{ "best_metric": 1.0809752941131592, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.019333478334420843, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0003866695666884168, "grad_norm": 2.3776214122772217, "learning_rate": 5e-05, "loss": 1.2604, "step": 1 }, { "epoch": 0.0003866695666884168, "eval_loss": 2.5150413513183594, "eval_runtime": 2.6663, "eval_samples_per_second": 18.753, "eval_steps_per_second": 4.876, "step": 1 }, { "epoch": 0.0007733391333768336, "grad_norm": 2.1519436836242676, "learning_rate": 0.0001, "loss": 1.6118, "step": 2 }, { "epoch": 0.0011600087000652505, "grad_norm": 1.3194416761398315, "learning_rate": 9.990365154573717e-05, "loss": 1.5957, "step": 3 }, { "epoch": 0.0015466782667536672, "grad_norm": 1.1811617612838745, "learning_rate": 9.961501876182148e-05, "loss": 1.7025, "step": 4 }, { "epoch": 0.0019333478334420842, "grad_norm": 1.202399492263794, "learning_rate": 9.913533761814537e-05, "loss": 1.7638, "step": 5 }, { "epoch": 0.002320017400130501, "grad_norm": 1.4361952543258667, "learning_rate": 9.846666218300807e-05, "loss": 1.5778, "step": 6 }, { "epoch": 0.0027066869668189177, "grad_norm": 1.75210702419281, "learning_rate": 9.761185582727977e-05, "loss": 1.6974, "step": 7 }, { "epoch": 0.0030933565335073345, "grad_norm": 2.1023099422454834, "learning_rate": 9.657457896300791e-05, "loss": 1.5147, "step": 8 }, { "epoch": 0.0034800261001957516, "grad_norm": 1.5686103105545044, "learning_rate": 9.535927336897098e-05, "loss": 1.452, "step": 9 }, { "epoch": 0.0038666956668841684, "grad_norm": 2.0143210887908936, "learning_rate": 9.397114317029975e-05, "loss": 1.3049, "step": 10 }, { "epoch": 0.004253365233572585, "grad_norm": 2.4440548419952393, "learning_rate": 9.241613255361455e-05, "loss": 1.3559, "step": 11 }, { "epoch": 0.004640034800261002, "grad_norm": 2.6818675994873047, "learning_rate": 9.070090031310558e-05, "loss": 1.5634, "step": 12 }, { "epoch": 0.005026704366949419, "grad_norm": 0.9897537231445312, "learning_rate": 8.883279133655399e-05, "loss": 0.9847, "step": 13 }, { "epoch": 0.005413373933637835, "grad_norm": 1.1883771419525146, "learning_rate": 8.681980515339464e-05, "loss": 1.1975, "step": 14 }, { "epoch": 0.005800043500326252, "grad_norm": 1.0952891111373901, "learning_rate": 8.467056167950311e-05, "loss": 1.2182, "step": 15 }, { "epoch": 0.006186713067014669, "grad_norm": 0.8882080316543579, "learning_rate": 8.239426430539243e-05, "loss": 1.2597, "step": 16 }, { "epoch": 0.006573382633703086, "grad_norm": 0.8250088691711426, "learning_rate": 8.000066048588211e-05, "loss": 1.3915, "step": 17 }, { "epoch": 0.006960052200391503, "grad_norm": 0.9978826642036438, "learning_rate": 7.75e-05, "loss": 1.3069, "step": 18 }, { "epoch": 0.00734672176707992, "grad_norm": 1.0820250511169434, "learning_rate": 7.490299105985507e-05, "loss": 1.4172, "step": 19 }, { "epoch": 0.007733391333768337, "grad_norm": 1.1229532957077026, "learning_rate": 7.222075445642904e-05, "loss": 1.2698, "step": 20 }, { "epoch": 0.008120060900456753, "grad_norm": 1.2130109071731567, "learning_rate": 6.946477593864228e-05, "loss": 1.2486, "step": 21 }, { "epoch": 0.00850673046714517, "grad_norm": 1.4362014532089233, "learning_rate": 6.664685702961344e-05, "loss": 1.195, "step": 22 }, { "epoch": 0.008893400033833588, "grad_norm": 1.292353630065918, "learning_rate": 6.377906449072578e-05, "loss": 1.1979, "step": 23 }, { "epoch": 0.009280069600522004, "grad_norm": 1.5231229066848755, "learning_rate": 6.087367864990233e-05, "loss": 1.1059, "step": 24 }, { "epoch": 0.009666739167210421, "grad_norm": 3.025895833969116, "learning_rate": 5.794314081535644e-05, "loss": 1.6276, "step": 25 }, { "epoch": 0.009666739167210421, "eval_loss": 1.1249579191207886, "eval_runtime": 2.0356, "eval_samples_per_second": 24.563, "eval_steps_per_second": 6.386, "step": 25 }, { "epoch": 0.010053408733898837, "grad_norm": 0.6131384968757629, "learning_rate": 5.500000000000001e-05, "loss": 1.0446, "step": 26 }, { "epoch": 0.010440078300587255, "grad_norm": 0.7854299545288086, "learning_rate": 5.205685918464356e-05, "loss": 1.1503, "step": 27 }, { "epoch": 0.01082674786727567, "grad_norm": 0.8582091927528381, "learning_rate": 4.912632135009769e-05, "loss": 1.2987, "step": 28 }, { "epoch": 0.011213417433964088, "grad_norm": 0.8346323370933533, "learning_rate": 4.6220935509274235e-05, "loss": 1.3962, "step": 29 }, { "epoch": 0.011600087000652504, "grad_norm": 0.8909927606582642, "learning_rate": 4.3353142970386564e-05, "loss": 1.3144, "step": 30 }, { "epoch": 0.011986756567340922, "grad_norm": 0.9254404902458191, "learning_rate": 4.053522406135775e-05, "loss": 1.147, "step": 31 }, { "epoch": 0.012373426134029338, "grad_norm": 0.9486504793167114, "learning_rate": 3.777924554357096e-05, "loss": 1.173, "step": 32 }, { "epoch": 0.012760095700717755, "grad_norm": 1.0398434400558472, "learning_rate": 3.509700894014496e-05, "loss": 1.1825, "step": 33 }, { "epoch": 0.013146765267406171, "grad_norm": 1.1759663820266724, "learning_rate": 3.250000000000001e-05, "loss": 1.2143, "step": 34 }, { "epoch": 0.013533434834094589, "grad_norm": 1.3558342456817627, "learning_rate": 2.9999339514117912e-05, "loss": 1.2427, "step": 35 }, { "epoch": 0.013920104400783007, "grad_norm": 1.5557582378387451, "learning_rate": 2.760573569460757e-05, "loss": 1.3781, "step": 36 }, { "epoch": 0.014306773967471422, "grad_norm": 2.1621055603027344, "learning_rate": 2.53294383204969e-05, "loss": 1.2148, "step": 37 }, { "epoch": 0.01469344353415984, "grad_norm": 0.437295526266098, "learning_rate": 2.3180194846605367e-05, "loss": 1.0218, "step": 38 }, { "epoch": 0.015080113100848256, "grad_norm": 0.5033637881278992, "learning_rate": 2.1167208663446025e-05, "loss": 1.0787, "step": 39 }, { "epoch": 0.015466782667536674, "grad_norm": 0.5792263150215149, "learning_rate": 1.9299099686894423e-05, "loss": 1.171, "step": 40 }, { "epoch": 0.01585345223422509, "grad_norm": 0.6566769480705261, "learning_rate": 1.758386744638546e-05, "loss": 1.3454, "step": 41 }, { "epoch": 0.016240121800913505, "grad_norm": 0.9425048232078552, "learning_rate": 1.602885682970026e-05, "loss": 1.269, "step": 42 }, { "epoch": 0.016626791367601923, "grad_norm": 0.7594242691993713, "learning_rate": 1.464072663102903e-05, "loss": 1.1869, "step": 43 }, { "epoch": 0.01701346093429034, "grad_norm": 0.8492668271064758, "learning_rate": 1.3425421036992098e-05, "loss": 1.2103, "step": 44 }, { "epoch": 0.017400130500978758, "grad_norm": 1.0016244649887085, "learning_rate": 1.2388144172720251e-05, "loss": 1.2328, "step": 45 }, { "epoch": 0.017786800067667176, "grad_norm": 0.9997175335884094, "learning_rate": 1.1533337816991932e-05, "loss": 1.102, "step": 46 }, { "epoch": 0.01817346963435559, "grad_norm": 1.1904468536376953, "learning_rate": 1.0864662381854632e-05, "loss": 1.1894, "step": 47 }, { "epoch": 0.018560139201044008, "grad_norm": 1.2717448472976685, "learning_rate": 1.0384981238178534e-05, "loss": 1.1643, "step": 48 }, { "epoch": 0.018946808767732425, "grad_norm": 2.184945821762085, "learning_rate": 1.0096348454262845e-05, "loss": 1.202, "step": 49 }, { "epoch": 0.019333478334420843, "grad_norm": 2.2247934341430664, "learning_rate": 1e-05, "loss": 1.2018, "step": 50 }, { "epoch": 0.019333478334420843, "eval_loss": 1.0809752941131592, "eval_runtime": 2.043, "eval_samples_per_second": 24.474, "eval_steps_per_second": 6.363, "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": 5.969948642440643e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }