{ "best_metric": 2.11165714263916, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.04958472790380563, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0009916945580761127, "grad_norm": 1.8227845430374146, "learning_rate": 5e-05, "loss": 2.9259, "step": 1 }, { "epoch": 0.0009916945580761127, "eval_loss": 2.9540276527404785, "eval_runtime": 1.1246, "eval_samples_per_second": 44.46, "eval_steps_per_second": 11.56, "step": 1 }, { "epoch": 0.0019833891161522253, "grad_norm": 1.9859800338745117, "learning_rate": 0.0001, "loss": 2.8428, "step": 2 }, { "epoch": 0.0029750836742283376, "grad_norm": 1.788472294807434, "learning_rate": 9.990365154573717e-05, "loss": 2.7766, "step": 3 }, { "epoch": 0.003966778232304451, "grad_norm": 1.7515558004379272, "learning_rate": 9.961501876182148e-05, "loss": 2.5321, "step": 4 }, { "epoch": 0.0049584727903805624, "grad_norm": 1.6862818002700806, "learning_rate": 9.913533761814537e-05, "loss": 2.405, "step": 5 }, { "epoch": 0.005950167348456675, "grad_norm": 1.08989417552948, "learning_rate": 9.846666218300807e-05, "loss": 2.3068, "step": 6 }, { "epoch": 0.006941861906532788, "grad_norm": 1.0072200298309326, "learning_rate": 9.761185582727977e-05, "loss": 2.2333, "step": 7 }, { "epoch": 0.007933556464608901, "grad_norm": 0.9319274425506592, "learning_rate": 9.657457896300791e-05, "loss": 2.1966, "step": 8 }, { "epoch": 0.008925251022685012, "grad_norm": 0.9776121377944946, "learning_rate": 9.535927336897098e-05, "loss": 2.1115, "step": 9 }, { "epoch": 0.009916945580761125, "grad_norm": 1.1010252237319946, "learning_rate": 9.397114317029975e-05, "loss": 2.3014, "step": 10 }, { "epoch": 0.010908640138837238, "grad_norm": 0.9887837767601013, "learning_rate": 9.241613255361455e-05, "loss": 2.1886, "step": 11 }, { "epoch": 0.01190033469691335, "grad_norm": 1.0444656610488892, "learning_rate": 9.070090031310558e-05, "loss": 2.172, "step": 12 }, { "epoch": 0.012892029254989463, "grad_norm": 0.9816225171089172, "learning_rate": 8.883279133655399e-05, "loss": 2.2176, "step": 13 }, { "epoch": 0.013883723813065576, "grad_norm": 0.8053462505340576, "learning_rate": 8.681980515339464e-05, "loss": 2.1568, "step": 14 }, { "epoch": 0.014875418371141688, "grad_norm": 0.7338224053382874, "learning_rate": 8.467056167950311e-05, "loss": 2.1749, "step": 15 }, { "epoch": 0.015867112929217803, "grad_norm": 0.7205262184143066, "learning_rate": 8.239426430539243e-05, "loss": 2.2502, "step": 16 }, { "epoch": 0.016858807487293914, "grad_norm": 0.7129595279693604, "learning_rate": 8.000066048588211e-05, "loss": 2.0921, "step": 17 }, { "epoch": 0.017850502045370024, "grad_norm": 0.6924590468406677, "learning_rate": 7.75e-05, "loss": 2.1471, "step": 18 }, { "epoch": 0.01884219660344614, "grad_norm": 0.6652086973190308, "learning_rate": 7.490299105985507e-05, "loss": 2.0456, "step": 19 }, { "epoch": 0.01983389116152225, "grad_norm": 0.6703733205795288, "learning_rate": 7.222075445642904e-05, "loss": 2.1318, "step": 20 }, { "epoch": 0.020825585719598364, "grad_norm": 0.6245272159576416, "learning_rate": 6.946477593864228e-05, "loss": 2.1297, "step": 21 }, { "epoch": 0.021817280277674475, "grad_norm": 0.653343915939331, "learning_rate": 6.664685702961344e-05, "loss": 2.1109, "step": 22 }, { "epoch": 0.02280897483575059, "grad_norm": 0.6606502532958984, "learning_rate": 6.377906449072578e-05, "loss": 2.1653, "step": 23 }, { "epoch": 0.0238006693938267, "grad_norm": 0.6672307848930359, "learning_rate": 6.087367864990233e-05, "loss": 2.1121, "step": 24 }, { "epoch": 0.024792363951902815, "grad_norm": 0.6210116744041443, "learning_rate": 5.794314081535644e-05, "loss": 2.049, "step": 25 }, { "epoch": 0.024792363951902815, "eval_loss": 2.1376192569732666, "eval_runtime": 1.1245, "eval_samples_per_second": 44.466, "eval_steps_per_second": 11.561, "step": 25 }, { "epoch": 0.025784058509978926, "grad_norm": 0.6506301164627075, "learning_rate": 5.500000000000001e-05, "loss": 2.1492, "step": 26 }, { "epoch": 0.02677575306805504, "grad_norm": 0.6272109746932983, "learning_rate": 5.205685918464356e-05, "loss": 2.1375, "step": 27 }, { "epoch": 0.02776744762613115, "grad_norm": 0.5856204628944397, "learning_rate": 4.912632135009769e-05, "loss": 2.0767, "step": 28 }, { "epoch": 0.028759142184207265, "grad_norm": 0.603814423084259, "learning_rate": 4.6220935509274235e-05, "loss": 2.1341, "step": 29 }, { "epoch": 0.029750836742283376, "grad_norm": 0.6377735137939453, "learning_rate": 4.3353142970386564e-05, "loss": 2.0204, "step": 30 }, { "epoch": 0.03074253130035949, "grad_norm": 0.6095825433731079, "learning_rate": 4.053522406135775e-05, "loss": 2.0747, "step": 31 }, { "epoch": 0.031734225858435605, "grad_norm": 0.5862390398979187, "learning_rate": 3.777924554357096e-05, "loss": 2.0728, "step": 32 }, { "epoch": 0.03272592041651171, "grad_norm": 0.5877420902252197, "learning_rate": 3.509700894014496e-05, "loss": 2.1091, "step": 33 }, { "epoch": 0.03371761497458783, "grad_norm": 0.5727083683013916, "learning_rate": 3.250000000000001e-05, "loss": 1.9683, "step": 34 }, { "epoch": 0.03470930953266394, "grad_norm": 0.5779207944869995, "learning_rate": 2.9999339514117912e-05, "loss": 2.084, "step": 35 }, { "epoch": 0.03570100409074005, "grad_norm": 0.6393936276435852, "learning_rate": 2.760573569460757e-05, "loss": 2.1341, "step": 36 }, { "epoch": 0.03669269864881616, "grad_norm": 0.6033120155334473, "learning_rate": 2.53294383204969e-05, "loss": 2.0806, "step": 37 }, { "epoch": 0.03768439320689228, "grad_norm": 0.6125691533088684, "learning_rate": 2.3180194846605367e-05, "loss": 2.2096, "step": 38 }, { "epoch": 0.03867608776496839, "grad_norm": 0.6041589379310608, "learning_rate": 2.1167208663446025e-05, "loss": 2.1368, "step": 39 }, { "epoch": 0.0396677823230445, "grad_norm": 0.601218581199646, "learning_rate": 1.9299099686894423e-05, "loss": 2.1579, "step": 40 }, { "epoch": 0.040659476881120614, "grad_norm": 0.588674008846283, "learning_rate": 1.758386744638546e-05, "loss": 2.064, "step": 41 }, { "epoch": 0.04165117143919673, "grad_norm": 0.5896679162979126, "learning_rate": 1.602885682970026e-05, "loss": 2.0999, "step": 42 }, { "epoch": 0.04264286599727284, "grad_norm": 0.6175012588500977, "learning_rate": 1.464072663102903e-05, "loss": 2.0315, "step": 43 }, { "epoch": 0.04363456055534895, "grad_norm": 0.6025582551956177, "learning_rate": 1.3425421036992098e-05, "loss": 2.0327, "step": 44 }, { "epoch": 0.044626255113425065, "grad_norm": 0.5947927236557007, "learning_rate": 1.2388144172720251e-05, "loss": 2.0573, "step": 45 }, { "epoch": 0.04561794967150118, "grad_norm": 0.6009608507156372, "learning_rate": 1.1533337816991932e-05, "loss": 2.1075, "step": 46 }, { "epoch": 0.04660964422957729, "grad_norm": 0.5778355598449707, "learning_rate": 1.0864662381854632e-05, "loss": 2.0815, "step": 47 }, { "epoch": 0.0476013387876534, "grad_norm": 0.6041818857192993, "learning_rate": 1.0384981238178534e-05, "loss": 2.1687, "step": 48 }, { "epoch": 0.048593033345729515, "grad_norm": 0.6211597323417664, "learning_rate": 1.0096348454262845e-05, "loss": 2.2201, "step": 49 }, { "epoch": 0.04958472790380563, "grad_norm": 0.6282414793968201, "learning_rate": 1e-05, "loss": 2.0931, "step": 50 }, { "epoch": 0.04958472790380563, "eval_loss": 2.11165714263916, "eval_runtime": 1.1461, "eval_samples_per_second": 43.626, "eval_steps_per_second": 11.343, "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": 7.83042868150272e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }