| { | |
| "best_metric": 10.367506980895996, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06281900274833137, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012563800549666275, | |
| "grad_norm": 0.061948925256729126, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3793, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012563800549666275, | |
| "eval_loss": 10.377693176269531, | |
| "eval_runtime": 0.0904, | |
| "eval_samples_per_second": 552.8, | |
| "eval_steps_per_second": 143.728, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002512760109933255, | |
| "grad_norm": 0.06327062845230103, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3791, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003769140164899882, | |
| "grad_norm": 0.054912880063056946, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3777, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00502552021986651, | |
| "grad_norm": 0.06808093935251236, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3793, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006281900274833137, | |
| "grad_norm": 0.07998302578926086, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3785, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007538280329799764, | |
| "grad_norm": 0.08304433524608612, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008794660384766392, | |
| "grad_norm": 0.08049525320529938, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3779, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01005104043973302, | |
| "grad_norm": 0.07767872512340546, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3801, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011307420494699646, | |
| "grad_norm": 0.08831847459077835, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3782, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012563800549666274, | |
| "grad_norm": 0.10801270604133606, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.381, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0138201806046329, | |
| "grad_norm": 0.1122453585267067, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3822, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015076560659599529, | |
| "grad_norm": 0.15279272198677063, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3747, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016332940714566157, | |
| "grad_norm": 0.08759787678718567, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3752, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017589320769532783, | |
| "grad_norm": 0.06836814433336258, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3765, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01884570082449941, | |
| "grad_norm": 0.06976384669542313, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3743, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02010208087946604, | |
| "grad_norm": 0.0702279806137085, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3759, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021358460934432666, | |
| "grad_norm": 0.06995182484388351, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3728, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.022614840989399292, | |
| "grad_norm": 0.08358803391456604, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3729, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.023871221044365922, | |
| "grad_norm": 0.08740617334842682, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.376, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02512760109933255, | |
| "grad_norm": 0.0925925076007843, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3768, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026383981154299175, | |
| "grad_norm": 0.1102653294801712, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.377, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0276403612092658, | |
| "grad_norm": 0.11750924587249756, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3732, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02889674126423243, | |
| "grad_norm": 0.14664867520332336, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3714, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030153121319199058, | |
| "grad_norm": 0.1726154237985611, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3727, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031409501374165684, | |
| "grad_norm": 0.20804773271083832, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3698, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.031409501374165684, | |
| "eval_loss": 10.371356010437012, | |
| "eval_runtime": 0.1169, | |
| "eval_samples_per_second": 427.697, | |
| "eval_steps_per_second": 111.201, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.032665881429132314, | |
| "grad_norm": 0.09042679518461227, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3756, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03392226148409894, | |
| "grad_norm": 0.08610530197620392, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.373, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03517864153906557, | |
| "grad_norm": 0.08801662921905518, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3724, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.036435021594032196, | |
| "grad_norm": 0.09608513861894608, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3699, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03769140164899882, | |
| "grad_norm": 0.09346794337034225, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3698, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03894778170396545, | |
| "grad_norm": 0.1273888796567917, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.3702, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04020416175893208, | |
| "grad_norm": 0.11089735478162766, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3707, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0414605418138987, | |
| "grad_norm": 0.13149495422840118, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3703, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04271692186886533, | |
| "grad_norm": 0.1491594761610031, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.3697, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04397330192383196, | |
| "grad_norm": 0.17393919825553894, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3708, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.045229681978798585, | |
| "grad_norm": 0.18291912972927094, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.3714, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.046486062033765214, | |
| "grad_norm": 0.18662983179092407, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3698, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.047742442088731844, | |
| "grad_norm": 0.11758657544851303, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3715, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04899882214369847, | |
| "grad_norm": 0.08886243402957916, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3718, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0502552021986651, | |
| "grad_norm": 0.09938018769025803, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3703, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05151158225363173, | |
| "grad_norm": 0.12390407174825668, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.3713, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05276796230859835, | |
| "grad_norm": 0.09068513661623001, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.3667, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05402434236356498, | |
| "grad_norm": 0.1155741810798645, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3689, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0552807224185316, | |
| "grad_norm": 0.11526913195848465, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3725, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05653710247349823, | |
| "grad_norm": 0.12869693338871002, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3692, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05779348252846486, | |
| "grad_norm": 0.14980974793434143, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3697, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.059049862583431485, | |
| "grad_norm": 0.155381977558136, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3677, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.060306242638398115, | |
| "grad_norm": 0.21512186527252197, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.3681, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.061562622693364745, | |
| "grad_norm": 0.23681750893592834, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.37, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06281900274833137, | |
| "grad_norm": 0.24694152176380157, | |
| "learning_rate": 1e-05, | |
| "loss": 10.362, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06281900274833137, | |
| "eval_loss": 10.367506980895996, | |
| "eval_runtime": 0.1, | |
| "eval_samples_per_second": 500.099, | |
| "eval_steps_per_second": 130.026, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 42768059596800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |