| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9978976874562018, | |
| "eval_steps": 500, | |
| "global_step": 267, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01868722261153936, | |
| "grad_norm": 3.5830482905634797, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.8152, | |
| "mean_token_accuracy": 0.7747266553342342, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03737444522307872, | |
| "grad_norm": 1.6625011834876648, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.7025, | |
| "mean_token_accuracy": 0.7917468748986721, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05606166783461808, | |
| "grad_norm": 1.5899441749058187, | |
| "learning_rate": 4.9998265374824964e-05, | |
| "loss": 0.629, | |
| "mean_token_accuracy": 0.8071001760661602, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07474889044615744, | |
| "grad_norm": 1.5979853248536116, | |
| "learning_rate": 4.993758157237536e-05, | |
| "loss": 0.5972, | |
| "mean_token_accuracy": 0.8143526442348957, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09343611305769679, | |
| "grad_norm": 1.2674965103641067, | |
| "learning_rate": 4.979043378581744e-05, | |
| "loss": 0.5727, | |
| "mean_token_accuracy": 0.8199357651174068, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11212333566923616, | |
| "grad_norm": 1.3685254142570102, | |
| "learning_rate": 4.9557389054153965e-05, | |
| "loss": 0.5555, | |
| "mean_token_accuracy": 0.8241050921380519, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1308105582807755, | |
| "grad_norm": 0.9457691254500147, | |
| "learning_rate": 4.923934542318854e-05, | |
| "loss": 0.5409, | |
| "mean_token_accuracy": 0.8273717932403087, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14949778089231489, | |
| "grad_norm": 0.9189569415750541, | |
| "learning_rate": 4.883752848487571e-05, | |
| "loss": 0.5272, | |
| "mean_token_accuracy": 0.8308477029204369, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16818500350385424, | |
| "grad_norm": 0.7752642460093544, | |
| "learning_rate": 4.835348665446049e-05, | |
| "loss": 0.5213, | |
| "mean_token_accuracy": 0.8322811633348465, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18687222611539359, | |
| "grad_norm": 0.8083941553455664, | |
| "learning_rate": 4.7789085203607664e-05, | |
| "loss": 0.5118, | |
| "mean_token_accuracy": 0.8346851594746113, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20555944872693296, | |
| "grad_norm": 0.9161612194082712, | |
| "learning_rate": 4.714649907251388e-05, | |
| "loss": 0.5088, | |
| "mean_token_accuracy": 0.8352511122822761, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22424667133847231, | |
| "grad_norm": 0.6723034421711911, | |
| "learning_rate": 4.6428204488701576e-05, | |
| "loss": 0.5018, | |
| "mean_token_accuracy": 0.837028643488884, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2429338939500117, | |
| "grad_norm": 0.7871127694104725, | |
| "learning_rate": 4.563696942479205e-05, | |
| "loss": 0.5061, | |
| "mean_token_accuracy": 0.8351837247610092, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.261621116561551, | |
| "grad_norm": 0.761272463434446, | |
| "learning_rate": 4.477584293202868e-05, | |
| "loss": 0.4939, | |
| "mean_token_accuracy": 0.8390413090586663, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2803083391730904, | |
| "grad_norm": 0.5083377211370889, | |
| "learning_rate": 4.384814339065424e-05, | |
| "loss": 0.4914, | |
| "mean_token_accuracy": 0.8395063504576683, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.29899556178462977, | |
| "grad_norm": 0.908648503032802, | |
| "learning_rate": 4.285744572241972e-05, | |
| "loss": 0.4972, | |
| "mean_token_accuracy": 0.8376469679176808, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3176827843961691, | |
| "grad_norm": 0.5938541774391267, | |
| "learning_rate": 4.180756761450171e-05, | |
| "loss": 0.4816, | |
| "mean_token_accuracy": 0.8424232035875321, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.33637000700770847, | |
| "grad_norm": 0.4849394515949123, | |
| "learning_rate": 4.070255480791492e-05, | |
| "loss": 0.491, | |
| "mean_token_accuracy": 0.8394017495214939, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35505722961924785, | |
| "grad_norm": 0.5718927262308711, | |
| "learning_rate": 3.954666550711159e-05, | |
| "loss": 0.4851, | |
| "mean_token_accuracy": 0.8409382797777653, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.37374445223078717, | |
| "grad_norm": 0.5859959003534665, | |
| "learning_rate": 3.8344353970845606e-05, | |
| "loss": 0.4862, | |
| "mean_token_accuracy": 0.8411718301475049, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.39243167484232655, | |
| "grad_norm": 0.3782337735273932, | |
| "learning_rate": 3.710025334753495e-05, | |
| "loss": 0.4834, | |
| "mean_token_accuracy": 0.8412449143826961, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.41111889745386593, | |
| "grad_norm": 0.41111283052381054, | |
| "learning_rate": 3.581915782126652e-05, | |
| "loss": 0.476, | |
| "mean_token_accuracy": 0.8432458408176899, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4298061200654053, | |
| "grad_norm": 0.3851706170856147, | |
| "learning_rate": 3.4506004137244676e-05, | |
| "loss": 0.4851, | |
| "mean_token_accuracy": 0.8405788190662861, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.44849334267694463, | |
| "grad_norm": 0.5062426249148336, | |
| "learning_rate": 3.3165852577875546e-05, | |
| "loss": 0.4785, | |
| "mean_token_accuracy": 0.8426314078271389, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.467180565288484, | |
| "grad_norm": 0.40499027788768055, | |
| "learning_rate": 3.180386746279663e-05, | |
| "loss": 0.4747, | |
| "mean_token_accuracy": 0.843725374341011, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4858677879000234, | |
| "grad_norm": 0.47044740848341193, | |
| "learning_rate": 3.04252972479953e-05, | |
| "loss": 0.472, | |
| "mean_token_accuracy": 0.8443724811077118, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5045550105115627, | |
| "grad_norm": 0.4272272972180237, | |
| "learning_rate": 2.90354543007051e-05, | |
| "loss": 0.4725, | |
| "mean_token_accuracy": 0.8439367160201072, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.523242233123102, | |
| "grad_norm": 0.4584455682048115, | |
| "learning_rate": 2.7639694428017792e-05, | |
| "loss": 0.4777, | |
| "mean_token_accuracy": 0.842538620531559, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5419294557346415, | |
| "grad_norm": 0.4589522708203329, | |
| "learning_rate": 2.6243396238098518e-05, | |
| "loss": 0.4693, | |
| "mean_token_accuracy": 0.8448904320597649, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5606166783461808, | |
| "grad_norm": 0.5239037802900407, | |
| "learning_rate": 2.4851940413536174e-05, | |
| "loss": 0.4697, | |
| "mean_token_accuracy": 0.8447436839342117, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5793039009577201, | |
| "grad_norm": 0.4866344062046232, | |
| "learning_rate": 2.347068897669999e-05, | |
| "loss": 0.4687, | |
| "mean_token_accuracy": 0.8448469452559948, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5979911235692595, | |
| "grad_norm": 0.3163374085877721, | |
| "learning_rate": 2.2104964627003848e-05, | |
| "loss": 0.4629, | |
| "mean_token_accuracy": 0.846843034029007, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6166783461807989, | |
| "grad_norm": 0.2747336073106856, | |
| "learning_rate": 2.0760030229702972e-05, | |
| "loss": 0.4612, | |
| "mean_token_accuracy": 0.8469885870814323, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6353655687923382, | |
| "grad_norm": 0.24722982457005138, | |
| "learning_rate": 1.9441068535263564e-05, | |
| "loss": 0.4596, | |
| "mean_token_accuracy": 0.8476050347089767, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6540527914038776, | |
| "grad_norm": 0.23852151209010736, | |
| "learning_rate": 1.815316220745756e-05, | |
| "loss": 0.4636, | |
| "mean_token_accuracy": 0.8460029393434525, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6727400140154169, | |
| "grad_norm": 0.2597676847867842, | |
| "learning_rate": 1.6901274237144782e-05, | |
| "loss": 0.4669, | |
| "mean_token_accuracy": 0.8451244607567787, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6914272366269563, | |
| "grad_norm": 0.8605153163863832, | |
| "learning_rate": 1.5690228817218815e-05, | |
| "loss": 0.4668, | |
| "mean_token_accuracy": 0.8468827910721302, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7101144592384957, | |
| "grad_norm": 0.24915841679008277, | |
| "learning_rate": 1.4524692752415493e-05, | |
| "loss": 0.4591, | |
| "mean_token_accuracy": 0.8473225735127926, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.728801681850035, | |
| "grad_norm": 0.29798920762515824, | |
| "learning_rate": 1.3409157475622094e-05, | |
| "loss": 0.4576, | |
| "mean_token_accuracy": 0.847739252448082, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7474889044615743, | |
| "grad_norm": 0.26110601129292016, | |
| "learning_rate": 1.2347921739987815e-05, | |
| "loss": 0.4611, | |
| "mean_token_accuracy": 0.8468295410275459, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7661761270731138, | |
| "grad_norm": 0.2785413649007615, | |
| "learning_rate": 1.1345075053532287e-05, | |
| "loss": 0.4615, | |
| "mean_token_accuracy": 0.846584790199995, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7848633496846531, | |
| "grad_norm": 0.281588896295376, | |
| "learning_rate": 1.0404481920087206e-05, | |
| "loss": 0.4532, | |
| "mean_token_accuracy": 0.8491566374897956, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8035505722961925, | |
| "grad_norm": 0.26784943568942043, | |
| "learning_rate": 9.529766947299371e-06, | |
| "loss": 0.4555, | |
| "mean_token_accuracy": 0.8485622465610504, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8222377949077319, | |
| "grad_norm": 0.22085700610769077, | |
| "learning_rate": 8.724300879081718e-06, | |
| "loss": 0.4584, | |
| "mean_token_accuracy": 0.8476461283862591, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8409250175192712, | |
| "grad_norm": 0.1833370072353519, | |
| "learning_rate": 7.991187606337009e-06, | |
| "loss": 0.452, | |
| "mean_token_accuracy": 0.8494263976812363, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8596122401308106, | |
| "grad_norm": 0.20272051001866034, | |
| "learning_rate": 7.333252206008559e-06, | |
| "loss": 0.4538, | |
| "mean_token_accuracy": 0.8487676382064819, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8782994627423499, | |
| "grad_norm": 0.19595652872474512, | |
| "learning_rate": 6.753030054550158e-06, | |
| "loss": 0.4506, | |
| "mean_token_accuracy": 0.8496683083474637, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8969866853538893, | |
| "grad_norm": 0.19319039281954486, | |
| "learning_rate": 6.25275705776658e-06, | |
| "loss": 0.4519, | |
| "mean_token_accuracy": 0.8493411011993885, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9156739079654287, | |
| "grad_norm": 0.20035376740680347, | |
| "learning_rate": 5.834361034674521e-06, | |
| "loss": 0.4557, | |
| "mean_token_accuracy": 0.8482660032808781, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.934361130576968, | |
| "grad_norm": 0.2010469617138832, | |
| "learning_rate": 5.499454288586379e-06, | |
| "loss": 0.453, | |
| "mean_token_accuracy": 0.8490205124020577, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9530483531885073, | |
| "grad_norm": 0.2001591137777418, | |
| "learning_rate": 5.24932739404462e-06, | |
| "loss": 0.4488, | |
| "mean_token_accuracy": 0.8502446681261062, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9717355758000468, | |
| "grad_norm": 0.18321355893669744, | |
| "learning_rate": 5.08494422354882e-06, | |
| "loss": 0.4518, | |
| "mean_token_accuracy": 0.849391470849514, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9904227984115861, | |
| "grad_norm": 0.18951844466307075, | |
| "learning_rate": 5.006938233240212e-06, | |
| "loss": 0.4554, | |
| "mean_token_accuracy": 0.8482832841575145, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.9978976874562018, | |
| "mean_token_accuracy": 0.8498711809515953, | |
| "step": 267, | |
| "total_flos": 2841831180075008.0, | |
| "train_loss": 0.4941176689519418, | |
| "train_runtime": 26749.4727, | |
| "train_samples_per_second": 1.28, | |
| "train_steps_per_second": 0.01 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 267, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2841831180075008.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |