| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500.0, | |
| "global_step": 2078, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02406159769008662, | |
| "grad_norm": 0.4678075313568115, | |
| "learning_rate": 0.0001997144304734381, | |
| "loss": 1.8271, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04812319538017324, | |
| "grad_norm": 1.846214771270752, | |
| "learning_rate": 0.00019885935289284243, | |
| "loss": 1.3151, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07218479307025986, | |
| "grad_norm": 0.2397667020559311, | |
| "learning_rate": 0.00019743965094021025, | |
| "loss": 1.2901, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09624639076034648, | |
| "grad_norm": 0.2530920207500458, | |
| "learning_rate": 0.00019546343308783103, | |
| "loss": 1.2714, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12030798845043311, | |
| "grad_norm": 0.28861427307128906, | |
| "learning_rate": 0.00019294198628763448, | |
| "loss": 1.2814, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.14436958614051973, | |
| "grad_norm": 0.31320950388908386, | |
| "learning_rate": 0.0001898897115070003, | |
| "loss": 1.2641, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.16843118383060635, | |
| "grad_norm": 0.2183404266834259, | |
| "learning_rate": 0.00018632404147920934, | |
| "loss": 1.2594, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.19249278152069296, | |
| "grad_norm": 0.23752006888389587, | |
| "learning_rate": 0.00018226534113829578, | |
| "loss": 1.2493, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2165543792107796, | |
| "grad_norm": 0.34118324518203735, | |
| "learning_rate": 0.00017773679130695595, | |
| "loss": 1.2513, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.24061597690086622, | |
| "grad_norm": 0.19650723040103912, | |
| "learning_rate": 0.0001727642563018167, | |
| "loss": 1.248, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2646775745909528, | |
| "grad_norm": 0.18454952538013458, | |
| "learning_rate": 0.0001673761362122227, | |
| "loss": 1.2366, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.28873917228103946, | |
| "grad_norm": 0.17576751112937927, | |
| "learning_rate": 0.00016160320469623483, | |
| "loss": 1.2339, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3128007699711261, | |
| "grad_norm": 0.19318638741970062, | |
| "learning_rate": 0.00015547843322025095, | |
| "loss": 1.2288, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3368623676612127, | |
| "grad_norm": 0.23209917545318604, | |
| "learning_rate": 0.00014903680274608503, | |
| "loss": 1.2315, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.36092396535129934, | |
| "grad_norm": 0.20469824969768524, | |
| "learning_rate": 0.0001423151039410329, | |
| "loss": 1.2243, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3849855630413859, | |
| "grad_norm": 0.1737692654132843, | |
| "learning_rate": 0.00013535172705200364, | |
| "loss": 1.2234, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.40904716073147257, | |
| "grad_norm": 0.14581188559532166, | |
| "learning_rate": 0.00012818644264382662, | |
| "loss": 1.2187, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4331087584215592, | |
| "grad_norm": 0.18442820012569427, | |
| "learning_rate": 0.0001208601744540244, | |
| "loss": 1.2141, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4571703561116458, | |
| "grad_norm": 0.16662022471427917, | |
| "learning_rate": 0.00011341476566136547, | |
| "loss": 1.2087, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.48123195380173245, | |
| "grad_norm": 0.13688209652900696, | |
| "learning_rate": 0.00010589273990312944, | |
| "loss": 1.2123, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5052935514918191, | |
| "grad_norm": 0.13166318833827972, | |
| "learning_rate": 9.833705840600763e-05, | |
| "loss": 1.2039, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5293551491819056, | |
| "grad_norm": 0.11860214918851852, | |
| "learning_rate": 9.07908746177598e-05, | |
| "loss": 1.2026, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5534167468719923, | |
| "grad_norm": 0.13417081534862518, | |
| "learning_rate": 8.3297287741021e-05, | |
| "loss": 1.2073, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.5774783445620789, | |
| "grad_norm": 0.11963389813899994, | |
| "learning_rate": 7.589909657692416e-05, | |
| "loss": 1.2105, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6015399422521656, | |
| "grad_norm": 0.11440490186214447, | |
| "learning_rate": 6.863855508443216e-05, | |
| "loss": 1.2002, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.6256015399422522, | |
| "grad_norm": 0.10429481416940689, | |
| "learning_rate": 6.155713105147687e-05, | |
| "loss": 1.1932, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6496631376323387, | |
| "grad_norm": 0.11212655156850815, | |
| "learning_rate": 5.469526925622783e-05, | |
| "loss": 1.1897, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6737247353224254, | |
| "grad_norm": 0.100895956158638, | |
| "learning_rate": 4.809216047116902e-05, | |
| "loss": 1.1937, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.697786333012512, | |
| "grad_norm": 0.10168924927711487, | |
| "learning_rate": 4.178551762929218e-05, | |
| "loss": 1.1909, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.7218479307025987, | |
| "grad_norm": 0.10396671295166016, | |
| "learning_rate": 3.581136043080835e-05, | |
| "loss": 1.192, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7459095283926853, | |
| "grad_norm": 0.09950781613588333, | |
| "learning_rate": 3.0203809620573042e-05, | |
| "loss": 1.1822, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.7699711260827719, | |
| "grad_norm": 0.0905219241976738, | |
| "learning_rate": 2.499489211118732e-05, | |
| "loss": 1.1886, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7940327237728585, | |
| "grad_norm": 0.09419446438550949, | |
| "learning_rate": 2.0214358064792172e-05, | |
| "loss": 1.1771, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.8180943214629451, | |
| "grad_norm": 0.08652393519878387, | |
| "learning_rate": 1.5889510978274558e-05, | |
| "loss": 1.1839, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8421559191530318, | |
| "grad_norm": 0.0858326181769371, | |
| "learning_rate": 1.2045051742333412e-05, | |
| "loss": 1.1825, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.8662175168431184, | |
| "grad_norm": 0.08168898522853851, | |
| "learning_rate": 8.702937565046632e-06, | |
| "loss": 1.1884, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.890279114533205, | |
| "grad_norm": 0.07847324758768082, | |
| "learning_rate": 5.882256565680689e-06, | |
| "loss": 1.1833, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.9143407122232916, | |
| "grad_norm": 0.07860458642244339, | |
| "learning_rate": 3.5991187549870077e-06, | |
| "loss": 1.1795, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.9384023099133783, | |
| "grad_norm": 0.07967723906040192, | |
| "learning_rate": 1.8665640246390836e-06, | |
| "loss": 1.183, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.9624639076034649, | |
| "grad_norm": 0.07612236589193344, | |
| "learning_rate": 6.944876713186777e-07, | |
| "loss": 1.1813, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9865255052935515, | |
| "grad_norm": 0.07368049770593643, | |
| "learning_rate": 8.958388081204971e-08, | |
| "loss": 1.1797, | |
| "step": 2050 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2078, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 5.08902708254102e+19, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |