{ "best_metric": 0.24849273264408112, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.09474182851729038, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0018948365703458077, "grad_norm": 13.85077953338623, "learning_rate": 0.0001, "loss": 8.6361, "step": 1 }, { "epoch": 0.0018948365703458077, "eval_loss": 8.892292022705078, "eval_runtime": 61.4624, "eval_samples_per_second": 3.628, "eval_steps_per_second": 1.822, "step": 1 }, { "epoch": 0.0037896731406916154, "grad_norm": 14.435070991516113, "learning_rate": 0.0002, "loss": 8.842, "step": 2 }, { "epoch": 0.005684509711037423, "grad_norm": 14.988022804260254, "learning_rate": 0.00019978589232386035, "loss": 7.7961, "step": 3 }, { "epoch": 0.007579346281383231, "grad_norm": 17.64569854736328, "learning_rate": 0.00019914448613738106, "loss": 4.5989, "step": 4 }, { "epoch": 0.009474182851729039, "grad_norm": 12.037191390991211, "learning_rate": 0.00019807852804032305, "loss": 1.1384, "step": 5 }, { "epoch": 0.011369019422074847, "grad_norm": 5.143069744110107, "learning_rate": 0.00019659258262890683, "loss": 0.632, "step": 6 }, { "epoch": 0.013263855992420654, "grad_norm": 2.461094617843628, "learning_rate": 0.0001946930129495106, "loss": 0.3919, "step": 7 }, { "epoch": 0.015158692562766462, "grad_norm": 16.442119598388672, "learning_rate": 0.0001923879532511287, "loss": 1.0052, "step": 8 }, { "epoch": 0.01705352913311227, "grad_norm": 11.127469062805176, "learning_rate": 0.00018968727415326884, "loss": 0.5526, "step": 9 }, { "epoch": 0.018948365703458078, "grad_norm": 0.8949048519134521, "learning_rate": 0.00018660254037844388, "loss": 0.3437, "step": 10 }, { "epoch": 0.020843202273803884, "grad_norm": 1.190866231918335, "learning_rate": 0.00018314696123025454, "loss": 0.2704, "step": 11 }, { "epoch": 0.022738038844149693, "grad_norm": 6.533585071563721, "learning_rate": 0.00017933533402912354, "loss": 0.6186, "step": 12 }, { "epoch": 0.0246328754144955, "grad_norm": 4.6861395835876465, "learning_rate": 0.00017518398074789775, "loss": 0.4758, "step": 13 }, { "epoch": 0.026527711984841308, "grad_norm": 33.712886810302734, "learning_rate": 0.00017071067811865476, "loss": 0.3945, "step": 14 }, { "epoch": 0.028422548555187114, "grad_norm": 4.942092418670654, "learning_rate": 0.00016593458151000688, "loss": 0.453, "step": 15 }, { "epoch": 0.030317385125532923, "grad_norm": 1.8084975481033325, "learning_rate": 0.00016087614290087208, "loss": 0.3536, "step": 16 }, { "epoch": 0.03221222169587873, "grad_norm": 3.7225804328918457, "learning_rate": 0.00015555702330196023, "loss": 0.4389, "step": 17 }, { "epoch": 0.03410705826622454, "grad_norm": 1.6545606851577759, "learning_rate": 0.00015000000000000001, "loss": 0.3758, "step": 18 }, { "epoch": 0.03600189483657035, "grad_norm": 0.42016923427581787, "learning_rate": 0.00014422886902190014, "loss": 0.3409, "step": 19 }, { "epoch": 0.037896731406916156, "grad_norm": 1.3284951448440552, "learning_rate": 0.000138268343236509, "loss": 0.3126, "step": 20 }, { "epoch": 0.03979156797726196, "grad_norm": 4.5330071449279785, "learning_rate": 0.00013214394653031616, "loss": 0.518, "step": 21 }, { "epoch": 0.04168640454760777, "grad_norm": 2.017454147338867, "learning_rate": 0.00012588190451025207, "loss": 0.3816, "step": 22 }, { "epoch": 0.04358124111795358, "grad_norm": 0.7925994396209717, "learning_rate": 0.00011950903220161285, "loss": 0.3194, "step": 23 }, { "epoch": 0.045476077688299386, "grad_norm": 1.7749615907669067, "learning_rate": 0.00011305261922200519, "loss": 0.3693, "step": 24 }, { "epoch": 0.04737091425864519, "grad_norm": 1.0830832719802856, "learning_rate": 0.00010654031292301432, "loss": 0.3185, "step": 25 }, { "epoch": 0.04737091425864519, "eval_loss": 0.32778090238571167, "eval_runtime": 62.3529, "eval_samples_per_second": 3.576, "eval_steps_per_second": 1.796, "step": 25 }, { "epoch": 0.049265750828991, "grad_norm": 1.4925986528396606, "learning_rate": 0.0001, "loss": 0.3496, "step": 26 }, { "epoch": 0.05116058739933681, "grad_norm": 1.0122554302215576, "learning_rate": 9.345968707698569e-05, "loss": 0.3341, "step": 27 }, { "epoch": 0.053055423969682616, "grad_norm": 2.3204073905944824, "learning_rate": 8.694738077799488e-05, "loss": 0.3444, "step": 28 }, { "epoch": 0.054950260540028426, "grad_norm": 0.687174916267395, "learning_rate": 8.049096779838719e-05, "loss": 0.3201, "step": 29 }, { "epoch": 0.05684509711037423, "grad_norm": 2.4244771003723145, "learning_rate": 7.411809548974792e-05, "loss": 0.2972, "step": 30 }, { "epoch": 0.05873993368072004, "grad_norm": 3.1649410724639893, "learning_rate": 6.785605346968386e-05, "loss": 0.3351, "step": 31 }, { "epoch": 0.060634770251065846, "grad_norm": 4.414581775665283, "learning_rate": 6.173165676349103e-05, "loss": 0.4242, "step": 32 }, { "epoch": 0.06252960682141165, "grad_norm": 4.019096851348877, "learning_rate": 5.577113097809989e-05, "loss": 0.4118, "step": 33 }, { "epoch": 0.06442444339175746, "grad_norm": 2.4438300132751465, "learning_rate": 5.000000000000002e-05, "loss": 0.3164, "step": 34 }, { "epoch": 0.06631927996210327, "grad_norm": 2.3303329944610596, "learning_rate": 4.444297669803981e-05, "loss": 0.3527, "step": 35 }, { "epoch": 0.06821411653244908, "grad_norm": 1.2413207292556763, "learning_rate": 3.9123857099127936e-05, "loss": 0.2543, "step": 36 }, { "epoch": 0.07010895310279489, "grad_norm": 0.9027528166770935, "learning_rate": 3.406541848999312e-05, "loss": 0.26, "step": 37 }, { "epoch": 0.0720037896731407, "grad_norm": 1.1008473634719849, "learning_rate": 2.9289321881345254e-05, "loss": 0.2368, "step": 38 }, { "epoch": 0.0738986262434865, "grad_norm": 1.1780225038528442, "learning_rate": 2.4816019252102273e-05, "loss": 0.2697, "step": 39 }, { "epoch": 0.07579346281383231, "grad_norm": 2.025906562805176, "learning_rate": 2.0664665970876496e-05, "loss": 0.3411, "step": 40 }, { "epoch": 0.07768829938417811, "grad_norm": 2.19376277923584, "learning_rate": 1.6853038769745467e-05, "loss": 0.2697, "step": 41 }, { "epoch": 0.07958313595452392, "grad_norm": 2.385338306427002, "learning_rate": 1.339745962155613e-05, "loss": 0.3528, "step": 42 }, { "epoch": 0.08147797252486973, "grad_norm": 1.4501081705093384, "learning_rate": 1.0312725846731175e-05, "loss": 0.1934, "step": 43 }, { "epoch": 0.08337280909521554, "grad_norm": 1.3427797555923462, "learning_rate": 7.612046748871327e-06, "loss": 0.2357, "step": 44 }, { "epoch": 0.08526764566556135, "grad_norm": 1.3562896251678467, "learning_rate": 5.306987050489442e-06, "loss": 0.3346, "step": 45 }, { "epoch": 0.08716248223590715, "grad_norm": 2.4184749126434326, "learning_rate": 3.40741737109318e-06, "loss": 0.1874, "step": 46 }, { "epoch": 0.08905731880625296, "grad_norm": 2.308922290802002, "learning_rate": 1.921471959676957e-06, "loss": 0.2183, "step": 47 }, { "epoch": 0.09095215537659877, "grad_norm": 2.909156084060669, "learning_rate": 8.555138626189618e-07, "loss": 0.2822, "step": 48 }, { "epoch": 0.09284699194694458, "grad_norm": 2.4265296459198, "learning_rate": 2.141076761396521e-07, "loss": 0.2447, "step": 49 }, { "epoch": 0.09474182851729038, "grad_norm": 1.9471189975738525, "learning_rate": 0.0, "loss": 0.2413, "step": 50 }, { "epoch": 0.09474182851729038, "eval_loss": 0.24849273264408112, "eval_runtime": 62.377, "eval_samples_per_second": 3.575, "eval_steps_per_second": 1.796, "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": 7.41887283560448e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }