| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.2338062924120914, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.030845157310302282, | |
| "grad_norm": 2.8206074237823486, | |
| "learning_rate": 1.0277492291880782e-05, | |
| "loss": 1.8082, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.061690314620604564, | |
| "grad_norm": 3.4183013439178467, | |
| "learning_rate": 2.0554984583761563e-05, | |
| "loss": 0.6538, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09253547193090685, | |
| "grad_norm": 2.170591354370117, | |
| "learning_rate": 3.083247687564235e-05, | |
| "loss": 0.4563, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12338062924120913, | |
| "grad_norm": 1.4687080383300781, | |
| "learning_rate": 4.110996916752313e-05, | |
| "loss": 0.4263, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15422578655151142, | |
| "grad_norm": 1.836676836013794, | |
| "learning_rate": 5.1387461459403907e-05, | |
| "loss": 0.3994, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1850709438618137, | |
| "grad_norm": 1.2718663215637207, | |
| "learning_rate": 6.16649537512847e-05, | |
| "loss": 0.3665, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.215916101172116, | |
| "grad_norm": 1.6945191621780396, | |
| "learning_rate": 7.194244604316547e-05, | |
| "loss": 0.3577, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.24676125848241826, | |
| "grad_norm": 1.2829898595809937, | |
| "learning_rate": 8.221993833504625e-05, | |
| "loss": 0.347, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27760641579272055, | |
| "grad_norm": 1.01521635055542, | |
| "learning_rate": 9.249743062692704e-05, | |
| "loss": 0.3288, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.30845157310302285, | |
| "grad_norm": 1.522111415863037, | |
| "learning_rate": 0.00010277492291880781, | |
| "loss": 0.3267, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3392967304133251, | |
| "grad_norm": 0.9678927659988403, | |
| "learning_rate": 0.00011305241521068859, | |
| "loss": 0.3198, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3701418877236274, | |
| "grad_norm": 1.2144405841827393, | |
| "learning_rate": 0.0001233299075025694, | |
| "loss": 0.3099, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4009870450339297, | |
| "grad_norm": 1.3122639656066895, | |
| "learning_rate": 0.00013360739979445017, | |
| "loss": 0.2929, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.431832202344232, | |
| "grad_norm": 1.0934101343154907, | |
| "learning_rate": 0.00014388489208633093, | |
| "loss": 0.3003, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4626773596545342, | |
| "grad_norm": 0.7938969731330872, | |
| "learning_rate": 0.00015416238437821172, | |
| "loss": 0.2956, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.4935225169648365, | |
| "grad_norm": 0.6571168303489685, | |
| "learning_rate": 0.0001644398766700925, | |
| "loss": 0.2736, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5243676742751388, | |
| "grad_norm": 1.0073938369750977, | |
| "learning_rate": 0.0001747173689619733, | |
| "loss": 0.2892, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.5552128315854411, | |
| "grad_norm": 0.9874083399772644, | |
| "learning_rate": 0.00018499486125385408, | |
| "loss": 0.2723, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.5860579888957433, | |
| "grad_norm": 1.1770968437194824, | |
| "learning_rate": 0.00019527235354573487, | |
| "loss": 0.2855, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.6169031462060457, | |
| "grad_norm": 1.00326669216156, | |
| "learning_rate": 0.00019997622717095418, | |
| "loss": 0.2587, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6477483035163479, | |
| "grad_norm": 1.0380828380584717, | |
| "learning_rate": 0.0001998067088192682, | |
| "loss": 0.2764, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.6785934608266502, | |
| "grad_norm": 1.430301547050476, | |
| "learning_rate": 0.00019947447034120033, | |
| "loss": 0.2565, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7094386181369525, | |
| "grad_norm": 1.0970648527145386, | |
| "learning_rate": 0.00019898005340261433, | |
| "loss": 0.2685, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.7402837754472548, | |
| "grad_norm": 0.9110261797904968, | |
| "learning_rate": 0.0001983242640774473, | |
| "loss": 0.2489, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.7711289327575571, | |
| "grad_norm": 1.0265332460403442, | |
| "learning_rate": 0.00019750817153352506, | |
| "loss": 0.2425, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.8019740900678594, | |
| "grad_norm": 0.8820884823799133, | |
| "learning_rate": 0.00019653310628944164, | |
| "loss": 0.2402, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.8328192473781616, | |
| "grad_norm": 0.933083713054657, | |
| "learning_rate": 0.00019540065804534467, | |
| "loss": 0.2444, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.863664404688464, | |
| "grad_norm": 0.8229042887687683, | |
| "learning_rate": 0.00019411267309116375, | |
| "loss": 0.2172, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8945095619987662, | |
| "grad_norm": 0.9641085267066956, | |
| "learning_rate": 0.00019267125129650688, | |
| "loss": 0.2501, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.9253547193090684, | |
| "grad_norm": 0.6993410587310791, | |
| "learning_rate": 0.00019107874268713254, | |
| "loss": 0.2246, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9561998766193708, | |
| "grad_norm": 1.0574674606323242, | |
| "learning_rate": 0.00018933774361357917, | |
| "loss": 0.2265, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.987045033929673, | |
| "grad_norm": 1.0701500177383423, | |
| "learning_rate": 0.0001874510925181983, | |
| "loss": 0.2116, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.0178901912399754, | |
| "grad_norm": 0.44411325454711914, | |
| "learning_rate": 0.0001854218653074927, | |
| "loss": 0.1978, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.0487353485502775, | |
| "grad_norm": 0.8408161401748657, | |
| "learning_rate": 0.0001832533703373043, | |
| "loss": 0.1701, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.0795805058605799, | |
| "grad_norm": 0.7417210936546326, | |
| "learning_rate": 0.0001809491430190276, | |
| "loss": 0.1873, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.1104256631708822, | |
| "grad_norm": 0.859341025352478, | |
| "learning_rate": 0.00017851294005564254, | |
| "loss": 0.1717, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.1412708204811843, | |
| "grad_norm": 0.6794934272766113, | |
| "learning_rate": 0.0001759487333169642, | |
| "loss": 0.1732, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.1721159777914867, | |
| "grad_norm": 0.5129622220993042, | |
| "learning_rate": 0.00017326070336409427, | |
| "loss": 0.172, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.202961135101789, | |
| "grad_norm": 0.5867941379547119, | |
| "learning_rate": 0.00017045323263363272, | |
| "loss": 0.1724, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.2338062924120914, | |
| "grad_norm": 0.887195348739624, | |
| "learning_rate": 0.0001675308982927608, | |
| "loss": 0.1655, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 4863, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4223873847328768e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |