| { | |
| "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": 0.12731152772903442, | |
| "learning_rate": 0.0001997144304734381, | |
| "loss": 1.4321, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04812319538017324, | |
| "grad_norm": 0.17785188555717468, | |
| "learning_rate": 0.00019885935289284243, | |
| "loss": 1.1646, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07218479307025986, | |
| "grad_norm": 0.20939375460147858, | |
| "learning_rate": 0.00019743965094021025, | |
| "loss": 1.1437, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09624639076034648, | |
| "grad_norm": 0.16228704154491425, | |
| "learning_rate": 0.00019546343308783103, | |
| "loss": 1.1293, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12030798845043311, | |
| "grad_norm": 0.17629307508468628, | |
| "learning_rate": 0.00019294198628763448, | |
| "loss": 1.1407, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.14436958614051973, | |
| "grad_norm": 0.21964997053146362, | |
| "learning_rate": 0.0001898897115070003, | |
| "loss": 1.1248, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.16843118383060635, | |
| "grad_norm": 0.14089353382587433, | |
| "learning_rate": 0.00018632404147920934, | |
| "loss": 1.1263, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.19249278152069296, | |
| "grad_norm": 15.953330039978027, | |
| "learning_rate": 0.00018226534113829578, | |
| "loss": 1.1168, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2165543792107796, | |
| "grad_norm": 0.1421365886926651, | |
| "learning_rate": 0.00017773679130695595, | |
| "loss": 1.1209, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.24061597690086622, | |
| "grad_norm": 0.12633951008319855, | |
| "learning_rate": 0.0001727642563018167, | |
| "loss": 1.1136, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2646775745909528, | |
| "grad_norm": 0.1551765352487564, | |
| "learning_rate": 0.0001673761362122227, | |
| "loss": 1.1031, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.28873917228103946, | |
| "grad_norm": 0.10191167891025543, | |
| "learning_rate": 0.00016160320469623483, | |
| "loss": 1.1027, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3128007699711261, | |
| "grad_norm": 0.10823129862546921, | |
| "learning_rate": 0.00015547843322025095, | |
| "loss": 1.0963, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3368623676612127, | |
| "grad_norm": 0.08364494144916534, | |
| "learning_rate": 0.00014903680274608503, | |
| "loss": 1.0993, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.36092396535129934, | |
| "grad_norm": 0.12315221130847931, | |
| "learning_rate": 0.0001423151039410329, | |
| "loss": 1.0921, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3849855630413859, | |
| "grad_norm": 0.1051948294043541, | |
| "learning_rate": 0.00013535172705200364, | |
| "loss": 1.0916, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.40904716073147257, | |
| "grad_norm": 0.10586602240800858, | |
| "learning_rate": 0.00012818644264382662, | |
| "loss": 1.0871, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4331087584215592, | |
| "grad_norm": 0.10873878002166748, | |
| "learning_rate": 0.0001208601744540244, | |
| "loss": 1.0819, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4571703561116458, | |
| "grad_norm": 0.08816947042942047, | |
| "learning_rate": 0.00011341476566136547, | |
| "loss": 1.0789, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.48123195380173245, | |
| "grad_norm": 0.09611134976148605, | |
| "learning_rate": 0.00010589273990312944, | |
| "loss": 1.0814, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5052935514918191, | |
| "grad_norm": 0.08588535338640213, | |
| "learning_rate": 9.833705840600763e-05, | |
| "loss": 1.0734, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5293551491819056, | |
| "grad_norm": 0.07991491258144379, | |
| "learning_rate": 9.07908746177598e-05, | |
| "loss": 1.0722, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5534167468719923, | |
| "grad_norm": 0.07974735647439957, | |
| "learning_rate": 8.3297287741021e-05, | |
| "loss": 1.0769, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.5774783445620789, | |
| "grad_norm": 0.08054530620574951, | |
| "learning_rate": 7.589909657692416e-05, | |
| "loss": 1.0801, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6015399422521656, | |
| "grad_norm": 0.08244979381561279, | |
| "learning_rate": 6.863855508443216e-05, | |
| "loss": 1.0704, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.6256015399422522, | |
| "grad_norm": 0.07688669115304947, | |
| "learning_rate": 6.155713105147687e-05, | |
| "loss": 1.0649, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6496631376323387, | |
| "grad_norm": 0.06365044414997101, | |
| "learning_rate": 5.469526925622783e-05, | |
| "loss": 1.061, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6737247353224254, | |
| "grad_norm": 0.061256468296051025, | |
| "learning_rate": 4.809216047116902e-05, | |
| "loss": 1.0646, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.697786333012512, | |
| "grad_norm": 0.06060384586453438, | |
| "learning_rate": 4.178551762929218e-05, | |
| "loss": 1.0626, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.7218479307025987, | |
| "grad_norm": 0.06605063378810883, | |
| "learning_rate": 3.581136043080835e-05, | |
| "loss": 1.0643, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7459095283926853, | |
| "grad_norm": 0.05938854441046715, | |
| "learning_rate": 3.0203809620573042e-05, | |
| "loss": 1.0551, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.7699711260827719, | |
| "grad_norm": 0.059756290167570114, | |
| "learning_rate": 2.499489211118732e-05, | |
| "loss": 1.0601, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7940327237728585, | |
| "grad_norm": 0.05975335091352463, | |
| "learning_rate": 2.0214358064792172e-05, | |
| "loss": 1.0499, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.8180943214629451, | |
| "grad_norm": 0.05708390101790428, | |
| "learning_rate": 1.5889510978274558e-05, | |
| "loss": 1.0557, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8421559191530318, | |
| "grad_norm": 0.05504734441637993, | |
| "learning_rate": 1.2045051742333412e-05, | |
| "loss": 1.0549, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.8662175168431184, | |
| "grad_norm": 0.055338677018880844, | |
| "learning_rate": 8.702937565046632e-06, | |
| "loss": 1.0611, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.890279114533205, | |
| "grad_norm": 0.05398984253406525, | |
| "learning_rate": 5.882256565680689e-06, | |
| "loss": 1.0554, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.9143407122232916, | |
| "grad_norm": 0.05350427329540253, | |
| "learning_rate": 3.5991187549870077e-06, | |
| "loss": 1.0526, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.9384023099133783, | |
| "grad_norm": 0.05145389959216118, | |
| "learning_rate": 1.8665640246390836e-06, | |
| "loss": 1.0552, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.9624639076034649, | |
| "grad_norm": 0.05064576491713524, | |
| "learning_rate": 6.944876713186777e-07, | |
| "loss": 1.0546, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9865255052935515, | |
| "grad_norm": 0.05046650767326355, | |
| "learning_rate": 8.958388081204971e-08, | |
| "loss": 1.053, | |
| "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": 1.4740522235991163e+20, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |