File size: 13,886 Bytes
ef62c7d |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.17761989342806395,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008880994671403197,
"grad_norm": 0.04571289196610451,
"learning_rate": 4.999451708687114e-06,
"logits/chosen": 14.56671142578125,
"logits/rejected": 15.112574577331543,
"logps/chosen": -0.26506316661834717,
"logps/rejected": -0.3439488410949707,
"loss": 0.9267,
"rewards/accuracies": 0.574999988079071,
"rewards/chosen": -0.39759472012519836,
"rewards/margins": 0.11832849681377411,
"rewards/rejected": -0.5159232020378113,
"step": 10
},
{
"epoch": 0.017761989342806393,
"grad_norm": 0.0512714721262455,
"learning_rate": 4.997807075247147e-06,
"logits/chosen": 14.376543045043945,
"logits/rejected": 14.862703323364258,
"logps/chosen": -0.2708089351654053,
"logps/rejected": -0.32412824034690857,
"loss": 0.936,
"rewards/accuracies": 0.5,
"rewards/chosen": -0.4062133729457855,
"rewards/margins": 0.07997899502515793,
"rewards/rejected": -0.4861923158168793,
"step": 20
},
{
"epoch": 0.02664298401420959,
"grad_norm": 0.058383647352457047,
"learning_rate": 4.9950668210706795e-06,
"logits/chosen": 14.208717346191406,
"logits/rejected": 15.370651245117188,
"logps/chosen": -0.28206294775009155,
"logps/rejected": -0.38387423753738403,
"loss": 0.9215,
"rewards/accuracies": 0.625,
"rewards/chosen": -0.42309442162513733,
"rewards/margins": 0.15271687507629395,
"rewards/rejected": -0.5758112668991089,
"step": 30
},
{
"epoch": 0.035523978685612786,
"grad_norm": 0.06262075155973434,
"learning_rate": 4.9912321481237616e-06,
"logits/chosen": 14.768765449523926,
"logits/rejected": 15.169331550598145,
"logps/chosen": -0.27857059240341187,
"logps/rejected": -0.3388269543647766,
"loss": 0.9386,
"rewards/accuracies": 0.5,
"rewards/chosen": -0.4178559184074402,
"rewards/margins": 0.09038447588682175,
"rewards/rejected": -0.5082404017448425,
"step": 40
},
{
"epoch": 0.04440497335701599,
"grad_norm": 0.06259036809206009,
"learning_rate": 4.986304738420684e-06,
"logits/chosen": 14.950456619262695,
"logits/rejected": 15.232122421264648,
"logps/chosen": -0.2961367070674896,
"logps/rejected": -0.3322262465953827,
"loss": 0.9317,
"rewards/accuracies": 0.44999998807907104,
"rewards/chosen": -0.44420504570007324,
"rewards/margins": 0.054134320467710495,
"rewards/rejected": -0.4983394145965576,
"step": 50
},
{
"epoch": 0.04440497335701599,
"eval_logits/chosen": 14.56529426574707,
"eval_logits/rejected": 14.895020484924316,
"eval_logps/chosen": -0.2806546986103058,
"eval_logps/rejected": -0.3486972451210022,
"eval_loss": 0.9381324052810669,
"eval_rewards/accuracies": 0.5274725556373596,
"eval_rewards/chosen": -0.4209820330142975,
"eval_rewards/margins": 0.10206379741430283,
"eval_rewards/rejected": -0.5230458974838257,
"eval_runtime": 25.2574,
"eval_samples_per_second": 28.823,
"eval_steps_per_second": 3.603,
"step": 50
},
{
"epoch": 0.05328596802841918,
"grad_norm": 0.07301533967256546,
"learning_rate": 4.980286753286196e-06,
"logits/chosen": 14.195574760437012,
"logits/rejected": 15.173194885253906,
"logps/chosen": -0.2693648636341095,
"logps/rejected": -0.33997970819473267,
"loss": 0.9319,
"rewards/accuracies": 0.512499988079071,
"rewards/chosen": -0.40404725074768066,
"rewards/margins": 0.10592226684093475,
"rewards/rejected": -0.5099694728851318,
"step": 60
},
{
"epoch": 0.06216696269982238,
"grad_norm": 0.0659889206290245,
"learning_rate": 4.973180832407471e-06,
"logits/chosen": 14.910173416137695,
"logits/rejected": 15.361429214477539,
"logps/chosen": -0.28456225991249084,
"logps/rejected": -0.3702812194824219,
"loss": 0.9185,
"rewards/accuracies": 0.625,
"rewards/chosen": -0.42684346437454224,
"rewards/margins": 0.12857840955257416,
"rewards/rejected": -0.5554218292236328,
"step": 70
},
{
"epoch": 0.07104795737122557,
"grad_norm": 0.05815625935792923,
"learning_rate": 4.964990092676263e-06,
"logits/chosen": 14.407182693481445,
"logits/rejected": 14.948204040527344,
"logps/chosen": -0.292889267206192,
"logps/rejected": -0.3381648063659668,
"loss": 0.9388,
"rewards/accuracies": 0.5375000238418579,
"rewards/chosen": -0.43933385610580444,
"rewards/margins": 0.06791339069604874,
"rewards/rejected": -0.5072472095489502,
"step": 80
},
{
"epoch": 0.07992895204262877,
"grad_norm": 0.06627190113067627,
"learning_rate": 4.9557181268217225e-06,
"logits/chosen": 14.622471809387207,
"logits/rejected": 15.167770385742188,
"logps/chosen": -0.28155821561813354,
"logps/rejected": -0.33633899688720703,
"loss": 0.9256,
"rewards/accuracies": 0.5375000238418579,
"rewards/chosen": -0.4223373532295227,
"rewards/margins": 0.08217118680477142,
"rewards/rejected": -0.5045084953308105,
"step": 90
},
{
"epoch": 0.08880994671403197,
"grad_norm": 0.0724545568227768,
"learning_rate": 4.9453690018345144e-06,
"logits/chosen": 14.289724349975586,
"logits/rejected": 14.882037162780762,
"logps/chosen": -0.2791440486907959,
"logps/rejected": -0.35329627990722656,
"loss": 0.9374,
"rewards/accuracies": 0.5375000238418579,
"rewards/chosen": -0.41871610283851624,
"rewards/margins": 0.11122839152812958,
"rewards/rejected": -0.5299445390701294,
"step": 100
},
{
"epoch": 0.08880994671403197,
"eval_logits/chosen": 14.337930679321289,
"eval_logits/rejected": 14.689269065856934,
"eval_logps/chosen": -0.2726942300796509,
"eval_logps/rejected": -0.34668418765068054,
"eval_loss": 0.9302808046340942,
"eval_rewards/accuracies": 0.5384615659713745,
"eval_rewards/chosen": -0.40904131531715393,
"eval_rewards/margins": 0.11098497360944748,
"eval_rewards/rejected": -0.5200263261795044,
"eval_runtime": 25.2585,
"eval_samples_per_second": 28.822,
"eval_steps_per_second": 3.603,
"step": 100
},
{
"epoch": 0.09769094138543517,
"grad_norm": 0.08156246691942215,
"learning_rate": 4.933947257182901e-06,
"logits/chosen": 14.499124526977539,
"logits/rejected": 14.916313171386719,
"logps/chosen": -0.2798352837562561,
"logps/rejected": -0.3477734327316284,
"loss": 0.9243,
"rewards/accuracies": 0.5625,
"rewards/chosen": -0.4197530150413513,
"rewards/margins": 0.10190720856189728,
"rewards/rejected": -0.5216602087020874,
"step": 110
},
{
"epoch": 0.10657193605683836,
"grad_norm": 0.08161844313144684,
"learning_rate": 4.921457902821578e-06,
"logits/chosen": 13.595013618469238,
"logits/rejected": 14.390353202819824,
"logps/chosen": -0.26682502031326294,
"logps/rejected": -0.3336995542049408,
"loss": 0.9123,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.400237500667572,
"rewards/margins": 0.10031183809041977,
"rewards/rejected": -0.5005493760108948,
"step": 120
},
{
"epoch": 0.11545293072824156,
"grad_norm": 0.28624778985977173,
"learning_rate": 4.907906416994146e-06,
"logits/chosen": 13.711044311523438,
"logits/rejected": 14.558542251586914,
"logps/chosen": -0.27874043583869934,
"logps/rejected": -0.3582325279712677,
"loss": 0.9163,
"rewards/accuracies": 0.5375000238418579,
"rewards/chosen": -0.41811060905456543,
"rewards/margins": 0.11923813819885254,
"rewards/rejected": -0.537348747253418,
"step": 130
},
{
"epoch": 0.12433392539964476,
"grad_norm": 0.10971464216709137,
"learning_rate": 4.893298743830168e-06,
"logits/chosen": 14.18798828125,
"logits/rejected": 14.993026733398438,
"logps/chosen": -0.2750400900840759,
"logps/rejected": -0.39451608061790466,
"loss": 0.9098,
"rewards/accuracies": 0.574999988079071,
"rewards/chosen": -0.4125601351261139,
"rewards/margins": 0.17921395599842072,
"rewards/rejected": -0.5917741060256958,
"step": 140
},
{
"epoch": 0.13321492007104796,
"grad_norm": 0.09321591258049011,
"learning_rate": 4.8776412907378845e-06,
"logits/chosen": 12.775139808654785,
"logits/rejected": 13.751996994018555,
"logps/chosen": -0.28446996212005615,
"logps/rejected": -0.36404967308044434,
"loss": 0.9104,
"rewards/accuracies": 0.5249999761581421,
"rewards/chosen": -0.42670494318008423,
"rewards/margins": 0.11936960369348526,
"rewards/rejected": -0.5460745096206665,
"step": 150
},
{
"epoch": 0.13321492007104796,
"eval_logits/chosen": 12.97266960144043,
"eval_logits/rejected": 13.47339916229248,
"eval_logps/chosen": -0.27297571301460266,
"eval_logps/rejected": -0.36854612827301025,
"eval_loss": 0.9143257737159729,
"eval_rewards/accuracies": 0.5824176073074341,
"eval_rewards/chosen": -0.4094635546207428,
"eval_rewards/margins": 0.14335563778877258,
"eval_rewards/rejected": -0.5528191924095154,
"eval_runtime": 25.2406,
"eval_samples_per_second": 28.842,
"eval_steps_per_second": 3.605,
"step": 150
},
{
"epoch": 0.14209591474245115,
"grad_norm": 0.11029861867427826,
"learning_rate": 4.860940925593703e-06,
"logits/chosen": 12.677947998046875,
"logits/rejected": 13.396716117858887,
"logps/chosen": -0.2631794512271881,
"logps/rejected": -0.37102141976356506,
"loss": 0.9051,
"rewards/accuracies": 0.550000011920929,
"rewards/chosen": -0.3947691321372986,
"rewards/margins": 0.161762997508049,
"rewards/rejected": -0.5565321445465088,
"step": 160
},
{
"epoch": 0.15097690941385436,
"grad_norm": 0.15728294849395752,
"learning_rate": 4.84320497372973e-06,
"logits/chosen": 12.620219230651855,
"logits/rejected": 13.189640998840332,
"logps/chosen": -0.2947639524936676,
"logps/rejected": -0.3843482732772827,
"loss": 0.8906,
"rewards/accuracies": 0.5625,
"rewards/chosen": -0.442145973443985,
"rewards/margins": 0.13437646627426147,
"rewards/rejected": -0.5765224099159241,
"step": 170
},
{
"epoch": 0.15985790408525755,
"grad_norm": 0.31504154205322266,
"learning_rate": 4.824441214720629e-06,
"logits/chosen": 11.487619400024414,
"logits/rejected": 12.33470344543457,
"logps/chosen": -0.271095871925354,
"logps/rejected": -0.4252637028694153,
"loss": 0.8766,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.406643807888031,
"rewards/margins": 0.2312517911195755,
"rewards/rejected": -0.6378955245018005,
"step": 180
},
{
"epoch": 0.16873889875666073,
"grad_norm": 0.19222252070903778,
"learning_rate": 4.804657878971252e-06,
"logits/chosen": 10.093737602233887,
"logits/rejected": 10.851752281188965,
"logps/chosen": -0.2679918110370636,
"logps/rejected": -0.437336266040802,
"loss": 0.884,
"rewards/accuracies": 0.637499988079071,
"rewards/chosen": -0.4019877314567566,
"rewards/margins": 0.2540166974067688,
"rewards/rejected": -0.6560044288635254,
"step": 190
},
{
"epoch": 0.17761989342806395,
"grad_norm": 0.2275688648223877,
"learning_rate": 4.783863644106502e-06,
"logits/chosen": 9.483477592468262,
"logits/rejected": 10.106366157531738,
"logps/chosen": -0.2957404553890228,
"logps/rejected": -0.40739065408706665,
"loss": 0.8767,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.4436107575893402,
"rewards/margins": 0.16747523844242096,
"rewards/rejected": -0.6110859513282776,
"step": 200
},
{
"epoch": 0.17761989342806395,
"eval_logits/chosen": 8.491498947143555,
"eval_logits/rejected": 8.999146461486816,
"eval_logps/chosen": -0.3135836124420166,
"eval_logps/rejected": -0.4829566180706024,
"eval_loss": 0.8664290904998779,
"eval_rewards/accuracies": 0.6263736486434937,
"eval_rewards/chosen": -0.4703753888607025,
"eval_rewards/margins": 0.2540595233440399,
"eval_rewards/rejected": -0.7244349122047424,
"eval_runtime": 25.2553,
"eval_samples_per_second": 28.826,
"eval_steps_per_second": 3.603,
"step": 200
}
],
"logging_steps": 10,
"max_steps": 1500,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.73069782703276e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|