| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 4825, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002072538860103627, | |
| "grad_norm": 0.5270228385925293, | |
| "learning_rate": 4.140786749482402e-07, | |
| "loss": 0.7597, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02072538860103627, | |
| "grad_norm": 0.3120118975639343, | |
| "learning_rate": 4.140786749482402e-05, | |
| "loss": 0.8058, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04145077720207254, | |
| "grad_norm": 0.3838038146495819, | |
| "learning_rate": 8.281573498964804e-05, | |
| "loss": 0.8085, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06217616580310881, | |
| "grad_norm": 0.33677420020103455, | |
| "learning_rate": 0.00012422360248447205, | |
| "loss": 0.8452, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08290155440414508, | |
| "grad_norm": 0.2833797335624695, | |
| "learning_rate": 0.00016563146997929608, | |
| "loss": 0.7836, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.10362694300518134, | |
| "grad_norm": 0.3029078245162964, | |
| "learning_rate": 0.0001999924354607825, | |
| "loss": 0.8032, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12435233160621761, | |
| "grad_norm": 0.30878347158432007, | |
| "learning_rate": 0.00019964190153093613, | |
| "loss": 0.8034, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.14507772020725387, | |
| "grad_norm": 0.1962185502052307, | |
| "learning_rate": 0.00019878125322990773, | |
| "loss": 0.8069, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.16580310880829016, | |
| "grad_norm": 0.2113143652677536, | |
| "learning_rate": 0.00019739761494902327, | |
| "loss": 0.8239, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.18652849740932642, | |
| "grad_norm": 0.36496707797050476, | |
| "learning_rate": 0.00019550431853565577, | |
| "loss": 0.7952, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.20725388601036268, | |
| "grad_norm": 0.4117984175682068, | |
| "learning_rate": 0.00019311127115144138, | |
| "loss": 0.8159, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.22797927461139897, | |
| "grad_norm": 0.25097981095314026, | |
| "learning_rate": 0.00019023099503382319, | |
| "loss": 0.8295, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.24870466321243523, | |
| "grad_norm": 0.2996521592140198, | |
| "learning_rate": 0.00018687856197021518, | |
| "loss": 0.8071, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2694300518134715, | |
| "grad_norm": 0.2897460162639618, | |
| "learning_rate": 0.0001830715144309886, | |
| "loss": 0.8338, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.29015544041450775, | |
| "grad_norm": 0.5588517785072327, | |
| "learning_rate": 0.0001788297737739727, | |
| "loss": 0.7572, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.31088082901554404, | |
| "grad_norm": 0.47002148628234863, | |
| "learning_rate": 0.00017417553600081358, | |
| "loss": 0.809, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.3316062176165803, | |
| "grad_norm": 0.3224999010562897, | |
| "learning_rate": 0.00016913315561067264, | |
| "loss": 0.7942, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.35233160621761656, | |
| "grad_norm": 0.5584061145782471, | |
| "learning_rate": 0.0001637290181590304, | |
| "loss": 0.8329, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.37305699481865284, | |
| "grad_norm": 0.3566969633102417, | |
| "learning_rate": 0.00015799140218846435, | |
| "loss": 0.7901, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.39378238341968913, | |
| "grad_norm": 0.27286580204963684, | |
| "learning_rate": 0.00015195033125388395, | |
| "loss": 0.8138, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.41450777202072536, | |
| "grad_norm": 0.3148711621761322, | |
| "learning_rate": 0.00014563741681653824, | |
| "loss": 0.7867, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.43523316062176165, | |
| "grad_norm": 0.3646707832813263, | |
| "learning_rate": 0.0001390856928288946, | |
| "loss": 0.7681, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.45595854922279794, | |
| "grad_norm": 0.32302677631378174, | |
| "learning_rate": 0.00013232944287596522, | |
| "loss": 0.8134, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.47668393782383417, | |
| "grad_norm": 0.7468949556350708, | |
| "learning_rate": 0.000125404020777609, | |
| "loss": 0.7862, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.49740932642487046, | |
| "grad_norm": 0.36616334319114685, | |
| "learning_rate": 0.00011834566559055394, | |
| "loss": 0.7675, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.5181347150259067, | |
| "grad_norm": 0.3042179346084595, | |
| "learning_rate": 0.00011119131197818904, | |
| "loss": 0.7824, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.538860103626943, | |
| "grad_norm": 0.6282315850257874, | |
| "learning_rate": 0.0001039783969404153, | |
| "loss": 0.8008, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.5595854922279793, | |
| "grad_norm": 0.309589147567749, | |
| "learning_rate": 9.674466391489112e-05, | |
| "loss": 0.7918, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.5803108808290155, | |
| "grad_norm": 0.6195072531700134, | |
| "learning_rate": 8.952796527476341e-05, | |
| "loss": 0.7714, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.6010362694300518, | |
| "grad_norm": 0.5037879943847656, | |
| "learning_rate": 8.236606425636553e-05, | |
| "loss": 0.8098, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.6217616580310881, | |
| "grad_norm": 0.3202759325504303, | |
| "learning_rate": 7.529643735334646e-05, | |
| "loss": 0.7303, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6424870466321243, | |
| "grad_norm": 0.4311729669570923, | |
| "learning_rate": 6.835607821125519e-05, | |
| "loss": 0.7717, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.6632124352331606, | |
| "grad_norm": 0.28787970542907715, | |
| "learning_rate": 6.158130404875231e-05, | |
| "loss": 0.7748, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.6839378238341969, | |
| "grad_norm": 0.28564584255218506, | |
| "learning_rate": 5.5007565618399506e-05, | |
| "loss": 0.8161, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.7046632124352331, | |
| "grad_norm": 0.5357826352119446, | |
| "learning_rate": 4.873136932795313e-05, | |
| "loss": 0.7594, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.7253886010362695, | |
| "grad_norm": 0.292579710483551, | |
| "learning_rate": 4.265882101960175e-05, | |
| "loss": 0.7572, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7461139896373057, | |
| "grad_norm": 0.29901111125946045, | |
| "learning_rate": 3.688632521467985e-05, | |
| "loss": 0.7514, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.7668393782383419, | |
| "grad_norm": 0.3171032667160034, | |
| "learning_rate": 3.144408798582336e-05, | |
| "loss": 0.7862, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.7875647668393783, | |
| "grad_norm": 0.43368250131607056, | |
| "learning_rate": 2.636058724251739e-05, | |
| "loss": 0.7994, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.8082901554404145, | |
| "grad_norm": 0.4301137924194336, | |
| "learning_rate": 2.1662423713092516e-05, | |
| "loss": 0.7646, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.8290155440414507, | |
| "grad_norm": 0.20049989223480225, | |
| "learning_rate": 1.737418174955542e-05, | |
| "loss": 0.7742, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.8497409326424871, | |
| "grad_norm": 0.5148625373840332, | |
| "learning_rate": 1.3518300683627982e-05, | |
| "loss": 0.7357, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.8704663212435233, | |
| "grad_norm": 0.38820308446884155, | |
| "learning_rate": 1.011495740715882e-05, | |
| "loss": 0.7536, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.8911917098445595, | |
| "grad_norm": 0.6004698276519775, | |
| "learning_rate": 7.1819607913342745e-06, | |
| "loss": 0.7238, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.9119170984455959, | |
| "grad_norm": 0.30640721321105957, | |
| "learning_rate": 4.734658497168276e-06, | |
| "loss": 0.7669, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.9326424870466321, | |
| "grad_norm": 0.23962052166461945, | |
| "learning_rate": 2.7858566649088814e-06, | |
| "loss": 0.7329, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.9533678756476683, | |
| "grad_norm": 0.2379899024963379, | |
| "learning_rate": 1.3457529026076777e-06, | |
| "loss": 0.7845, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.9740932642487047, | |
| "grad_norm": 0.291648268699646, | |
| "learning_rate": 4.218829245063227e-07, | |
| "loss": 0.773, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.9948186528497409, | |
| "grad_norm": 0.7486833930015564, | |
| "learning_rate": 1.9081118468888824e-08, | |
| "loss": 0.8057, | |
| "step": 4800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4825, | |
| "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": 1.3151301866366976e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |