{ "best_metric": 0.7001811861991882, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.10710938545990092, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0021421877091980183, "grad_norm": 50.62263107299805, "learning_rate": 5e-05, "loss": 135.4249, "step": 1 }, { "epoch": 0.0021421877091980183, "eval_loss": 3.7290472984313965, "eval_runtime": 1.894, "eval_samples_per_second": 26.399, "eval_steps_per_second": 6.864, "step": 1 }, { "epoch": 0.0042843754183960366, "grad_norm": 51.79439926147461, "learning_rate": 0.0001, "loss": 135.4853, "step": 2 }, { "epoch": 0.006426563127594056, "grad_norm": 41.13816452026367, "learning_rate": 9.990365154573717e-05, "loss": 115.4843, "step": 3 }, { "epoch": 0.008568750836792073, "grad_norm": 47.22391891479492, "learning_rate": 9.961501876182148e-05, "loss": 107.7687, "step": 4 }, { "epoch": 0.010710938545990093, "grad_norm": 53.1937255859375, "learning_rate": 9.913533761814537e-05, "loss": 99.0971, "step": 5 }, { "epoch": 0.012853126255188111, "grad_norm": 60.40630340576172, "learning_rate": 9.846666218300807e-05, "loss": 84.7703, "step": 6 }, { "epoch": 0.01499531396438613, "grad_norm": 63.6907958984375, "learning_rate": 9.761185582727977e-05, "loss": 71.1636, "step": 7 }, { "epoch": 0.017137501673584146, "grad_norm": 50.863460540771484, "learning_rate": 9.657457896300791e-05, "loss": 60.1154, "step": 8 }, { "epoch": 0.019279689382782166, "grad_norm": 44.446754455566406, "learning_rate": 9.535927336897098e-05, "loss": 51.6302, "step": 9 }, { "epoch": 0.021421877091980186, "grad_norm": 38.45900344848633, "learning_rate": 9.397114317029975e-05, "loss": 45.8112, "step": 10 }, { "epoch": 0.023564064801178203, "grad_norm": 55.98357391357422, "learning_rate": 9.241613255361455e-05, "loss": 42.1688, "step": 11 }, { "epoch": 0.025706252510376223, "grad_norm": 62.22966384887695, "learning_rate": 9.070090031310558e-05, "loss": 40.1158, "step": 12 }, { "epoch": 0.02784844021957424, "grad_norm": 43.237266540527344, "learning_rate": 8.883279133655399e-05, "loss": 49.6329, "step": 13 }, { "epoch": 0.02999062792877226, "grad_norm": 56.661930084228516, "learning_rate": 8.681980515339464e-05, "loss": 54.1158, "step": 14 }, { "epoch": 0.032132815637970276, "grad_norm": 36.406776428222656, "learning_rate": 8.467056167950311e-05, "loss": 39.4958, "step": 15 }, { "epoch": 0.03427500334716829, "grad_norm": 25.86240005493164, "learning_rate": 8.239426430539243e-05, "loss": 28.7934, "step": 16 }, { "epoch": 0.036417191056366316, "grad_norm": 20.257965087890625, "learning_rate": 8.000066048588211e-05, "loss": 26.7077, "step": 17 }, { "epoch": 0.03855937876556433, "grad_norm": 16.05629539489746, "learning_rate": 7.75e-05, "loss": 24.8365, "step": 18 }, { "epoch": 0.04070156647476235, "grad_norm": 10.645811080932617, "learning_rate": 7.490299105985507e-05, "loss": 23.427, "step": 19 }, { "epoch": 0.04284375418396037, "grad_norm": 8.209049224853516, "learning_rate": 7.222075445642904e-05, "loss": 22.857, "step": 20 }, { "epoch": 0.04498594189315839, "grad_norm": 7.825160026550293, "learning_rate": 6.946477593864228e-05, "loss": 22.7208, "step": 21 }, { "epoch": 0.047128129602356406, "grad_norm": 3.304943323135376, "learning_rate": 6.664685702961344e-05, "loss": 22.5555, "step": 22 }, { "epoch": 0.04927031731155442, "grad_norm": 3.214045286178589, "learning_rate": 6.377906449072578e-05, "loss": 22.4719, "step": 23 }, { "epoch": 0.051412505020752446, "grad_norm": 3.0567023754119873, "learning_rate": 6.087367864990233e-05, "loss": 22.5119, "step": 24 }, { "epoch": 0.05355469272995046, "grad_norm": 15.677796363830566, "learning_rate": 5.794314081535644e-05, "loss": 23.024, "step": 25 }, { "epoch": 0.05355469272995046, "eval_loss": 0.7074735760688782, "eval_runtime": 1.8945, "eval_samples_per_second": 26.393, "eval_steps_per_second": 6.862, "step": 25 }, { "epoch": 0.05569688043914848, "grad_norm": 7.93866491317749, "learning_rate": 5.500000000000001e-05, "loss": 22.9822, "step": 26 }, { "epoch": 0.0578390681483465, "grad_norm": 3.1443004608154297, "learning_rate": 5.205685918464356e-05, "loss": 22.786, "step": 27 }, { "epoch": 0.05998125585754452, "grad_norm": 2.8703548908233643, "learning_rate": 4.912632135009769e-05, "loss": 22.4311, "step": 28 }, { "epoch": 0.062123443566742535, "grad_norm": 2.1649084091186523, "learning_rate": 4.6220935509274235e-05, "loss": 22.4676, "step": 29 }, { "epoch": 0.06426563127594055, "grad_norm": 1.565459966659546, "learning_rate": 4.3353142970386564e-05, "loss": 22.4245, "step": 30 }, { "epoch": 0.06640781898513858, "grad_norm": 1.9081851243972778, "learning_rate": 4.053522406135775e-05, "loss": 22.479, "step": 31 }, { "epoch": 0.06855000669433658, "grad_norm": 1.3694819211959839, "learning_rate": 3.777924554357096e-05, "loss": 22.4532, "step": 32 }, { "epoch": 0.07069219440353461, "grad_norm": 1.3111183643341064, "learning_rate": 3.509700894014496e-05, "loss": 22.4501, "step": 33 }, { "epoch": 0.07283438211273263, "grad_norm": 1.5006563663482666, "learning_rate": 3.250000000000001e-05, "loss": 22.4873, "step": 34 }, { "epoch": 0.07497656982193064, "grad_norm": 5.990767955780029, "learning_rate": 2.9999339514117912e-05, "loss": 22.5241, "step": 35 }, { "epoch": 0.07711875753112866, "grad_norm": 1.6189005374908447, "learning_rate": 2.760573569460757e-05, "loss": 22.4759, "step": 36 }, { "epoch": 0.07926094524032669, "grad_norm": 1.4039047956466675, "learning_rate": 2.53294383204969e-05, "loss": 22.445, "step": 37 }, { "epoch": 0.0814031329495247, "grad_norm": 1.4595952033996582, "learning_rate": 2.3180194846605367e-05, "loss": 22.4729, "step": 38 }, { "epoch": 0.08354532065872272, "grad_norm": 4.050112247467041, "learning_rate": 2.1167208663446025e-05, "loss": 22.478, "step": 39 }, { "epoch": 0.08568750836792074, "grad_norm": 3.0547168254852295, "learning_rate": 1.9299099686894423e-05, "loss": 22.411, "step": 40 }, { "epoch": 0.08782969607711875, "grad_norm": 1.3965966701507568, "learning_rate": 1.758386744638546e-05, "loss": 22.4308, "step": 41 }, { "epoch": 0.08997188378631678, "grad_norm": 1.4640690088272095, "learning_rate": 1.602885682970026e-05, "loss": 22.4479, "step": 42 }, { "epoch": 0.09211407149551479, "grad_norm": 2.038416624069214, "learning_rate": 1.464072663102903e-05, "loss": 22.442, "step": 43 }, { "epoch": 0.09425625920471281, "grad_norm": 1.304911732673645, "learning_rate": 1.3425421036992098e-05, "loss": 22.4374, "step": 44 }, { "epoch": 0.09639844691391083, "grad_norm": 1.4404685497283936, "learning_rate": 1.2388144172720251e-05, "loss": 22.4142, "step": 45 }, { "epoch": 0.09854063462310884, "grad_norm": 1.2715855836868286, "learning_rate": 1.1533337816991932e-05, "loss": 22.3841, "step": 46 }, { "epoch": 0.10068282233230687, "grad_norm": 0.9410794973373413, "learning_rate": 1.0864662381854632e-05, "loss": 22.4332, "step": 47 }, { "epoch": 0.10282501004150489, "grad_norm": 1.003109335899353, "learning_rate": 1.0384981238178534e-05, "loss": 22.4137, "step": 48 }, { "epoch": 0.1049671977507029, "grad_norm": 1.374916911125183, "learning_rate": 1.0096348454262845e-05, "loss": 22.4539, "step": 49 }, { "epoch": 0.10710938545990092, "grad_norm": 0.7090279459953308, "learning_rate": 1e-05, "loss": 22.4465, "step": 50 }, { "epoch": 0.10710938545990092, "eval_loss": 0.7001811861991882, "eval_runtime": 1.8911, "eval_samples_per_second": 26.44, "eval_steps_per_second": 6.874, "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": 6.059534154779853e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }