{ "best_metric": 0.6615861654281616, "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": 1.3176531791687012, "learning_rate": 5e-05, "loss": 0.9697, "step": 1 }, { "epoch": 0.001825025664423406, "eval_loss": 2.5229265689849854, "eval_runtime": 3.8556, "eval_samples_per_second": 12.968, "eval_steps_per_second": 3.372, "step": 1 }, { "epoch": 0.003650051328846812, "grad_norm": 1.630506992340088, "learning_rate": 0.0001, "loss": 1.3083, "step": 2 }, { "epoch": 0.0054750769932702175, "grad_norm": 1.8489680290222168, "learning_rate": 9.990365154573717e-05, "loss": 1.4425, "step": 3 }, { "epoch": 0.007300102657693624, "grad_norm": 2.4052317142486572, "learning_rate": 9.961501876182148e-05, "loss": 1.3483, "step": 4 }, { "epoch": 0.009125128322117029, "grad_norm": 2.0575854778289795, "learning_rate": 9.913533761814537e-05, "loss": 1.1161, "step": 5 }, { "epoch": 0.010950153986540435, "grad_norm": 2.147378444671631, "learning_rate": 9.846666218300807e-05, "loss": 1.1304, "step": 6 }, { "epoch": 0.012775179650963841, "grad_norm": 1.1892378330230713, "learning_rate": 9.761185582727977e-05, "loss": 0.9857, "step": 7 }, { "epoch": 0.014600205315387247, "grad_norm": 1.6439237594604492, "learning_rate": 9.657457896300791e-05, "loss": 0.9272, "step": 8 }, { "epoch": 0.016425230979810655, "grad_norm": 0.9776643514633179, "learning_rate": 9.535927336897098e-05, "loss": 1.0677, "step": 9 }, { "epoch": 0.018250256644234058, "grad_norm": 0.9577232599258423, "learning_rate": 9.397114317029975e-05, "loss": 1.09, "step": 10 }, { "epoch": 0.020075282308657464, "grad_norm": 1.4068362712860107, "learning_rate": 9.241613255361455e-05, "loss": 1.3253, "step": 11 }, { "epoch": 0.02190030797308087, "grad_norm": 0.9625767469406128, "learning_rate": 9.070090031310558e-05, "loss": 1.1651, "step": 12 }, { "epoch": 0.023725333637504276, "grad_norm": 1.6563161611557007, "learning_rate": 8.883279133655399e-05, "loss": 0.5638, "step": 13 }, { "epoch": 0.025550359301927682, "grad_norm": 1.3329405784606934, "learning_rate": 8.681980515339464e-05, "loss": 0.4003, "step": 14 }, { "epoch": 0.02737538496635109, "grad_norm": 0.6971666216850281, "learning_rate": 8.467056167950311e-05, "loss": 0.5639, "step": 15 }, { "epoch": 0.029200410630774495, "grad_norm": 0.8540834784507751, "learning_rate": 8.239426430539243e-05, "loss": 0.7347, "step": 16 }, { "epoch": 0.0310254362951979, "grad_norm": 0.8000940680503845, "learning_rate": 8.000066048588211e-05, "loss": 0.8151, "step": 17 }, { "epoch": 0.03285046195962131, "grad_norm": 0.7030327320098877, "learning_rate": 7.75e-05, "loss": 0.78, "step": 18 }, { "epoch": 0.03467548762404472, "grad_norm": 0.6044463515281677, "learning_rate": 7.490299105985507e-05, "loss": 0.7334, "step": 19 }, { "epoch": 0.036500513288468116, "grad_norm": 0.5641461610794067, "learning_rate": 7.222075445642904e-05, "loss": 0.6636, "step": 20 }, { "epoch": 0.03832553895289152, "grad_norm": 0.6785281896591187, "learning_rate": 6.946477593864228e-05, "loss": 0.8334, "step": 21 }, { "epoch": 0.04015056461731493, "grad_norm": 0.8149616122245789, "learning_rate": 6.664685702961344e-05, "loss": 0.8656, "step": 22 }, { "epoch": 0.041975590281738334, "grad_norm": 0.8082972168922424, "learning_rate": 6.377906449072578e-05, "loss": 1.0427, "step": 23 }, { "epoch": 0.04380061594616174, "grad_norm": 0.9252455234527588, "learning_rate": 6.087367864990233e-05, "loss": 1.0318, "step": 24 }, { "epoch": 0.045625641610585146, "grad_norm": 1.4149811267852783, "learning_rate": 5.794314081535644e-05, "loss": 1.0031, "step": 25 }, { "epoch": 0.045625641610585146, "eval_loss": 0.7057486176490784, "eval_runtime": 3.5209, "eval_samples_per_second": 14.201, "eval_steps_per_second": 3.692, "step": 25 }, { "epoch": 0.04745066727500855, "grad_norm": 0.35791102051734924, "learning_rate": 5.500000000000001e-05, "loss": 0.3363, "step": 26 }, { "epoch": 0.04927569293943196, "grad_norm": 0.4550030529499054, "learning_rate": 5.205685918464356e-05, "loss": 0.6224, "step": 27 }, { "epoch": 0.051100718603855365, "grad_norm": 0.48958098888397217, "learning_rate": 4.912632135009769e-05, "loss": 0.6362, "step": 28 }, { "epoch": 0.05292574426827877, "grad_norm": 0.44201797246932983, "learning_rate": 4.6220935509274235e-05, "loss": 0.5601, "step": 29 }, { "epoch": 0.05475076993270218, "grad_norm": 0.6427817344665527, "learning_rate": 4.3353142970386564e-05, "loss": 0.701, "step": 30 }, { "epoch": 0.05657579559712558, "grad_norm": 0.5233768224716187, "learning_rate": 4.053522406135775e-05, "loss": 0.6829, "step": 31 }, { "epoch": 0.05840082126154899, "grad_norm": 0.5784444212913513, "learning_rate": 3.777924554357096e-05, "loss": 0.699, "step": 32 }, { "epoch": 0.060225846925972396, "grad_norm": 0.4978267252445221, "learning_rate": 3.509700894014496e-05, "loss": 0.7049, "step": 33 }, { "epoch": 0.0620508725903958, "grad_norm": 0.5924655199050903, "learning_rate": 3.250000000000001e-05, "loss": 0.8093, "step": 34 }, { "epoch": 0.06387589825481921, "grad_norm": 0.6393359303474426, "learning_rate": 2.9999339514117912e-05, "loss": 0.9385, "step": 35 }, { "epoch": 0.06570092391924262, "grad_norm": 0.7333190441131592, "learning_rate": 2.760573569460757e-05, "loss": 1.0239, "step": 36 }, { "epoch": 0.06752594958366602, "grad_norm": 0.7314161658287048, "learning_rate": 2.53294383204969e-05, "loss": 0.9217, "step": 37 }, { "epoch": 0.06935097524808943, "grad_norm": 0.3770674765110016, "learning_rate": 2.3180194846605367e-05, "loss": 0.4129, "step": 38 }, { "epoch": 0.07117600091251283, "grad_norm": 0.31523048877716064, "learning_rate": 2.1167208663446025e-05, "loss": 0.3984, "step": 39 }, { "epoch": 0.07300102657693623, "grad_norm": 0.3684380054473877, "learning_rate": 1.9299099686894423e-05, "loss": 0.5525, "step": 40 }, { "epoch": 0.07482605224135964, "grad_norm": 0.4422256052494049, "learning_rate": 1.758386744638546e-05, "loss": 0.6015, "step": 41 }, { "epoch": 0.07665107790578304, "grad_norm": 0.4704034626483917, "learning_rate": 1.602885682970026e-05, "loss": 0.56, "step": 42 }, { "epoch": 0.07847610357020646, "grad_norm": 0.4587417542934418, "learning_rate": 1.464072663102903e-05, "loss": 0.6929, "step": 43 }, { "epoch": 0.08030112923462986, "grad_norm": 0.5037869215011597, "learning_rate": 1.3425421036992098e-05, "loss": 0.6836, "step": 44 }, { "epoch": 0.08212615489905327, "grad_norm": 0.56147301197052, "learning_rate": 1.2388144172720251e-05, "loss": 0.8363, "step": 45 }, { "epoch": 0.08395118056347667, "grad_norm": 0.5316286683082581, "learning_rate": 1.1533337816991932e-05, "loss": 0.6747, "step": 46 }, { "epoch": 0.08577620622790008, "grad_norm": 0.5714614987373352, "learning_rate": 1.0864662381854632e-05, "loss": 0.7197, "step": 47 }, { "epoch": 0.08760123189232348, "grad_norm": 0.622653067111969, "learning_rate": 1.0384981238178534e-05, "loss": 0.9239, "step": 48 }, { "epoch": 0.0894262575567469, "grad_norm": 0.7487273216247559, "learning_rate": 1.0096348454262845e-05, "loss": 1.0149, "step": 49 }, { "epoch": 0.09125128322117029, "grad_norm": 0.8299003839492798, "learning_rate": 1e-05, "loss": 0.959, "step": 50 }, { "epoch": 0.09125128322117029, "eval_loss": 0.6615861654281616, "eval_runtime": 3.4787, "eval_samples_per_second": 14.373, "eval_steps_per_second": 3.737, "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 }