File size: 13,168 Bytes
1e9aa82 |
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 |
{
"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": 0.7230468392372131,
"learning_rate": 1.25e-07,
"logits/chosen": 9.993395805358887,
"logits/rejected": 10.444890022277832,
"logps/chosen": -0.8203260898590088,
"logps/rejected": -0.8579692840576172,
"loss": 1.4012,
"rewards/accuracies": 0.546875,
"rewards/chosen": -1.6406521797180176,
"rewards/margins": 0.07528629899024963,
"rewards/rejected": -1.7159385681152344,
"step": 1
},
{
"epoch": 0.026348291477974475,
"grad_norm": 1.0001572370529175,
"learning_rate": 2.5e-07,
"logits/chosen": 10.52372932434082,
"logits/rejected": 10.788372993469238,
"logps/chosen": -0.8189243078231812,
"logps/rejected": -0.9178226590156555,
"loss": 1.2834,
"rewards/accuracies": 0.625,
"rewards/chosen": -1.6378486156463623,
"rewards/margins": 0.19779649376869202,
"rewards/rejected": -1.835645318031311,
"step": 2
},
{
"epoch": 0.03952243721696171,
"grad_norm": 0.979387640953064,
"learning_rate": 3.75e-07,
"logits/chosen": 10.042590141296387,
"logits/rejected": 10.521858215332031,
"logps/chosen": -0.917183518409729,
"logps/rejected": -0.9847703576087952,
"loss": 1.3664,
"rewards/accuracies": 0.5546875,
"rewards/chosen": -1.834367036819458,
"rewards/margins": 0.13517364859580994,
"rewards/rejected": -1.9695407152175903,
"step": 3
},
{
"epoch": 0.05269658295594895,
"grad_norm": 1.867851972579956,
"learning_rate": 5e-07,
"logits/chosen": 10.141695022583008,
"logits/rejected": 10.483091354370117,
"logps/chosen": -0.8512520790100098,
"logps/rejected": -0.8865377902984619,
"loss": 1.4018,
"rewards/accuracies": 0.546875,
"rewards/chosen": -1.7025041580200195,
"rewards/margins": 0.0705714151263237,
"rewards/rejected": -1.7730755805969238,
"step": 4
},
{
"epoch": 0.06587072869493618,
"grad_norm": 0.5915809273719788,
"learning_rate": 6.249999999999999e-07,
"logits/chosen": 10.462024688720703,
"logits/rejected": 11.114532470703125,
"logps/chosen": -0.7721583247184753,
"logps/rejected": -0.7985925078392029,
"loss": 1.3829,
"rewards/accuracies": 0.5625,
"rewards/chosen": -1.5443166494369507,
"rewards/margins": 0.052868396043777466,
"rewards/rejected": -1.5971850156784058,
"step": 5
},
{
"epoch": 0.07904487443392343,
"grad_norm": 0.6252888441085815,
"learning_rate": 7.5e-07,
"logits/chosen": 10.718672752380371,
"logits/rejected": 11.112823486328125,
"logps/chosen": -0.8559192419052124,
"logps/rejected": -0.9305768013000488,
"loss": 1.3618,
"rewards/accuracies": 0.5859375,
"rewards/chosen": -1.7118384838104248,
"rewards/margins": 0.1493152379989624,
"rewards/rejected": -1.8611536026000977,
"step": 6
},
{
"epoch": 0.09221902017291066,
"grad_norm": 0.7208986878395081,
"learning_rate": 8.75e-07,
"logits/chosen": 9.864439010620117,
"logits/rejected": 10.09216022491455,
"logps/chosen": -0.7553099393844604,
"logps/rejected": -0.8098596930503845,
"loss": 1.3613,
"rewards/accuracies": 0.5859375,
"rewards/chosen": -1.510619878768921,
"rewards/margins": 0.10909969359636307,
"rewards/rejected": -1.619719386100769,
"step": 7
},
{
"epoch": 0.1053931659118979,
"grad_norm": 1.6331408023834229,
"learning_rate": 1e-06,
"logits/chosen": 10.65585994720459,
"logits/rejected": 11.107338905334473,
"logps/chosen": -0.774090051651001,
"logps/rejected": -0.8291972279548645,
"loss": 1.3462,
"rewards/accuracies": 0.625,
"rewards/chosen": -1.548180103302002,
"rewards/margins": 0.11021438986063004,
"rewards/rejected": -1.658394455909729,
"step": 8
},
{
"epoch": 0.11856731165088513,
"grad_norm": 1.0860488414764404,
"learning_rate": 9.994504457428556e-07,
"logits/chosen": 10.446334838867188,
"logits/rejected": 10.82742691040039,
"logps/chosen": -0.938445508480072,
"logps/rejected": -0.8894600868225098,
"loss": 1.5125,
"rewards/accuracies": 0.53125,
"rewards/chosen": -1.876891016960144,
"rewards/margins": -0.09797099232673645,
"rewards/rejected": -1.7789201736450195,
"step": 9
},
{
"epoch": 0.13174145738987236,
"grad_norm": 1.3078101873397827,
"learning_rate": 9.97802991010949e-07,
"logits/chosen": 10.292729377746582,
"logits/rejected": 10.629972457885742,
"logps/chosen": -0.8660728931427002,
"logps/rejected": -0.881781280040741,
"loss": 1.4654,
"rewards/accuracies": 0.5390625,
"rewards/chosen": -1.7321457862854004,
"rewards/margins": 0.0314166434109211,
"rewards/rejected": -1.763562560081482,
"step": 10
},
{
"epoch": 0.14491560312885962,
"grad_norm": 1.0685713291168213,
"learning_rate": 9.950612572673255e-07,
"logits/chosen": 10.143664360046387,
"logits/rejected": 10.639056205749512,
"logps/chosen": -0.8788573145866394,
"logps/rejected": -0.9421562552452087,
"loss": 1.3638,
"rewards/accuracies": 0.5625,
"rewards/chosen": -1.7577146291732788,
"rewards/margins": 0.12659788131713867,
"rewards/rejected": -1.8843125104904175,
"step": 11
},
{
"epoch": 0.15808974886784685,
"grad_norm": 0.9801668524742126,
"learning_rate": 9.912312714377879e-07,
"logits/chosen": 10.19462776184082,
"logits/rejected": 10.269098281860352,
"logps/chosen": -0.8250212669372559,
"logps/rejected": -0.8715258836746216,
"loss": 1.3649,
"rewards/accuracies": 0.59375,
"rewards/chosen": -1.6500425338745117,
"rewards/margins": 0.09300932288169861,
"rewards/rejected": -1.7430517673492432,
"step": 12
},
{
"epoch": 0.17126389460683408,
"grad_norm": 0.9345762729644775,
"learning_rate": 9.863214526624063e-07,
"logits/chosen": 9.898378372192383,
"logits/rejected": 10.37912368774414,
"logps/chosen": -0.8251993656158447,
"logps/rejected": -0.9702485799789429,
"loss": 1.3106,
"rewards/accuracies": 0.5546875,
"rewards/chosen": -1.6503987312316895,
"rewards/margins": 0.2900983989238739,
"rewards/rejected": -1.9404971599578857,
"step": 13
},
{
"epoch": 0.1844380403458213,
"grad_norm": 0.6539536118507385,
"learning_rate": 9.8034259378842e-07,
"logits/chosen": 10.518888473510742,
"logits/rejected": 11.198535919189453,
"logps/chosen": -0.7980682253837585,
"logps/rejected": -0.8631402254104614,
"loss": 1.3561,
"rewards/accuracies": 0.609375,
"rewards/chosen": -1.596136450767517,
"rewards/margins": 0.13014405965805054,
"rewards/rejected": -1.7262804508209229,
"step": 14
},
{
"epoch": 0.19761218608480857,
"grad_norm": 0.3341844975948334,
"learning_rate": 9.73307837645217e-07,
"logits/chosen": 10.087669372558594,
"logits/rejected": 10.595584869384766,
"logps/chosen": -0.7868794798851013,
"logps/rejected": -0.8722506165504456,
"loss": 1.3174,
"rewards/accuracies": 0.5546875,
"rewards/chosen": -1.5737589597702026,
"rewards/margins": 0.17074236273765564,
"rewards/rejected": -1.7445012331008911,
"step": 15
},
{
"epoch": 0.2107863318237958,
"grad_norm": 1.1852020025253296,
"learning_rate": 9.652326481535433e-07,
"logits/chosen": 10.743181228637695,
"logits/rejected": 11.05751895904541,
"logps/chosen": -0.791871190071106,
"logps/rejected": -0.8441797494888306,
"loss": 1.3868,
"rewards/accuracies": 0.5078125,
"rewards/chosen": -1.583742380142212,
"rewards/margins": 0.1046171486377716,
"rewards/rejected": -1.6883594989776611,
"step": 16
},
{
"epoch": 0.22396047756278303,
"grad_norm": 0.5402158498764038,
"learning_rate": 9.561347763324483e-07,
"logits/chosen": 10.244048118591309,
"logits/rejected": 10.602608680725098,
"logps/chosen": -0.8015426993370056,
"logps/rejected": -0.823470950126648,
"loss": 1.4002,
"rewards/accuracies": 0.5546875,
"rewards/chosen": -1.6030853986740112,
"rewards/margins": 0.04385652765631676,
"rewards/rejected": -1.646941900253296,
"step": 17
},
{
"epoch": 0.23713462330177026,
"grad_norm": 1.1475958824157715,
"learning_rate": 9.460342212786932e-07,
"logits/chosen": 10.25997543334961,
"logits/rejected": 10.875801086425781,
"logps/chosen": -0.9126402735710144,
"logps/rejected": -0.8353321552276611,
"loss": 1.5624,
"rewards/accuracies": 0.5390625,
"rewards/chosen": -1.8252805471420288,
"rewards/margins": -0.1546163707971573,
"rewards/rejected": -1.6706643104553223,
"step": 18
},
{
"epoch": 0.2503087690407575,
"grad_norm": 0.7070759534835815,
"learning_rate": 9.349531862043951e-07,
"logits/chosen": 10.557324409484863,
"logits/rejected": 10.653444290161133,
"logps/chosen": -0.8390055894851685,
"logps/rejected": -0.8851607441902161,
"loss": 1.3597,
"rewards/accuracies": 0.671875,
"rewards/chosen": -1.678011178970337,
"rewards/margins": 0.09231019765138626,
"rewards/rejected": -1.7703214883804321,
"step": 19
},
{
"epoch": 0.2634829147797447,
"grad_norm": 1.4036712646484375,
"learning_rate": 9.229160296295487e-07,
"logits/chosen": 10.47518253326416,
"logits/rejected": 11.045392990112305,
"logps/chosen": -0.861572265625,
"logps/rejected": -0.8943375945091248,
"loss": 1.4097,
"rewards/accuracies": 0.578125,
"rewards/chosen": -1.72314453125,
"rewards/margins": 0.06553083658218384,
"rewards/rejected": -1.7886751890182495,
"step": 20
},
{
"epoch": 0.276657060518732,
"grad_norm": 0.537728488445282,
"learning_rate": 9.099492118367122e-07,
"logits/chosen": 10.20445728302002,
"logits/rejected": 10.791345596313477,
"logps/chosen": -0.8058649301528931,
"logps/rejected": -0.9033350944519043,
"loss": 1.2939,
"rewards/accuracies": 0.625,
"rewards/chosen": -1.6117298603057861,
"rewards/margins": 0.19494034349918365,
"rewards/rejected": -1.8066701889038086,
"step": 21
},
{
"epoch": 0.28983120625771924,
"grad_norm": 1.7850818634033203,
"learning_rate": 8.960812367055646e-07,
"logits/chosen": 10.360614776611328,
"logits/rejected": 10.701253890991211,
"logps/chosen": -0.8701018691062927,
"logps/rejected": -0.8806692957878113,
"loss": 1.4251,
"rewards/accuracies": 0.5625,
"rewards/chosen": -1.7402037382125854,
"rewards/margins": 0.021134957671165466,
"rewards/rejected": -1.7613385915756226,
"step": 22
},
{
"epoch": 0.3030053519967065,
"grad_norm": 0.34783315658569336,
"learning_rate": 8.813425890551909e-07,
"logits/chosen": 10.343542098999023,
"logits/rejected": 10.988011360168457,
"logps/chosen": -0.8861572742462158,
"logps/rejected": -0.8626466989517212,
"loss": 1.4816,
"rewards/accuracies": 0.546875,
"rewards/chosen": -1.7723145484924316,
"rewards/margins": -0.04702116921544075,
"rewards/rejected": -1.7252933979034424,
"step": 23
},
{
"epoch": 0.3161794977356937,
"grad_norm": 0.642213761806488,
"learning_rate": 8.657656676318345e-07,
"logits/chosen": 10.253456115722656,
"logits/rejected": 10.651442527770996,
"logps/chosen": -0.8050903677940369,
"logps/rejected": -0.8499569296836853,
"loss": 1.3893,
"rewards/accuracies": 0.5078125,
"rewards/chosen": -1.6101807355880737,
"rewards/margins": 0.08973318338394165,
"rewards/rejected": -1.6999138593673706,
"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
}
|