| { | |
| "best_metric": 0.9232883453369141, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5449591280653951, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010899182561307902, | |
| "grad_norm": 0.44811156392097473, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2002, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010899182561307902, | |
| "eval_loss": 4.223792552947998, | |
| "eval_runtime": 3.8318, | |
| "eval_samples_per_second": 13.049, | |
| "eval_steps_per_second": 3.393, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021798365122615803, | |
| "grad_norm": 1.021632194519043, | |
| "learning_rate": 0.0001, | |
| "loss": 2.148, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0326975476839237, | |
| "grad_norm": 0.9980731010437012, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.2893, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.043596730245231606, | |
| "grad_norm": 1.0220195055007935, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.1774, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05449591280653951, | |
| "grad_norm": 2.2285709381103516, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.0259, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0653950953678474, | |
| "grad_norm": 2.1914050579071045, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.9019, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07629427792915532, | |
| "grad_norm": 2.1680335998535156, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.5856, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08719346049046321, | |
| "grad_norm": 1.131940484046936, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.7922, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09809264305177112, | |
| "grad_norm": 2.424546480178833, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.9594, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10899182561307902, | |
| "grad_norm": 2.9618523120880127, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.1351, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11989100817438691, | |
| "grad_norm": 3.0317416191101074, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.3154, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1307901907356948, | |
| "grad_norm": 27.891477584838867, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.0553, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14168937329700274, | |
| "grad_norm": 0.6846345067024231, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.916, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15258855585831063, | |
| "grad_norm": 1.2937723398208618, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.2441, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16348773841961853, | |
| "grad_norm": 1.1620546579360962, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.951, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17438692098092642, | |
| "grad_norm": 0.7650942802429199, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.8049, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18528610354223432, | |
| "grad_norm": 0.6716667413711548, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.7987, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19618528610354224, | |
| "grad_norm": 0.6872152090072632, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.7885, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20708446866485014, | |
| "grad_norm": 0.943435788154602, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.4622, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21798365122615804, | |
| "grad_norm": 0.8941364288330078, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.3777, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22888283378746593, | |
| "grad_norm": 0.8765055537223816, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.4962, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23978201634877383, | |
| "grad_norm": 1.6470309495925903, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.3022, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2506811989100817, | |
| "grad_norm": 2.299093723297119, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2873, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2615803814713896, | |
| "grad_norm": 2.423143148422241, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.9864, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2724795640326976, | |
| "grad_norm": 15.225419998168945, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.782, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2724795640326976, | |
| "eval_loss": 1.0677134990692139, | |
| "eval_runtime": 3.4902, | |
| "eval_samples_per_second": 14.326, | |
| "eval_steps_per_second": 3.725, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28337874659400547, | |
| "grad_norm": 0.5296501517295837, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.0336, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.29427792915531337, | |
| "grad_norm": 0.7905092239379883, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.9395, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.30517711171662126, | |
| "grad_norm": 0.870593249797821, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.8031, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31607629427792916, | |
| "grad_norm": 1.0186721086502075, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.6599, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32697547683923706, | |
| "grad_norm": 0.8736789226531982, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.6304, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33787465940054495, | |
| "grad_norm": 0.8303609490394592, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.6325, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.34877384196185285, | |
| "grad_norm": 1.5313987731933594, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.1085, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.35967302452316074, | |
| "grad_norm": 2.020516872406006, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.2162, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.37057220708446864, | |
| "grad_norm": 2.331284761428833, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.2472, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3814713896457766, | |
| "grad_norm": 3.2050352096557617, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.6133, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3923705722070845, | |
| "grad_norm": 1.7887552976608276, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.2783, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4032697547683924, | |
| "grad_norm": 4.835048675537109, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.1539, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4141689373297003, | |
| "grad_norm": 0.3986741602420807, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.9201, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4250681198910082, | |
| "grad_norm": 0.4235083758831024, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.1297, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4359673024523161, | |
| "grad_norm": 0.4803415536880493, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.8341, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44686648501362397, | |
| "grad_norm": 0.5387624502182007, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.6072, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.45776566757493187, | |
| "grad_norm": 0.5342338681221008, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.6247, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.46866485013623976, | |
| "grad_norm": 0.5330402851104736, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.6158, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.47956403269754766, | |
| "grad_norm": 0.6515064239501953, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2648, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4904632152588556, | |
| "grad_norm": 0.6812955141067505, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.0259, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5013623978201635, | |
| "grad_norm": 0.7213007211685181, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.3959, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5122615803814714, | |
| "grad_norm": 1.5422643423080444, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.7053, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5231607629427792, | |
| "grad_norm": 1.1095118522644043, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.5057, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5340599455040872, | |
| "grad_norm": 1.8260787725448608, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.7838, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5449591280653951, | |
| "grad_norm": 6.559061527252197, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2138, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5449591280653951, | |
| "eval_loss": 0.9232883453369141, | |
| "eval_runtime": 3.4923, | |
| "eval_samples_per_second": 14.317, | |
| "eval_steps_per_second": 3.723, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |