File size: 15,509 Bytes
69b9b1b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.3161794977356937,
"eval_steps": 500,
"global_step": 24,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013174145738987238,
"grad_norm": 0.48070791363716125,
"learning_rate": 6.25e-08,
"logits/chosen": 10.32492733001709,
"logits/rejected": 10.282785415649414,
"logps/chosen": -176.09544372558594,
"logps/ref_chosen": -176.09544372558594,
"logps/ref_rejected": -181.75552368164062,
"logps/rejected": -181.75552368164062,
"loss": 0.6931,
"rewards/accuracies": 0.0,
"rewards/chosen": 0.0,
"rewards/margins": 0.0,
"rewards/rejected": 0.0,
"step": 1
},
{
"epoch": 0.026348291477974475,
"grad_norm": 0.4185059070587158,
"learning_rate": 1.25e-07,
"logits/chosen": 10.530074119567871,
"logits/rejected": 10.672085762023926,
"logps/chosen": -173.2084503173828,
"logps/ref_chosen": -173.2084503173828,
"logps/ref_rejected": -187.02206420898438,
"logps/rejected": -187.02206420898438,
"loss": 0.6931,
"rewards/accuracies": 0.0,
"rewards/chosen": 0.0,
"rewards/margins": 0.0,
"rewards/rejected": 0.0,
"step": 2
},
{
"epoch": 0.03952243721696171,
"grad_norm": 0.3848375082015991,
"learning_rate": 1.875e-07,
"logits/chosen": 10.340475082397461,
"logits/rejected": 10.486526489257812,
"logps/chosen": -169.6623992919922,
"logps/ref_chosen": -169.080810546875,
"logps/ref_rejected": -182.52792358398438,
"logps/rejected": -182.80642700195312,
"loss": 0.6947,
"rewards/accuracies": 0.3828125,
"rewards/chosen": -0.005815833806991577,
"rewards/margins": -0.0030306153930723667,
"rewards/rejected": -0.002785218646749854,
"step": 3
},
{
"epoch": 0.05269658295594895,
"grad_norm": 0.7261964678764343,
"learning_rate": 2.5e-07,
"logits/chosen": 10.3652925491333,
"logits/rejected": 10.412069320678711,
"logps/chosen": -177.03428649902344,
"logps/ref_chosen": -176.78369140625,
"logps/ref_rejected": -180.0931396484375,
"logps/rejected": -180.21463012695312,
"loss": 0.6938,
"rewards/accuracies": 0.4765625,
"rewards/chosen": -0.0025058696046471596,
"rewards/margins": -0.0012909012148156762,
"rewards/rejected": -0.0012149682734161615,
"step": 4
},
{
"epoch": 0.06587072869493618,
"grad_norm": 0.3572319746017456,
"learning_rate": 3.1249999999999997e-07,
"logits/chosen": 10.757452011108398,
"logits/rejected": 10.791389465332031,
"logps/chosen": -169.12631225585938,
"logps/ref_chosen": -168.522216796875,
"logps/ref_rejected": -176.08982849121094,
"logps/rejected": -176.59901428222656,
"loss": 0.6936,
"rewards/accuracies": 0.4609375,
"rewards/chosen": -0.0060411859303712845,
"rewards/margins": -0.0009493756806477904,
"rewards/rejected": -0.0050918105989694595,
"step": 5
},
{
"epoch": 0.07904487443392343,
"grad_norm": 0.4071093201637268,
"learning_rate": 3.75e-07,
"logits/chosen": 11.003137588500977,
"logits/rejected": 11.056475639343262,
"logps/chosen": -174.662353515625,
"logps/ref_chosen": -174.5843048095703,
"logps/ref_rejected": -181.65040588378906,
"logps/rejected": -181.72401428222656,
"loss": 0.6932,
"rewards/accuracies": 0.5078125,
"rewards/chosen": -0.0007804610067978501,
"rewards/margins": -4.43047538283281e-05,
"rewards/rejected": -0.0007361561874859035,
"step": 6
},
{
"epoch": 0.09221902017291066,
"grad_norm": 0.7951124906539917,
"learning_rate": 4.375e-07,
"logits/chosen": 10.003807067871094,
"logits/rejected": 10.067156791687012,
"logps/chosen": -171.4049530029297,
"logps/ref_chosen": -170.4031219482422,
"logps/ref_rejected": -181.00917053222656,
"logps/rejected": -181.8280792236328,
"loss": 0.6941,
"rewards/accuracies": 0.4453125,
"rewards/chosen": -0.010018287226557732,
"rewards/margins": -0.0018291514134034514,
"rewards/rejected": -0.008189136162400246,
"step": 7
},
{
"epoch": 0.1053931659118979,
"grad_norm": 0.5591660737991333,
"learning_rate": 5e-07,
"logits/chosen": 10.874868392944336,
"logits/rejected": 10.79828929901123,
"logps/chosen": -179.36700439453125,
"logps/ref_chosen": -178.47369384765625,
"logps/ref_rejected": -184.52243041992188,
"logps/rejected": -185.44284057617188,
"loss": 0.693,
"rewards/accuracies": 0.5078125,
"rewards/chosen": -0.008933190256357193,
"rewards/margins": 0.0002710025873966515,
"rewards/rejected": -0.009204192087054253,
"step": 8
},
{
"epoch": 0.11856731165088513,
"grad_norm": 0.45744186639785767,
"learning_rate": 4.997252228714278e-07,
"logits/chosen": 10.472944259643555,
"logits/rejected": 10.640350341796875,
"logps/chosen": -175.36553955078125,
"logps/ref_chosen": -174.38418579101562,
"logps/ref_rejected": -182.0985565185547,
"logps/rejected": -183.1609649658203,
"loss": 0.6928,
"rewards/accuracies": 0.5234375,
"rewards/chosen": -0.009813489392399788,
"rewards/margins": 0.0008107352769002318,
"rewards/rejected": -0.010624224320054054,
"step": 9
},
{
"epoch": 0.13174145738987236,
"grad_norm": 0.3784727156162262,
"learning_rate": 4.989014955054745e-07,
"logits/chosen": 10.471797943115234,
"logits/rejected": 10.57437515258789,
"logps/chosen": -173.78768920898438,
"logps/ref_chosen": -172.48837280273438,
"logps/ref_rejected": -179.625,
"logps/rejected": -180.91595458984375,
"loss": 0.6932,
"rewards/accuracies": 0.4765625,
"rewards/chosen": -0.012993087992072105,
"rewards/margins": -8.335959864780307e-05,
"rewards/rejected": -0.012909728102385998,
"step": 10
},
{
"epoch": 0.14491560312885962,
"grad_norm": 0.4041476547718048,
"learning_rate": 4.975306286336627e-07,
"logits/chosen": 10.539186477661133,
"logits/rejected": 10.477883338928223,
"logps/chosen": -172.62416076660156,
"logps/ref_chosen": -169.97216796875,
"logps/ref_rejected": -180.00955200195312,
"logps/rejected": -182.72525024414062,
"loss": 0.6929,
"rewards/accuracies": 0.546875,
"rewards/chosen": -0.026519589126110077,
"rewards/margins": 0.0006374535150825977,
"rewards/rejected": -0.027157040312886238,
"step": 11
},
{
"epoch": 0.15808974886784685,
"grad_norm": 0.5964677333831787,
"learning_rate": 4.956156357188939e-07,
"logits/chosen": 10.28010082244873,
"logits/rejected": 10.401304244995117,
"logps/chosen": -178.43714904785156,
"logps/ref_chosen": -175.83639526367188,
"logps/ref_rejected": -181.73045349121094,
"logps/rejected": -184.20223999023438,
"loss": 0.6938,
"rewards/accuracies": 0.4375,
"rewards/chosen": -0.026007818058133125,
"rewards/margins": -0.0012897354317829013,
"rewards/rejected": -0.024718083441257477,
"step": 12
},
{
"epoch": 0.17126389460683408,
"grad_norm": 0.488361120223999,
"learning_rate": 4.931607263312032e-07,
"logits/chosen": 10.292243957519531,
"logits/rejected": 10.386707305908203,
"logps/chosen": -173.99058532714844,
"logps/ref_chosen": -170.8806610107422,
"logps/ref_rejected": -180.6468963623047,
"logps/rejected": -184.01853942871094,
"loss": 0.6919,
"rewards/accuracies": 0.5234375,
"rewards/chosen": -0.03109920769929886,
"rewards/margins": 0.002617327030748129,
"rewards/rejected": -0.033716537058353424,
"step": 13
},
{
"epoch": 0.1844380403458213,
"grad_norm": 0.45636966824531555,
"learning_rate": 4.9017129689421e-07,
"logits/chosen": 10.729025840759277,
"logits/rejected": 10.921786308288574,
"logps/chosen": -174.65345764160156,
"logps/ref_chosen": -171.15963745117188,
"logps/ref_rejected": -180.73471069335938,
"logps/rejected": -184.30807495117188,
"loss": 0.6928,
"rewards/accuracies": 0.515625,
"rewards/chosen": -0.03493800014257431,
"rewards/margins": 0.0007955244509503245,
"rewards/rejected": -0.03573352098464966,
"step": 14
},
{
"epoch": 0.19761218608480857,
"grad_norm": 0.3838670551776886,
"learning_rate": 4.866539188226085e-07,
"logits/chosen": 10.265353202819824,
"logits/rejected": 10.378411293029785,
"logps/chosen": -177.72991943359375,
"logps/ref_chosen": -173.84222412109375,
"logps/ref_rejected": -182.6996612548828,
"logps/rejected": -186.89825439453125,
"loss": 0.6916,
"rewards/accuracies": 0.515625,
"rewards/chosen": -0.03887684643268585,
"rewards/margins": 0.003108714707195759,
"rewards/rejected": -0.04198555648326874,
"step": 15
},
{
"epoch": 0.2107863318237958,
"grad_norm": 0.3698700964450836,
"learning_rate": 4.826163240767716e-07,
"logits/chosen": 10.751184463500977,
"logits/rejected": 10.945128440856934,
"logps/chosen": -181.60301208496094,
"logps/ref_chosen": -178.638671875,
"logps/ref_rejected": -185.8243408203125,
"logps/rejected": -188.93057250976562,
"loss": 0.6925,
"rewards/accuracies": 0.5234375,
"rewards/chosen": -0.029643364250659943,
"rewards/margins": 0.0014189946232363582,
"rewards/rejected": -0.03106236271560192,
"step": 16
},
{
"epoch": 0.22396047756278303,
"grad_norm": 0.5419145822525024,
"learning_rate": 4.780673881662242e-07,
"logits/chosen": 10.279337882995605,
"logits/rejected": 10.265542984008789,
"logps/chosen": -176.72821044921875,
"logps/ref_chosen": -172.87332153320312,
"logps/ref_rejected": -177.30355834960938,
"logps/rejected": -181.23831176757812,
"loss": 0.6928,
"rewards/accuracies": 0.484375,
"rewards/chosen": -0.038549020886421204,
"rewards/margins": 0.0007985997945070267,
"rewards/rejected": -0.03934762626886368,
"step": 17
},
{
"epoch": 0.23713462330177026,
"grad_norm": 0.5288915038108826,
"learning_rate": 4.730171106393466e-07,
"logits/chosen": 10.508716583251953,
"logits/rejected": 10.601346969604492,
"logps/chosen": -176.69735717773438,
"logps/ref_chosen": -172.82644653320312,
"logps/ref_rejected": -180.93768310546875,
"logps/rejected": -184.82861328125,
"loss": 0.6931,
"rewards/accuracies": 0.5234375,
"rewards/chosen": -0.038708824664354324,
"rewards/margins": 0.00020039017545059323,
"rewards/rejected": -0.03890921175479889,
"step": 18
},
{
"epoch": 0.2503087690407575,
"grad_norm": 0.45863935351371765,
"learning_rate": 4.6747659310219757e-07,
"logits/chosen": 10.509140014648438,
"logits/rejected": 10.403264999389648,
"logps/chosen": -183.62411499023438,
"logps/ref_chosen": -179.5069122314453,
"logps/ref_rejected": -185.01487731933594,
"logps/rejected": -189.2952880859375,
"loss": 0.6924,
"rewards/accuracies": 0.5078125,
"rewards/chosen": -0.041171781718730927,
"rewards/margins": 0.0016320659779012203,
"rewards/rejected": -0.04280385002493858,
"step": 19
},
{
"epoch": 0.2634829147797447,
"grad_norm": 0.6024115085601807,
"learning_rate": 4.6145801481477433e-07,
"logits/chosen": 10.452649116516113,
"logits/rejected": 10.525249481201172,
"logps/chosen": -174.3675994873047,
"logps/ref_chosen": -170.23623657226562,
"logps/ref_rejected": -177.55618286132812,
"logps/rejected": -181.85946655273438,
"loss": 0.6923,
"rewards/accuracies": 0.5078125,
"rewards/chosen": -0.04131368175148964,
"rewards/margins": 0.0017191548831760883,
"rewards/rejected": -0.04303283616900444,
"step": 20
},
{
"epoch": 0.276657060518732,
"grad_norm": 0.4595341384410858,
"learning_rate": 4.549746059183561e-07,
"logits/chosen": 10.422194480895996,
"logits/rejected": 10.483356475830078,
"logps/chosen": -180.44906616210938,
"logps/ref_chosen": -176.3700408935547,
"logps/ref_rejected": -182.80032348632812,
"logps/rejected": -187.17276000976562,
"loss": 0.6917,
"rewards/accuracies": 0.5703125,
"rewards/chosen": -0.04079030081629753,
"rewards/margins": 0.0029342519119381905,
"rewards/rejected": -0.04372455179691315,
"step": 21
},
{
"epoch": 0.28983120625771924,
"grad_norm": 0.3111652731895447,
"learning_rate": 4.480406183527823e-07,
"logits/chosen": 10.481276512145996,
"logits/rejected": 10.559721946716309,
"logps/chosen": -177.63865661621094,
"logps/ref_chosen": -173.29742431640625,
"logps/ref_rejected": -177.54916381835938,
"logps/rejected": -182.2364044189453,
"loss": 0.6915,
"rewards/accuracies": 0.6015625,
"rewards/chosen": -0.043412309139966965,
"rewards/margins": 0.003460067557170987,
"rewards/rejected": -0.04687237739562988,
"step": 22
},
{
"epoch": 0.3030053519967065,
"grad_norm": 0.520114541053772,
"learning_rate": 4.4067129452759546e-07,
"logits/chosen": 10.153634071350098,
"logits/rejected": 10.433453559875488,
"logps/chosen": -174.9644012451172,
"logps/ref_chosen": -170.41177368164062,
"logps/ref_rejected": -182.7073974609375,
"logps/rejected": -187.5763397216797,
"loss": 0.6916,
"rewards/accuracies": 0.5625,
"rewards/chosen": -0.04552610218524933,
"rewards/margins": 0.0031630881130695343,
"rewards/rejected": -0.04868919029831886,
"step": 23
},
{
"epoch": 0.3161794977356937,
"grad_norm": 0.38157743215560913,
"learning_rate": 4.3288283381591725e-07,
"logits/chosen": 10.212328910827637,
"logits/rejected": 10.149028778076172,
"logps/chosen": -178.75759887695312,
"logps/ref_chosen": -174.15003967285156,
"logps/ref_rejected": -181.65594482421875,
"logps/rejected": -186.58934020996094,
"loss": 0.6916,
"rewards/accuracies": 0.5703125,
"rewards/chosen": -0.046075694262981415,
"rewards/margins": 0.003258442971855402,
"rewards/rejected": -0.04933413863182068,
"step": 24
}
],
"logging_steps": 1,
"max_steps": 75,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 12,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|