{ "best_metric": 0.5693678259849548, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.03663339133620295, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.000732667826724059, "grad_norm": 4.796708583831787, "learning_rate": 5e-05, "loss": 2.8347, "step": 1 }, { "epoch": 0.000732667826724059, "eval_loss": 5.17229700088501, "eval_runtime": 491.1433, "eval_samples_per_second": 18.722, "eval_steps_per_second": 2.341, "step": 1 }, { "epoch": 0.001465335653448118, "grad_norm": 6.125755310058594, "learning_rate": 0.0001, "loss": 3.5887, "step": 2 }, { "epoch": 0.0021980034801721768, "grad_norm": 5.237848281860352, "learning_rate": 9.989294616193017e-05, "loss": 3.2376, "step": 3 }, { "epoch": 0.002930671306896236, "grad_norm": 5.488912105560303, "learning_rate": 9.957224306869053e-05, "loss": 2.4575, "step": 4 }, { "epoch": 0.0036633391336202948, "grad_norm": 3.8870604038238525, "learning_rate": 9.903926402016153e-05, "loss": 1.6627, "step": 5 }, { "epoch": 0.0043960069603443536, "grad_norm": 2.9564926624298096, "learning_rate": 9.829629131445342e-05, "loss": 1.2304, "step": 6 }, { "epoch": 0.005128674787068413, "grad_norm": 3.092305898666382, "learning_rate": 9.73465064747553e-05, "loss": 1.1038, "step": 7 }, { "epoch": 0.005861342613792472, "grad_norm": 2.3101096153259277, "learning_rate": 9.619397662556435e-05, "loss": 0.9461, "step": 8 }, { "epoch": 0.006594010440516531, "grad_norm": 2.5642993450164795, "learning_rate": 9.484363707663442e-05, "loss": 0.9138, "step": 9 }, { "epoch": 0.0073266782672405896, "grad_norm": 2.010706663131714, "learning_rate": 9.330127018922194e-05, "loss": 0.8775, "step": 10 }, { "epoch": 0.008059346093964649, "grad_norm": 2.091142416000366, "learning_rate": 9.157348061512727e-05, "loss": 0.853, "step": 11 }, { "epoch": 0.008792013920688707, "grad_norm": 2.038872480392456, "learning_rate": 8.966766701456177e-05, "loss": 0.924, "step": 12 }, { "epoch": 0.009524681747412767, "grad_norm": 1.9082609415054321, "learning_rate": 8.759199037394887e-05, "loss": 0.8933, "step": 13 }, { "epoch": 0.010257349574136826, "grad_norm": 1.5480622053146362, "learning_rate": 8.535533905932738e-05, "loss": 0.8669, "step": 14 }, { "epoch": 0.010990017400860884, "grad_norm": 1.204441785812378, "learning_rate": 8.296729075500344e-05, "loss": 0.7837, "step": 15 }, { "epoch": 0.011722685227584944, "grad_norm": 1.2647548913955688, "learning_rate": 8.043807145043604e-05, "loss": 0.7536, "step": 16 }, { "epoch": 0.012455353054309002, "grad_norm": 1.1925547122955322, "learning_rate": 7.777851165098012e-05, "loss": 0.641, "step": 17 }, { "epoch": 0.013188020881033062, "grad_norm": 1.10440194606781, "learning_rate": 7.500000000000001e-05, "loss": 0.6021, "step": 18 }, { "epoch": 0.01392068870775712, "grad_norm": 1.087410569190979, "learning_rate": 7.211443451095007e-05, "loss": 0.5846, "step": 19 }, { "epoch": 0.014653356534481179, "grad_norm": 1.1993662118911743, "learning_rate": 6.91341716182545e-05, "loss": 0.6422, "step": 20 }, { "epoch": 0.01538602436120524, "grad_norm": 1.2699971199035645, "learning_rate": 6.607197326515808e-05, "loss": 0.6474, "step": 21 }, { "epoch": 0.016118692187929298, "grad_norm": 1.2045824527740479, "learning_rate": 6.294095225512603e-05, "loss": 0.5928, "step": 22 }, { "epoch": 0.016851360014653358, "grad_norm": 1.435655951499939, "learning_rate": 5.9754516100806423e-05, "loss": 0.6175, "step": 23 }, { "epoch": 0.017584027841377414, "grad_norm": 1.69428551197052, "learning_rate": 5.6526309611002594e-05, "loss": 0.6678, "step": 24 }, { "epoch": 0.018316695668101474, "grad_norm": 2.149271249771118, "learning_rate": 5.327015646150716e-05, "loss": 0.7861, "step": 25 }, { "epoch": 0.018316695668101474, "eval_loss": 0.6588581204414368, "eval_runtime": 491.5573, "eval_samples_per_second": 18.706, "eval_steps_per_second": 2.34, "step": 25 }, { "epoch": 0.019049363494825534, "grad_norm": 1.6137243509292603, "learning_rate": 5e-05, "loss": 0.7756, "step": 26 }, { "epoch": 0.01978203132154959, "grad_norm": 1.26747465133667, "learning_rate": 4.6729843538492847e-05, "loss": 0.6441, "step": 27 }, { "epoch": 0.02051469914827365, "grad_norm": 1.2265703678131104, "learning_rate": 4.347369038899744e-05, "loss": 0.627, "step": 28 }, { "epoch": 0.02124736697499771, "grad_norm": 1.0557516813278198, "learning_rate": 4.0245483899193595e-05, "loss": 0.5974, "step": 29 }, { "epoch": 0.021980034801721768, "grad_norm": 1.0866754055023193, "learning_rate": 3.705904774487396e-05, "loss": 0.6379, "step": 30 }, { "epoch": 0.022712702628445828, "grad_norm": 1.123220443725586, "learning_rate": 3.392802673484193e-05, "loss": 0.5748, "step": 31 }, { "epoch": 0.023445370455169888, "grad_norm": 1.2740416526794434, "learning_rate": 3.086582838174551e-05, "loss": 0.5974, "step": 32 }, { "epoch": 0.024178038281893945, "grad_norm": 1.1661179065704346, "learning_rate": 2.7885565489049946e-05, "loss": 0.4786, "step": 33 }, { "epoch": 0.024910706108618005, "grad_norm": 1.375145673751831, "learning_rate": 2.500000000000001e-05, "loss": 0.6214, "step": 34 }, { "epoch": 0.025643373935342065, "grad_norm": 1.1276419162750244, "learning_rate": 2.2221488349019903e-05, "loss": 0.5566, "step": 35 }, { "epoch": 0.026376041762066125, "grad_norm": 1.2904120683670044, "learning_rate": 1.9561928549563968e-05, "loss": 0.5779, "step": 36 }, { "epoch": 0.02710870958879018, "grad_norm": 1.4637553691864014, "learning_rate": 1.703270924499656e-05, "loss": 0.6633, "step": 37 }, { "epoch": 0.02784137741551424, "grad_norm": 1.1279934644699097, "learning_rate": 1.4644660940672627e-05, "loss": 0.7174, "step": 38 }, { "epoch": 0.0285740452422383, "grad_norm": 0.9128093719482422, "learning_rate": 1.2408009626051137e-05, "loss": 0.6951, "step": 39 }, { "epoch": 0.029306713068962358, "grad_norm": 0.9181010723114014, "learning_rate": 1.0332332985438248e-05, "loss": 0.5927, "step": 40 }, { "epoch": 0.03003938089568642, "grad_norm": 0.8616317510604858, "learning_rate": 8.426519384872733e-06, "loss": 0.5294, "step": 41 }, { "epoch": 0.03077204872241048, "grad_norm": 0.9883503913879395, "learning_rate": 6.698729810778065e-06, "loss": 0.6009, "step": 42 }, { "epoch": 0.03150471654913454, "grad_norm": 0.9856258034706116, "learning_rate": 5.156362923365588e-06, "loss": 0.5573, "step": 43 }, { "epoch": 0.032237384375858595, "grad_norm": 0.9469846487045288, "learning_rate": 3.8060233744356633e-06, "loss": 0.4878, "step": 44 }, { "epoch": 0.03297005220258265, "grad_norm": 0.8723491430282593, "learning_rate": 2.653493525244721e-06, "loss": 0.4456, "step": 45 }, { "epoch": 0.033702720029306715, "grad_norm": 0.9594306349754333, "learning_rate": 1.70370868554659e-06, "loss": 0.5013, "step": 46 }, { "epoch": 0.03443538785603077, "grad_norm": 1.0781900882720947, "learning_rate": 9.607359798384785e-07, "loss": 0.5283, "step": 47 }, { "epoch": 0.03516805568275483, "grad_norm": 1.1100373268127441, "learning_rate": 4.277569313094809e-07, "loss": 0.5124, "step": 48 }, { "epoch": 0.03590072350947889, "grad_norm": 1.2396796941757202, "learning_rate": 1.0705383806982606e-07, "loss": 0.6077, "step": 49 }, { "epoch": 0.03663339133620295, "grad_norm": 1.576565146446228, "learning_rate": 0.0, "loss": 0.7111, "step": 50 }, { "epoch": 0.03663339133620295, "eval_loss": 0.5693678259849548, "eval_runtime": 496.4155, "eval_samples_per_second": 18.523, "eval_steps_per_second": 2.317, "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": 6.631381723512832e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }