{ "best_metric": 0.8755273222923279, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.2508623392913139, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005017246785826278, "grad_norm": 10.303523063659668, "learning_rate": 5e-05, "loss": 20.3254, "step": 1 }, { "epoch": 0.005017246785826278, "eval_loss": 1.2978161573410034, "eval_runtime": 4.7491, "eval_samples_per_second": 10.528, "eval_steps_per_second": 2.737, "step": 1 }, { "epoch": 0.010034493571652555, "grad_norm": 10.276937484741211, "learning_rate": 0.0001, "loss": 21.204, "step": 2 }, { "epoch": 0.015051740357478834, "grad_norm": 9.593537330627441, "learning_rate": 9.990365154573717e-05, "loss": 21.2612, "step": 3 }, { "epoch": 0.02006898714330511, "grad_norm": 7.457390308380127, "learning_rate": 9.961501876182148e-05, "loss": 20.5788, "step": 4 }, { "epoch": 0.02508623392913139, "grad_norm": 6.21054744720459, "learning_rate": 9.913533761814537e-05, "loss": 20.2998, "step": 5 }, { "epoch": 0.030103480714957668, "grad_norm": 6.098522186279297, "learning_rate": 9.846666218300807e-05, "loss": 16.6053, "step": 6 }, { "epoch": 0.035120727500783946, "grad_norm": 5.591812610626221, "learning_rate": 9.761185582727977e-05, "loss": 15.4707, "step": 7 }, { "epoch": 0.04013797428661022, "grad_norm": 4.332369327545166, "learning_rate": 9.657457896300791e-05, "loss": 14.4678, "step": 8 }, { "epoch": 0.045155221072436504, "grad_norm": 4.643701076507568, "learning_rate": 9.535927336897098e-05, "loss": 14.5388, "step": 9 }, { "epoch": 0.05017246785826278, "grad_norm": 4.316195487976074, "learning_rate": 9.397114317029975e-05, "loss": 14.6748, "step": 10 }, { "epoch": 0.055189714644089054, "grad_norm": 6.267123222351074, "learning_rate": 9.241613255361455e-05, "loss": 14.7721, "step": 11 }, { "epoch": 0.060206961429915336, "grad_norm": 4.699112892150879, "learning_rate": 9.070090031310558e-05, "loss": 14.8929, "step": 12 }, { "epoch": 0.06522420821574161, "grad_norm": 6.970594882965088, "learning_rate": 8.883279133655399e-05, "loss": 15.4255, "step": 13 }, { "epoch": 0.07024145500156789, "grad_norm": 8.095081329345703, "learning_rate": 8.681980515339464e-05, "loss": 16.0384, "step": 14 }, { "epoch": 0.07525870178739416, "grad_norm": 5.648611545562744, "learning_rate": 8.467056167950311e-05, "loss": 16.1937, "step": 15 }, { "epoch": 0.08027594857322044, "grad_norm": 4.975302219390869, "learning_rate": 8.239426430539243e-05, "loss": 16.0918, "step": 16 }, { "epoch": 0.08529319535904673, "grad_norm": 4.795402526855469, "learning_rate": 8.000066048588211e-05, "loss": 16.0038, "step": 17 }, { "epoch": 0.09031044214487301, "grad_norm": 7.83776330947876, "learning_rate": 7.75e-05, "loss": 16.4963, "step": 18 }, { "epoch": 0.09532768893069928, "grad_norm": 3.627122163772583, "learning_rate": 7.490299105985507e-05, "loss": 14.9381, "step": 19 }, { "epoch": 0.10034493571652556, "grad_norm": 3.868642568588257, "learning_rate": 7.222075445642904e-05, "loss": 13.6192, "step": 20 }, { "epoch": 0.10536218250235184, "grad_norm": 3.3879823684692383, "learning_rate": 6.946477593864228e-05, "loss": 12.9079, "step": 21 }, { "epoch": 0.11037942928817811, "grad_norm": 2.9493606090545654, "learning_rate": 6.664685702961344e-05, "loss": 12.8852, "step": 22 }, { "epoch": 0.11539667607400439, "grad_norm": 3.189535617828369, "learning_rate": 6.377906449072578e-05, "loss": 13.657, "step": 23 }, { "epoch": 0.12041392285983067, "grad_norm": 3.6464903354644775, "learning_rate": 6.087367864990233e-05, "loss": 13.5806, "step": 24 }, { "epoch": 0.12543116964565695, "grad_norm": 4.111282825469971, "learning_rate": 5.794314081535644e-05, "loss": 14.581, "step": 25 }, { "epoch": 0.12543116964565695, "eval_loss": 0.9173004627227783, "eval_runtime": 4.6046, "eval_samples_per_second": 10.859, "eval_steps_per_second": 2.823, "step": 25 }, { "epoch": 0.13044841643148322, "grad_norm": 7.0074028968811035, "learning_rate": 5.500000000000001e-05, "loss": 14.6113, "step": 26 }, { "epoch": 0.1354656632173095, "grad_norm": 7.817895412445068, "learning_rate": 5.205685918464356e-05, "loss": 15.3695, "step": 27 }, { "epoch": 0.14048291000313579, "grad_norm": 6.956982612609863, "learning_rate": 4.912632135009769e-05, "loss": 15.822, "step": 28 }, { "epoch": 0.14550015678896205, "grad_norm": 4.960094928741455, "learning_rate": 4.6220935509274235e-05, "loss": 15.6277, "step": 29 }, { "epoch": 0.15051740357478832, "grad_norm": 4.474605560302734, "learning_rate": 4.3353142970386564e-05, "loss": 15.7418, "step": 30 }, { "epoch": 0.15553465036061462, "grad_norm": 4.103686809539795, "learning_rate": 4.053522406135775e-05, "loss": 13.9589, "step": 31 }, { "epoch": 0.1605518971464409, "grad_norm": 5.2068376541137695, "learning_rate": 3.777924554357096e-05, "loss": 13.031, "step": 32 }, { "epoch": 0.16556914393226718, "grad_norm": 4.783890724182129, "learning_rate": 3.509700894014496e-05, "loss": 12.818, "step": 33 }, { "epoch": 0.17058639071809345, "grad_norm": 4.218921661376953, "learning_rate": 3.250000000000001e-05, "loss": 13.144, "step": 34 }, { "epoch": 0.17560363750391972, "grad_norm": 3.8665473461151123, "learning_rate": 2.9999339514117912e-05, "loss": 13.379, "step": 35 }, { "epoch": 0.18062088428974601, "grad_norm": 3.703275442123413, "learning_rate": 2.760573569460757e-05, "loss": 13.6023, "step": 36 }, { "epoch": 0.18563813107557228, "grad_norm": 3.7159953117370605, "learning_rate": 2.53294383204969e-05, "loss": 13.6124, "step": 37 }, { "epoch": 0.19065537786139855, "grad_norm": 3.394871950149536, "learning_rate": 2.3180194846605367e-05, "loss": 14.1037, "step": 38 }, { "epoch": 0.19567262464722485, "grad_norm": 4.415946960449219, "learning_rate": 2.1167208663446025e-05, "loss": 14.1554, "step": 39 }, { "epoch": 0.20068987143305111, "grad_norm": 4.950469970703125, "learning_rate": 1.9299099686894423e-05, "loss": 15.051, "step": 40 }, { "epoch": 0.20570711821887738, "grad_norm": 4.831371307373047, "learning_rate": 1.758386744638546e-05, "loss": 14.5962, "step": 41 }, { "epoch": 0.21072436500470368, "grad_norm": 4.842825889587402, "learning_rate": 1.602885682970026e-05, "loss": 15.6923, "step": 42 }, { "epoch": 0.21574161179052995, "grad_norm": 4.159366130828857, "learning_rate": 1.464072663102903e-05, "loss": 15.3636, "step": 43 }, { "epoch": 0.22075885857635622, "grad_norm": 3.6262786388397217, "learning_rate": 1.3425421036992098e-05, "loss": 13.3886, "step": 44 }, { "epoch": 0.2257761053621825, "grad_norm": 2.7398009300231934, "learning_rate": 1.2388144172720251e-05, "loss": 12.5319, "step": 45 }, { "epoch": 0.23079335214800878, "grad_norm": 2.7315304279327393, "learning_rate": 1.1533337816991932e-05, "loss": 12.5121, "step": 46 }, { "epoch": 0.23581059893383505, "grad_norm": 3.2367587089538574, "learning_rate": 1.0864662381854632e-05, "loss": 12.881, "step": 47 }, { "epoch": 0.24082784571966134, "grad_norm": 3.7576241493225098, "learning_rate": 1.0384981238178534e-05, "loss": 13.4895, "step": 48 }, { "epoch": 0.2458450925054876, "grad_norm": 4.879652500152588, "learning_rate": 1.0096348454262845e-05, "loss": 14.1439, "step": 49 }, { "epoch": 0.2508623392913139, "grad_norm": 4.576759338378906, "learning_rate": 1e-05, "loss": 13.8784, "step": 50 }, { "epoch": 0.2508623392913139, "eval_loss": 0.8755273222923279, "eval_runtime": 4.9809, "eval_samples_per_second": 10.038, "eval_steps_per_second": 2.61, "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": 7.849213880612946e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }