{ "best_metric": 0.34431764483451843, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.017562346329469618, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00035124692658939234, "grad_norm": 32.33164596557617, "learning_rate": 5e-05, "loss": 7.295, "step": 1 }, { "epoch": 0.00035124692658939234, "eval_loss": 6.720856666564941, "eval_runtime": 156.451, "eval_samples_per_second": 122.594, "eval_steps_per_second": 15.327, "step": 1 }, { "epoch": 0.0007024938531787847, "grad_norm": 20.42613983154297, "learning_rate": 0.0001, "loss": 5.6671, "step": 2 }, { "epoch": 0.001053740779768177, "grad_norm": 17.6084041595459, "learning_rate": 9.989294616193017e-05, "loss": 5.0421, "step": 3 }, { "epoch": 0.0014049877063575693, "grad_norm": 12.435327529907227, "learning_rate": 9.957224306869053e-05, "loss": 3.7242, "step": 4 }, { "epoch": 0.0017562346329469617, "grad_norm": 7.746137619018555, "learning_rate": 9.903926402016153e-05, "loss": 2.4652, "step": 5 }, { "epoch": 0.002107481559536354, "grad_norm": 6.379279613494873, "learning_rate": 9.829629131445342e-05, "loss": 2.0208, "step": 6 }, { "epoch": 0.0024587284861257463, "grad_norm": 5.064046382904053, "learning_rate": 9.73465064747553e-05, "loss": 1.9224, "step": 7 }, { "epoch": 0.0028099754127151387, "grad_norm": 3.3626673221588135, "learning_rate": 9.619397662556435e-05, "loss": 1.6533, "step": 8 }, { "epoch": 0.003161222339304531, "grad_norm": 3.397329807281494, "learning_rate": 9.484363707663442e-05, "loss": 1.6428, "step": 9 }, { "epoch": 0.0035124692658939235, "grad_norm": 2.8703525066375732, "learning_rate": 9.330127018922194e-05, "loss": 1.463, "step": 10 }, { "epoch": 0.003863716192483316, "grad_norm": 2.8161332607269287, "learning_rate": 9.157348061512727e-05, "loss": 1.4809, "step": 11 }, { "epoch": 0.004214963119072708, "grad_norm": 3.1667091846466064, "learning_rate": 8.966766701456177e-05, "loss": 1.4349, "step": 12 }, { "epoch": 0.0045662100456621, "grad_norm": 9.532793998718262, "learning_rate": 8.759199037394887e-05, "loss": 2.3772, "step": 13 }, { "epoch": 0.004917456972251493, "grad_norm": 9.30787467956543, "learning_rate": 8.535533905932738e-05, "loss": 2.2553, "step": 14 }, { "epoch": 0.005268703898840885, "grad_norm": 3.823763370513916, "learning_rate": 8.296729075500344e-05, "loss": 1.2486, "step": 15 }, { "epoch": 0.005619950825430277, "grad_norm": 2.9557015895843506, "learning_rate": 8.043807145043604e-05, "loss": 1.2194, "step": 16 }, { "epoch": 0.00597119775201967, "grad_norm": 2.5102148056030273, "learning_rate": 7.777851165098012e-05, "loss": 1.0607, "step": 17 }, { "epoch": 0.006322444678609062, "grad_norm": 2.5833821296691895, "learning_rate": 7.500000000000001e-05, "loss": 1.0379, "step": 18 }, { "epoch": 0.0066736916051984545, "grad_norm": 2.5676543712615967, "learning_rate": 7.211443451095007e-05, "loss": 0.8999, "step": 19 }, { "epoch": 0.007024938531787847, "grad_norm": 2.8049817085266113, "learning_rate": 6.91341716182545e-05, "loss": 0.8568, "step": 20 }, { "epoch": 0.007376185458377239, "grad_norm": 3.0544097423553467, "learning_rate": 6.607197326515808e-05, "loss": 0.903, "step": 21 }, { "epoch": 0.007727432384966632, "grad_norm": 4.006994247436523, "learning_rate": 6.294095225512603e-05, "loss": 0.9096, "step": 22 }, { "epoch": 0.008078679311556024, "grad_norm": 3.790771245956421, "learning_rate": 5.9754516100806423e-05, "loss": 0.7895, "step": 23 }, { "epoch": 0.008429926238145416, "grad_norm": 4.485472679138184, "learning_rate": 5.6526309611002594e-05, "loss": 0.7663, "step": 24 }, { "epoch": 0.008781173164734809, "grad_norm": 5.253767967224121, "learning_rate": 5.327015646150716e-05, "loss": 0.7798, "step": 25 }, { "epoch": 0.008781173164734809, "eval_loss": 0.7907594442367554, "eval_runtime": 156.0209, "eval_samples_per_second": 122.932, "eval_steps_per_second": 15.37, "step": 25 }, { "epoch": 0.0091324200913242, "grad_norm": 9.727386474609375, "learning_rate": 5e-05, "loss": 1.3832, "step": 26 }, { "epoch": 0.009483667017913594, "grad_norm": 3.473416805267334, "learning_rate": 4.6729843538492847e-05, "loss": 0.7419, "step": 27 }, { "epoch": 0.009834913944502985, "grad_norm": 3.7304646968841553, "learning_rate": 4.347369038899744e-05, "loss": 0.6936, "step": 28 }, { "epoch": 0.010186160871092378, "grad_norm": 4.400600433349609, "learning_rate": 4.0245483899193595e-05, "loss": 0.727, "step": 29 }, { "epoch": 0.01053740779768177, "grad_norm": 3.219212293624878, "learning_rate": 3.705904774487396e-05, "loss": 0.5337, "step": 30 }, { "epoch": 0.010888654724271163, "grad_norm": 3.264662742614746, "learning_rate": 3.392802673484193e-05, "loss": 0.4812, "step": 31 }, { "epoch": 0.011239901650860555, "grad_norm": 3.56425142288208, "learning_rate": 3.086582838174551e-05, "loss": 0.4327, "step": 32 }, { "epoch": 0.011591148577449948, "grad_norm": 3.1250643730163574, "learning_rate": 2.7885565489049946e-05, "loss": 0.41, "step": 33 }, { "epoch": 0.01194239550403934, "grad_norm": 4.0995025634765625, "learning_rate": 2.500000000000001e-05, "loss": 0.4297, "step": 34 }, { "epoch": 0.012293642430628733, "grad_norm": 4.862830638885498, "learning_rate": 2.2221488349019903e-05, "loss": 0.3674, "step": 35 }, { "epoch": 0.012644889357218124, "grad_norm": 4.865777492523193, "learning_rate": 1.9561928549563968e-05, "loss": 0.3747, "step": 36 }, { "epoch": 0.012996136283807516, "grad_norm": 6.4057297706604, "learning_rate": 1.703270924499656e-05, "loss": 0.3631, "step": 37 }, { "epoch": 0.013347383210396909, "grad_norm": 6.418877601623535, "learning_rate": 1.4644660940672627e-05, "loss": 0.566, "step": 38 }, { "epoch": 0.0136986301369863, "grad_norm": 8.97852611541748, "learning_rate": 1.2408009626051137e-05, "loss": 0.7829, "step": 39 }, { "epoch": 0.014049877063575694, "grad_norm": 3.1506459712982178, "learning_rate": 1.0332332985438248e-05, "loss": 0.3834, "step": 40 }, { "epoch": 0.014401123990165085, "grad_norm": 2.6444480419158936, "learning_rate": 8.426519384872733e-06, "loss": 0.276, "step": 41 }, { "epoch": 0.014752370916754479, "grad_norm": 3.4384701251983643, "learning_rate": 6.698729810778065e-06, "loss": 0.2862, "step": 42 }, { "epoch": 0.01510361784334387, "grad_norm": 3.31412410736084, "learning_rate": 5.156362923365588e-06, "loss": 0.2387, "step": 43 }, { "epoch": 0.015454864769933263, "grad_norm": 3.034747838973999, "learning_rate": 3.8060233744356633e-06, "loss": 0.2058, "step": 44 }, { "epoch": 0.015806111696522657, "grad_norm": 3.0769245624542236, "learning_rate": 2.653493525244721e-06, "loss": 0.2244, "step": 45 }, { "epoch": 0.016157358623112048, "grad_norm": 3.2714991569519043, "learning_rate": 1.70370868554659e-06, "loss": 0.206, "step": 46 }, { "epoch": 0.01650860554970144, "grad_norm": 3.8294384479522705, "learning_rate": 9.607359798384785e-07, "loss": 0.2396, "step": 47 }, { "epoch": 0.01685985247629083, "grad_norm": 4.286280632019043, "learning_rate": 4.277569313094809e-07, "loss": 0.2454, "step": 48 }, { "epoch": 0.017211099402880226, "grad_norm": 4.210233688354492, "learning_rate": 1.0705383806982606e-07, "loss": 0.2245, "step": 49 }, { "epoch": 0.017562346329469618, "grad_norm": 7.076987266540527, "learning_rate": 0.0, "loss": 0.306, "step": 50 }, { "epoch": 0.017562346329469618, "eval_loss": 0.34431764483451843, "eval_runtime": 157.5906, "eval_samples_per_second": 121.708, "eval_steps_per_second": 15.217, "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": 3.216011515920384e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }