{ "best_metric": 1.739266037940979, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.05167958656330749, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0010335917312661498, "grad_norm": 0.9239017367362976, "learning_rate": 5e-05, "loss": 2.0724, "step": 1 }, { "epoch": 0.0010335917312661498, "eval_loss": 2.6242575645446777, "eval_runtime": 0.778, "eval_samples_per_second": 64.271, "eval_steps_per_second": 16.71, "step": 1 }, { "epoch": 0.0020671834625322996, "grad_norm": 1.0708829164505005, "learning_rate": 0.0001, "loss": 2.1152, "step": 2 }, { "epoch": 0.0031007751937984496, "grad_norm": 1.0626616477966309, "learning_rate": 9.990365154573717e-05, "loss": 2.1412, "step": 3 }, { "epoch": 0.004134366925064599, "grad_norm": 1.091120719909668, "learning_rate": 9.961501876182148e-05, "loss": 2.016, "step": 4 }, { "epoch": 0.00516795865633075, "grad_norm": 0.9137864112854004, "learning_rate": 9.913533761814537e-05, "loss": 1.9655, "step": 5 }, { "epoch": 0.006201550387596899, "grad_norm": 0.8222112059593201, "learning_rate": 9.846666218300807e-05, "loss": 1.9691, "step": 6 }, { "epoch": 0.007235142118863049, "grad_norm": 0.8061633706092834, "learning_rate": 9.761185582727977e-05, "loss": 1.9128, "step": 7 }, { "epoch": 0.008268733850129198, "grad_norm": 0.8582802414894104, "learning_rate": 9.657457896300791e-05, "loss": 1.8709, "step": 8 }, { "epoch": 0.009302325581395349, "grad_norm": 0.9123162031173706, "learning_rate": 9.535927336897098e-05, "loss": 1.9577, "step": 9 }, { "epoch": 0.0103359173126615, "grad_norm": 0.7822127938270569, "learning_rate": 9.397114317029975e-05, "loss": 1.8656, "step": 10 }, { "epoch": 0.011369509043927648, "grad_norm": 0.9331071972846985, "learning_rate": 9.241613255361455e-05, "loss": 1.9662, "step": 11 }, { "epoch": 0.012403100775193798, "grad_norm": 1.3675150871276855, "learning_rate": 9.070090031310558e-05, "loss": 1.9806, "step": 12 }, { "epoch": 0.013436692506459949, "grad_norm": 1.1646320819854736, "learning_rate": 8.883279133655399e-05, "loss": 1.8357, "step": 13 }, { "epoch": 0.014470284237726097, "grad_norm": 1.270059585571289, "learning_rate": 8.681980515339464e-05, "loss": 1.7306, "step": 14 }, { "epoch": 0.015503875968992248, "grad_norm": 1.0986566543579102, "learning_rate": 8.467056167950311e-05, "loss": 1.6902, "step": 15 }, { "epoch": 0.016537467700258397, "grad_norm": 0.9277008175849915, "learning_rate": 8.239426430539243e-05, "loss": 1.5689, "step": 16 }, { "epoch": 0.01757105943152455, "grad_norm": 0.7451536655426025, "learning_rate": 8.000066048588211e-05, "loss": 1.7069, "step": 17 }, { "epoch": 0.018604651162790697, "grad_norm": 0.6214572787284851, "learning_rate": 7.75e-05, "loss": 1.6968, "step": 18 }, { "epoch": 0.019638242894056846, "grad_norm": 0.683086097240448, "learning_rate": 7.490299105985507e-05, "loss": 1.6891, "step": 19 }, { "epoch": 0.020671834625323, "grad_norm": 0.7283631563186646, "learning_rate": 7.222075445642904e-05, "loss": 1.6948, "step": 20 }, { "epoch": 0.021705426356589147, "grad_norm": 0.7793617248535156, "learning_rate": 6.946477593864228e-05, "loss": 1.8125, "step": 21 }, { "epoch": 0.022739018087855296, "grad_norm": 0.8741857409477234, "learning_rate": 6.664685702961344e-05, "loss": 1.8514, "step": 22 }, { "epoch": 0.023772609819121448, "grad_norm": 0.9736992120742798, "learning_rate": 6.377906449072578e-05, "loss": 1.8525, "step": 23 }, { "epoch": 0.024806201550387597, "grad_norm": 1.1014063358306885, "learning_rate": 6.087367864990233e-05, "loss": 1.8171, "step": 24 }, { "epoch": 0.025839793281653745, "grad_norm": 1.6239304542541504, "learning_rate": 5.794314081535644e-05, "loss": 1.8691, "step": 25 }, { "epoch": 0.025839793281653745, "eval_loss": 1.805835247039795, "eval_runtime": 0.7785, "eval_samples_per_second": 64.225, "eval_steps_per_second": 16.698, "step": 25 }, { "epoch": 0.026873385012919897, "grad_norm": 0.563585102558136, "learning_rate": 5.500000000000001e-05, "loss": 1.602, "step": 26 }, { "epoch": 0.027906976744186046, "grad_norm": 0.5569491386413574, "learning_rate": 5.205685918464356e-05, "loss": 1.4559, "step": 27 }, { "epoch": 0.028940568475452195, "grad_norm": 0.5632328391075134, "learning_rate": 4.912632135009769e-05, "loss": 1.5699, "step": 28 }, { "epoch": 0.029974160206718347, "grad_norm": 0.5582482218742371, "learning_rate": 4.6220935509274235e-05, "loss": 1.5948, "step": 29 }, { "epoch": 0.031007751937984496, "grad_norm": 0.5458480715751648, "learning_rate": 4.3353142970386564e-05, "loss": 1.5245, "step": 30 }, { "epoch": 0.03204134366925065, "grad_norm": 0.5486528277397156, "learning_rate": 4.053522406135775e-05, "loss": 1.6522, "step": 31 }, { "epoch": 0.03307493540051679, "grad_norm": 0.4946439862251282, "learning_rate": 3.777924554357096e-05, "loss": 1.677, "step": 32 }, { "epoch": 0.034108527131782945, "grad_norm": 0.5885268449783325, "learning_rate": 3.509700894014496e-05, "loss": 1.6474, "step": 33 }, { "epoch": 0.0351421188630491, "grad_norm": 0.5598137378692627, "learning_rate": 3.250000000000001e-05, "loss": 1.6737, "step": 34 }, { "epoch": 0.03617571059431524, "grad_norm": 0.5388458967208862, "learning_rate": 2.9999339514117912e-05, "loss": 1.6732, "step": 35 }, { "epoch": 0.037209302325581395, "grad_norm": 0.6448724269866943, "learning_rate": 2.760573569460757e-05, "loss": 1.7968, "step": 36 }, { "epoch": 0.03824289405684755, "grad_norm": 1.0652443170547485, "learning_rate": 2.53294383204969e-05, "loss": 1.8869, "step": 37 }, { "epoch": 0.03927648578811369, "grad_norm": 0.5180839896202087, "learning_rate": 2.3180194846605367e-05, "loss": 1.5899, "step": 38 }, { "epoch": 0.040310077519379844, "grad_norm": 0.4015357494354248, "learning_rate": 2.1167208663446025e-05, "loss": 1.4246, "step": 39 }, { "epoch": 0.041343669250646, "grad_norm": 0.36983615159988403, "learning_rate": 1.9299099686894423e-05, "loss": 1.4877, "step": 40 }, { "epoch": 0.04237726098191214, "grad_norm": 0.3772043287754059, "learning_rate": 1.758386744638546e-05, "loss": 1.489, "step": 41 }, { "epoch": 0.043410852713178294, "grad_norm": 0.3773873448371887, "learning_rate": 1.602885682970026e-05, "loss": 1.48, "step": 42 }, { "epoch": 0.044444444444444446, "grad_norm": 0.35318583250045776, "learning_rate": 1.464072663102903e-05, "loss": 1.5648, "step": 43 }, { "epoch": 0.04547803617571059, "grad_norm": 0.38485991954803467, "learning_rate": 1.3425421036992098e-05, "loss": 1.5377, "step": 44 }, { "epoch": 0.046511627906976744, "grad_norm": 0.3673318326473236, "learning_rate": 1.2388144172720251e-05, "loss": 1.6161, "step": 45 }, { "epoch": 0.047545219638242896, "grad_norm": 0.3764628469944, "learning_rate": 1.1533337816991932e-05, "loss": 1.6054, "step": 46 }, { "epoch": 0.04857881136950904, "grad_norm": 0.5201135873794556, "learning_rate": 1.0864662381854632e-05, "loss": 1.7079, "step": 47 }, { "epoch": 0.04961240310077519, "grad_norm": 0.5968867540359497, "learning_rate": 1.0384981238178534e-05, "loss": 1.7181, "step": 48 }, { "epoch": 0.050645994832041345, "grad_norm": 0.8235591650009155, "learning_rate": 1.0096348454262845e-05, "loss": 1.7999, "step": 49 }, { "epoch": 0.05167958656330749, "grad_norm": 1.5277827978134155, "learning_rate": 1e-05, "loss": 1.89, "step": 50 }, { "epoch": 0.05167958656330749, "eval_loss": 1.739266037940979, "eval_runtime": 0.7761, "eval_samples_per_second": 64.421, "eval_steps_per_second": 16.749, "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": 1.059536353886208e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }