{ "best_metric": 1.1867320537567139, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.02226737551145378, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00044534751022907564, "grad_norm": 47.00421142578125, "learning_rate": 5e-05, "loss": 5.2543, "step": 1 }, { "epoch": 0.00044534751022907564, "eval_loss": 6.243781089782715, "eval_runtime": 737.4692, "eval_samples_per_second": 20.513, "eval_steps_per_second": 2.564, "step": 1 }, { "epoch": 0.0008906950204581513, "grad_norm": 45.821319580078125, "learning_rate": 0.0001, "loss": 5.2971, "step": 2 }, { "epoch": 0.001336042530687227, "grad_norm": 47.45862579345703, "learning_rate": 9.989294616193017e-05, "loss": 5.4538, "step": 3 }, { "epoch": 0.0017813900409163026, "grad_norm": 70.39472961425781, "learning_rate": 9.957224306869053e-05, "loss": 5.7192, "step": 4 }, { "epoch": 0.002226737551145378, "grad_norm": 76.26249694824219, "learning_rate": 9.903926402016153e-05, "loss": 4.7385, "step": 5 }, { "epoch": 0.002672085061374454, "grad_norm": 83.42272186279297, "learning_rate": 9.829629131445342e-05, "loss": 4.399, "step": 6 }, { "epoch": 0.0031174325716035295, "grad_norm": 77.07828521728516, "learning_rate": 9.73465064747553e-05, "loss": 3.9627, "step": 7 }, { "epoch": 0.003562780081832605, "grad_norm": 70.13909149169922, "learning_rate": 9.619397662556435e-05, "loss": 3.5779, "step": 8 }, { "epoch": 0.00400812759206168, "grad_norm": 46.44620895385742, "learning_rate": 9.484363707663442e-05, "loss": 3.2747, "step": 9 }, { "epoch": 0.004453475102290756, "grad_norm": 49.42829513549805, "learning_rate": 9.330127018922194e-05, "loss": 2.744, "step": 10 }, { "epoch": 0.0048988226125198315, "grad_norm": 48.85025405883789, "learning_rate": 9.157348061512727e-05, "loss": 2.5355, "step": 11 }, { "epoch": 0.005344170122748908, "grad_norm": 45.37143325805664, "learning_rate": 8.966766701456177e-05, "loss": 2.6555, "step": 12 }, { "epoch": 0.0057895176329779835, "grad_norm": 44.338478088378906, "learning_rate": 8.759199037394887e-05, "loss": 2.4589, "step": 13 }, { "epoch": 0.006234865143207059, "grad_norm": 37.574886322021484, "learning_rate": 8.535533905932738e-05, "loss": 2.1478, "step": 14 }, { "epoch": 0.006680212653436135, "grad_norm": 40.13383483886719, "learning_rate": 8.296729075500344e-05, "loss": 1.8073, "step": 15 }, { "epoch": 0.00712556016366521, "grad_norm": 44.1107292175293, "learning_rate": 8.043807145043604e-05, "loss": 1.7844, "step": 16 }, { "epoch": 0.007570907673894286, "grad_norm": 41.8834114074707, "learning_rate": 7.777851165098012e-05, "loss": 1.8501, "step": 17 }, { "epoch": 0.00801625518412336, "grad_norm": 41.976158142089844, "learning_rate": 7.500000000000001e-05, "loss": 1.6489, "step": 18 }, { "epoch": 0.008461602694352437, "grad_norm": 43.49707794189453, "learning_rate": 7.211443451095007e-05, "loss": 1.5935, "step": 19 }, { "epoch": 0.008906950204581512, "grad_norm": 29.12820816040039, "learning_rate": 6.91341716182545e-05, "loss": 1.2958, "step": 20 }, { "epoch": 0.009352297714810588, "grad_norm": 35.42374038696289, "learning_rate": 6.607197326515808e-05, "loss": 1.3354, "step": 21 }, { "epoch": 0.009797645225039663, "grad_norm": 37.46640396118164, "learning_rate": 6.294095225512603e-05, "loss": 1.5067, "step": 22 }, { "epoch": 0.01024299273526874, "grad_norm": 36.21051025390625, "learning_rate": 5.9754516100806423e-05, "loss": 1.4837, "step": 23 }, { "epoch": 0.010688340245497816, "grad_norm": 36.641109466552734, "learning_rate": 5.6526309611002594e-05, "loss": 1.2959, "step": 24 }, { "epoch": 0.01113368775572689, "grad_norm": 34.847164154052734, "learning_rate": 5.327015646150716e-05, "loss": 1.4527, "step": 25 }, { "epoch": 0.01113368775572689, "eval_loss": 1.3544864654541016, "eval_runtime": 736.2259, "eval_samples_per_second": 20.548, "eval_steps_per_second": 2.569, "step": 25 }, { "epoch": 0.011579035265955967, "grad_norm": 30.952394485473633, "learning_rate": 5e-05, "loss": 1.5383, "step": 26 }, { "epoch": 0.012024382776185042, "grad_norm": 32.05979919433594, "learning_rate": 4.6729843538492847e-05, "loss": 1.4933, "step": 27 }, { "epoch": 0.012469730286414118, "grad_norm": 27.44908332824707, "learning_rate": 4.347369038899744e-05, "loss": 1.1802, "step": 28 }, { "epoch": 0.012915077796643193, "grad_norm": 29.982824325561523, "learning_rate": 4.0245483899193595e-05, "loss": 1.2624, "step": 29 }, { "epoch": 0.01336042530687227, "grad_norm": 26.732736587524414, "learning_rate": 3.705904774487396e-05, "loss": 1.1506, "step": 30 }, { "epoch": 0.013805772817101344, "grad_norm": 29.822994232177734, "learning_rate": 3.392802673484193e-05, "loss": 1.1674, "step": 31 }, { "epoch": 0.01425112032733042, "grad_norm": 28.42780876159668, "learning_rate": 3.086582838174551e-05, "loss": 1.0655, "step": 32 }, { "epoch": 0.014696467837559495, "grad_norm": 27.28021812438965, "learning_rate": 2.7885565489049946e-05, "loss": 1.3545, "step": 33 }, { "epoch": 0.015141815347788572, "grad_norm": 26.741413116455078, "learning_rate": 2.500000000000001e-05, "loss": 1.0021, "step": 34 }, { "epoch": 0.015587162858017646, "grad_norm": 38.1240119934082, "learning_rate": 2.2221488349019903e-05, "loss": 1.1049, "step": 35 }, { "epoch": 0.01603251036824672, "grad_norm": 31.203073501586914, "learning_rate": 1.9561928549563968e-05, "loss": 1.1722, "step": 36 }, { "epoch": 0.016477857878475798, "grad_norm": 28.79928207397461, "learning_rate": 1.703270924499656e-05, "loss": 1.0829, "step": 37 }, { "epoch": 0.016923205388704874, "grad_norm": 29.13315773010254, "learning_rate": 1.4644660940672627e-05, "loss": 1.2533, "step": 38 }, { "epoch": 0.01736855289893395, "grad_norm": 31.34278678894043, "learning_rate": 1.2408009626051137e-05, "loss": 1.338, "step": 39 }, { "epoch": 0.017813900409163023, "grad_norm": 25.4918155670166, "learning_rate": 1.0332332985438248e-05, "loss": 1.1436, "step": 40 }, { "epoch": 0.0182592479193921, "grad_norm": 27.85494041442871, "learning_rate": 8.426519384872733e-06, "loss": 1.1686, "step": 41 }, { "epoch": 0.018704595429621176, "grad_norm": 29.38884925842285, "learning_rate": 6.698729810778065e-06, "loss": 1.0788, "step": 42 }, { "epoch": 0.019149942939850253, "grad_norm": 29.656871795654297, "learning_rate": 5.156362923365588e-06, "loss": 1.2324, "step": 43 }, { "epoch": 0.019595290450079326, "grad_norm": 38.212669372558594, "learning_rate": 3.8060233744356633e-06, "loss": 0.9916, "step": 44 }, { "epoch": 0.020040637960308402, "grad_norm": 32.79332733154297, "learning_rate": 2.653493525244721e-06, "loss": 1.0483, "step": 45 }, { "epoch": 0.02048598547053748, "grad_norm": 32.203372955322266, "learning_rate": 1.70370868554659e-06, "loss": 1.3274, "step": 46 }, { "epoch": 0.020931332980766555, "grad_norm": 26.626222610473633, "learning_rate": 9.607359798384785e-07, "loss": 1.0576, "step": 47 }, { "epoch": 0.02137668049099563, "grad_norm": 31.617427825927734, "learning_rate": 4.277569313094809e-07, "loss": 1.1872, "step": 48 }, { "epoch": 0.021822028001224705, "grad_norm": 30.30613136291504, "learning_rate": 1.0705383806982606e-07, "loss": 1.1083, "step": 49 }, { "epoch": 0.02226737551145378, "grad_norm": 34.23044204711914, "learning_rate": 0.0, "loss": 1.2354, "step": 50 }, { "epoch": 0.02226737551145378, "eval_loss": 1.1867320537567139, "eval_runtime": 736.9926, "eval_samples_per_second": 20.527, "eval_steps_per_second": 2.566, "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": 1.0952750720352256e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }