File size: 15,518 Bytes
4267dba |
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": 0.5010076761245728,
"learning_rate": 6.25e-08,
"logits/chosen": 9.988622665405273,
"logits/rejected": 10.698101997375488,
"logps/chosen": -102.88545989990234,
"logps/ref_chosen": -102.88545989990234,
"logps/ref_rejected": -121.84871673583984,
"logps/rejected": -121.84871673583984,
"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": 0.7802621126174927,
"learning_rate": 1.25e-07,
"logits/chosen": 10.208279609680176,
"logits/rejected": 11.06594467163086,
"logps/chosen": -107.70349884033203,
"logps/ref_chosen": -107.70349884033203,
"logps/ref_rejected": -121.89966583251953,
"logps/rejected": -121.89966583251953,
"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": 0.5995805859565735,
"learning_rate": 1.875e-07,
"logits/chosen": 10.029329299926758,
"logits/rejected": 11.023927688598633,
"logps/chosen": -107.6470947265625,
"logps/ref_chosen": -107.98188781738281,
"logps/ref_rejected": -124.51527404785156,
"logps/rejected": -124.29098510742188,
"loss": 0.6926,
"rewards/accuracies": 0.5,
"rewards/chosen": 0.0033478327095508575,
"rewards/margins": 0.001104944385588169,
"rewards/rejected": 0.0022428883239626884,
"step": 3
},
{
"epoch": 0.05269658295594895,
"grad_norm": 0.5383147597312927,
"learning_rate": 2.5e-07,
"logits/chosen": 9.823471069335938,
"logits/rejected": 10.842323303222656,
"logps/chosen": -109.73627471923828,
"logps/ref_chosen": -109.20836639404297,
"logps/ref_rejected": -119.23908996582031,
"logps/rejected": -119.65444946289062,
"loss": 0.6937,
"rewards/accuracies": 0.5078125,
"rewards/chosen": -0.005279023200273514,
"rewards/margins": -0.001125341048464179,
"rewards/rejected": -0.004153682850301266,
"step": 4
},
{
"epoch": 0.06587072869493618,
"grad_norm": 0.5302512645721436,
"learning_rate": 3.1249999999999997e-07,
"logits/chosen": 10.209351539611816,
"logits/rejected": 10.967523574829102,
"logps/chosen": -103.73981475830078,
"logps/ref_chosen": -103.87680053710938,
"logps/ref_rejected": -118.41618347167969,
"logps/rejected": -118.11978149414062,
"loss": 0.694,
"rewards/accuracies": 0.4453125,
"rewards/chosen": 0.0013697518734261394,
"rewards/margins": -0.001594369299709797,
"rewards/rejected": 0.002964121289551258,
"step": 5
},
{
"epoch": 0.07904487443392343,
"grad_norm": 0.6919645667076111,
"learning_rate": 3.75e-07,
"logits/chosen": 10.676691055297852,
"logits/rejected": 11.460196495056152,
"logps/chosen": -108.08129119873047,
"logps/ref_chosen": -107.58968353271484,
"logps/ref_rejected": -122.07303619384766,
"logps/rejected": -122.37925720214844,
"loss": 0.6941,
"rewards/accuracies": 0.421875,
"rewards/chosen": -0.004916056990623474,
"rewards/margins": -0.0018538986332714558,
"rewards/rejected": -0.0030621583573520184,
"step": 6
},
{
"epoch": 0.09221902017291066,
"grad_norm": 0.40329915285110474,
"learning_rate": 4.375e-07,
"logits/chosen": 10.017489433288574,
"logits/rejected": 10.722752571105957,
"logps/chosen": -107.77075958251953,
"logps/ref_chosen": -107.42727661132812,
"logps/ref_rejected": -116.87063598632812,
"logps/rejected": -116.98759460449219,
"loss": 0.6943,
"rewards/accuracies": 0.4140625,
"rewards/chosen": -0.0034348624758422375,
"rewards/margins": -0.0022651171311736107,
"rewards/rejected": -0.0011697453446686268,
"step": 7
},
{
"epoch": 0.1053931659118979,
"grad_norm": 0.4481956362724304,
"learning_rate": 5e-07,
"logits/chosen": 10.191514015197754,
"logits/rejected": 11.094213485717773,
"logps/chosen": -106.06684112548828,
"logps/ref_chosen": -105.60282135009766,
"logps/ref_rejected": -119.53916931152344,
"logps/rejected": -119.9333267211914,
"loss": 0.6935,
"rewards/accuracies": 0.4765625,
"rewards/chosen": -0.004640196915715933,
"rewards/margins": -0.0006986188236624002,
"rewards/rejected": -0.003941578324884176,
"step": 8
},
{
"epoch": 0.11856731165088513,
"grad_norm": 0.5002302527427673,
"learning_rate": 4.997252228714278e-07,
"logits/chosen": 10.164933204650879,
"logits/rejected": 11.139327049255371,
"logps/chosen": -106.06144714355469,
"logps/ref_chosen": -105.46086120605469,
"logps/ref_rejected": -119.00373840332031,
"logps/rejected": -119.59027862548828,
"loss": 0.6932,
"rewards/accuracies": 0.4921875,
"rewards/chosen": -0.006005657836794853,
"rewards/margins": -0.00014029807061888278,
"rewards/rejected": -0.005865359678864479,
"step": 9
},
{
"epoch": 0.13174145738987236,
"grad_norm": 0.6467388868331909,
"learning_rate": 4.989014955054745e-07,
"logits/chosen": 9.98875904083252,
"logits/rejected": 10.815544128417969,
"logps/chosen": -105.14952850341797,
"logps/ref_chosen": -104.21009826660156,
"logps/ref_rejected": -118.9209213256836,
"logps/rejected": -119.72019958496094,
"loss": 0.6939,
"rewards/accuracies": 0.515625,
"rewards/chosen": -0.00939436536282301,
"rewards/margins": -0.0014015533961355686,
"rewards/rejected": -0.007992811501026154,
"step": 10
},
{
"epoch": 0.14491560312885962,
"grad_norm": 0.8090001344680786,
"learning_rate": 4.975306286336627e-07,
"logits/chosen": 9.946345329284668,
"logits/rejected": 11.13135814666748,
"logps/chosen": -107.09854125976562,
"logps/ref_chosen": -105.94319152832031,
"logps/ref_rejected": -122.76007843017578,
"logps/rejected": -123.9129409790039,
"loss": 0.6932,
"rewards/accuracies": 0.46875,
"rewards/chosen": -0.01155336108058691,
"rewards/margins": -2.4825334548950195e-05,
"rewards/rejected": -0.011528536677360535,
"step": 11
},
{
"epoch": 0.15808974886784685,
"grad_norm": 0.49643445014953613,
"learning_rate": 4.956156357188939e-07,
"logits/chosen": 9.876545906066895,
"logits/rejected": 10.567835807800293,
"logps/chosen": -109.7830810546875,
"logps/ref_chosen": -109.08442687988281,
"logps/ref_rejected": -121.41947174072266,
"logps/rejected": -122.12468719482422,
"loss": 0.6931,
"rewards/accuracies": 0.46875,
"rewards/chosen": -0.006986413151025772,
"rewards/margins": 6.572058191522956e-05,
"rewards/rejected": -0.00705213425680995,
"step": 12
},
{
"epoch": 0.17126389460683408,
"grad_norm": 0.5409023761749268,
"learning_rate": 4.931607263312032e-07,
"logits/chosen": 9.916489601135254,
"logits/rejected": 10.99366283416748,
"logps/chosen": -105.78418731689453,
"logps/ref_chosen": -104.62150573730469,
"logps/ref_rejected": -119.55384063720703,
"logps/rejected": -120.60539245605469,
"loss": 0.6937,
"rewards/accuracies": 0.46875,
"rewards/chosen": -0.011626748368144035,
"rewards/margins": -0.0011113437358289957,
"rewards/rejected": -0.010515404865145683,
"step": 13
},
{
"epoch": 0.1844380403458213,
"grad_norm": 0.9010350108146667,
"learning_rate": 4.9017129689421e-07,
"logits/chosen": 10.480968475341797,
"logits/rejected": 11.599580764770508,
"logps/chosen": -107.57891845703125,
"logps/ref_chosen": -106.179443359375,
"logps/ref_rejected": -120.73036193847656,
"logps/rejected": -122.02151489257812,
"loss": 0.6937,
"rewards/accuracies": 0.46875,
"rewards/chosen": -0.013994838111102581,
"rewards/margins": -0.0010832665720954537,
"rewards/rejected": -0.012911571189761162,
"step": 14
},
{
"epoch": 0.19761218608480857,
"grad_norm": 0.8957933187484741,
"learning_rate": 4.866539188226085e-07,
"logits/chosen": 9.80737018585205,
"logits/rejected": 10.738137245178223,
"logps/chosen": -107.41307067871094,
"logps/ref_chosen": -105.70547485351562,
"logps/ref_rejected": -118.89997863769531,
"logps/rejected": -120.64563751220703,
"loss": 0.693,
"rewards/accuracies": 0.5390625,
"rewards/chosen": -0.01707591488957405,
"rewards/margins": 0.00038063188549131155,
"rewards/rejected": -0.017456548288464546,
"step": 15
},
{
"epoch": 0.2107863318237958,
"grad_norm": 0.7111092805862427,
"learning_rate": 4.826163240767716e-07,
"logits/chosen": 10.634671211242676,
"logits/rejected": 11.238730430603027,
"logps/chosen": -110.74053955078125,
"logps/ref_chosen": -108.86376953125,
"logps/ref_rejected": -122.1635513305664,
"logps/rejected": -124.17098999023438,
"loss": 0.6925,
"rewards/accuracies": 0.53125,
"rewards/chosen": -0.018767736852169037,
"rewards/margins": 0.0013066575629636645,
"rewards/rejected": -0.02007439360022545,
"step": 16
},
{
"epoch": 0.22396047756278303,
"grad_norm": 0.5599011778831482,
"learning_rate": 4.780673881662242e-07,
"logits/chosen": 10.138323783874512,
"logits/rejected": 10.76909065246582,
"logps/chosen": -104.49694061279297,
"logps/ref_chosen": -102.93986511230469,
"logps/ref_rejected": -119.43718719482422,
"logps/rejected": -121.1658935546875,
"loss": 0.6923,
"rewards/accuracies": 0.5859375,
"rewards/chosen": -0.015570812858641148,
"rewards/margins": 0.0017161847790703177,
"rewards/rejected": -0.0172869972884655,
"step": 17
},
{
"epoch": 0.23713462330177026,
"grad_norm": 0.7006244659423828,
"learning_rate": 4.730171106393466e-07,
"logits/chosen": 10.374225616455078,
"logits/rejected": 11.157809257507324,
"logps/chosen": -105.8244400024414,
"logps/ref_chosen": -103.81341552734375,
"logps/ref_rejected": -117.45123291015625,
"logps/rejected": -119.37814331054688,
"loss": 0.6936,
"rewards/accuracies": 0.4453125,
"rewards/chosen": -0.020110249519348145,
"rewards/margins": -0.0008410783484578133,
"rewards/rejected": -0.019269172102212906,
"step": 18
},
{
"epoch": 0.2503087690407575,
"grad_norm": 0.49562451243400574,
"learning_rate": 4.6747659310219757e-07,
"logits/chosen": 10.303974151611328,
"logits/rejected": 10.965604782104492,
"logps/chosen": -109.81462860107422,
"logps/ref_chosen": -107.85797119140625,
"logps/ref_rejected": -121.88042449951172,
"logps/rejected": -124.41007232666016,
"loss": 0.6903,
"rewards/accuracies": 0.625,
"rewards/chosen": -0.019566601142287254,
"rewards/margins": 0.005729879252612591,
"rewards/rejected": -0.02529647946357727,
"step": 19
},
{
"epoch": 0.2634829147797447,
"grad_norm": 0.48442593216896057,
"learning_rate": 4.6145801481477433e-07,
"logits/chosen": 10.682939529418945,
"logits/rejected": 11.487958908081055,
"logps/chosen": -105.8414077758789,
"logps/ref_chosen": -103.42721557617188,
"logps/ref_rejected": -116.7796630859375,
"logps/rejected": -119.14535522460938,
"loss": 0.6934,
"rewards/accuracies": 0.4609375,
"rewards/chosen": -0.024141818284988403,
"rewards/margins": -0.00048486533341929317,
"rewards/rejected": -0.023656953126192093,
"step": 20
},
{
"epoch": 0.276657060518732,
"grad_norm": 0.6605204343795776,
"learning_rate": 4.549746059183561e-07,
"logits/chosen": 9.703460693359375,
"logits/rejected": 10.792010307312012,
"logps/chosen": -109.3312759399414,
"logps/ref_chosen": -106.60163879394531,
"logps/ref_rejected": -124.56562805175781,
"logps/rejected": -127.45460510253906,
"loss": 0.6924,
"rewards/accuracies": 0.5,
"rewards/chosen": -0.027296334505081177,
"rewards/margins": 0.0015935557894408703,
"rewards/rejected": -0.028889887034893036,
"step": 21
},
{
"epoch": 0.28983120625771924,
"grad_norm": 0.8831092715263367,
"learning_rate": 4.480406183527823e-07,
"logits/chosen": 10.168815612792969,
"logits/rejected": 11.040711402893066,
"logps/chosen": -107.1961669921875,
"logps/ref_chosen": -103.77696228027344,
"logps/ref_rejected": -118.73616027832031,
"logps/rejected": -121.80266571044922,
"loss": 0.695,
"rewards/accuracies": 0.4453125,
"rewards/chosen": -0.03419206291437149,
"rewards/margins": -0.0035268948413431644,
"rewards/rejected": -0.030665166676044464,
"step": 22
},
{
"epoch": 0.3030053519967065,
"grad_norm": 0.37249696254730225,
"learning_rate": 4.4067129452759546e-07,
"logits/chosen": 10.050610542297363,
"logits/rejected": 11.06921100616455,
"logps/chosen": -108.137451171875,
"logps/ref_chosen": -104.72956085205078,
"logps/ref_rejected": -121.35556030273438,
"logps/rejected": -124.6715316772461,
"loss": 0.6937,
"rewards/accuracies": 0.5,
"rewards/chosen": -0.03407883644104004,
"rewards/margins": -0.0009191110148094594,
"rewards/rejected": -0.03315972909331322,
"step": 23
},
{
"epoch": 0.3161794977356937,
"grad_norm": 0.5831263661384583,
"learning_rate": 4.3288283381591725e-07,
"logits/chosen": 10.146599769592285,
"logits/rejected": 10.979142189025879,
"logps/chosen": -109.36030578613281,
"logps/ref_chosen": -105.88758087158203,
"logps/ref_rejected": -125.69054412841797,
"logps/rejected": -129.528076171875,
"loss": 0.6914,
"rewards/accuracies": 0.5390625,
"rewards/chosen": -0.034727297723293304,
"rewards/margins": 0.003648004261776805,
"rewards/rejected": -0.03837530314922333,
"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
}
|