{ "best_metric": 0.1398579329252243, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.13635588886995056, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0027271177773990113, "grad_norm": 21.658449172973633, "learning_rate": 5e-05, "loss": 2.9231, "step": 1 }, { "epoch": 0.0027271177773990113, "eval_loss": 2.9426522254943848, "eval_runtime": 64.1272, "eval_samples_per_second": 38.517, "eval_steps_per_second": 4.819, "step": 1 }, { "epoch": 0.005454235554798023, "grad_norm": 21.53768539428711, "learning_rate": 0.0001, "loss": 2.9106, "step": 2 }, { "epoch": 0.008181353332197034, "grad_norm": 19.886701583862305, "learning_rate": 9.989294616193017e-05, "loss": 1.673, "step": 3 }, { "epoch": 0.010908471109596045, "grad_norm": 9.48361873626709, "learning_rate": 9.957224306869053e-05, "loss": 0.5446, "step": 4 }, { "epoch": 0.013635588886995058, "grad_norm": 1.5007044076919556, "learning_rate": 9.903926402016153e-05, "loss": 0.1746, "step": 5 }, { "epoch": 0.01636270666439407, "grad_norm": 9.450408935546875, "learning_rate": 9.829629131445342e-05, "loss": 0.4116, "step": 6 }, { "epoch": 0.01908982444179308, "grad_norm": 7.336299896240234, "learning_rate": 9.73465064747553e-05, "loss": 0.2719, "step": 7 }, { "epoch": 0.02181694221919209, "grad_norm": 4.336707592010498, "learning_rate": 9.619397662556435e-05, "loss": 0.2299, "step": 8 }, { "epoch": 0.0245440599965911, "grad_norm": 1.3587143421173096, "learning_rate": 9.484363707663442e-05, "loss": 0.1498, "step": 9 }, { "epoch": 0.027271177773990116, "grad_norm": 0.9061511158943176, "learning_rate": 9.330127018922194e-05, "loss": 0.1441, "step": 10 }, { "epoch": 0.029998295551389127, "grad_norm": 1.321189045906067, "learning_rate": 9.157348061512727e-05, "loss": 0.1538, "step": 11 }, { "epoch": 0.03272541332878814, "grad_norm": 0.26327088475227356, "learning_rate": 8.966766701456177e-05, "loss": 0.1401, "step": 12 }, { "epoch": 0.03545253110618715, "grad_norm": 1.1897369623184204, "learning_rate": 8.759199037394887e-05, "loss": 0.1502, "step": 13 }, { "epoch": 0.03817964888358616, "grad_norm": 0.77036052942276, "learning_rate": 8.535533905932738e-05, "loss": 0.1472, "step": 14 }, { "epoch": 0.040906766660985174, "grad_norm": 0.8085651397705078, "learning_rate": 8.296729075500344e-05, "loss": 0.1503, "step": 15 }, { "epoch": 0.04363388443838418, "grad_norm": 0.3734496235847473, "learning_rate": 8.043807145043604e-05, "loss": 0.1409, "step": 16 }, { "epoch": 0.046361002215783195, "grad_norm": 0.7530269622802734, "learning_rate": 7.777851165098012e-05, "loss": 0.1494, "step": 17 }, { "epoch": 0.0490881199931822, "grad_norm": 0.06689649075269699, "learning_rate": 7.500000000000001e-05, "loss": 0.1399, "step": 18 }, { "epoch": 0.05181523777058122, "grad_norm": 0.05610128864645958, "learning_rate": 7.211443451095007e-05, "loss": 0.1343, "step": 19 }, { "epoch": 0.05454235554798023, "grad_norm": 0.19992050528526306, "learning_rate": 6.91341716182545e-05, "loss": 0.1307, "step": 20 }, { "epoch": 0.05726947332537924, "grad_norm": 1.1490880250930786, "learning_rate": 6.607197326515808e-05, "loss": 0.1627, "step": 21 }, { "epoch": 0.05999659110277825, "grad_norm": 0.048507459461688995, "learning_rate": 6.294095225512603e-05, "loss": 0.1381, "step": 22 }, { "epoch": 0.06272370888017727, "grad_norm": 0.7477880716323853, "learning_rate": 5.9754516100806423e-05, "loss": 0.1483, "step": 23 }, { "epoch": 0.06545082665757627, "grad_norm": 0.5407776236534119, "learning_rate": 5.6526309611002594e-05, "loss": 0.1416, "step": 24 }, { "epoch": 0.06817794443497528, "grad_norm": 0.16068331897258759, "learning_rate": 5.327015646150716e-05, "loss": 0.1329, "step": 25 }, { "epoch": 0.06817794443497528, "eval_loss": 0.1451548933982849, "eval_runtime": 145.5197, "eval_samples_per_second": 16.974, "eval_steps_per_second": 2.123, "step": 25 }, { "epoch": 0.0709050622123743, "grad_norm": 0.35424989461898804, "learning_rate": 5e-05, "loss": 0.1402, "step": 26 }, { "epoch": 0.07363217998977331, "grad_norm": 0.8786327838897705, "learning_rate": 4.6729843538492847e-05, "loss": 0.1679, "step": 27 }, { "epoch": 0.07635929776717232, "grad_norm": 0.3818786144256592, "learning_rate": 4.347369038899744e-05, "loss": 0.1432, "step": 28 }, { "epoch": 0.07908641554457133, "grad_norm": 0.20813222229480743, "learning_rate": 4.0245483899193595e-05, "loss": 0.1409, "step": 29 }, { "epoch": 0.08181353332197035, "grad_norm": 0.11854073405265808, "learning_rate": 3.705904774487396e-05, "loss": 0.1374, "step": 30 }, { "epoch": 0.08454065109936935, "grad_norm": 0.2889731228351593, "learning_rate": 3.392802673484193e-05, "loss": 0.1413, "step": 31 }, { "epoch": 0.08726776887676836, "grad_norm": 0.2108319252729416, "learning_rate": 3.086582838174551e-05, "loss": 0.1411, "step": 32 }, { "epoch": 0.08999488665416738, "grad_norm": 0.1877073049545288, "learning_rate": 2.7885565489049946e-05, "loss": 0.1409, "step": 33 }, { "epoch": 0.09272200443156639, "grad_norm": 0.16740399599075317, "learning_rate": 2.500000000000001e-05, "loss": 0.1412, "step": 34 }, { "epoch": 0.0954491222089654, "grad_norm": 0.2124919891357422, "learning_rate": 2.2221488349019903e-05, "loss": 0.1409, "step": 35 }, { "epoch": 0.0981762399863644, "grad_norm": 0.12486357986927032, "learning_rate": 1.9561928549563968e-05, "loss": 0.1392, "step": 36 }, { "epoch": 0.10090335776376343, "grad_norm": 0.18787531554698944, "learning_rate": 1.703270924499656e-05, "loss": 0.1371, "step": 37 }, { "epoch": 0.10363047554116243, "grad_norm": 0.04871739074587822, "learning_rate": 1.4644660940672627e-05, "loss": 0.1379, "step": 38 }, { "epoch": 0.10635759331856144, "grad_norm": 0.07164865732192993, "learning_rate": 1.2408009626051137e-05, "loss": 0.139, "step": 39 }, { "epoch": 0.10908471109596046, "grad_norm": 0.04980754479765892, "learning_rate": 1.0332332985438248e-05, "loss": 0.1351, "step": 40 }, { "epoch": 0.11181182887335947, "grad_norm": 0.21772225201129913, "learning_rate": 8.426519384872733e-06, "loss": 0.1418, "step": 41 }, { "epoch": 0.11453894665075848, "grad_norm": 0.25015074014663696, "learning_rate": 6.698729810778065e-06, "loss": 0.1437, "step": 42 }, { "epoch": 0.11726606442815748, "grad_norm": 0.02500380203127861, "learning_rate": 5.156362923365588e-06, "loss": 0.1348, "step": 43 }, { "epoch": 0.1199931822055565, "grad_norm": 0.0305391326546669, "learning_rate": 3.8060233744356633e-06, "loss": 0.1343, "step": 44 }, { "epoch": 0.12272029998295551, "grad_norm": 0.14004138112068176, "learning_rate": 2.653493525244721e-06, "loss": 0.1392, "step": 45 }, { "epoch": 0.12544741776035453, "grad_norm": 0.02942681685090065, "learning_rate": 1.70370868554659e-06, "loss": 0.1334, "step": 46 }, { "epoch": 0.12817453553775354, "grad_norm": 0.19898109138011932, "learning_rate": 9.607359798384785e-07, "loss": 0.1411, "step": 47 }, { "epoch": 0.13090165331515255, "grad_norm": 0.22045519948005676, "learning_rate": 4.277569313094809e-07, "loss": 0.1412, "step": 48 }, { "epoch": 0.13362877109255156, "grad_norm": 0.1419573575258255, "learning_rate": 1.0705383806982606e-07, "loss": 0.1391, "step": 49 }, { "epoch": 0.13635588886995056, "grad_norm": 0.052116479724645615, "learning_rate": 0.0, "loss": 0.1363, "step": 50 }, { "epoch": 0.13635588886995056, "eval_loss": 0.1398579329252243, "eval_runtime": 145.2684, "eval_samples_per_second": 17.003, "eval_steps_per_second": 2.127, "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": 5.259107997057024e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }