{ "best_metric": 0.5816426277160645, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.05623110986153089, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001124622197230618, "grad_norm": 7.744973659515381, "learning_rate": 5e-05, "loss": 3.3563, "step": 1 }, { "epoch": 0.001124622197230618, "eval_loss": 4.355260848999023, "eval_runtime": 89.0946, "eval_samples_per_second": 67.232, "eval_steps_per_second": 8.407, "step": 1 }, { "epoch": 0.002249244394461236, "grad_norm": 10.753813743591309, "learning_rate": 0.0001, "loss": 3.6884, "step": 2 }, { "epoch": 0.0033738665916918536, "grad_norm": 9.511582374572754, "learning_rate": 9.989294616193017e-05, "loss": 3.6548, "step": 3 }, { "epoch": 0.004498488788922472, "grad_norm": 6.902701377868652, "learning_rate": 9.957224306869053e-05, "loss": 2.9258, "step": 4 }, { "epoch": 0.0056231109861530895, "grad_norm": 6.2129597663879395, "learning_rate": 9.903926402016153e-05, "loss": 2.6649, "step": 5 }, { "epoch": 0.006747733183383707, "grad_norm": 5.534676551818848, "learning_rate": 9.829629131445342e-05, "loss": 2.3874, "step": 6 }, { "epoch": 0.007872355380614324, "grad_norm": 4.8019490242004395, "learning_rate": 9.73465064747553e-05, "loss": 1.9629, "step": 7 }, { "epoch": 0.008996977577844944, "grad_norm": 5.386327266693115, "learning_rate": 9.619397662556435e-05, "loss": 1.9214, "step": 8 }, { "epoch": 0.010121599775075561, "grad_norm": 5.991131782531738, "learning_rate": 9.484363707663442e-05, "loss": 1.5818, "step": 9 }, { "epoch": 0.011246221972306179, "grad_norm": 4.490484237670898, "learning_rate": 9.330127018922194e-05, "loss": 1.4747, "step": 10 }, { "epoch": 0.012370844169536797, "grad_norm": 5.1978302001953125, "learning_rate": 9.157348061512727e-05, "loss": 1.4303, "step": 11 }, { "epoch": 0.013495466366767414, "grad_norm": 5.289309024810791, "learning_rate": 8.966766701456177e-05, "loss": 1.3564, "step": 12 }, { "epoch": 0.014620088563998032, "grad_norm": 20.05726432800293, "learning_rate": 8.759199037394887e-05, "loss": 1.9222, "step": 13 }, { "epoch": 0.015744710761228648, "grad_norm": 15.33587646484375, "learning_rate": 8.535533905932738e-05, "loss": 1.7137, "step": 14 }, { "epoch": 0.016869332958459268, "grad_norm": 7.184302806854248, "learning_rate": 8.296729075500344e-05, "loss": 1.4597, "step": 15 }, { "epoch": 0.017993955155689887, "grad_norm": 3.5889511108398438, "learning_rate": 8.043807145043604e-05, "loss": 1.2129, "step": 16 }, { "epoch": 0.019118577352920503, "grad_norm": 3.522836685180664, "learning_rate": 7.777851165098012e-05, "loss": 1.1153, "step": 17 }, { "epoch": 0.020243199550151122, "grad_norm": 3.6899452209472656, "learning_rate": 7.500000000000001e-05, "loss": 0.9469, "step": 18 }, { "epoch": 0.02136782174738174, "grad_norm": 3.8417608737945557, "learning_rate": 7.211443451095007e-05, "loss": 0.9241, "step": 19 }, { "epoch": 0.022492443944612358, "grad_norm": 3.2292802333831787, "learning_rate": 6.91341716182545e-05, "loss": 0.9226, "step": 20 }, { "epoch": 0.023617066141842974, "grad_norm": 2.7979719638824463, "learning_rate": 6.607197326515808e-05, "loss": 0.8226, "step": 21 }, { "epoch": 0.024741688339073593, "grad_norm": 2.768580198287964, "learning_rate": 6.294095225512603e-05, "loss": 0.7311, "step": 22 }, { "epoch": 0.02586631053630421, "grad_norm": 3.7674660682678223, "learning_rate": 5.9754516100806423e-05, "loss": 0.763, "step": 23 }, { "epoch": 0.02699093273353483, "grad_norm": 3.7000515460968018, "learning_rate": 5.6526309611002594e-05, "loss": 0.7011, "step": 24 }, { "epoch": 0.028115554930765445, "grad_norm": 4.338658809661865, "learning_rate": 5.327015646150716e-05, "loss": 0.7529, "step": 25 }, { "epoch": 0.028115554930765445, "eval_loss": 0.8154560923576355, "eval_runtime": 88.9811, "eval_samples_per_second": 67.318, "eval_steps_per_second": 8.418, "step": 25 }, { "epoch": 0.029240177127996064, "grad_norm": 3.9729034900665283, "learning_rate": 5e-05, "loss": 1.0358, "step": 26 }, { "epoch": 0.03036479932522668, "grad_norm": 4.659002780914307, "learning_rate": 4.6729843538492847e-05, "loss": 0.9305, "step": 27 }, { "epoch": 0.031489421522457296, "grad_norm": 4.61726188659668, "learning_rate": 4.347369038899744e-05, "loss": 0.9645, "step": 28 }, { "epoch": 0.032614043719687916, "grad_norm": 3.477609634399414, "learning_rate": 4.0245483899193595e-05, "loss": 0.7763, "step": 29 }, { "epoch": 0.033738665916918535, "grad_norm": 2.484680652618408, "learning_rate": 3.705904774487396e-05, "loss": 0.7179, "step": 30 }, { "epoch": 0.034863288114149155, "grad_norm": 2.2007455825805664, "learning_rate": 3.392802673484193e-05, "loss": 0.6509, "step": 31 }, { "epoch": 0.035987910311379774, "grad_norm": 1.9197261333465576, "learning_rate": 3.086582838174551e-05, "loss": 0.566, "step": 32 }, { "epoch": 0.03711253250861039, "grad_norm": 2.2877860069274902, "learning_rate": 2.7885565489049946e-05, "loss": 0.5644, "step": 33 }, { "epoch": 0.038237154705841006, "grad_norm": 2.6936111450195312, "learning_rate": 2.500000000000001e-05, "loss": 0.5342, "step": 34 }, { "epoch": 0.039361776903071626, "grad_norm": 2.989370584487915, "learning_rate": 2.2221488349019903e-05, "loss": 0.545, "step": 35 }, { "epoch": 0.040486399100302245, "grad_norm": 2.734513282775879, "learning_rate": 1.9561928549563968e-05, "loss": 0.4799, "step": 36 }, { "epoch": 0.04161102129753286, "grad_norm": 3.855745315551758, "learning_rate": 1.703270924499656e-05, "loss": 0.5051, "step": 37 }, { "epoch": 0.04273564349476348, "grad_norm": 4.42442512512207, "learning_rate": 1.4644660940672627e-05, "loss": 0.8314, "step": 38 }, { "epoch": 0.043860265691994096, "grad_norm": 2.021456718444824, "learning_rate": 1.2408009626051137e-05, "loss": 0.6981, "step": 39 }, { "epoch": 0.044984887889224716, "grad_norm": 1.7155187129974365, "learning_rate": 1.0332332985438248e-05, "loss": 0.6955, "step": 40 }, { "epoch": 0.04610951008645533, "grad_norm": 1.8176416158676147, "learning_rate": 8.426519384872733e-06, "loss": 0.6259, "step": 41 }, { "epoch": 0.04723413228368595, "grad_norm": 1.7540547847747803, "learning_rate": 6.698729810778065e-06, "loss": 0.561, "step": 42 }, { "epoch": 0.04835875448091657, "grad_norm": 1.9893765449523926, "learning_rate": 5.156362923365588e-06, "loss": 0.6543, "step": 43 }, { "epoch": 0.04948337667814719, "grad_norm": 1.8578767776489258, "learning_rate": 3.8060233744356633e-06, "loss": 0.5677, "step": 44 }, { "epoch": 0.050607998875377806, "grad_norm": 1.9309836626052856, "learning_rate": 2.653493525244721e-06, "loss": 0.5467, "step": 45 }, { "epoch": 0.05173262107260842, "grad_norm": 2.186310291290283, "learning_rate": 1.70370868554659e-06, "loss": 0.5394, "step": 46 }, { "epoch": 0.05285724326983904, "grad_norm": 1.9131931066513062, "learning_rate": 9.607359798384785e-07, "loss": 0.4731, "step": 47 }, { "epoch": 0.05398186546706966, "grad_norm": 2.7403504848480225, "learning_rate": 4.277569313094809e-07, "loss": 0.4916, "step": 48 }, { "epoch": 0.05510648766430028, "grad_norm": 2.281416416168213, "learning_rate": 1.0705383806982606e-07, "loss": 0.4393, "step": 49 }, { "epoch": 0.05623110986153089, "grad_norm": 5.036102294921875, "learning_rate": 0.0, "loss": 0.4817, "step": 50 }, { "epoch": 0.05623110986153089, "eval_loss": 0.5816426277160645, "eval_runtime": 88.7214, "eval_samples_per_second": 67.515, "eval_steps_per_second": 8.442, "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": 2.9539319471407104e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }