{ "best_metric": 1.0611395835876465, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.025039907352342797, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005007981470468559, "grad_norm": 7.2735490798950195, "learning_rate": 5e-05, "loss": 27.6765, "step": 1 }, { "epoch": 0.0005007981470468559, "eval_loss": 1.6915992498397827, "eval_runtime": 3.9192, "eval_samples_per_second": 12.758, "eval_steps_per_second": 3.317, "step": 1 }, { "epoch": 0.0010015962940937118, "grad_norm": 9.645286560058594, "learning_rate": 0.0001, "loss": 28.8861, "step": 2 }, { "epoch": 0.0015023944411405679, "grad_norm": 6.561025619506836, "learning_rate": 9.990365154573717e-05, "loss": 23.5428, "step": 3 }, { "epoch": 0.0020031925881874237, "grad_norm": 6.4700422286987305, "learning_rate": 9.961501876182148e-05, "loss": 23.4867, "step": 4 }, { "epoch": 0.0025039907352342795, "grad_norm": 6.575279712677002, "learning_rate": 9.913533761814537e-05, "loss": 22.8772, "step": 5 }, { "epoch": 0.0030047888822811357, "grad_norm": 5.742631912231445, "learning_rate": 9.846666218300807e-05, "loss": 22.2415, "step": 6 }, { "epoch": 0.0035055870293279915, "grad_norm": 5.252403259277344, "learning_rate": 9.761185582727977e-05, "loss": 21.6715, "step": 7 }, { "epoch": 0.004006385176374847, "grad_norm": 4.608903884887695, "learning_rate": 9.657457896300791e-05, "loss": 20.1559, "step": 8 }, { "epoch": 0.004507183323421703, "grad_norm": 4.294509410858154, "learning_rate": 9.535927336897098e-05, "loss": 22.0346, "step": 9 }, { "epoch": 0.005007981470468559, "grad_norm": 5.621428966522217, "learning_rate": 9.397114317029975e-05, "loss": 21.4893, "step": 10 }, { "epoch": 0.005508779617515415, "grad_norm": 5.655107498168945, "learning_rate": 9.241613255361455e-05, "loss": 18.073, "step": 11 }, { "epoch": 0.0060095777645622715, "grad_norm": 4.809823036193848, "learning_rate": 9.070090031310558e-05, "loss": 16.1442, "step": 12 }, { "epoch": 0.006510375911609127, "grad_norm": 8.046764373779297, "learning_rate": 8.883279133655399e-05, "loss": 21.9141, "step": 13 }, { "epoch": 0.007011174058655983, "grad_norm": 7.144588470458984, "learning_rate": 8.681980515339464e-05, "loss": 22.6744, "step": 14 }, { "epoch": 0.007511972205702839, "grad_norm": 5.577089786529541, "learning_rate": 8.467056167950311e-05, "loss": 19.4013, "step": 15 }, { "epoch": 0.008012770352749695, "grad_norm": 4.5405731201171875, "learning_rate": 8.239426430539243e-05, "loss": 17.4941, "step": 16 }, { "epoch": 0.00851356849979655, "grad_norm": 5.8107147216796875, "learning_rate": 8.000066048588211e-05, "loss": 18.2896, "step": 17 }, { "epoch": 0.009014366646843406, "grad_norm": 4.332961082458496, "learning_rate": 7.75e-05, "loss": 18.1127, "step": 18 }, { "epoch": 0.009515164793890262, "grad_norm": 4.734344959259033, "learning_rate": 7.490299105985507e-05, "loss": 18.5457, "step": 19 }, { "epoch": 0.010015962940937118, "grad_norm": 4.264060020446777, "learning_rate": 7.222075445642904e-05, "loss": 18.2222, "step": 20 }, { "epoch": 0.010516761087983974, "grad_norm": 3.800395965576172, "learning_rate": 6.946477593864228e-05, "loss": 18.5526, "step": 21 }, { "epoch": 0.01101755923503083, "grad_norm": 3.4941272735595703, "learning_rate": 6.664685702961344e-05, "loss": 17.8441, "step": 22 }, { "epoch": 0.011518357382077687, "grad_norm": 3.7239904403686523, "learning_rate": 6.377906449072578e-05, "loss": 18.2648, "step": 23 }, { "epoch": 0.012019155529124543, "grad_norm": 3.749605655670166, "learning_rate": 6.087367864990233e-05, "loss": 17.3797, "step": 24 }, { "epoch": 0.012519953676171399, "grad_norm": 6.037412643432617, "learning_rate": 5.794314081535644e-05, "loss": 18.479, "step": 25 }, { "epoch": 0.012519953676171399, "eval_loss": 1.1073193550109863, "eval_runtime": 3.9929, "eval_samples_per_second": 12.522, "eval_steps_per_second": 3.256, "step": 25 }, { "epoch": 0.013020751823218255, "grad_norm": 6.128429889678955, "learning_rate": 5.500000000000001e-05, "loss": 20.2164, "step": 26 }, { "epoch": 0.01352154997026511, "grad_norm": 7.410825729370117, "learning_rate": 5.205685918464356e-05, "loss": 20.2266, "step": 27 }, { "epoch": 0.014022348117311966, "grad_norm": 4.50378942489624, "learning_rate": 4.912632135009769e-05, "loss": 17.0934, "step": 28 }, { "epoch": 0.014523146264358822, "grad_norm": 4.2456464767456055, "learning_rate": 4.6220935509274235e-05, "loss": 17.7946, "step": 29 }, { "epoch": 0.015023944411405678, "grad_norm": 3.301119327545166, "learning_rate": 4.3353142970386564e-05, "loss": 19.8457, "step": 30 }, { "epoch": 0.015524742558452534, "grad_norm": 3.3931143283843994, "learning_rate": 4.053522406135775e-05, "loss": 17.4589, "step": 31 }, { "epoch": 0.01602554070549939, "grad_norm": 3.908799409866333, "learning_rate": 3.777924554357096e-05, "loss": 17.9799, "step": 32 }, { "epoch": 0.016526338852546247, "grad_norm": 4.308777809143066, "learning_rate": 3.509700894014496e-05, "loss": 18.2389, "step": 33 }, { "epoch": 0.0170271369995931, "grad_norm": 5.028868198394775, "learning_rate": 3.250000000000001e-05, "loss": 18.8644, "step": 34 }, { "epoch": 0.01752793514663996, "grad_norm": 5.518270492553711, "learning_rate": 2.9999339514117912e-05, "loss": 17.9908, "step": 35 }, { "epoch": 0.018028733293686813, "grad_norm": 4.996335506439209, "learning_rate": 2.760573569460757e-05, "loss": 15.7478, "step": 36 }, { "epoch": 0.01852953144073367, "grad_norm": 6.510356426239014, "learning_rate": 2.53294383204969e-05, "loss": 16.2257, "step": 37 }, { "epoch": 0.019030329587780524, "grad_norm": 5.005591869354248, "learning_rate": 2.3180194846605367e-05, "loss": 21.489, "step": 38 }, { "epoch": 0.019531127734827382, "grad_norm": 9.856449127197266, "learning_rate": 2.1167208663446025e-05, "loss": 21.2883, "step": 39 }, { "epoch": 0.020031925881874236, "grad_norm": 3.623931646347046, "learning_rate": 1.9299099686894423e-05, "loss": 17.6629, "step": 40 }, { "epoch": 0.020532724028921093, "grad_norm": 3.4106252193450928, "learning_rate": 1.758386744638546e-05, "loss": 15.4309, "step": 41 }, { "epoch": 0.021033522175967947, "grad_norm": 4.296844005584717, "learning_rate": 1.602885682970026e-05, "loss": 17.6033, "step": 42 }, { "epoch": 0.021534320323014805, "grad_norm": 4.559662342071533, "learning_rate": 1.464072663102903e-05, "loss": 16.8699, "step": 43 }, { "epoch": 0.02203511847006166, "grad_norm": 4.427708625793457, "learning_rate": 1.3425421036992098e-05, "loss": 17.4621, "step": 44 }, { "epoch": 0.022535916617108517, "grad_norm": 3.9432215690612793, "learning_rate": 1.2388144172720251e-05, "loss": 17.8905, "step": 45 }, { "epoch": 0.023036714764155374, "grad_norm": 3.188026189804077, "learning_rate": 1.1533337816991932e-05, "loss": 17.3133, "step": 46 }, { "epoch": 0.02353751291120223, "grad_norm": 3.24480938911438, "learning_rate": 1.0864662381854632e-05, "loss": 16.5617, "step": 47 }, { "epoch": 0.024038311058249086, "grad_norm": 3.795017719268799, "learning_rate": 1.0384981238178534e-05, "loss": 16.9529, "step": 48 }, { "epoch": 0.02453910920529594, "grad_norm": 3.4241626262664795, "learning_rate": 1.0096348454262845e-05, "loss": 14.9861, "step": 49 }, { "epoch": 0.025039907352342797, "grad_norm": 5.961770057678223, "learning_rate": 1e-05, "loss": 17.1319, "step": 50 }, { "epoch": 0.025039907352342797, "eval_loss": 1.0611395835876465, "eval_runtime": 3.8308, "eval_samples_per_second": 13.052, "eval_steps_per_second": 3.394, "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": 5.9050464574754e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }