| { | |
| "best_metric": 1.835883617401123, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.13593882752761258, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027187765505522514, | |
| "grad_norm": 1.8446872234344482, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027187765505522514, | |
| "eval_loss": 3.4761812686920166, | |
| "eval_runtime": 3.86, | |
| "eval_samples_per_second": 12.953, | |
| "eval_steps_per_second": 3.368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005437553101104503, | |
| "grad_norm": 1.8384300470352173, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1166, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008156329651656755, | |
| "grad_norm": 1.742788553237915, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.1483, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010875106202209005, | |
| "grad_norm": 1.6164594888687134, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.7983, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013593882752761258, | |
| "grad_norm": 1.7915750741958618, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.5768, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01631265930331351, | |
| "grad_norm": 1.8303508758544922, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.3811, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019031435853865762, | |
| "grad_norm": 1.5399417877197266, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.3666, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02175021240441801, | |
| "grad_norm": 1.2493640184402466, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.2269, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024468988954970263, | |
| "grad_norm": 1.1250720024108887, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.2005, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027187765505522515, | |
| "grad_norm": 1.0368432998657227, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.1366, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029906542056074768, | |
| "grad_norm": 0.9859645366668701, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.9241, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03262531860662702, | |
| "grad_norm": 0.9766353368759155, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.9443, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03534409515717927, | |
| "grad_norm": 0.8744819760322571, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.0566, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.038062871707731524, | |
| "grad_norm": 0.8641797304153442, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.115, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04078164825828377, | |
| "grad_norm": 0.7743111252784729, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.1498, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04350042480883602, | |
| "grad_norm": 0.8845915198326111, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.15, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04621920135938828, | |
| "grad_norm": 0.783896267414093, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.9129, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.048937977909940526, | |
| "grad_norm": 0.7092758417129517, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.9772, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.051656754460492775, | |
| "grad_norm": 0.7224475741386414, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.0502, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05437553101104503, | |
| "grad_norm": 0.7935304641723633, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.0447, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05709430756159728, | |
| "grad_norm": 0.7622972726821899, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.9269, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.059813084112149535, | |
| "grad_norm": 0.731041669845581, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.9865, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06253186066270179, | |
| "grad_norm": 0.7223778963088989, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.8974, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06525063721325404, | |
| "grad_norm": 0.7909101247787476, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.8845, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06796941376380629, | |
| "grad_norm": 0.876282274723053, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.7724, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06796941376380629, | |
| "eval_loss": 1.8876161575317383, | |
| "eval_runtime": 3.5153, | |
| "eval_samples_per_second": 14.224, | |
| "eval_steps_per_second": 3.698, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07068819031435854, | |
| "grad_norm": 0.7148436903953552, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.1067, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07340696686491079, | |
| "grad_norm": 0.6958780288696289, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.0677, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07612574341546305, | |
| "grad_norm": 0.6679629683494568, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.0391, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0788445199660153, | |
| "grad_norm": 0.6717768907546997, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.9869, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08156329651656755, | |
| "grad_norm": 0.6259593963623047, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.866, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0842820730671198, | |
| "grad_norm": 0.7161216735839844, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.9687, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08700084961767204, | |
| "grad_norm": 0.7441960573196411, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.9273, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08971962616822429, | |
| "grad_norm": 0.7459737658500671, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.9958, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09243840271877656, | |
| "grad_norm": 0.6967633366584778, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.8823, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0951571792693288, | |
| "grad_norm": 0.669630765914917, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.8409, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09787595581988105, | |
| "grad_norm": 0.7518098950386047, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.7421, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1005947323704333, | |
| "grad_norm": 0.7188749313354492, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.7415, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10331350892098555, | |
| "grad_norm": 0.9793473482131958, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.9251, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10603228547153781, | |
| "grad_norm": 0.6875200867652893, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.9748, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10875106202209006, | |
| "grad_norm": 0.6666844487190247, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.0227, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11146983857264231, | |
| "grad_norm": 0.6823920607566833, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.9829, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11418861512319456, | |
| "grad_norm": 0.6978684067726135, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.9509, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11690739167374681, | |
| "grad_norm": 0.6857638955116272, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.9204, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11962616822429907, | |
| "grad_norm": 0.7402970194816589, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.9686, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12234494477485132, | |
| "grad_norm": 0.6844517588615417, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.8972, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12506372132540358, | |
| "grad_norm": 0.7217066884040833, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.9522, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12778249787595583, | |
| "grad_norm": 0.6970483064651489, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.8359, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.13050127442650808, | |
| "grad_norm": 0.7298968434333801, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.8112, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.13322005097706033, | |
| "grad_norm": 0.7759461402893066, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.8007, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13593882752761258, | |
| "grad_norm": 0.8110302090644836, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6085, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13593882752761258, | |
| "eval_loss": 1.835883617401123, | |
| "eval_runtime": 3.5145, | |
| "eval_samples_per_second": 14.227, | |
| "eval_steps_per_second": 3.699, | |
| "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": 5.979273768059535e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |