{ "best_metric": 0.6624909043312073, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.09125128322117029, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001825025664423406, "grad_norm": 1.2515958547592163, "learning_rate": 5e-05, "loss": 0.9697, "step": 1 }, { "epoch": 0.001825025664423406, "eval_loss": 2.5229265689849854, "eval_runtime": 3.8268, "eval_samples_per_second": 13.066, "eval_steps_per_second": 3.397, "step": 1 }, { "epoch": 0.003650051328846812, "grad_norm": 1.5493718385696411, "learning_rate": 0.0001, "loss": 1.3083, "step": 2 }, { "epoch": 0.0054750769932702175, "grad_norm": 1.7595566511154175, "learning_rate": 9.990365154573717e-05, "loss": 1.4476, "step": 3 }, { "epoch": 0.007300102657693624, "grad_norm": 2.353404998779297, "learning_rate": 9.961501876182148e-05, "loss": 1.356, "step": 4 }, { "epoch": 0.009125128322117029, "grad_norm": 2.011380910873413, "learning_rate": 9.913533761814537e-05, "loss": 1.1238, "step": 5 }, { "epoch": 0.010950153986540435, "grad_norm": 2.0997350215911865, "learning_rate": 9.846666218300807e-05, "loss": 1.1367, "step": 6 }, { "epoch": 0.012775179650963841, "grad_norm": 1.229623556137085, "learning_rate": 9.761185582727977e-05, "loss": 0.9918, "step": 7 }, { "epoch": 0.014600205315387247, "grad_norm": 1.6905843019485474, "learning_rate": 9.657457896300791e-05, "loss": 0.9314, "step": 8 }, { "epoch": 0.016425230979810655, "grad_norm": 1.0064281225204468, "learning_rate": 9.535927336897098e-05, "loss": 1.0703, "step": 9 }, { "epoch": 0.018250256644234058, "grad_norm": 0.9494696259498596, "learning_rate": 9.397114317029975e-05, "loss": 1.0912, "step": 10 }, { "epoch": 0.020075282308657464, "grad_norm": 1.3577463626861572, "learning_rate": 9.241613255361455e-05, "loss": 1.3263, "step": 11 }, { "epoch": 0.02190030797308087, "grad_norm": 0.9360014796257019, "learning_rate": 9.070090031310558e-05, "loss": 1.1669, "step": 12 }, { "epoch": 0.023725333637504276, "grad_norm": 1.6023494005203247, "learning_rate": 8.883279133655399e-05, "loss": 0.5603, "step": 13 }, { "epoch": 0.025550359301927682, "grad_norm": 1.2993015050888062, "learning_rate": 8.681980515339464e-05, "loss": 0.3988, "step": 14 }, { "epoch": 0.02737538496635109, "grad_norm": 0.6793809533119202, "learning_rate": 8.467056167950311e-05, "loss": 0.5632, "step": 15 }, { "epoch": 0.029200410630774495, "grad_norm": 0.8038601875305176, "learning_rate": 8.239426430539243e-05, "loss": 0.7339, "step": 16 }, { "epoch": 0.0310254362951979, "grad_norm": 0.8021077513694763, "learning_rate": 8.000066048588211e-05, "loss": 0.818, "step": 17 }, { "epoch": 0.03285046195962131, "grad_norm": 0.7069315910339355, "learning_rate": 7.75e-05, "loss": 0.7835, "step": 18 }, { "epoch": 0.03467548762404472, "grad_norm": 0.5893568992614746, "learning_rate": 7.490299105985507e-05, "loss": 0.7313, "step": 19 }, { "epoch": 0.036500513288468116, "grad_norm": 0.5406357049942017, "learning_rate": 7.222075445642904e-05, "loss": 0.6624, "step": 20 }, { "epoch": 0.03832553895289152, "grad_norm": 0.6607678532600403, "learning_rate": 6.946477593864228e-05, "loss": 0.8342, "step": 21 }, { "epoch": 0.04015056461731493, "grad_norm": 0.792115330696106, "learning_rate": 6.664685702961344e-05, "loss": 0.8649, "step": 22 }, { "epoch": 0.041975590281738334, "grad_norm": 0.7838982343673706, "learning_rate": 6.377906449072578e-05, "loss": 1.0413, "step": 23 }, { "epoch": 0.04380061594616174, "grad_norm": 1.043294072151184, "learning_rate": 6.087367864990233e-05, "loss": 1.0317, "step": 24 }, { "epoch": 0.045625641610585146, "grad_norm": 1.3635772466659546, "learning_rate": 5.794314081535644e-05, "loss": 1.0042, "step": 25 }, { "epoch": 0.045625641610585146, "eval_loss": 0.7043926119804382, "eval_runtime": 3.4873, "eval_samples_per_second": 14.338, "eval_steps_per_second": 3.728, "step": 25 }, { "epoch": 0.04745066727500855, "grad_norm": 0.3378469944000244, "learning_rate": 5.500000000000001e-05, "loss": 0.3361, "step": 26 }, { "epoch": 0.04927569293943196, "grad_norm": 0.44695428013801575, "learning_rate": 5.205685918464356e-05, "loss": 0.6215, "step": 27 }, { "epoch": 0.051100718603855365, "grad_norm": 0.47721779346466064, "learning_rate": 4.912632135009769e-05, "loss": 0.6365, "step": 28 }, { "epoch": 0.05292574426827877, "grad_norm": 0.4388028085231781, "learning_rate": 4.6220935509274235e-05, "loss": 0.5601, "step": 29 }, { "epoch": 0.05475076993270218, "grad_norm": 0.6377593278884888, "learning_rate": 4.3353142970386564e-05, "loss": 0.7038, "step": 30 }, { "epoch": 0.05657579559712558, "grad_norm": 0.5090797543525696, "learning_rate": 4.053522406135775e-05, "loss": 0.6832, "step": 31 }, { "epoch": 0.05840082126154899, "grad_norm": 0.5677505135536194, "learning_rate": 3.777924554357096e-05, "loss": 0.6987, "step": 32 }, { "epoch": 0.060225846925972396, "grad_norm": 0.4946117401123047, "learning_rate": 3.509700894014496e-05, "loss": 0.7062, "step": 33 }, { "epoch": 0.0620508725903958, "grad_norm": 0.5816937685012817, "learning_rate": 3.250000000000001e-05, "loss": 0.8111, "step": 34 }, { "epoch": 0.06387589825481921, "grad_norm": 0.6310498118400574, "learning_rate": 2.9999339514117912e-05, "loss": 0.9409, "step": 35 }, { "epoch": 0.06570092391924262, "grad_norm": 0.7215195298194885, "learning_rate": 2.760573569460757e-05, "loss": 1.026, "step": 36 }, { "epoch": 0.06752594958366602, "grad_norm": 0.7104012370109558, "learning_rate": 2.53294383204969e-05, "loss": 0.9222, "step": 37 }, { "epoch": 0.06935097524808943, "grad_norm": 0.37331992387771606, "learning_rate": 2.3180194846605367e-05, "loss": 0.4136, "step": 38 }, { "epoch": 0.07117600091251283, "grad_norm": 0.314970999956131, "learning_rate": 2.1167208663446025e-05, "loss": 0.3985, "step": 39 }, { "epoch": 0.07300102657693623, "grad_norm": 0.3620467483997345, "learning_rate": 1.9299099686894423e-05, "loss": 0.5525, "step": 40 }, { "epoch": 0.07482605224135964, "grad_norm": 0.43271878361701965, "learning_rate": 1.758386744638546e-05, "loss": 0.6026, "step": 41 }, { "epoch": 0.07665107790578304, "grad_norm": 0.47089946269989014, "learning_rate": 1.602885682970026e-05, "loss": 0.56, "step": 42 }, { "epoch": 0.07847610357020646, "grad_norm": 0.466452032327652, "learning_rate": 1.464072663102903e-05, "loss": 0.6937, "step": 43 }, { "epoch": 0.08030112923462986, "grad_norm": 0.5172701478004456, "learning_rate": 1.3425421036992098e-05, "loss": 0.6848, "step": 44 }, { "epoch": 0.08212615489905327, "grad_norm": 0.5539178848266602, "learning_rate": 1.2388144172720251e-05, "loss": 0.8384, "step": 45 }, { "epoch": 0.08395118056347667, "grad_norm": 0.5189438462257385, "learning_rate": 1.1533337816991932e-05, "loss": 0.6768, "step": 46 }, { "epoch": 0.08577620622790008, "grad_norm": 0.556174635887146, "learning_rate": 1.0864662381854632e-05, "loss": 0.7213, "step": 47 }, { "epoch": 0.08760123189232348, "grad_norm": 0.6025025248527527, "learning_rate": 1.0384981238178534e-05, "loss": 0.9243, "step": 48 }, { "epoch": 0.0894262575567469, "grad_norm": 0.7314310669898987, "learning_rate": 1.0096348454262845e-05, "loss": 1.0179, "step": 49 }, { "epoch": 0.09125128322117029, "grad_norm": 0.8207038044929504, "learning_rate": 1e-05, "loss": 0.961, "step": 50 }, { "epoch": 0.09125128322117029, "eval_loss": 0.6624909043312073, "eval_runtime": 3.5014, "eval_samples_per_second": 14.28, "eval_steps_per_second": 3.713, "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": 5.968083617316864e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }