{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9850746268656714, "eval_steps": 500, "global_step": 525, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.05685856432125089, "grad_norm": 0.7364946007728577, "learning_rate": 1.8518518518518518e-05, "loss": 2.6696, "step": 10 }, { "epoch": 0.11371712864250177, "grad_norm": 0.35253632068634033, "learning_rate": 3.7037037037037037e-05, "loss": 2.4653, "step": 20 }, { "epoch": 0.17057569296375266, "grad_norm": 0.3261440098285675, "learning_rate": 4.999552306674344e-05, "loss": 2.3603, "step": 30 }, { "epoch": 0.22743425728500355, "grad_norm": 0.34980908036231995, "learning_rate": 4.9915977740145865e-05, "loss": 2.2758, "step": 40 }, { "epoch": 0.28429282160625446, "grad_norm": 0.31713271141052246, "learning_rate": 4.973730929382489e-05, "loss": 2.2152, "step": 50 }, { "epoch": 0.3411513859275053, "grad_norm": 0.4006229639053345, "learning_rate": 4.946022852363932e-05, "loss": 2.163, "step": 60 }, { "epoch": 0.39800995024875624, "grad_norm": 0.4309302568435669, "learning_rate": 4.9085837738743645e-05, "loss": 2.1219, "step": 70 }, { "epoch": 0.4548685145700071, "grad_norm": 0.41214120388031006, "learning_rate": 4.8615626376276627e-05, "loss": 2.0718, "step": 80 }, { "epoch": 0.511727078891258, "grad_norm": 0.4962936341762543, "learning_rate": 4.8051465075940336e-05, "loss": 2.0389, "step": 90 }, { "epoch": 0.5685856432125089, "grad_norm": 0.6769933104515076, "learning_rate": 4.73955982380429e-05, "loss": 2.0079, "step": 100 }, { "epoch": 0.6254442075337597, "grad_norm": 0.5076603293418884, "learning_rate": 4.665063509461097e-05, "loss": 2.0021, "step": 110 }, { "epoch": 0.6823027718550106, "grad_norm": 0.49396389722824097, "learning_rate": 4.581953932909403e-05, "loss": 1.97, "step": 120 }, { "epoch": 0.7391613361762616, "grad_norm": 0.5190107226371765, "learning_rate": 4.49056172859561e-05, "loss": 1.9661, "step": 130 }, { "epoch": 0.7960199004975125, "grad_norm": 0.5600285530090332, "learning_rate": 4.391250481706078e-05, "loss": 1.9294, "step": 140 }, { "epoch": 0.8528784648187633, "grad_norm": 0.5234688520431519, "learning_rate": 4.284415281717847e-05, "loss": 1.9263, "step": 150 }, { "epoch": 0.9097370291400142, "grad_norm": 0.4960320293903351, "learning_rate": 4.1704811506159904e-05, "loss": 1.9453, "step": 160 }, { "epoch": 0.9665955934612651, "grad_norm": 0.5181735754013062, "learning_rate": 4.0499013520305975e-05, "loss": 1.8972, "step": 170 }, { "epoch": 1.023454157782516, "grad_norm": 0.6533639430999756, "learning_rate": 3.9231555880201655e-05, "loss": 1.9302, "step": 180 }, { "epoch": 1.080312722103767, "grad_norm": 0.5052580237388611, "learning_rate": 3.7907480906751014e-05, "loss": 1.8674, "step": 190 }, { "epoch": 1.1371712864250179, "grad_norm": 0.4947746992111206, "learning_rate": 3.6532056161335147e-05, "loss": 1.8639, "step": 200 }, { "epoch": 1.1940298507462686, "grad_norm": 0.5192781686782837, "learning_rate": 3.511075348989692e-05, "loss": 1.86, "step": 210 }, { "epoch": 1.2508884150675195, "grad_norm": 0.5064213275909424, "learning_rate": 3.364922725432147e-05, "loss": 1.832, "step": 220 }, { "epoch": 1.3077469793887704, "grad_norm": 0.520462691783905, "learning_rate": 3.2153291837714214e-05, "loss": 1.8467, "step": 230 }, { "epoch": 1.3646055437100213, "grad_norm": 0.48832887411117554, "learning_rate": 3.0628898513067353e-05, "loss": 1.838, "step": 240 }, { "epoch": 1.4214641080312722, "grad_norm": 0.6568878293037415, "learning_rate": 2.908211176733781e-05, "loss": 1.8377, "step": 250 }, { "epoch": 1.4783226723525231, "grad_norm": 0.6199402809143066, "learning_rate": 2.751908517512671e-05, "loss": 1.8426, "step": 260 }, { "epoch": 1.535181236673774, "grad_norm": 0.5781152844429016, "learning_rate": 2.5946036917941762e-05, "loss": 1.8193, "step": 270 }, { "epoch": 1.5920398009950247, "grad_norm": 0.5179237127304077, "learning_rate": 2.4369225046434392e-05, "loss": 1.8371, "step": 280 }, { "epoch": 1.6488983653162759, "grad_norm": 0.6433179974555969, "learning_rate": 2.279492258402559e-05, "loss": 1.8118, "step": 290 }, { "epoch": 1.7057569296375266, "grad_norm": 0.522022008895874, "learning_rate": 2.1229392570965657e-05, "loss": 1.8143, "step": 300 }, { "epoch": 1.7626154939587777, "grad_norm": 0.6466122269630432, "learning_rate": 1.9678863148109977e-05, "loss": 1.8214, "step": 310 }, { "epoch": 1.8194740582800284, "grad_norm": 0.5710527896881104, "learning_rate": 1.814950277953485e-05, "loss": 1.8147, "step": 320 }, { "epoch": 1.8763326226012793, "grad_norm": 0.582222580909729, "learning_rate": 1.6647395712565256e-05, "loss": 1.7966, "step": 330 }, { "epoch": 1.9331911869225302, "grad_norm": 0.5713987350463867, "learning_rate": 1.5178517772841655e-05, "loss": 1.7946, "step": 340 }, { "epoch": 1.9900497512437811, "grad_norm": 0.5466066002845764, "learning_rate": 1.3748712590720304e-05, "loss": 1.7996, "step": 350 }, { "epoch": 2.046908315565032, "grad_norm": 0.5649642944335938, "learning_rate": 1.2363668353585487e-05, "loss": 1.7954, "step": 360 }, { "epoch": 2.1037668798862827, "grad_norm": 0.5820536613464355, "learning_rate": 1.1028895176559767e-05, "loss": 1.7484, "step": 370 }, { "epoch": 2.160625444207534, "grad_norm": 0.5737554430961609, "learning_rate": 9.749703181638356e-06, "loss": 1.7479, "step": 380 }, { "epoch": 2.2174840085287846, "grad_norm": 0.5488157272338867, "learning_rate": 8.531181372455161e-06, "loss": 1.767, "step": 390 }, { "epoch": 2.2743425728500357, "grad_norm": 0.5780847668647766, "learning_rate": 7.378177388723001e-06, "loss": 1.7762, "step": 400 }, { "epoch": 2.3312011371712864, "grad_norm": 0.5912370085716248, "learning_rate": 6.2952782208908625e-06, "loss": 1.7534, "step": 410 }, { "epoch": 2.388059701492537, "grad_norm": 0.6620157957077026, "learning_rate": 5.2867919617408556e-06, "loss": 1.7494, "step": 420 }, { "epoch": 2.4449182658137882, "grad_norm": 0.5841735005378723, "learning_rate": 4.35673066752249e-06, "loss": 1.7481, "step": 430 }, { "epoch": 2.501776830135039, "grad_norm": 0.5628016591072083, "learning_rate": 3.508794396807749e-06, "loss": 1.7517, "step": 440 }, { "epoch": 2.55863539445629, "grad_norm": 0.5885946154594421, "learning_rate": 2.7463564905650858e-06, "loss": 1.7676, "step": 450 }, { "epoch": 2.6154939587775408, "grad_norm": 0.5894684791564941, "learning_rate": 2.0724501520125506e-06, "loss": 1.7411, "step": 460 }, { "epoch": 2.672352523098792, "grad_norm": 0.6206966042518616, "learning_rate": 1.4897563796393593e-06, "loss": 1.7338, "step": 470 }, { "epoch": 2.7292110874200426, "grad_norm": 0.5665762424468994, "learning_rate": 1.0005933014019308e-06, "loss": 1.7395, "step": 480 }, { "epoch": 2.7860696517412933, "grad_norm": 0.5661548972129822, "learning_rate": 6.069069525261011e-07, "loss": 1.7523, "step": 490 }, { "epoch": 2.8429282160625444, "grad_norm": 0.5656740665435791, "learning_rate": 3.10263533604116e-07, "loss": 1.7606, "step": 500 }, { "epoch": 2.8429282160625444, "eval_loss": 1.8154741525650024, "eval_runtime": 207.4227, "eval_samples_per_second": 48.211, "eval_steps_per_second": 0.757, "step": 500 }, { "epoch": 2.8997867803837956, "grad_norm": 0.565244734287262, "learning_rate": 1.1184317978602809e-07, "loss": 1.7441, "step": 510 }, { "epoch": 2.9566453447050463, "grad_norm": 0.5718834400177002, "learning_rate": 1.2435265853436017e-08, "loss": 1.7484, "step": 520 }, { "epoch": 2.9850746268656714, "step": 525, "total_flos": 4.318254146969928e+17, "train_loss": 1.9003193955194382, "train_runtime": 24288.4682, "train_samples_per_second": 11.116, "train_steps_per_second": 0.022 } ], "logging_steps": 10, "max_steps": 525, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.318254146969928e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }