{ "best_metric": 0.6206071972846985, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.031140521603736863, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006228104320747372, "grad_norm": 34.961917877197266, "learning_rate": 5e-05, "loss": 4.4055, "step": 1 }, { "epoch": 0.0006228104320747372, "eval_loss": 5.756421089172363, "eval_runtime": 463.9618, "eval_samples_per_second": 23.314, "eval_steps_per_second": 2.916, "step": 1 }, { "epoch": 0.0012456208641494744, "grad_norm": 25.625226974487305, "learning_rate": 0.0001, "loss": 4.1662, "step": 2 }, { "epoch": 0.0018684312962242117, "grad_norm": 18.706308364868164, "learning_rate": 9.989294616193017e-05, "loss": 3.099, "step": 3 }, { "epoch": 0.002491241728298949, "grad_norm": 14.237258911132812, "learning_rate": 9.957224306869053e-05, "loss": 1.2839, "step": 4 }, { "epoch": 0.003114052160373686, "grad_norm": 7.653135299682617, "learning_rate": 9.903926402016153e-05, "loss": 0.7328, "step": 5 }, { "epoch": 0.0037368625924484233, "grad_norm": 7.604238986968994, "learning_rate": 9.829629131445342e-05, "loss": 0.6975, "step": 6 }, { "epoch": 0.004359673024523161, "grad_norm": 4.739212512969971, "learning_rate": 9.73465064747553e-05, "loss": 0.6526, "step": 7 }, { "epoch": 0.004982483456597898, "grad_norm": 4.953818321228027, "learning_rate": 9.619397662556435e-05, "loss": 0.6595, "step": 8 }, { "epoch": 0.005605293888672635, "grad_norm": 5.076328754425049, "learning_rate": 9.484363707663442e-05, "loss": 0.8259, "step": 9 }, { "epoch": 0.006228104320747372, "grad_norm": 4.2572736740112305, "learning_rate": 9.330127018922194e-05, "loss": 0.7653, "step": 10 }, { "epoch": 0.00685091475282211, "grad_norm": 5.306685447692871, "learning_rate": 9.157348061512727e-05, "loss": 0.9771, "step": 11 }, { "epoch": 0.007473725184896847, "grad_norm": 5.197048187255859, "learning_rate": 8.966766701456177e-05, "loss": 1.1657, "step": 12 }, { "epoch": 0.008096535616971585, "grad_norm": 5.541998863220215, "learning_rate": 8.759199037394887e-05, "loss": 1.0405, "step": 13 }, { "epoch": 0.008719346049046322, "grad_norm": 4.117219924926758, "learning_rate": 8.535533905932738e-05, "loss": 0.7929, "step": 14 }, { "epoch": 0.009342156481121059, "grad_norm": 3.033407688140869, "learning_rate": 8.296729075500344e-05, "loss": 0.5813, "step": 15 }, { "epoch": 0.009964966913195795, "grad_norm": 3.0356810092926025, "learning_rate": 8.043807145043604e-05, "loss": 0.5848, "step": 16 }, { "epoch": 0.010587777345270534, "grad_norm": 3.6332268714904785, "learning_rate": 7.777851165098012e-05, "loss": 0.5569, "step": 17 }, { "epoch": 0.01121058777734527, "grad_norm": 4.638049602508545, "learning_rate": 7.500000000000001e-05, "loss": 0.575, "step": 18 }, { "epoch": 0.011833398209420008, "grad_norm": 3.121140718460083, "learning_rate": 7.211443451095007e-05, "loss": 0.4935, "step": 19 }, { "epoch": 0.012456208641494744, "grad_norm": 3.2301628589630127, "learning_rate": 6.91341716182545e-05, "loss": 0.6655, "step": 20 }, { "epoch": 0.013079019073569483, "grad_norm": 3.529449462890625, "learning_rate": 6.607197326515808e-05, "loss": 0.6141, "step": 21 }, { "epoch": 0.01370182950564422, "grad_norm": 3.159022808074951, "learning_rate": 6.294095225512603e-05, "loss": 0.5717, "step": 22 }, { "epoch": 0.014324639937718956, "grad_norm": 3.829219341278076, "learning_rate": 5.9754516100806423e-05, "loss": 0.6012, "step": 23 }, { "epoch": 0.014947450369793693, "grad_norm": 4.6542487144470215, "learning_rate": 5.6526309611002594e-05, "loss": 0.832, "step": 24 }, { "epoch": 0.015570260801868432, "grad_norm": 5.967838764190674, "learning_rate": 5.327015646150716e-05, "loss": 1.376, "step": 25 }, { "epoch": 0.015570260801868432, "eval_loss": 0.6481190919876099, "eval_runtime": 464.1823, "eval_samples_per_second": 23.303, "eval_steps_per_second": 2.915, "step": 25 }, { "epoch": 0.01619307123394317, "grad_norm": 4.6942877769470215, "learning_rate": 5e-05, "loss": 0.7529, "step": 26 }, { "epoch": 0.016815881666017905, "grad_norm": 2.933812379837036, "learning_rate": 4.6729843538492847e-05, "loss": 0.5804, "step": 27 }, { "epoch": 0.017438692098092644, "grad_norm": 2.9494214057922363, "learning_rate": 4.347369038899744e-05, "loss": 0.6122, "step": 28 }, { "epoch": 0.01806150253016738, "grad_norm": 3.9514541625976562, "learning_rate": 4.0245483899193595e-05, "loss": 0.586, "step": 29 }, { "epoch": 0.018684312962242117, "grad_norm": 2.456082820892334, "learning_rate": 3.705904774487396e-05, "loss": 0.5001, "step": 30 }, { "epoch": 0.019307123394316856, "grad_norm": 3.063210964202881, "learning_rate": 3.392802673484193e-05, "loss": 0.6416, "step": 31 }, { "epoch": 0.01992993382639159, "grad_norm": 2.158895969390869, "learning_rate": 3.086582838174551e-05, "loss": 0.4718, "step": 32 }, { "epoch": 0.02055274425846633, "grad_norm": 3.134558916091919, "learning_rate": 2.7885565489049946e-05, "loss": 0.6344, "step": 33 }, { "epoch": 0.021175554690541068, "grad_norm": 5.159844875335693, "learning_rate": 2.500000000000001e-05, "loss": 0.5952, "step": 34 }, { "epoch": 0.021798365122615803, "grad_norm": 3.6120400428771973, "learning_rate": 2.2221488349019903e-05, "loss": 0.7819, "step": 35 }, { "epoch": 0.02242117555469054, "grad_norm": 3.597929000854492, "learning_rate": 1.9561928549563968e-05, "loss": 0.753, "step": 36 }, { "epoch": 0.023043985986765277, "grad_norm": 4.944601535797119, "learning_rate": 1.703270924499656e-05, "loss": 1.0505, "step": 37 }, { "epoch": 0.023666796418840015, "grad_norm": 5.831929683685303, "learning_rate": 1.4644660940672627e-05, "loss": 0.8816, "step": 38 }, { "epoch": 0.024289606850914754, "grad_norm": 3.287022829055786, "learning_rate": 1.2408009626051137e-05, "loss": 0.74, "step": 39 }, { "epoch": 0.02491241728298949, "grad_norm": 2.3541550636291504, "learning_rate": 1.0332332985438248e-05, "loss": 0.4848, "step": 40 }, { "epoch": 0.025535227715064227, "grad_norm": 3.2387115955352783, "learning_rate": 8.426519384872733e-06, "loss": 0.6658, "step": 41 }, { "epoch": 0.026158038147138966, "grad_norm": 2.4414989948272705, "learning_rate": 6.698729810778065e-06, "loss": 0.5423, "step": 42 }, { "epoch": 0.0267808485792137, "grad_norm": 2.677088737487793, "learning_rate": 5.156362923365588e-06, "loss": 0.4431, "step": 43 }, { "epoch": 0.02740365901128844, "grad_norm": 2.6570982933044434, "learning_rate": 3.8060233744356633e-06, "loss": 0.5932, "step": 44 }, { "epoch": 0.028026469443363178, "grad_norm": 2.9952850341796875, "learning_rate": 2.653493525244721e-06, "loss": 0.5313, "step": 45 }, { "epoch": 0.028649279875437913, "grad_norm": 2.977844476699829, "learning_rate": 1.70370868554659e-06, "loss": 0.5879, "step": 46 }, { "epoch": 0.02927209030751265, "grad_norm": 2.791550397872925, "learning_rate": 9.607359798384785e-07, "loss": 0.5124, "step": 47 }, { "epoch": 0.029894900739587386, "grad_norm": 3.966216802597046, "learning_rate": 4.277569313094809e-07, "loss": 0.7275, "step": 48 }, { "epoch": 0.030517711171662125, "grad_norm": 4.126320838928223, "learning_rate": 1.0705383806982606e-07, "loss": 0.7949, "step": 49 }, { "epoch": 0.031140521603736863, "grad_norm": 5.07513952255249, "learning_rate": 0.0, "loss": 1.1318, "step": 50 }, { "epoch": 0.031140521603736863, "eval_loss": 0.6206071972846985, "eval_runtime": 476.0766, "eval_samples_per_second": 22.721, "eval_steps_per_second": 2.842, "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": 8.435490789261312e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }