epoch": 0.4333095577746077,
|
| 1949 |
-
"grad_norm": 1.3276335000991821,
|
| 1950 |
-
"learning_rate": 4.7470124011422555e-05,
|
| 1951 |
-
"loss": 0.4941,
|
| 1952 |
-
"num_input_tokens_seen": 15080688,
|
| 1953 |
-
"step": 1215
|
| 1954 |
-
},
|
| 1955 |
-
{
|
| 1956 |
-
"epoch": 0.43509272467902993,
|
| 1957 |
-
"grad_norm": 1.2513278722763062,
|
| 1958 |
-
"learning_rate": 4.744962132421943e-05,
|
| 1959 |
-
"loss": 0.4719,
|
| 1960 |
-
"num_input_tokens_seen": 15141456,
|
| 1961 |
-
"step": 1220
|
| 1962 |
-
},
|
| 1963 |
-
{
|
| 1964 |
-
"epoch": 0.4368758915834522,
|
| 1965 |
-
"grad_norm": 1.1449891328811646,
|
| 1966 |
-
"learning_rate": 4.742904035714199e-05,
|
| 1967 |
-
"loss": 0.4811,
|
| 1968 |
-
"num_input_tokens_seen": 15202768,
|
| 1969 |
-
"step": 1225
|
| 1970 |
-
},
|
| 1971 |
-
{
|
| 1972 |
-
"epoch": 0.43865905848787445,
|
| 1973 |
-
"grad_norm": 1.0668220520019531,
|
| 1974 |
-
"learning_rate": 4.7408381181954284e-05,
|
| 1975 |
-
"loss": 0.4801,
|
| 1976 |
-
"num_input_tokens_seen": 15266416,
|
| 1977 |
-
"step": 1230
|
| 1978 |
-
},
|
| 1979 |
-
{
|
| 1980 |
-
"epoch": 0.4404422253922967,
|
| 1981 |
-
"grad_norm": 1.576777458190918,
|
| 1982 |
-
"learning_rate": 4.7387643870693055e-05,
|
| 1983 |
-
"loss": 0.4551,
|
| 1984 |
-
"num_input_tokens_seen": 15328416,
|
| 1985 |
-
"step": 1235
|
| 1986 |
-
},
|
| 1987 |
-
{
|
| 1988 |
-
"epoch": 0.442225392296719,
|
| 1989 |
-
"grad_norm": 1.0677021741867065,
|
| 1990 |
-
"learning_rate": 4.736682849566751e-05,
|
| 1991 |
-
"loss": 0.3682,
|
| 1992 |
-
"num_input_tokens_seen": 15387392,
|
| 1993 |
-
"step": 1240
|
| 1994 |
-
},
|
| 1995 |
-
{
|
| 1996 |
-
"epoch": 0.44400855920114124,
|
| 1997 |
-
"grad_norm": 1.105083703994751,
|
| 1998 |
-
"learning_rate": 4.734593512945904e-05,
|
| 1999 |
-
"loss": 0.4721,
|
| 2000 |
-
"num_input_tokens_seen": 15444928,
|
| 2001 |
-
"step": 1245
|
| 2002 |
-
},
|
| 2003 |
-
{
|
| 2004 |
-
"epoch": 0.4457917261055635,
|
| 2005 |
-
"grad_norm": 1.1016100645065308,
|
| 2006 |
-
"learning_rate": 4.7324963844920986e-05,
|
| 2007 |
-
"loss": 0.4568,
|
| 2008 |
-
"num_input_tokens_seen": 15505488,
|
| 2009 |
-
"step": 1250
|
| 2010 |
-
},
|
| 2011 |
-
{
|
| 2012 |
-
"epoch": 0.4475748930099857,
|
| 2013 |
-
"grad_norm": 1.4010059833526611,
|
| 2014 |
-
"learning_rate": 4.7303914715178396e-05,
|
| 2015 |
-
"loss": 0.5337,
|
| 2016 |
-
"num_input_tokens_seen": 15566336,
|
| 2017 |
-
"step": 1255
|
| 2018 |
-
},
|
| 2019 |
-
{
|
| 2020 |
-
"epoch": 0.44935805991440797,
|
| 2021 |
-
"grad_norm": 1.149238109588623,
|
| 2022 |
-
"learning_rate": 4.728278781362777e-05,
|
| 2023 |
-
"loss": 0.3965,
|
| 2024 |
-
"num_input_tokens_seen": 15632768,
|
| 2025 |
-
"step": 1260
|
| 2026 |
-
},
|
| 2027 |
-
{
|
| 2028 |
-
"epoch": 0.45114122681883023,
|
| 2029 |
-
"grad_norm": 1.4296883344650269,
|
| 2030 |
-
"learning_rate": 4.7261583213936746e-05,
|
| 2031 |
-
"loss": 0.5366,
|
| 2032 |
-
"num_input_tokens_seen": 15694944,
|
| 2033 |
-
"step": 1265
|
| 2034 |
-
},
|
| 2035 |
-
{
|
| 2036 |
-
"epoch": 0.4529243937232525,
|
| 2037 |
-
"grad_norm": 1.2786849737167358,
|
| 2038 |
-
"learning_rate": 4.7240300990043926e-05,
|
| 2039 |
-
"loss": 0.4339,
|
| 2040 |
-
"num_input_tokens_seen": 15756496,
|
| 2041 |
-
"step": 1270
|
| 2042 |
-
},
|
| 2043 |
-
{
|
| 2044 |
-
"epoch": 0.45470756062767476,
|
| 2045 |
-
"grad_norm": 1.1299382448196411,
|
| 2046 |
-
"learning_rate": 4.721894121615859e-05,
|
| 2047 |
-
"loss": 0.4866,
|
| 2048 |
-
"num_input_tokens_seen": 15821200,
|
| 2049 |
-
"step": 1275
|
| 2050 |
-
},
|
| 2051 |
-
{
|
| 2052 |
-
"epoch": 0.456490727532097,
|
| 2053 |
-
"grad_norm": 1.1465532779693604,
|
| 2054 |
-
"learning_rate": 4.7197503966760375e-05,
|
| 2055 |
-
"loss": 0.4288,
|
| 2056 |
-
"num_input_tokens_seen": 15882736,
|
| 2057 |
-
"step": 1280
|
| 2058 |
-
},
|
| 2059 |
-
{
|
| 2060 |
-
"epoch": 0.4582738944365193,
|
| 2061 |
-
"grad_norm": 1.4677292108535767,
|
| 2062 |
-
"learning_rate": 4.717598931659913e-05,
|
| 2063 |
-
"loss": 0.443,
|
| 2064 |
-
"num_input_tokens_seen": 15944560,
|
| 2065 |
-
"step": 1285
|
| 2066 |
-
},
|
| 2067 |
-
{
|
| 2068 |
-
"epoch": 0.4600570613409415,
|
| 2069 |
-
"grad_norm": 1.8437912464141846,
|
| 2070 |
-
"learning_rate": 4.7154397340694556e-05,
|
| 2071 |
-
"loss": 0.4923,
|
| 2072 |
-
"num_input_tokens_seen": 16006784,
|
| 2073 |
-
"step": 1290
|
| 2074 |
-
},
|
| 2075 |
-
{
|
| 2076 |
-
"epoch": 0.46184022824536375,
|
| 2077 |
-
"grad_norm": 1.5408210754394531,
|
| 2078 |
-
"learning_rate": 4.713272811433599e-05,
|
| 2079 |
-
"loss": 0.4868,
|
| 2080 |
-
"num_input_tokens_seen": 16068896,
|
| 2081 |
-
"step": 1295
|
| 2082 |
-
},
|
| 2083 |
-
{
|
| 2084 |
-
"epoch": 0.463623395149786,
|
| 2085 |
-
"grad_norm": 1.1977325677871704,
|
| 2086 |
-
"learning_rate": 4.711098171308214e-05,
|
| 2087 |
-
"loss": 0.4781,
|
| 2088 |
-
"num_input_tokens_seen": 16128640,
|
| 2089 |
-
"step": 1300
|
| 2090 |
-
},
|
| 2091 |
-
{
|
| 2092 |
-
"epoch": 0.4654065620542083,
|
| 2093 |
-
"grad_norm": 1.470975399017334,
|
| 2094 |
-
"learning_rate": 4.708915821276082e-05,
|
| 2095 |
-
"loss": 0.4748,
|
| 2096 |
-
"num_input_tokens_seen": 16192800,
|
| 2097 |
-
"step": 1305
|
| 2098 |
-
},
|
| 2099 |
-
{
|
| 2100 |
-
"epoch": 0.46718972895863053,
|
| 2101 |
-
"grad_norm": 1.460138201713562,
|
| 2102 |
-
"learning_rate": 4.706725768946866e-05,
|
| 2103 |
-
"loss": 0.5107,
|
| 2104 |
-
"num_input_tokens_seen": 16251248,
|
| 2105 |
-
"step": 1310
|
| 2106 |
-
},
|
| 2107 |
-
{
|
| 2108 |
-
"epoch": 0.4689728958630528,
|
| 2109 |
-
"grad_norm": 1.2103915214538574,
|
| 2110 |
-
"learning_rate": 4.7045280219570896e-05,
|
| 2111 |
-
"loss": 0.4768,
|
| 2112 |
-
"num_input_tokens_seen": 16314704,
|
| 2113 |
-
"step": 1315
|
| 2114 |
-
},
|
| 2115 |
-
{
|
| 2116 |
-
"epoch": 0.47075606276747506,
|
| 2117 |
-
"grad_norm": 1.1669901609420776,
|
| 2118 |
-
"learning_rate": 4.702322587970104e-05,
|
| 2119 |
-
"loss": 0.4624,
|
| 2120 |
-
"num_input_tokens_seen": 16375792,
|
| 2121 |
-
"step": 1320
|
| 2122 |
-
},
|
| 2123 |
-
{
|
| 2124 |
-
"epoch": 0.47253922967189727,
|
| 2125 |
-
"grad_norm": 1.1790727376937866,
|
| 2126 |
-
"learning_rate": 4.700109474676064e-05,
|
| 2127 |
-
"loss": 0.4735,
|
| 2128 |
-
"num_input_tokens_seen": 16438672,
|
| 2129 |
-
"step": 1325
|
| 2130 |
-
},
|
| 2131 |
-
{
|
| 2132 |
-
"epoch": 0.4743223965763195,
|
| 2133 |
-
"grad_norm": 1.019875407218933,
|
| 2134 |
-
"learning_rate": 4.697888689791906e-05,
|
| 2135 |
-
"loss": 0.3809,
|
| 2136 |
-
"num_input_tokens_seen": 16498896,
|
| 2137 |
-
"step": 1330
|
| 2138 |
-
},
|
| 2139 |
-
{
|
| 2140 |
-
"epoch": 0.4761055634807418,
|
| 2141 |
-
"grad_norm": 1.2999383211135864,
|
| 2142 |
-
"learning_rate": 4.6956602410613115e-05,
|
| 2143 |
-
"loss": 0.4421,
|
| 2144 |
-
"num_input_tokens_seen": 16566736,
|
| 2145 |
-
"step": 1335
|
| 2146 |
-
},
|
| 2147 |
-
{
|
| 2148 |
-
"epoch": 0.47788873038516405,
|
| 2149 |
-
"grad_norm": 1.4289456605911255,
|
| 2150 |
-
"learning_rate": 4.6934241362546874e-05,
|
| 2151 |
-
"loss": 0.5083,
|
| 2152 |
-
"num_input_tokens_seen": 16630480,
|
| 2153 |
-
"step": 1340
|
| 2154 |
-
},
|
| 2155 |
-
{
|
| 2156 |
-
"epoch": 0.4796718972895863,
|
| 2157 |
-
"grad_norm": 1.2647002935409546,
|
| 2158 |
-
"learning_rate": 4.691180383169137e-05,
|
| 2159 |
-
"loss": 0.5118,
|
| 2160 |
-
"num_input_tokens_seen": 16688832,
|
| 2161 |
-
"step": 1345
|
| 2162 |
-
},
|
| 2163 |
-
{
|
| 2164 |
-
"epoch": 0.4814550641940086,
|
| 2165 |
-
"grad_norm": 1.1783503293991089,
|
| 2166 |
-
"learning_rate": 4.688928989628431e-05,
|
| 2167 |
-
"loss": 0.4128,
|
| 2168 |
-
"num_input_tokens_seen": 16752432,
|
| 2169 |
-
"step": 1350
|
| 2170 |
-
},
|
| 2171 |
-
{
|
| 2172 |
-
"epoch": 0.48323823109843084,
|
| 2173 |
-
"grad_norm": 1.2250187397003174,
|
| 2174 |
-
"learning_rate": 4.686669963482983e-05,
|
| 2175 |
-
"loss": 0.3974,
|
| 2176 |
-
"num_input_tokens_seen": 16814912,
|
| 2177 |
-
"step": 1355
|
| 2178 |
-
},
|
| 2179 |
-
{
|
| 2180 |
-
"epoch": 0.48502139800285304,
|
| 2181 |
-
"grad_norm": 1.5874429941177368,
|
| 2182 |
-
"learning_rate": 4.6844033126098206e-05,
|
| 2183 |
-
"loss": 0.5244,
|
| 2184 |
-
"num_input_tokens_seen": 16875696,
|
| 2185 |
-
"step": 1360
|
| 2186 |
-
},
|
| 2187 |
-
{
|
| 2188 |
-
"epoch": 0.4868045649072753,
|
| 2189 |
-
"grad_norm": 1.5424435138702393,
|
| 2190 |
-
"learning_rate": 4.682129044912558e-05,
|
| 2191 |
-
"loss": 0.3909,
|
| 2192 |
-
"num_input_tokens_seen": 16934768,
|
| 2193 |
-
"step": 1365
|
| 2194 |
-
},
|
| 2195 |
-
{
|
| 2196 |
-
"epoch": 0.48858773181169757,
|
| 2197 |
-
"grad_norm": 1.395538568496704,
|
| 2198 |
-
"learning_rate": 4.679847168321368e-05,
|
| 2199 |
-
"loss": 0.4208,
|
| 2200 |
-
"num_input_tokens_seen": 16994192,
|
| 2201 |
-
"step": 1370
|
| 2202 |
-
},
|
| 2203 |
-
{
|
| 2204 |
-
"epoch": 0.49037089871611983,
|
| 2205 |
-
"grad_norm": 1.3311400413513184,
|
| 2206 |
-
"learning_rate": 4.677557690792956e-05,
|
| 2207 |
-
"loss": 0.5148,
|
| 2208 |
-
"num_input_tokens_seen": 17055952,
|
| 2209 |
-
"step": 1375
|
| 2210 |
-
},
|
| 2211 |
-
{
|
| 2212 |
-
"epoch": 0.4921540656205421,
|
| 2213 |
-
"grad_norm": 1.0483784675598145,
|
| 2214 |
-
"learning_rate": 4.6752606203105314e-05,
|
| 2215 |
-
"loss": 0.4838,
|
| 2216 |
-
"num_input_tokens_seen": 17118352,
|
| 2217 |
-
"step": 1380
|
| 2218 |
-
},
|
| 2219 |
-
{
|
| 2220 |
-
"epoch": 0.49393723252496435,
|
| 2221 |
-
"grad_norm": 1.4240469932556152,
|
| 2222 |
-
"learning_rate": 4.6729559648837777e-05,
|
| 2223 |
-
"loss": 0.4676,
|
| 2224 |
-
"num_input_tokens_seen": 17181856,
|
| 2225 |
-
"step": 1385
|
| 2226 |
-
},
|
| 2227 |
-
{
|
| 2228 |
-
"epoch": 0.4957203994293866,
|
| 2229 |
-
"grad_norm": 1.1497527360916138,
|
| 2230 |
-
"learning_rate": 4.6706437325488285e-05,
|
| 2231 |
-
"loss": 0.4607,
|
| 2232 |
-
"num_input_tokens_seen": 17239040,
|
| 2233 |
-
"step": 1390
|
| 2234 |
-
},
|
| 2235 |
-
{
|
| 2236 |
-
"epoch": 0.4975035663338088,
|
| 2237 |
-
"grad_norm": 1.324589490890503,
|
| 2238 |
-
"learning_rate": 4.6683239313682356e-05,
|
| 2239 |
-
"loss": 0.3867,
|
| 2240 |
-
"num_input_tokens_seen": 17300096,
|
| 2241 |
-
"step": 1395
|
| 2242 |
-
},
|
| 2243 |
-
{
|
| 2244 |
-
"epoch": 0.4992867332382311,
|
| 2245 |
-
"grad_norm": 1.401481032371521,
|
| 2246 |
-
"learning_rate": 4.6659965694309446e-05,
|
| 2247 |
-
"loss": 0.477,
|
| 2248 |
-
"num_input_tokens_seen": 17367088,
|
| 2249 |
-
"step": 1400
|
| 2250 |
-
},
|
| 2251 |
-
{
|
| 2252 |
-
"epoch": 0.5010699001426534,
|
| 2253 |
-
"grad_norm": 1.0556763410568237,
|
| 2254 |
-
"learning_rate": 4.6636616548522637e-05,
|
| 2255 |
-
"loss": 0.4092,
|
| 2256 |
-
"num_input_tokens_seen": 17427648,
|
| 2257 |
-
"step": 1405
|
| 2258 |
-
},
|
| 2259 |
-
{
|
| 2260 |
-
"epoch": 0.5028530670470756,
|
| 2261 |
-
"grad_norm": 1.5187320709228516,
|
| 2262 |
-
"learning_rate": 4.661319195773837e-05,
|
| 2263 |
-
"loss": 0.4266,
|
| 2264 |
-
"num_input_tokens_seen": 17491664,
|
| 2265 |
-
"step": 1410
|
| 2266 |
-
},
|
| 2267 |
-
{
|
| 2268 |
-
"epoch": 0.5046362339514978,
|
| 2269 |
-
"grad_norm": 1.2626229524612427,
|
| 2270 |
-
"learning_rate": 4.658969200363614e-05,
|
| 2271 |
-
"loss": 0.5192,
|
| 2272 |
-
"num_input_tokens_seen": 17553312,
|
| 2273 |
-
"step": 1415
|
| 2274 |
-
},
|
| 2275 |
-
{
|
| 2276 |
-
"epoch": 0.5064194008559201,
|
| 2277 |
-
"grad_norm": 1.3596255779266357,
|
| 2278 |
-
"learning_rate": 4.6566116768158254e-05,
|
| 2279 |
-
"loss": 0.4983,
|
| 2280 |
-
"num_input_tokens_seen": 17614656,
|
| 2281 |
-
"step": 1420
|
| 2282 |
-
},
|
| 2283 |
-
{
|
| 2284 |
-
"epoch": 0.5082025677603423,
|
| 2285 |
-
"grad_norm": 1.131866455078125,
|
| 2286 |
-
"learning_rate": 4.6542466333509496e-05,
|
| 2287 |
-
"loss": 0.4593,
|
| 2288 |
-
"num_input_tokens_seen": 17673104,
|
| 2289 |
-
"step": 1425
|
| 2290 |
-
},
|
| 2291 |
-
{
|
| 2292 |
-
"epoch": 0.5099857346647646,
|
| 2293 |
-
"grad_norm": 1.1720597743988037,
|
| 2294 |
-
"learning_rate": 4.651874078215688e-05,
|
| 2295 |
-
"loss": 0.3885,
|
| 2296 |
-
"num_input_tokens_seen": 17733920,
|
| 2297 |
-
"step": 1430
|
| 2298 |
-
},
|
| 2299 |
-
{
|
| 2300 |
-
"epoch": 0.5117689015691869,
|
| 2301 |
-
"grad_norm": 1.1201550960540771,
|
| 2302 |
-
"learning_rate": 4.6494940196829326e-05,
|
| 2303 |
-
"loss": 0.4661,
|
| 2304 |
-
"num_input_tokens_seen": 17795024,
|
| 2305 |
-
"step": 1435
|
| 2306 |
-
},
|
| 2307 |
-
{
|
| 2308 |
-
"epoch": 0.5135520684736091,
|
| 2309 |
-
"grad_norm": 1.4359281063079834,
|
| 2310 |
-
"learning_rate": 4.647106466051741e-05,
|
| 2311 |
-
"loss": 0.4327,
|
| 2312 |
-
"num_input_tokens_seen": 17856080,
|
| 2313 |
-
"step": 1440
|
| 2314 |
-
},
|
| 2315 |
-
{
|
| 2316 |
-
"epoch": 0.5153352353780314,
|
| 2317 |
-
"grad_norm": 1.2126119136810303,
|
| 2318 |
-
"learning_rate": 4.644711425647305e-05,
|
| 2319 |
-
"loss": 0.4281,
|
| 2320 |
-
"num_input_tokens_seen": 17918592,
|
| 2321 |
-
"step": 1445
|
| 2322 |
-
},
|
| 2323 |
-
{
|
| 2324 |
-
"epoch": 0.5171184022824536,
|
| 2325 |
-
"grad_norm": 1.1998052597045898,
|
| 2326 |
-
"learning_rate": 4.642308906820921e-05,
|
| 2327 |
-
"loss": 0.4234,
|
| 2328 |
-
"num_input_tokens_seen": 17985056,
|
| 2329 |
-
"step": 1450
|
| 2330 |
-
},
|
| 2331 |
-
{
|
| 2332 |
-
"epoch": 0.5189015691868759,
|
| 2333 |
-
"grad_norm": 1.2513782978057861,
|
| 2334 |
-
"learning_rate": 4.6398989179499635e-05,
|
| 2335 |
-
"loss": 0.4952,
|
| 2336 |
-
"num_input_tokens_seen": 18047856,
|
| 2337 |
-
"step": 1455
|
| 2338 |
-
},
|
| 2339 |
-
{
|
| 2340 |
-
"epoch": 0.5206847360912982,
|
| 2341 |
-
"grad_norm": 1.5451606512069702,
|
| 2342 |
-
"learning_rate": 4.637481467437854e-05,
|
| 2343 |
-
"loss": 0.4061,
|
| 2344 |
-
"num_input_tokens_seen": 18110608,
|
| 2345 |
-
"step": 1460
|
| 2346 |
-
},
|
| 2347 |
-
{
|
| 2348 |
-
"epoch": 0.5224679029957204,
|
| 2349 |
-
"grad_norm": 1.280383586883545,
|
| 2350 |
-
"learning_rate": 4.635056563714031e-05,
|
| 2351 |
-
"loss": 0.4709,
|
| 2352 |
-
"num_input_tokens_seen": 18170192,
|
| 2353 |
-
"step": 1465
|
| 2354 |
-
},
|
| 2355 |
-
{
|
| 2356 |
-
"epoch": 0.5242510699001427,
|
| 2357 |
-
"grad_norm": 1.536872386932373,
|
| 2358 |
-
"learning_rate": 4.632624215233924e-05,
|
| 2359 |
-
"loss": 0.5166,
|
| 2360 |
-
"num_input_tokens_seen": 18234512,
|
| 2361 |
-
"step": 1470
|
| 2362 |
-
},
|
| 2363 |
-
{
|
| 2364 |
-
"epoch": 0.526034236804565,
|
| 2365 |
-
"grad_norm": 1.1344192028045654,
|
| 2366 |
-
"learning_rate": 4.6301844304789185e-05,
|
| 2367 |
-
"loss": 0.4313,
|
| 2368 |
-
"num_input_tokens_seen": 18297872,
|
| 2369 |
-
"step": 1475
|
| 2370 |
-
},
|
| 2371 |
-
{
|
| 2372 |
-
"epoch": 0.5278174037089871,
|
| 2373 |
-
"grad_norm": 1.2558397054672241,
|
| 2374 |
-
"learning_rate": 4.6277372179563336e-05,
|
| 2375 |
-
"loss": 0.4426,
|
| 2376 |
-
"num_input_tokens_seen": 18360688,
|
| 2377 |
-
"step": 1480
|
| 2378 |
-
},
|
| 2379 |
-
{
|
| 2380 |
-
"epoch": 0.5296005706134094,
|
| 2381 |
-
"grad_norm": 1.3379613161087036,
|
| 2382 |
-
"learning_rate": 4.625282586199384e-05,
|
| 2383 |
-
"loss": 0.4684,
|
| 2384 |
-
"num_input_tokens_seen": 18421600,
|
| 2385 |
-
"step": 1485
|
| 2386 |
-
},
|
| 2387 |
-
{
|
| 2388 |
-
"epoch": 0.5313837375178316,
|
| 2389 |
-
"grad_norm": 1.471182942390442,
|
| 2390 |
-
"learning_rate": 4.622820543767159e-05,
|
| 2391 |
-
"loss": 0.3746,
|
| 2392 |
-
"num_input_tokens_seen": 18482608,
|
| 2393 |
-
"step": 1490
|
| 2394 |
-
},
|
| 2395 |
-
{
|
| 2396 |
-
"epoch": 0.5331669044222539,
|
| 2397 |
-
"grad_norm": 1.147135853767395,
|
| 2398 |
-
"learning_rate": 4.6203510992445844e-05,
|
| 2399 |
-
"loss": 0.3896,
|
| 2400 |
-
"num_input_tokens_seen": 18542720,
|
| 2401 |
-
"step": 1495
|
| 2402 |
-
},
|
| 2403 |
-
{
|
| 2404 |
-
"epoch": 0.5349500713266762,
|
| 2405 |
-
"grad_norm": 1.6015293598175049,
|
| 2406 |
-
"learning_rate": 4.617874261242399e-05,
|
| 2407 |
-
"loss": 0.4613,
|
| 2408 |
-
"num_input_tokens_seen": 18604304,
|
| 2409 |
-
"step": 1500
|
| 2410 |
-
},
|
| 2411 |
-
{
|
| 2412 |
-
"epoch": 0.5367332382310984,
|
| 2413 |
-
"grad_norm": 1.1261463165283203,
|
| 2414 |
-
"learning_rate": 4.615390038397121e-05,
|
| 2415 |
-
"loss": 0.4636,
|
| 2416 |
-
"num_input_tokens_seen": 18666336,
|
| 2417 |
-
"step": 1505
|
| 2418 |
-
},
|
| 2419 |
-
{
|
| 2420 |
-
"epoch": 0.5385164051355207,
|
| 2421 |
-
"grad_norm": 1.1836202144622803,
|
| 2422 |
-
"learning_rate": 4.612898439371019e-05,
|
| 2423 |
-
"loss": 0.4072,
|
| 2424 |
-
"num_input_tokens_seen": 18724912,
|
| 2425 |
-
"step": 1510
|
| 2426 |
-
},
|
| 2427 |
-
{
|
| 2428 |
-
"epoch": 0.5402995720399429,
|
| 2429 |
-
"grad_norm": 1.108585238456726,
|
| 2430 |
-
"learning_rate": 4.6103994728520815e-05,
|
| 2431 |
-
"loss": 0.3483,
|
| 2432 |
-
"num_input_tokens_seen": 18786352,
|
| 2433 |
-
"step": 1515
|
| 2434 |
-
},
|
| 2435 |
-
{
|
| 2436 |
-
"epoch": 0.5420827389443652,
|
| 2437 |
-
"grad_norm": 1.3794957399368286,
|
| 2438 |
-
"learning_rate": 4.607893147553989e-05,
|
| 2439 |
-
"loss": 0.4259,
|
| 2440 |
-
"num_input_tokens_seen": 18851488,
|
| 2441 |
-
"step": 1520
|
| 2442 |
-
},
|
| 2443 |
-
{
|
| 2444 |
-
"epoch": 0.5438659058487875,
|
| 2445 |
-
"grad_norm": 1.4083433151245117,
|
| 2446 |
-
"learning_rate": 4.605379472216076e-05,
|
| 2447 |
-
"loss": 0.4364,
|
| 2448 |
-
"num_input_tokens_seen": 18915008,
|
| 2449 |
-
"step": 1525
|
| 2450 |
-
},
|
| 2451 |
-
{
|
| 2452 |
-
"epoch": 0.5456490727532097,
|
| 2453 |
-
"grad_norm": 1.3088963031768799,
|
| 2454 |
-
"learning_rate": 4.602858455603313e-05,
|
| 2455 |
-
"loss": 0.4098,
|
| 2456 |
-
"num_input_tokens_seen": 18976256,
|
| 2457 |
-
"step": 1530
|
| 2458 |
-
},
|
| 2459 |
-
{
|
| 2460 |
-
"epoch": 0.547432239657632,
|
| 2461 |
-
"grad_norm": 1.3022725582122803,
|
| 2462 |
-
"learning_rate": 4.600330106506263e-05,
|
| 2463 |
-
"loss": 0.4449,
|
| 2464 |
-
"num_input_tokens_seen": 19036560,
|
| 2465 |
-
"step": 1535
|
| 2466 |
-
},
|
| 2467 |
-
{
|
| 2468 |
-
"epoch": 0.5492154065620543,
|
| 2469 |
-
"grad_norm": 1.7286397218704224,
|
| 2470 |
-
"learning_rate": 4.597794433741061e-05,
|
| 2471 |
-
"loss": 0.5088,
|
| 2472 |
-
"num_input_tokens_seen": 19097568,
|
| 2473 |
-
"step": 1540
|
| 2474 |
-
},
|
| 2475 |
-
{
|
| 2476 |
-
"epoch": 0.5509985734664765,
|
| 2477 |
-
"grad_norm": 1.4286762475967407,
|
| 2478 |
-
"learning_rate": 4.5952514461493754e-05,
|
| 2479 |
-
"loss": 0.445,
|
| 2480 |
-
"num_input_tokens_seen": 19158592,
|
| 2481 |
-
"step": 1545
|
| 2482 |
-
},
|
| 2483 |
-
{
|
| 2484 |
-
"epoch": 0.5527817403708987,
|
| 2485 |
-
"grad_norm": 1.2713367938995361,
|
| 2486 |
-
"learning_rate": 4.5927011525983824e-05,
|
| 2487 |
-
"loss": 0.3791,
|
| 2488 |
-
"num_input_tokens_seen": 19215600,
|
| 2489 |
-
"step": 1550
|
| 2490 |
-
},
|
| 2491 |
-
{
|
| 2492 |
-
"epoch": 0.5545649072753209,
|
| 2493 |
-
"grad_norm": 1.3422623872756958,
|
| 2494 |
-
"learning_rate": 4.590143561980736e-05,
|
| 2495 |
-
"loss": 0.4897,
|
| 2496 |
-
"num_input_tokens_seen": 19277184,
|
| 2497 |
-
"step": 1555
|
| 2498 |
-
},
|
| 2499 |
-
{
|
| 2500 |
-
"epoch": 0.5563480741797432,
|
| 2501 |
-
"grad_norm": 1.278333306312561,
|
| 2502 |
-
"learning_rate": 4.5875786832145287e-05,
|
| 2503 |
-
"loss": 0.4426,
|
| 2504 |
-
"num_input_tokens_seen": 19338032,
|
| 2505 |
-
"step": 1560
|
| 2506 |
-
},
|
| 2507 |
-
{
|
| 2508 |
-
"epoch": 0.5581312410841655,
|
| 2509 |
-
"grad_norm": 1.4938713312149048,
|
| 2510 |
-
"learning_rate": 4.5850065252432706e-05,
|
| 2511 |
-
"loss": 0.4246,
|
| 2512 |
-
"num_input_tokens_seen": 19397040,
|
| 2513 |
-
"step": 1565
|
| 2514 |
-
},
|
| 2515 |
-
{
|
| 2516 |
-
"epoch": 0.5599144079885877,
|
| 2517 |
-
"grad_norm": 2.4364399909973145,
|
| 2518 |
-
"learning_rate": 4.582427097035854e-05,
|
| 2519 |
-
"loss": 0.4777,
|
| 2520 |
-
"num_input_tokens_seen": 19456144,
|
| 2521 |
-
"step": 1570
|
| 2522 |
-
},
|
| 2523 |
-
{
|
| 2524 |
-
"epoch": 0.56169757489301,
|
| 2525 |
-
"grad_norm": 3.5539422035217285,
|
| 2526 |
-
"learning_rate": 4.579840407586517e-05,
|
| 2527 |
-
"loss": 0.4894,
|
| 2528 |
-
"num_input_tokens_seen": 19518176,
|
| 2529 |
-
"step": 1575
|
| 2530 |
-
},
|
| 2531 |
-
{
|
| 2532 |
-
"epoch": 0.5634807417974322,
|
| 2533 |
-
"grad_norm": 1.4036399126052856,
|
| 2534 |
-
"learning_rate": 4.577246465914825e-05,
|
| 2535 |
-
"loss": 0.4704,
|
| 2536 |
-
"num_input_tokens_seen": 19581024,
|
| 2537 |
-
"step": 1580
|
| 2538 |
-
},
|
| 2539 |
-
{
|
| 2540 |
-
"epoch": 0.5652639087018545,
|
| 2541 |
-
"grad_norm": 0.9552262425422668,
|
| 2542 |
-
"learning_rate": 4.5746452810656225e-05,
|
| 2543 |
-
"loss": 0.4527,
|
| 2544 |
-
"num_input_tokens_seen": 19643104,
|
| 2545 |
-
"step": 1585
|
| 2546 |
-
},
|
| 2547 |
-
{
|
| 2548 |
-
"epoch": 0.5670470756062768,
|
| 2549 |
-
"grad_norm": 1.2145711183547974,
|
| 2550 |
-
"learning_rate": 4.572036862109017e-05,
|
| 2551 |
-
"loss": 0.4612,
|
| 2552 |
-
"num_input_tokens_seen": 19702528,
|
| 2553 |
-
"step": 1590
|
| 2554 |
-
},
|
| 2555 |
-
{
|
| 2556 |
-
"epoch": 0.568830242510699,
|
| 2557 |
-
"grad_norm": 1.0046789646148682,
|
| 2558 |
-
"learning_rate": 4.5694212181403374e-05,
|
| 2559 |
-
"loss": 0.4235,
|
| 2560 |
-
"num_input_tokens_seen": 19763424,
|
| 2561 |
-
"step": 1595
|
| 2562 |
-
},
|
| 2563 |
-
{
|
| 2564 |
-
"epoch": 0.5706134094151213,
|
| 2565 |
-
"grad_norm": 1.3540983200073242,
|
| 2566 |
-
"learning_rate": 4.5667983582801064e-05,
|
| 2567 |
-
"loss": 0.3833,
|
| 2568 |
-
"num_input_tokens_seen": 19823200,
|
| 2569 |
-
"step": 1600
|
| 2570 |
-
},
|
| 2571 |
-
{
|
| 2572 |
-
"epoch": 0.5723965763195435,
|
| 2573 |
-
"grad_norm": 1.2544758319854736,
|
| 2574 |
-
"learning_rate": 4.5641682916740084e-05,
|
| 2575 |
-
"loss": 0.4586,
|
| 2576 |
-
"num_input_tokens_seen": 19883888,
|
| 2577 |
-
"step": 1605
|
| 2578 |
-
},
|
| 2579 |
-
{
|
| 2580 |
-
"epoch": 0.5741797432239658,
|
| 2581 |
-
"grad_norm": 1.1667801141738892,
|
| 2582 |
-
"learning_rate": 4.5615310274928556e-05,
|
| 2583 |
-
"loss": 0.5969,
|
| 2584 |
-
"num_input_tokens_seen": 19949840,
|
| 2585 |
-
"step": 1610
|
| 2586 |
-
},
|
| 2587 |
-
{
|
| 2588 |
-
"epoch": 0.5759629101283881,
|
| 2589 |
-
"grad_norm": 0.9844037294387817,
|
| 2590 |
-
"learning_rate": 4.5588865749325594e-05,
|
| 2591 |
-
"loss": 0.3798,
|
| 2592 |
-
"num_input_tokens_seen": 20014640,
|
| 2593 |
-
"step": 1615
|
| 2594 |
-
},
|
| 2595 |
-
{
|
| 2596 |
-
"epoch": 0.5777460770328102,
|
| 2597 |
-
"grad_norm": 1.3161027431488037,
|
| 2598 |
-
"learning_rate": 4.556234943214095e-05,
|
| 2599 |
-
"loss": 0.4234,
|
| 2600 |
-
"num_input_tokens_seen": 20077008,
|
| 2601 |
-
"step": 1620
|
| 2602 |
-
},
|
| 2603 |
-
{
|
| 2604 |
-
"epoch": 0.5795292439372325,
|
| 2605 |
-
"grad_norm": 1.1113629341125488,
|
| 2606 |
-
"learning_rate": 4.5535761415834724e-05,
|
| 2607 |
-
"loss": 0.4714,
|
| 2608 |
-
"num_input_tokens_seen": 20141488,
|
| 2609 |
-
"step": 1625
|
| 2610 |
-
},
|
| 2611 |
-
{
|
| 2612 |
-
"epoch": 0.5813124108416547,
|
| 2613 |
-
"grad_norm": 1.3117053508758545,
|
| 2614 |
-
"learning_rate": 4.550910179311699e-05,
|
| 2615 |
-
"loss": 0.5514,
|
| 2616 |
-
"num_input_tokens_seen": 20206016,
|
| 2617 |
-
"step": 1630
|
| 2618 |
-
},
|
| 2619 |
-
{
|
| 2620 |
-
"epoch": 0.583095577746077,
|
| 2621 |
-
"grad_norm": 1.151132345199585,
|
| 2622 |
-
"learning_rate": 4.5482370656947554e-05,
|
| 2623 |
-
"loss": 0.4626,
|
| 2624 |
-
"num_input_tokens_seen": 20270880,
|
| 2625 |
-
"step": 1635
|
| 2626 |
-
},
|
| 2627 |
-
{
|
| 2628 |
-
"epoch": 0.5848787446504993,
|
| 2629 |
-
"grad_norm": 2.0122318267822266,
|
| 2630 |
-
"learning_rate": 4.5455568100535545e-05,
|
| 2631 |
-
"loss": 0.4758,
|
| 2632 |
-
"num_input_tokens_seen": 20334448,
|
| 2633 |
-
"step": 1640
|
| 2634 |
-
},
|
| 2635 |
-
{
|
| 2636 |
-
"epoch": 0.5866619115549215,
|
| 2637 |
-
"grad_norm": 1.6800963878631592,
|
| 2638 |
-
"learning_rate": 4.542869421733915e-05,
|
| 2639 |
-
"loss": 0.4178,
|
| 2640 |
-
"num_input_tokens_seen": 20398480,
|
| 2641 |
-
"step": 1645
|
| 2642 |
-
},
|
| 2643 |
-
{
|
| 2644 |
-
"epoch": 0.5884450784593438,
|
| 2645 |
-
"grad_norm": 1.4573643207550049,
|
| 2646 |
-
"learning_rate": 4.540174910106526e-05,
|
| 2647 |
-
"loss": 0.4314,
|
| 2648 |
-
"num_input_tokens_seen": 20458128,
|
| 2649 |
-
"step": 1650
|
| 2650 |
-
},
|
| 2651 |
-
{
|
| 2652 |
-
"epoch": 0.5902282453637661,
|
| 2653 |
-
"grad_norm": 1.1499691009521484,
|
| 2654 |
-
"learning_rate": 4.537473284566914e-05,
|
| 2655 |
-
"loss": 0.4182,
|
| 2656 |
-
"num_input_tokens_seen": 20521840,
|
| 2657 |
-
"step": 1655
|
| 2658 |
-
},
|
| 2659 |
-
{
|
| 2660 |
-
"epoch": 0.5920114122681883,
|
| 2661 |
-
"grad_norm": 1.1684014797210693,
|
| 2662 |
-
"learning_rate": 4.5347645545354136e-05,
|
| 2663 |
-
"loss": 0.3945,
|
| 2664 |
-
"num_input_tokens_seen": 20582304,
|
| 2665 |
-
"step": 1660
|
| 2666 |
-
},
|
| 2667 |
-
{
|
| 2668 |
-
"epoch": 0.5937945791726106,
|
| 2669 |
-
"grad_norm": 1.358035683631897,
|
| 2670 |
-
"learning_rate": 4.532048729457128e-05,
|
| 2671 |
-
"loss": 0.4674,
|
| 2672 |
-
"num_input_tokens_seen": 20642656,
|
| 2673 |
-
"step": 1665
|
| 2674 |
-
},
|
| 2675 |
-
{
|
| 2676 |
-
"epoch": 0.5955777460770328,
|
| 2677 |
-
"grad_norm": 1.285057783126831,
|
| 2678 |
-
"learning_rate": 4.5293258188019055e-05,
|
| 2679 |
-
"loss": 0.4027,
|
| 2680 |
-
"num_input_tokens_seen": 20709664,
|
| 2681 |
-
"step": 1670
|
| 2682 |
-
},
|
| 2683 |
-
{
|
| 2684 |
-
"epoch": 0.5973609129814551,
|
| 2685 |
-
"grad_norm": 1.0107051134109497,
|
| 2686 |
-
"learning_rate": 4.526595832064296e-05,
|
| 2687 |
-
"loss": 0.4402,
|
| 2688 |
-
"num_input_tokens_seen": 20769888,
|
| 2689 |
-
"step": 1675
|
| 2690 |
-
},
|
| 2691 |
-
{
|
| 2692 |
-
"epoch": 0.5991440798858774,
|
| 2693 |
-
"grad_norm": 1.144665241241455,
|
| 2694 |
-
"learning_rate": 4.523858778763528e-05,
|
| 2695 |
-
"loss": 0.4725,
|
| 2696 |
-
"num_input_tokens_seen": 20834912,
|
| 2697 |
-
"step": 1680
|
| 2698 |
-
},
|
| 2699 |
-
{
|
| 2700 |
-
"epoch": 0.6009272467902995,
|
| 2701 |
-
"grad_norm": 1.5452603101730347,
|
| 2702 |
-
"learning_rate": 4.521114668443464e-05,
|
| 2703 |
-
"loss": 0.4413,
|
| 2704 |
-
"num_input_tokens_seen": 20896784,
|
| 2705 |
-
"step": 1685
|
| 2706 |
-
},
|
| 2707 |
-
{
|
| 2708 |
-
"epoch": 0.6027104136947218,
|
| 2709 |
-
"grad_norm": 1.0601692199707031,
|
| 2710 |
-
"learning_rate": 4.518363510672583e-05,
|
| 2711 |
-
"loss": 0.4758,
|
| 2712 |
-
"num_input_tokens_seen": 20954224,
|
| 2713 |
-
"step": 1690
|
| 2714 |
-
},
|
| 2715 |
-
{
|
| 2716 |
-
"epoch": 0.604493580599144,
|
| 2717 |
-
"grad_norm": 1.6150104999542236,
|
| 2718 |
-
"learning_rate": 4.515605315043928e-05,
|
| 2719 |
-
"loss": 0.4027,
|
| 2720 |
-
"num_input_tokens_seen": 21019760,
|
| 2721 |
-
"step": 1695
|
| 2722 |
-
},
|
| 2723 |
-
{
|
| 2724 |
-
"epoch": 0.6062767475035663,
|
| 2725 |
-
"grad_norm": 1.3952018022537231,
|
| 2726 |
-
"learning_rate": 4.512840091175089e-05,
|
| 2727 |
-
"loss": 0.4497,
|
| 2728 |
-
"num_input_tokens_seen": 21081952,
|
| 2729 |
-
"step": 1700
|
| 2730 |
-
},
|
| 2731 |
-
{
|
| 2732 |
-
"epoch": 0.6080599144079886,
|
| 2733 |
-
"grad_norm": 1.6579699516296387,
|
| 2734 |
-
"learning_rate": 4.5100678487081614e-05,
|
| 2735 |
-
"loss": 0.4343,
|
| 2736 |
-
"num_input_tokens_seen": 21145680,
|
| 2737 |
-
"step": 1705
|
| 2738 |
-
},
|
| 2739 |
-
{
|
| 2740 |
-
"epoch": 0.6098430813124108,
|
| 2741 |
-
"grad_norm": 1.5067193508148193,
|
| 2742 |
-
"learning_rate": 4.507288597309711e-05,
|
| 2743 |
-
"loss": 0.4142,
|
| 2744 |
-
"num_input_tokens_seen": 21206048,
|
| 2745 |
-
"step": 1710
|
| 2746 |
-
},
|
| 2747 |
-
{
|
| 2748 |
-
"epoch": 0.6116262482168331,
|
| 2749 |
-
"grad_norm": 1.2458901405334473,
|
| 2750 |
-
"learning_rate": 4.504502346670748e-05,
|
| 2751 |
-
"loss": 0.5092,
|
| 2752 |
-
"num_input_tokens_seen": 21269520,
|
| 2753 |
-
"step": 1715
|
| 2754 |
-
},
|
| 2755 |
-
{
|
| 2756 |
-
"epoch": 0.6134094151212554,
|
| 2757 |
-
"grad_norm": 1.33489990234375,
|
| 2758 |
-
"learning_rate": 4.5017091065066837e-05,
|
| 2759 |
-
"loss": 0.4563,
|
| 2760 |
-
"num_input_tokens_seen": 21331136,
|
| 2761 |
-
"step": 1720
|
| 2762 |
-
},
|
| 2763 |
-
{
|
| 2764 |
-
"epoch": 0.6151925820256776,
|
| 2765 |
-
"grad_norm": 1.4016698598861694,
|
| 2766 |
-
"learning_rate": 4.4989088865573035e-05,
|
| 2767 |
-
"loss": 0.3743,
|
| 2768 |
-
"num_input_tokens_seen": 21392496,
|
| 2769 |
-
"step": 1725
|
| 2770 |
-
},
|
| 2771 |
-
{
|
| 2772 |
-
"epoch": 0.6169757489300999,
|
| 2773 |
-
"grad_norm": 1.5638152360916138,
|
| 2774 |
-
"learning_rate": 4.496101696586732e-05,
|
| 2775 |
-
"loss": 0.4823,
|
| 2776 |
-
"num_input_tokens_seen": 21455504,
|
| 2777 |
-
"step": 1730
|
| 2778 |
-
},
|
| 2779 |
-
{
|
| 2780 |
-
"epoch": 0.6187589158345221,
|
| 2781 |
-
"grad_norm": 1.2184085845947266,
|
| 2782 |
-
"learning_rate": 4.4932875463833944e-05,
|
| 2783 |
-
"loss": 0.4219,
|
| 2784 |
-
"num_input_tokens_seen": 21518800,
|
| 2785 |
-
"step": 1735
|
| 2786 |
-
},
|
| 2787 |
-
{
|
| 2788 |
-
"epoch": 0.6205420827389444,
|
| 2789 |
-
"grad_norm": 1.5745280981063843,
|
| 2790 |
-
"learning_rate": 4.490466445759988e-05,
|
| 2791 |
-
"loss": 0.506,
|
| 2792 |
-
"num_input_tokens_seen": 21579120,
|
| 2793 |
-
"step": 1740
|
| 2794 |
-
},
|
| 2795 |
-
{
|
| 2796 |
-
"epoch": 0.6223252496433667,
|
| 2797 |
-
"grad_norm": 1.4783879518508911,
|
| 2798 |
-
"learning_rate": 4.487638404553445e-05,
|
| 2799 |
-
"loss": 0.4638,
|
| 2800 |
-
"num_input_tokens_seen": 21638528,
|
| 2801 |
-
"step": 1745
|
| 2802 |
-
},
|
| 2803 |
-
{
|
| 2804 |
-
"epoch": 0.6241084165477889,
|
| 2805 |
-
"grad_norm": 1.4319891929626465,
|
| 2806 |
-
"learning_rate": 4.484803432624899e-05,
|
| 2807 |
-
"loss": 0.434,
|
| 2808 |
-
"num_input_tokens_seen": 21703664,
|
| 2809 |
-
"step": 1750
|
| 2810 |
-
},
|
| 2811 |
-
{
|
| 2812 |
-
"epoch": 0.6258915834522111,
|
| 2813 |
-
"grad_norm": 1.3542821407318115,
|
| 2814 |
-
"learning_rate": 4.48196153985965e-05,
|
| 2815 |
-
"loss": 0.4472,
|
| 2816 |
-
"num_input_tokens_seen": 21764336,
|
| 2817 |
-
"step": 1755
|
| 2818 |
-
},
|
| 2819 |
-
{
|
| 2820 |
-
"epoch": 0.6276747503566333,
|
| 2821 |
-
"grad_norm": 1.1602082252502441,
|
| 2822 |
-
"learning_rate": 4.4791127361671304e-05,
|
| 2823 |
-
"loss": 0.3541,
|
| 2824 |
-
"num_input_tokens_seen": 21825392,
|
| 2825 |
-
"step": 1760
|
| 2826 |
-
},
|
| 2827 |
-
{
|
| 2828 |
-
"epoch": 0.6294579172610556,
|
| 2829 |
-
"grad_norm": 1.6145776510238647,
|
| 2830 |
-
"learning_rate": 4.476257031480871e-05,
|
| 2831 |
-
"loss": 0.4401,
|
| 2832 |
-
"num_input_tokens_seen": 21886848,
|
| 2833 |
-
"step": 1765
|
| 2834 |
-
},
|
| 2835 |
-
{
|
| 2836 |
-
"epoch": 0.6312410841654779,
|
| 2837 |
-
"grad_norm": 1.1257821321487427,
|
| 2838 |
-
"learning_rate": 4.4733944357584644e-05,
|
| 2839 |
-
"loss": 0.5242,
|
| 2840 |
-
"num_input_tokens_seen": 21951680,
|
| 2841 |
-
"step": 1770
|
| 2842 |
-
},
|
| 2843 |
-
{
|
| 2844 |
-
"epoch": 0.6330242510699001,
|
| 2845 |
-
"grad_norm": 1.4322980642318726,
|
| 2846 |
-
"learning_rate": 4.470524958981534e-05,
|
| 2847 |
-
"loss": 0.4926,
|
| 2848 |
-
"num_input_tokens_seen": 22016624,
|
| 2849 |
-
"step": 1775
|
| 2850 |
-
},
|
| 2851 |
-
{
|
| 2852 |
-
"epoch": 0.6348074179743224,
|
| 2853 |
-
"grad_norm": 1.255799651145935,
|
| 2854 |
-
"learning_rate": 4.4676486111556936e-05,
|
| 2855 |
-
"loss": 0.4128,
|
| 2856 |
-
"num_input_tokens_seen": 22079040,
|
| 2857 |
-
"step": 1780
|
| 2858 |
-
},
|
| 2859 |
-
{
|
| 2860 |
-
"epoch": 0.6365905848787446,
|
| 2861 |
-
"grad_norm": 1.157120943069458,
|
| 2862 |
-
"learning_rate": 4.46476540231052e-05,
|
| 2863 |
-
"loss": 0.3521,
|
| 2864 |
-
"num_input_tokens_seen": 22142400,
|
| 2865 |
-
"step": 1785
|
| 2866 |
-
},
|
| 2867 |
-
{
|
| 2868 |
-
"epoch": 0.6383737517831669,
|
| 2869 |
-
"grad_norm": 1.5262624025344849,
|
| 2870 |
-
"learning_rate": 4.461875342499509e-05,
|
| 2871 |
-
"loss": 0.4028,
|
| 2872 |
-
"num_input_tokens_seen": 22199136,
|
| 2873 |
-
"step": 1790
|
| 2874 |
-
},
|
| 2875 |
-
{
|
| 2876 |
-
"epoch": 0.6401569186875892,
|
| 2877 |
-
"grad_norm": 1.7937567234039307,
|
| 2878 |
-
"learning_rate": 4.458978441800048e-05,
|
| 2879 |
-
"loss": 0.4126,
|
| 2880 |
-
"num_input_tokens_seen": 22260608,
|
| 2881 |
-
"step": 1795
|
| 2882 |
-
},
|
| 2883 |
-
{
|
| 2884 |
-
"epoch": 0.6419400855920114,
|
| 2885 |
-
"grad_norm": 1.3475735187530518,
|
| 2886 |
-
"learning_rate": 4.456074710313378e-05,
|
| 2887 |
-
"loss": 0.4692,
|
| 2888 |
-
"num_input_tokens_seen": 22322272,
|
| 2889 |
-
"step": 1800
|
| 2890 |
-
},
|
| 2891 |
-
{
|
| 2892 |
-
"epoch": 0.6437232524964337,
|
| 2893 |
-
"grad_norm": 1.2804908752441406,
|
| 2894 |
-
"learning_rate": 4.4531641581645576e-05,
|
| 2895 |
-
"loss": 0.4931,
|
| 2896 |
-
"num_input_tokens_seen": 22384368,
|
| 2897 |
-
"step": 1805
|
| 2898 |
-
},
|
| 2899 |
-
{
|
| 2900 |
-
"epoch": 0.645506419400856,
|
| 2901 |
-
"grad_norm": 1.2529658079147339,
|
| 2902 |
-
"learning_rate": 4.4502467955024294e-05,
|
| 2903 |
-
"loss": 0.386,
|
| 2904 |
-
"num_input_tokens_seen": 22447888,
|
| 2905 |
-
"step": 1810
|
| 2906 |
-
},
|
| 2907 |
-
{
|
| 2908 |
-
"epoch": 0.6472895863052782,
|
| 2909 |
-
"grad_norm": 1.3398923873901367,
|
| 2910 |
-
"learning_rate": 4.447322632499581e-05,
|
| 2911 |
-
"loss": 0.4522,
|
| 2912 |
-
"num_input_tokens_seen": 22514704,
|
| 2913 |
-
"step": 1815
|
| 2914 |
-
},
|
| 2915 |
-
{
|
| 2916 |
-
"epoch": 0.6490727532097005,
|
| 2917 |
-
"grad_norm": 1.320273518562317,
|
| 2918 |
-
"learning_rate": 4.444391679352315e-05,
|
| 2919 |
-
"loss": 0.4082,
|
| 2920 |
-
"num_input_tokens_seen": 22573024,
|
| 2921 |
-
"step": 1820
|
| 2922 |
-
},
|
| 2923 |
-
{
|
| 2924 |
-
"epoch": 0.6508559201141226,
|
| 2925 |
-
"grad_norm": 1.2203108072280884,
|
| 2926 |
-
"learning_rate": 4.441453946280612e-05,
|
| 2927 |
-
"loss": 0.4551,
|
| 2928 |
-
"num_input_tokens_seen": 22632080,
|
| 2929 |
-
"step": 1825
|
| 2930 |
-
},
|
| 2931 |
-
{
|
| 2932 |
-
"epoch": 0.6526390870185449,
|
| 2933 |
-
"grad_norm": 1.1191906929016113,
|
| 2934 |
-
"learning_rate": 4.4385094435280873e-05,
|
| 2935 |
-
"loss": 0.3873,
|
| 2936 |
-
"num_input_tokens_seen": 22692192,
|
| 2937 |
-
"step": 1830
|
| 2938 |
-
},
|
| 2939 |
-
{
|
| 2940 |
-
"epoch": 0.6544222539229672,
|
| 2941 |
-
"grad_norm": 1.249611496925354,
|
| 2942 |
-
"learning_rate": 4.435558181361969e-05,
|
| 2943 |
-
"loss": 0.398,
|
| 2944 |
-
"num_input_tokens_seen": 22754624,
|
| 2945 |
-
"step": 1835
|
| 2946 |
-
},
|
| 2947 |
-
{
|
| 2948 |
-
"epoch": 0.6562054208273894,
|
| 2949 |
-
"grad_norm": 1.4326295852661133,
|
| 2950 |
-
"learning_rate": 4.432600170073048e-05,
|
| 2951 |
-
"loss": 0.4159,
|
| 2952 |
-
"num_input_tokens_seen": 22819616,
|
| 2953 |
-
"step": 1840
|
| 2954 |
-
},
|
| 2955 |
-
{
|
| 2956 |
-
"epoch": 0.6579885877318117,
|
| 2957 |
-
"grad_norm": 1.2453666925430298,
|
| 2958 |
-
"learning_rate": 4.429635419975655e-05,
|
| 2959 |
-
"loss": 0.4343,
|
| 2960 |
-
"num_input_tokens_seen": 22879136,
|
| 2961 |
-
"step": 1845
|
| 2962 |
-
},
|
| 2963 |
-
{
|
| 2964 |
-
"epoch": 0.6597717546362339,
|
| 2965 |
-
"grad_norm": 1.1724647283554077,
|
| 2966 |
-
"learning_rate": 4.426663941407614e-05,
|
| 2967 |
-
"loss": 0.4287,
|
| 2968 |
-
"num_input_tokens_seen": 22940528,
|
| 2969 |
-
"step": 1850
|
| 2970 |
-
},
|
| 2971 |
-
{
|
| 2972 |
-
"epoch": 0.6615549215406562,
|
| 2973 |
-
"grad_norm": 1.185964822769165,
|
| 2974 |
-
"learning_rate": 4.423685744730213e-05,
|
| 2975 |
-
"loss": 0.3901,
|
| 2976 |
-
"num_input_tokens_seen": 23004128,
|
| 2977 |
-
"step": 1855
|
| 2978 |
-
},
|
| 2979 |
-
{
|
| 2980 |
-
"epoch": 0.6633380884450785,
|
| 2981 |
-
"grad_norm": 1.167861819267273,
|
| 2982 |
-
"learning_rate": 4.420700840328162e-05,
|
| 2983 |
-
"loss": 0.512,
|
| 2984 |
-
"num_input_tokens_seen": 23066240,
|
| 2985 |
-
"step": 1860
|
| 2986 |
-
},
|
| 2987 |
-
{
|
| 2988 |
-
"epoch": 0.6651212553495007,
|
| 2989 |
-
"grad_norm": 1.6327167749404907,
|
| 2990 |
-
"learning_rate": 4.417709238609566e-05,
|
| 2991 |
-
"loss": 0.4102,
|
| 2992 |
-
"num_input_tokens_seen": 23126128,
|
| 2993 |
-
"step": 1865
|
| 2994 |
-
},
|
| 2995 |
-
{
|
| 2996 |
-
"epoch": 0.666904422253923,
|
| 2997 |
-
"grad_norm": 1.0951687097549438,
|
| 2998 |
-
"learning_rate": 4.4147109500058776e-05,
|
| 2999 |
-
"loss": 0.4767,
|
| 3000 |
-
"num_input_tokens_seen": 23182704,
|
| 3001 |
-
"step": 1870
|
| 3002 |
-
},
|
| 3003 |
-
{
|
| 3004 |
-
"epoch": 0.6686875891583453,
|
| 3005 |
-
"grad_norm": 1.1051822900772095,
|
| 3006 |
-
"learning_rate": 4.411705984971868e-05,
|
| 3007 |
-
"loss": 0.4009,
|
| 3008 |
-
"num_input_tokens_seen": 23244816,
|
| 3009 |
-
"step": 1875
|
| 3010 |
-
},
|
| 3011 |
-
{
|
| 3012 |
-
"epoch": 0.6704707560627675,
|
| 3013 |
-
"grad_norm": 1.4562581777572632,
|
| 3014 |
-
"learning_rate": 4.408694353985589e-05,
|
| 3015 |
-
"loss": 0.5083,
|
| 3016 |
-
"num_input_tokens_seen": 23307776,
|
| 3017 |
-
"step": 1880
|
| 3018 |
-
},
|
| 3019 |
-
{
|
| 3020 |
-
"epoch": 0.6722539229671898,
|
| 3021 |
-
"grad_norm": 1.4651310443878174,
|
| 3022 |
-
"learning_rate": 4.4056760675483356e-05,
|
| 3023 |
-
"loss": 0.5302,
|
| 3024 |
-
"num_input_tokens_seen": 23370368,
|
| 3025 |
-
"step": 1885
|
| 3026 |
-
},
|
| 3027 |
-
{
|
| 3028 |
-
"epoch": 0.6740370898716119,
|
| 3029 |
-
"grad_norm": 1.1008446216583252,
|
| 3030 |
-
"learning_rate": 4.402651136184609e-05,
|
| 3031 |
-
"loss": 0.3035,
|
| 3032 |
-
"num_input_tokens_seen": 23436192,
|
| 3033 |
-
"step": 1890
|
| 3034 |
-
},
|
| 3035 |
-
{
|
| 3036 |
-
"epoch": 0.6758202567760342,
|
| 3037 |
-
"grad_norm": 1.7820332050323486,
|
| 3038 |
-
"learning_rate": 4.3996195704420826e-05,
|
| 3039 |
-
"loss": 0.3972,
|
| 3040 |
-
"num_input_tokens_seen": 23501408,
|
| 3041 |
-
"step": 1895
|
| 3042 |
-
},
|
| 3043 |
-
{
|
| 3044 |
-
"epoch": 0.6776034236804565,
|
| 3045 |
-
"grad_norm": 1.2907474040985107,
|
| 3046 |
-
"learning_rate": 4.396581380891562e-05,
|
| 3047 |
-
"loss": 0.4644,
|
| 3048 |
-
"num_input_tokens_seen": 23561072,
|
| 3049 |
-
"step": 1900
|
| 3050 |
-
}
|
| 3051 |
-
],
|
| 3052 |
-
"logging_steps": 5,
|
| 3053 |
-
"max_steps": 8412,
|
| 3054 |
-
"num_input_tokens_seen": 23561072,
|
| 3055 |
-
"num_train_epochs": 3,
|
| 3056 |
-
"save_steps": 100,
|
| 3057 |
-
"stateful_callbacks": {
|
| 3058 |
-
"TrainerControl": {
|
| 3059 |
-
"args": {
|
| 3060 |
-
"should_epoch_stop": false,
|
| 3061 |
-
"should_evaluate": false,
|
| 3062 |
-
"should_log": false,
|
| 3063 |
-
"should_save": true,
|
| 3064 |
-
"should_training_stop": false
|
| 3065 |
-
},
|
| 3066 |
-
"attributes": {}
|
| 3067 |
-
}
|
| 3068 |
-
},
|
| 3069 |
-
"total_flos": 1.8654332564260454e+17,
|
| 3070 |
-
"train_batch_size": 2,
|
| 3071 |
-
"trial_name": null,
|
| 3072 |
-
"trial_params": null
|
| 3073 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|