| { | |
| "best_metric": 1.8655270338058472, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008405392059005852, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016810784118011704, | |
| "grad_norm": 0.17082159221172333, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016810784118011704, | |
| "eval_loss": 2.3799219131469727, | |
| "eval_runtime": 2.3228, | |
| "eval_samples_per_second": 21.525, | |
| "eval_steps_per_second": 5.597, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003362156823602341, | |
| "grad_norm": 0.19622649252414703, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5198, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005043235235403511, | |
| "grad_norm": 0.19902303814888, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.5994, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006724313647204682, | |
| "grad_norm": 0.16339901089668274, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.5168, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008405392059005853, | |
| "grad_norm": 0.22906166315078735, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.3187, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010086470470807023, | |
| "grad_norm": 0.29557499289512634, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.3431, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011767548882608194, | |
| "grad_norm": 0.3163169324398041, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.3465, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013448627294409363, | |
| "grad_norm": 0.3222096264362335, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.3375, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015129705706210534, | |
| "grad_norm": 0.481373131275177, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.0273, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016810784118011705, | |
| "grad_norm": 0.5350996851921082, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.0263, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018491862529812875, | |
| "grad_norm": 0.9788709282875061, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.8296, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0020172940941614046, | |
| "grad_norm": 2.732243061065674, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.7063, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021854019353415217, | |
| "grad_norm": 0.23717454075813293, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.1399, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002353509776521639, | |
| "grad_norm": 0.2221975326538086, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.4619, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0025216176177017555, | |
| "grad_norm": 0.24104826152324677, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.49, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026897254588818726, | |
| "grad_norm": 0.2259531468153, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.5433, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0028578333000619897, | |
| "grad_norm": 0.22414153814315796, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.3368, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003025941141242107, | |
| "grad_norm": 0.25792089104652405, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.3838, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003194048982422224, | |
| "grad_norm": 0.26396581530570984, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.2951, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003362156823602341, | |
| "grad_norm": 0.30141481757164, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.2208, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003530264664782458, | |
| "grad_norm": 0.3778812885284424, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.0571, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003698372505962575, | |
| "grad_norm": 0.4476301670074463, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.8565, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003866480347142692, | |
| "grad_norm": 0.7593006491661072, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.7111, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004034588188322809, | |
| "grad_norm": 0.8695580959320068, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.5087, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004202696029502926, | |
| "grad_norm": 1.982232689857483, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.3368, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004202696029502926, | |
| "eval_loss": 1.9113479852676392, | |
| "eval_runtime": 1.946, | |
| "eval_samples_per_second": 25.694, | |
| "eval_steps_per_second": 6.681, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004370803870683043, | |
| "grad_norm": 0.14445090293884277, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.2152, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00453891171186316, | |
| "grad_norm": 0.16464228928089142, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.4849, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004707019553043278, | |
| "grad_norm": 0.16222713887691498, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.55, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004875127394223394, | |
| "grad_norm": 0.17735609412193298, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.4982, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005043235235403511, | |
| "grad_norm": 0.19524605572223663, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.2699, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0052113430765836286, | |
| "grad_norm": 0.23801714181900024, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.2262, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005379450917763745, | |
| "grad_norm": 0.2888990640640259, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.2045, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005547558758943863, | |
| "grad_norm": 0.3643498420715332, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.1918, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0057156666001239795, | |
| "grad_norm": 0.541460394859314, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.8194, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005883774441304096, | |
| "grad_norm": 0.5131947994232178, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.8698, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006051882282484214, | |
| "grad_norm": 0.539517343044281, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.7306, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00621999012366433, | |
| "grad_norm": 1.157737135887146, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.1995, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006388097964844448, | |
| "grad_norm": 0.17678390443325043, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.1394, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006556205806024565, | |
| "grad_norm": 0.15295378863811493, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.4535, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006724313647204682, | |
| "grad_norm": 0.15033498406410217, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.5573, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006892421488384799, | |
| "grad_norm": 0.15413157641887665, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.5748, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007060529329564916, | |
| "grad_norm": 0.1657361090183258, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.4065, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007228637170745033, | |
| "grad_norm": 0.18961718678474426, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.3127, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.00739674501192515, | |
| "grad_norm": 0.2206818163394928, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.2371, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007564852853105267, | |
| "grad_norm": 0.2731553912162781, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.2691, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007732960694285384, | |
| "grad_norm": 0.3540036976337433, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.8958, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0079010685354655, | |
| "grad_norm": 0.37952375411987305, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.7871, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008069176376645618, | |
| "grad_norm": 0.5129942893981934, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.839, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008237284217825736, | |
| "grad_norm": 0.6360666751861572, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.2121, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008405392059005852, | |
| "grad_norm": 0.9608060121536255, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0535, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008405392059005852, | |
| "eval_loss": 1.8655270338058472, | |
| "eval_runtime": 1.9442, | |
| "eval_samples_per_second": 25.717, | |
| "eval_steps_per_second": 6.687, | |
| "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": 2.2299489528184832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |