{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.8844665561083471, "eval_steps": 100, "global_step": 400, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.02211166390270868, "grad_norm": 0.15348762273788452, "learning_rate": 0.00012857142857142858, "loss": 0.3086357593536377, "step": 10 }, { "epoch": 0.04422332780541736, "grad_norm": 0.18878376483917236, "learning_rate": 0.00019993599198164715, "loss": 0.20254485607147216, "step": 20 }, { "epoch": 0.06633499170812604, "grad_norm": 0.1501179039478302, "learning_rate": 0.00019942441937309684, "loss": 0.17662062644958496, "step": 30 }, { "epoch": 0.08844665561083472, "grad_norm": 0.22809264063835144, "learning_rate": 0.00019840389289753896, "loss": 0.1831057548522949, "step": 40 }, { "epoch": 0.11055831951354339, "grad_norm": 0.18418847024440765, "learning_rate": 0.00019687963663271409, "loss": 0.15948907136917115, "step": 50 }, { "epoch": 0.13266998341625208, "grad_norm": 0.32137757539749146, "learning_rate": 0.00019485945325049288, "loss": 0.15973985195159912, "step": 60 }, { "epoch": 0.15478164731896074, "grad_norm": 0.20718726515769958, "learning_rate": 0.00019235368407497788, "loss": 0.17318328619003295, "step": 70 }, { "epoch": 0.17689331122166943, "grad_norm": 0.13116584718227386, "learning_rate": 0.00018937515614523797, "loss": 0.14626134634017945, "step": 80 }, { "epoch": 0.19900497512437812, "grad_norm": 0.1647884100675583, "learning_rate": 0.0001859391165536615, "loss": 0.1785536527633667, "step": 90 }, { "epoch": 0.22111663902708678, "grad_norm": 0.18008048832416534, "learning_rate": 0.0001820631543960496, "loss": 0.16188329458236694, "step": 100 }, { "epoch": 0.22111663902708678, "eval_loss": 0.16310861706733704, "eval_runtime": 31.07, "eval_samples_per_second": 6.437, "eval_steps_per_second": 3.219, "step": 100 }, { "epoch": 0.24322830292979547, "grad_norm": 0.14600931107997894, "learning_rate": 0.000177767110732988, "loss": 0.1460275173187256, "step": 110 }, { "epoch": 0.26533996683250416, "grad_norm": 0.25409597158432007, "learning_rate": 0.0001730729770234054, "loss": 0.1481616497039795, "step": 120 }, { "epoch": 0.28745163073521285, "grad_norm": 0.19037796556949615, "learning_rate": 0.00016800478255023658, "loss": 0.13189032077789306, "step": 130 }, { "epoch": 0.3095632946379215, "grad_norm": 0.17498186230659485, "learning_rate": 0.00016258847141445928, "loss": 0.13937866687774658, "step": 140 }, { "epoch": 0.33167495854063017, "grad_norm": 0.20093761384487152, "learning_rate": 0.00015685176972717223, "loss": 0.14852123260498046, "step": 150 }, { "epoch": 0.35378662244333886, "grad_norm": 0.2791161835193634, "learning_rate": 0.0001508240436795589, "loss": 0.13668410778045653, "step": 160 }, { "epoch": 0.37589828634604755, "grad_norm": 0.22740238904953003, "learning_rate": 0.00014453614921727668, "loss": 0.14316325187683104, "step": 170 }, { "epoch": 0.39800995024875624, "grad_norm": 0.2161274552345276, "learning_rate": 0.0001380202740887891, "loss": 0.12174032926559449, "step": 180 }, { "epoch": 0.4201216141514649, "grad_norm": 0.18681354820728302, "learning_rate": 0.00013130977307619594, "loss": 0.13955849409103394, "step": 190 }, { "epoch": 0.44223327805417356, "grad_norm": 0.2361515313386917, "learning_rate": 0.00012443899725201482, "loss": 0.13372476100921632, "step": 200 }, { "epoch": 0.44223327805417356, "eval_loss": 0.13203567266464233, "eval_runtime": 31.1218, "eval_samples_per_second": 6.426, "eval_steps_per_second": 3.213, "step": 200 }, { "epoch": 0.46434494195688225, "grad_norm": 0.21914763748645782, "learning_rate": 0.00011744311813595006, "loss": 0.1153406023979187, "step": 210 }, { "epoch": 0.48645660585959094, "grad_norm": 0.15631644427776337, "learning_rate": 0.00011035794765178941, "loss": 0.12997454404830933, "step": 220 }, { "epoch": 0.5085682697622996, "grad_norm": 0.20152823626995087, "learning_rate": 0.00010321975480607129, "loss": 0.1341830849647522, "step": 230 }, { "epoch": 0.5306799336650083, "grad_norm": 0.25537344813346863, "learning_rate": 9.606508002694386e-05, "loss": 0.12994074821472168, "step": 240 }, { "epoch": 0.552791597567717, "grad_norm": 0.2107098400592804, "learning_rate": 8.893054811361624e-05, "loss": 0.13043956756591796, "step": 250 }, { "epoch": 0.5749032614704257, "grad_norm": 0.22411906719207764, "learning_rate": 8.185268075391388e-05, "loss": 0.1208024263381958, "step": 260 }, { "epoch": 0.5970149253731343, "grad_norm": 0.4044502377510071, "learning_rate": 7.486770956966171e-05, "loss": 0.11572929620742797, "step": 270 }, { "epoch": 0.619126589275843, "grad_norm": 0.205791637301445, "learning_rate": 6.801139064691562e-05, "loss": 0.10089305639266968, "step": 280 }, { "epoch": 0.6412382531785517, "grad_norm": 0.2793091833591461, "learning_rate": 6.131882150046291e-05, "loss": 0.11170923709869385, "step": 290 }, { "epoch": 0.6633499170812603, "grad_norm": 0.21104425191879272, "learning_rate": 5.48242614095509e-05, "loss": 0.11723569631576539, "step": 300 }, { "epoch": 0.6633499170812603, "eval_loss": 0.1226131021976471, "eval_runtime": 31.1578, "eval_samples_per_second": 6.419, "eval_steps_per_second": 3.209, "step": 300 }, { "epoch": 0.685461580983969, "grad_norm": 0.23795899748802185, "learning_rate": 4.856095604454539e-05, "loss": 0.10257929563522339, "step": 310 }, { "epoch": 0.7075732448866777, "grad_norm": 0.2890011966228485, "learning_rate": 4.256096728225548e-05, "loss": 0.10419625043869019, "step": 320 }, { "epoch": 0.7296849087893864, "grad_norm": 0.3154986798763275, "learning_rate": 3.6855009081101355e-05, "loss": 0.09712555408477783, "step": 330 }, { "epoch": 0.7517965726920951, "grad_norm": 0.25235816836357117, "learning_rate": 3.147229025627922e-05, "loss": 0.11032156944274903, "step": 340 }, { "epoch": 0.7739082365948038, "grad_norm": 0.3916188180446625, "learning_rate": 2.6440364959758802e-05, "loss": 0.10476597547531127, "step": 350 }, { "epoch": 0.7960199004975125, "grad_norm": 0.39090999960899353, "learning_rate": 2.178499163050617e-05, "loss": 0.10685886144638061, "step": 360 }, { "epoch": 0.8181315644002212, "grad_norm": 0.3829365074634552, "learning_rate": 1.753000113696617e-05, "loss": 0.09261282086372376, "step": 370 }, { "epoch": 0.8402432283029297, "grad_norm": 0.23521588742733002, "learning_rate": 1.3697174786783584e-05, "loss": 0.09778770804405212, "step": 380 }, { "epoch": 0.8623548922056384, "grad_norm": 0.2212682068347931, "learning_rate": 1.0306132828231308e-05, "loss": 0.09821119904518127, "step": 390 }, { "epoch": 0.8844665561083471, "grad_norm": 0.20046958327293396, "learning_rate": 7.374234014107484e-06, "loss": 0.11094816923141479, "step": 400 }, { "epoch": 0.8844665561083471, "eval_loss": 0.11389771103858948, "eval_runtime": 31.2529, "eval_samples_per_second": 6.399, "eval_steps_per_second": 3.2, "step": 400 } ], "logging_steps": 10, "max_steps": 453, "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": false }, "attributes": {} } }, "total_flos": 4.200085684875264e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }