{ "best_metric": 1.6783268451690674, "best_model_checkpoint": "miner_id_24/checkpoint-100", "epoch": 0.2770083102493075, "eval_steps": 100, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002770083102493075, "grad_norm": 0.9283442497253418, "learning_rate": 5e-06, "loss": 2.05, "step": 1 }, { "epoch": 0.002770083102493075, "eval_loss": 2.1240499019622803, "eval_runtime": 95.1756, "eval_samples_per_second": 6.388, "eval_steps_per_second": 1.597, "step": 1 }, { "epoch": 0.00554016620498615, "grad_norm": 0.955880343914032, "learning_rate": 1e-05, "loss": 2.0261, "step": 2 }, { "epoch": 0.008310249307479225, "grad_norm": 0.9946913123130798, "learning_rate": 1.5e-05, "loss": 2.0557, "step": 3 }, { "epoch": 0.0110803324099723, "grad_norm": 0.9017006158828735, "learning_rate": 2e-05, "loss": 2.0127, "step": 4 }, { "epoch": 0.013850415512465374, "grad_norm": 1.0481677055358887, "learning_rate": 2.5e-05, "loss": 1.9824, "step": 5 }, { "epoch": 0.01662049861495845, "grad_norm": 0.7929118275642395, "learning_rate": 3e-05, "loss": 2.0085, "step": 6 }, { "epoch": 0.019390581717451522, "grad_norm": 0.7500401139259338, "learning_rate": 3.5e-05, "loss": 1.9579, "step": 7 }, { "epoch": 0.0221606648199446, "grad_norm": 0.6779894232749939, "learning_rate": 4e-05, "loss": 1.9187, "step": 8 }, { "epoch": 0.024930747922437674, "grad_norm": 0.644287645816803, "learning_rate": 4.5e-05, "loss": 1.9291, "step": 9 }, { "epoch": 0.027700831024930747, "grad_norm": 0.6950892806053162, "learning_rate": 5e-05, "loss": 1.9033, "step": 10 }, { "epoch": 0.030470914127423823, "grad_norm": 0.6530030369758606, "learning_rate": 5.500000000000001e-05, "loss": 1.849, "step": 11 }, { "epoch": 0.0332409972299169, "grad_norm": 0.6152698993682861, "learning_rate": 6e-05, "loss": 1.8331, "step": 12 }, { "epoch": 0.036011080332409975, "grad_norm": 0.638900637626648, "learning_rate": 6.500000000000001e-05, "loss": 1.7434, "step": 13 }, { "epoch": 0.038781163434903045, "grad_norm": 0.6423549056053162, "learning_rate": 7e-05, "loss": 1.809, "step": 14 }, { "epoch": 0.04155124653739612, "grad_norm": 0.6707618236541748, "learning_rate": 7.500000000000001e-05, "loss": 1.8022, "step": 15 }, { "epoch": 0.0443213296398892, "grad_norm": 0.6206409335136414, "learning_rate": 8e-05, "loss": 1.7494, "step": 16 }, { "epoch": 0.04709141274238227, "grad_norm": 0.5846340656280518, "learning_rate": 8.5e-05, "loss": 1.7886, "step": 17 }, { "epoch": 0.04986149584487535, "grad_norm": 0.5503649115562439, "learning_rate": 9e-05, "loss": 1.7373, "step": 18 }, { "epoch": 0.05263157894736842, "grad_norm": 0.55040043592453, "learning_rate": 9.5e-05, "loss": 1.7224, "step": 19 }, { "epoch": 0.055401662049861494, "grad_norm": 0.5535205006599426, "learning_rate": 0.0001, "loss": 1.6901, "step": 20 }, { "epoch": 0.05817174515235457, "grad_norm": 0.559658408164978, "learning_rate": 9.999787808528638e-05, "loss": 1.6755, "step": 21 }, { "epoch": 0.060941828254847646, "grad_norm": 0.5673468708992004, "learning_rate": 9.999151252124639e-05, "loss": 1.6903, "step": 22 }, { "epoch": 0.06371191135734072, "grad_norm": 0.5480718612670898, "learning_rate": 9.99809038481674e-05, "loss": 1.8207, "step": 23 }, { "epoch": 0.0664819944598338, "grad_norm": 0.5410633087158203, "learning_rate": 9.996605296647737e-05, "loss": 1.7156, "step": 24 }, { "epoch": 0.06925207756232687, "grad_norm": 0.5444090366363525, "learning_rate": 9.99469611366685e-05, "loss": 1.695, "step": 25 }, { "epoch": 0.07202216066481995, "grad_norm": 0.5443681478500366, "learning_rate": 9.992362997919016e-05, "loss": 1.6809, "step": 26 }, { "epoch": 0.07479224376731301, "grad_norm": 0.5565460920333862, "learning_rate": 9.98960614743114e-05, "loss": 1.7007, "step": 27 }, { "epoch": 0.07756232686980609, "grad_norm": 0.5411592721939087, "learning_rate": 9.986425796195287e-05, "loss": 1.7413, "step": 28 }, { "epoch": 0.08033240997229917, "grad_norm": 0.5616833567619324, "learning_rate": 9.982822214148821e-05, "loss": 1.6731, "step": 29 }, { "epoch": 0.08310249307479224, "grad_norm": 0.5728862881660461, "learning_rate": 9.978795707151492e-05, "loss": 1.7152, "step": 30 }, { "epoch": 0.08587257617728532, "grad_norm": 0.5711526274681091, "learning_rate": 9.974346616959476e-05, "loss": 1.6633, "step": 31 }, { "epoch": 0.0886426592797784, "grad_norm": 0.5852300524711609, "learning_rate": 9.969475321196373e-05, "loss": 1.6699, "step": 32 }, { "epoch": 0.09141274238227147, "grad_norm": 0.5722000598907471, "learning_rate": 9.96418223332115e-05, "loss": 1.6235, "step": 33 }, { "epoch": 0.09418282548476455, "grad_norm": 0.6049830317497253, "learning_rate": 9.958467802593046e-05, "loss": 1.7123, "step": 34 }, { "epoch": 0.09695290858725762, "grad_norm": 0.6205933690071106, "learning_rate": 9.952332514033447e-05, "loss": 1.6483, "step": 35 }, { "epoch": 0.0997229916897507, "grad_norm": 0.5876198410987854, "learning_rate": 9.94577688838472e-05, "loss": 1.6032, "step": 36 }, { "epoch": 0.10249307479224377, "grad_norm": 0.568473756313324, "learning_rate": 9.938801482065998e-05, "loss": 1.6591, "step": 37 }, { "epoch": 0.10526315789473684, "grad_norm": 0.5977758765220642, "learning_rate": 9.93140688712598e-05, "loss": 1.5954, "step": 38 }, { "epoch": 0.10803324099722991, "grad_norm": 0.6168347597122192, "learning_rate": 9.923593731192655e-05, "loss": 1.7199, "step": 39 }, { "epoch": 0.11080332409972299, "grad_norm": 0.567383348941803, "learning_rate": 9.915362677420044e-05, "loss": 1.5559, "step": 40 }, { "epoch": 0.11357340720221606, "grad_norm": 0.5804698467254639, "learning_rate": 9.906714424431913e-05, "loss": 1.595, "step": 41 }, { "epoch": 0.11634349030470914, "grad_norm": 0.6087197661399841, "learning_rate": 9.897649706262473e-05, "loss": 1.6415, "step": 42 }, { "epoch": 0.11911357340720222, "grad_norm": 0.6603733897209167, "learning_rate": 9.888169292294076e-05, "loss": 1.7308, "step": 43 }, { "epoch": 0.12188365650969529, "grad_norm": 0.597120463848114, "learning_rate": 9.87827398719192e-05, "loss": 1.651, "step": 44 }, { "epoch": 0.12465373961218837, "grad_norm": 0.563897967338562, "learning_rate": 9.867964630835743e-05, "loss": 1.5197, "step": 45 }, { "epoch": 0.12742382271468145, "grad_norm": 0.5994200706481934, "learning_rate": 9.857242098248542e-05, "loss": 1.6037, "step": 46 }, { "epoch": 0.13019390581717452, "grad_norm": 0.643892765045166, "learning_rate": 9.846107299522304e-05, "loss": 1.6028, "step": 47 }, { "epoch": 0.1329639889196676, "grad_norm": 0.6362243294715881, "learning_rate": 9.834561179740762e-05, "loss": 1.7313, "step": 48 }, { "epoch": 0.13573407202216067, "grad_norm": 0.8057113885879517, "learning_rate": 9.82260471889917e-05, "loss": 1.8693, "step": 49 }, { "epoch": 0.13850415512465375, "grad_norm": 1.2995071411132812, "learning_rate": 9.810238931821138e-05, "loss": 2.3462, "step": 50 }, { "epoch": 0.14127423822714683, "grad_norm": 0.9156427383422852, "learning_rate": 9.797464868072488e-05, "loss": 1.9039, "step": 51 }, { "epoch": 0.1440443213296399, "grad_norm": 0.7253287434577942, "learning_rate": 9.784283611872169e-05, "loss": 1.7885, "step": 52 }, { "epoch": 0.14681440443213298, "grad_norm": 0.5801952481269836, "learning_rate": 9.770696282000244e-05, "loss": 1.7586, "step": 53 }, { "epoch": 0.14958448753462603, "grad_norm": 0.48791196942329407, "learning_rate": 9.756704031702918e-05, "loss": 1.7201, "step": 54 }, { "epoch": 0.1523545706371191, "grad_norm": 0.47324320673942566, "learning_rate": 9.742308048594665e-05, "loss": 1.7283, "step": 55 }, { "epoch": 0.15512465373961218, "grad_norm": 0.44494226574897766, "learning_rate": 9.727509554557417e-05, "loss": 1.7024, "step": 56 }, { "epoch": 0.15789473684210525, "grad_norm": 0.45924824476242065, "learning_rate": 9.712309805636863e-05, "loss": 1.6947, "step": 57 }, { "epoch": 0.16066481994459833, "grad_norm": 0.5117136240005493, "learning_rate": 9.696710091935841e-05, "loss": 1.7821, "step": 58 }, { "epoch": 0.1634349030470914, "grad_norm": 0.4841713607311249, "learning_rate": 9.68071173750483e-05, "loss": 1.6528, "step": 59 }, { "epoch": 0.16620498614958448, "grad_norm": 0.4830092787742615, "learning_rate": 9.664316100229578e-05, "loss": 1.7166, "step": 60 }, { "epoch": 0.16897506925207756, "grad_norm": 0.4221424162387848, "learning_rate": 9.647524571715843e-05, "loss": 1.6441, "step": 61 }, { "epoch": 0.17174515235457063, "grad_norm": 0.4262312650680542, "learning_rate": 9.630338577171282e-05, "loss": 1.6742, "step": 62 }, { "epoch": 0.1745152354570637, "grad_norm": 0.4470296800136566, "learning_rate": 9.612759575284483e-05, "loss": 1.6873, "step": 63 }, { "epoch": 0.1772853185595568, "grad_norm": 0.43828487396240234, "learning_rate": 9.594789058101153e-05, "loss": 1.6717, "step": 64 }, { "epoch": 0.18005540166204986, "grad_norm": 0.44721511006355286, "learning_rate": 9.576428550897489e-05, "loss": 1.6437, "step": 65 }, { "epoch": 0.18282548476454294, "grad_norm": 0.4734845459461212, "learning_rate": 9.557679612050708e-05, "loss": 1.617, "step": 66 }, { "epoch": 0.18559556786703602, "grad_norm": 0.4750541150569916, "learning_rate": 9.538543832906773e-05, "loss": 1.6971, "step": 67 }, { "epoch": 0.1883656509695291, "grad_norm": 0.45159047842025757, "learning_rate": 9.519022837645337e-05, "loss": 1.6612, "step": 68 }, { "epoch": 0.19113573407202217, "grad_norm": 0.45829257369041443, "learning_rate": 9.499118283141887e-05, "loss": 1.5972, "step": 69 }, { "epoch": 0.19390581717451524, "grad_norm": 0.49154049158096313, "learning_rate": 9.478831858827104e-05, "loss": 1.6616, "step": 70 }, { "epoch": 0.19667590027700832, "grad_norm": 0.47941017150878906, "learning_rate": 9.458165286543476e-05, "loss": 1.6312, "step": 71 }, { "epoch": 0.1994459833795014, "grad_norm": 0.47044363617897034, "learning_rate": 9.437120320399158e-05, "loss": 1.6031, "step": 72 }, { "epoch": 0.20221606648199447, "grad_norm": 0.4906218349933624, "learning_rate": 9.415698746619079e-05, "loss": 1.6558, "step": 73 }, { "epoch": 0.20498614958448755, "grad_norm": 0.46305832266807556, "learning_rate": 9.393902383393347e-05, "loss": 1.626, "step": 74 }, { "epoch": 0.2077562326869806, "grad_norm": 0.4860275983810425, "learning_rate": 9.371733080722911e-05, "loss": 1.6518, "step": 75 }, { "epoch": 0.21052631578947367, "grad_norm": 0.49080756306648254, "learning_rate": 9.349192720262555e-05, "loss": 1.5951, "step": 76 }, { "epoch": 0.21329639889196675, "grad_norm": 0.512401282787323, "learning_rate": 9.326283215161178e-05, "loss": 1.5436, "step": 77 }, { "epoch": 0.21606648199445982, "grad_norm": 0.48431679606437683, "learning_rate": 9.303006509899418e-05, "loss": 1.693, "step": 78 }, { "epoch": 0.2188365650969529, "grad_norm": 0.5012890696525574, "learning_rate": 9.279364580124614e-05, "loss": 1.6496, "step": 79 }, { "epoch": 0.22160664819944598, "grad_norm": 0.5362542867660522, "learning_rate": 9.255359432483105e-05, "loss": 1.5378, "step": 80 }, { "epoch": 0.22437673130193905, "grad_norm": 0.5153225660324097, "learning_rate": 9.230993104449939e-05, "loss": 1.5482, "step": 81 }, { "epoch": 0.22714681440443213, "grad_norm": 0.5314464569091797, "learning_rate": 9.206267664155907e-05, "loss": 1.6165, "step": 82 }, { "epoch": 0.2299168975069252, "grad_norm": 0.5320023894309998, "learning_rate": 9.181185210212034e-05, "loss": 1.5757, "step": 83 }, { "epoch": 0.23268698060941828, "grad_norm": 0.542969286441803, "learning_rate": 9.155747871531444e-05, "loss": 1.5714, "step": 84 }, { "epoch": 0.23545706371191136, "grad_norm": 0.5345393419265747, "learning_rate": 9.129957807148666e-05, "loss": 1.5333, "step": 85 }, { "epoch": 0.23822714681440443, "grad_norm": 0.5255215167999268, "learning_rate": 9.103817206036382e-05, "loss": 1.5549, "step": 86 }, { "epoch": 0.2409972299168975, "grad_norm": 0.5266215801239014, "learning_rate": 9.077328286919638e-05, "loss": 1.5857, "step": 87 }, { "epoch": 0.24376731301939059, "grad_norm": 0.5361652374267578, "learning_rate": 9.050493298087523e-05, "loss": 1.5605, "step": 88 }, { "epoch": 0.24653739612188366, "grad_norm": 0.5425163507461548, "learning_rate": 9.02331451720234e-05, "loss": 1.6093, "step": 89 }, { "epoch": 0.24930747922437674, "grad_norm": 0.5160465240478516, "learning_rate": 8.995794251106295e-05, "loss": 1.5442, "step": 90 }, { "epoch": 0.2520775623268698, "grad_norm": 0.5372593998908997, "learning_rate": 8.967934835625689e-05, "loss": 1.5728, "step": 91 }, { "epoch": 0.2548476454293629, "grad_norm": 0.5655612349510193, "learning_rate": 8.939738635372664e-05, "loss": 1.5368, "step": 92 }, { "epoch": 0.25761772853185594, "grad_norm": 0.5733644366264343, "learning_rate": 8.911208043544513e-05, "loss": 1.5212, "step": 93 }, { "epoch": 0.26038781163434904, "grad_norm": 0.5658868551254272, "learning_rate": 8.882345481720533e-05, "loss": 1.5177, "step": 94 }, { "epoch": 0.2631578947368421, "grad_norm": 0.5318059325218201, "learning_rate": 8.853153399656513e-05, "loss": 1.5302, "step": 95 }, { "epoch": 0.2659279778393352, "grad_norm": 0.5699280500411987, "learning_rate": 8.823634275076791e-05, "loss": 1.544, "step": 96 }, { "epoch": 0.26869806094182824, "grad_norm": 0.6027292013168335, "learning_rate": 8.793790613463955e-05, "loss": 1.5461, "step": 97 }, { "epoch": 0.27146814404432135, "grad_norm": 0.6108666062355042, "learning_rate": 8.763624947846195e-05, "loss": 1.5956, "step": 98 }, { "epoch": 0.2742382271468144, "grad_norm": 0.7130281329154968, "learning_rate": 8.7331398385823e-05, "loss": 1.6505, "step": 99 }, { "epoch": 0.2770083102493075, "grad_norm": 1.1027400493621826, "learning_rate": 8.702337873144343e-05, "loss": 2.2798, "step": 100 }, { "epoch": 0.2770083102493075, "eval_loss": 1.6783268451690674, "eval_runtime": 96.3073, "eval_samples_per_second": 6.313, "eval_steps_per_second": 1.578, "step": 100 } ], "logging_steps": 1, "max_steps": 361, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "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": false }, "attributes": {} } }, "total_flos": 1.427158308225024e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }