File size: 10,666 Bytes
c4ed2d0 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.10872519706441967,
"eval_steps": 50,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007248346470961312,
"grad_norm": 0.07201674580574036,
"learning_rate": 4.999451708687114e-06,
"logits/chosen": -1.9793262481689453,
"logits/rejected": -2.5381760597229004,
"logps/chosen": -0.28126341104507446,
"logps/rejected": -0.3779803514480591,
"loss": 7.3904,
"rewards/accuracies": 0.550000011920929,
"rewards/chosen": -0.4218950867652893,
"rewards/margins": 0.14507544040679932,
"rewards/rejected": -0.5669704675674438,
"step": 10
},
{
"epoch": 0.014496692941922623,
"grad_norm": 0.07562297582626343,
"learning_rate": 4.997807075247147e-06,
"logits/chosen": -2.0567643642425537,
"logits/rejected": -2.4989147186279297,
"logps/chosen": -0.27690139412879944,
"logps/rejected": -0.33544114232063293,
"loss": 7.3756,
"rewards/accuracies": 0.574999988079071,
"rewards/chosen": -0.41535210609436035,
"rewards/margins": 0.08780960738658905,
"rewards/rejected": -0.5031617283821106,
"step": 20
},
{
"epoch": 0.021745039412883936,
"grad_norm": 0.09685570746660233,
"learning_rate": 4.9950668210706795e-06,
"logits/chosen": -2.10174298286438,
"logits/rejected": -2.378197431564331,
"logps/chosen": -0.26717427372932434,
"logps/rejected": -0.30565372109413147,
"loss": 7.451,
"rewards/accuracies": 0.4375,
"rewards/chosen": -0.4007614254951477,
"rewards/margins": 0.05771917849779129,
"rewards/rejected": -0.4584805369377136,
"step": 30
},
{
"epoch": 0.028993385883845247,
"grad_norm": 0.08213861286640167,
"learning_rate": 4.9912321481237616e-06,
"logits/chosen": -2.1633317470550537,
"logits/rejected": -2.387866497039795,
"logps/chosen": -0.27634260058403015,
"logps/rejected": -0.37035584449768066,
"loss": 7.3892,
"rewards/accuracies": 0.6499999761581421,
"rewards/chosen": -0.4145139157772064,
"rewards/margins": 0.14101983606815338,
"rewards/rejected": -0.555533766746521,
"step": 40
},
{
"epoch": 0.03624173235480656,
"grad_norm": 0.08846044540405273,
"learning_rate": 4.986304738420684e-06,
"logits/chosen": -2.1402599811553955,
"logits/rejected": -2.4459526538848877,
"logps/chosen": -0.2535383999347687,
"logps/rejected": -0.3090876042842865,
"loss": 7.5171,
"rewards/accuracies": 0.512499988079071,
"rewards/chosen": -0.3803076148033142,
"rewards/margins": 0.08332376182079315,
"rewards/rejected": -0.4636313319206238,
"step": 50
},
{
"epoch": 0.03624173235480656,
"eval_logits/chosen": -2.1165692806243896,
"eval_logits/rejected": -2.476428747177124,
"eval_logps/chosen": -0.2828062176704407,
"eval_logps/rejected": -0.3432886600494385,
"eval_loss": 0.9120001792907715,
"eval_rewards/accuracies": 0.5089285969734192,
"eval_rewards/chosen": -0.4242093861103058,
"eval_rewards/margins": 0.09072363376617432,
"eval_rewards/rejected": -0.5149329900741577,
"eval_runtime": 30.971,
"eval_samples_per_second": 28.801,
"eval_steps_per_second": 3.616,
"step": 50
},
{
"epoch": 0.04349007882576787,
"grad_norm": 0.11753705143928528,
"learning_rate": 4.980286753286196e-06,
"logits/chosen": -2.0575368404388428,
"logits/rejected": -2.5456700325012207,
"logps/chosen": -0.24622221291065216,
"logps/rejected": -0.32402220368385315,
"loss": 7.3926,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.36933332681655884,
"rewards/margins": 0.11669999361038208,
"rewards/rejected": -0.48603329062461853,
"step": 60
},
{
"epoch": 0.05073842529672919,
"grad_norm": 0.09996571391820908,
"learning_rate": 4.973180832407471e-06,
"logits/chosen": -1.9278606176376343,
"logits/rejected": -2.4620182514190674,
"logps/chosen": -0.2596542239189148,
"logps/rejected": -0.3665880560874939,
"loss": 7.185,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.3894812762737274,
"rewards/margins": 0.160400852560997,
"rewards/rejected": -0.5498821139335632,
"step": 70
},
{
"epoch": 0.057986771767690494,
"grad_norm": 0.07287321239709854,
"learning_rate": 4.964990092676263e-06,
"logits/chosen": -2.078031063079834,
"logits/rejected": -2.461479663848877,
"logps/chosen": -0.24513795971870422,
"logps/rejected": -0.3448730707168579,
"loss": 7.365,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.36770695447921753,
"rewards/margins": 0.14960262179374695,
"rewards/rejected": -0.5173095464706421,
"step": 80
},
{
"epoch": 0.0652351182386518,
"grad_norm": 0.09656044095754623,
"learning_rate": 4.9557181268217225e-06,
"logits/chosen": -1.9979238510131836,
"logits/rejected": -2.4381277561187744,
"logps/chosen": -0.24047240614891052,
"logps/rejected": -0.3277527987957001,
"loss": 7.2664,
"rewards/accuracies": 0.6000000238418579,
"rewards/chosen": -0.36070865392684937,
"rewards/margins": 0.13092057406902313,
"rewards/rejected": -0.4916292130947113,
"step": 90
},
{
"epoch": 0.07248346470961312,
"grad_norm": 0.08125138282775879,
"learning_rate": 4.9453690018345144e-06,
"logits/chosen": -1.8948112726211548,
"logits/rejected": -2.4755520820617676,
"logps/chosen": -0.20189261436462402,
"logps/rejected": -0.29732149839401245,
"loss": 7.2542,
"rewards/accuracies": 0.5874999761581421,
"rewards/chosen": -0.30283889174461365,
"rewards/margins": 0.14314329624176025,
"rewards/rejected": -0.44598227739334106,
"step": 100
},
{
"epoch": 0.07248346470961312,
"eval_logits/chosen": -2.12322735786438,
"eval_logits/rejected": -2.481174945831299,
"eval_logps/chosen": -0.2438412606716156,
"eval_logps/rejected": -0.3260033428668976,
"eval_loss": 0.891861081123352,
"eval_rewards/accuracies": 0.5625,
"eval_rewards/chosen": -0.3657619059085846,
"eval_rewards/margins": 0.12324309349060059,
"eval_rewards/rejected": -0.48900502920150757,
"eval_runtime": 30.3299,
"eval_samples_per_second": 29.41,
"eval_steps_per_second": 3.693,
"step": 100
},
{
"epoch": 0.07973181118057443,
"grad_norm": 0.05962231010198593,
"learning_rate": 4.933947257182901e-06,
"logits/chosen": -2.1134355068206787,
"logits/rejected": -2.516538381576538,
"logps/chosen": -0.237023264169693,
"logps/rejected": -0.31476154923439026,
"loss": 7.1749,
"rewards/accuracies": 0.550000011920929,
"rewards/chosen": -0.3555349111557007,
"rewards/margins": 0.11660744249820709,
"rewards/rejected": -0.4721423089504242,
"step": 110
},
{
"epoch": 0.08698015765153574,
"grad_norm": 0.06015922501683235,
"learning_rate": 4.921457902821578e-06,
"logits/chosen": -2.0215041637420654,
"logits/rejected": -2.4902031421661377,
"logps/chosen": -0.1890055537223816,
"logps/rejected": -0.3192065358161926,
"loss": 7.142,
"rewards/accuracies": 0.637499988079071,
"rewards/chosen": -0.2835083603858948,
"rewards/margins": 0.19530144333839417,
"rewards/rejected": -0.47880974411964417,
"step": 120
},
{
"epoch": 0.09422850412249706,
"grad_norm": 0.06430571526288986,
"learning_rate": 4.907906416994146e-06,
"logits/chosen": -2.0684752464294434,
"logits/rejected": -2.510018825531006,
"logps/chosen": -0.2073744535446167,
"logps/rejected": -0.3121300935745239,
"loss": 7.1438,
"rewards/accuracies": 0.612500011920929,
"rewards/chosen": -0.31106168031692505,
"rewards/margins": 0.15713343024253845,
"rewards/rejected": -0.4681951403617859,
"step": 130
},
{
"epoch": 0.10147685059345837,
"grad_norm": 0.08829955011606216,
"learning_rate": 4.893298743830168e-06,
"logits/chosen": -2.026458263397217,
"logits/rejected": -2.496157646179199,
"logps/chosen": -0.19946983456611633,
"logps/rejected": -0.32050156593322754,
"loss": 7.1196,
"rewards/accuracies": 0.625,
"rewards/chosen": -0.2992047667503357,
"rewards/margins": 0.18154758214950562,
"rewards/rejected": -0.4807523787021637,
"step": 140
},
{
"epoch": 0.10872519706441967,
"grad_norm": 0.09773921221494675,
"learning_rate": 4.8776412907378845e-06,
"logits/chosen": -2.101029872894287,
"logits/rejected": -2.5849032402038574,
"logps/chosen": -0.18889756500720978,
"logps/rejected": -0.36427801847457886,
"loss": 7.1227,
"rewards/accuracies": 0.6499999761581421,
"rewards/chosen": -0.28334635496139526,
"rewards/margins": 0.26307064294815063,
"rewards/rejected": -0.5464169979095459,
"step": 150
},
{
"epoch": 0.10872519706441967,
"eval_logits/chosen": -2.1945455074310303,
"eval_logits/rejected": -2.559415578842163,
"eval_logps/chosen": -0.22209034860134125,
"eval_logps/rejected": -0.32476040720939636,
"eval_loss": 0.8760393261909485,
"eval_rewards/accuracies": 0.5803571343421936,
"eval_rewards/chosen": -0.33313554525375366,
"eval_rewards/margins": 0.15400508046150208,
"eval_rewards/rejected": -0.48714062571525574,
"eval_runtime": 30.3484,
"eval_samples_per_second": 29.392,
"eval_steps_per_second": 3.69,
"step": 150
}
],
"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": 5.563909198850294e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|