| { | |
| "best_metric": 0.7794634103775024, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.030554876558298704, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.11097531165974e-05, | |
| "eval_loss": 1.0963929891586304, | |
| "eval_runtime": 283.1419, | |
| "eval_samples_per_second": 24.334, | |
| "eval_steps_per_second": 6.085, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006110975311659741, | |
| "grad_norm": 0.1534706950187683, | |
| "learning_rate": 4.2000000000000004e-05, | |
| "loss": 1.0834, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012221950623319481, | |
| "grad_norm": 0.1410927176475525, | |
| "learning_rate": 8.400000000000001e-05, | |
| "loss": 0.962, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018332925934979223, | |
| "grad_norm": 0.14470386505126953, | |
| "learning_rate": 0.000126, | |
| "loss": 1.0437, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0024443901246638962, | |
| "grad_norm": 0.1557340919971466, | |
| "learning_rate": 0.00016800000000000002, | |
| "loss": 0.9856, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0030554876558298704, | |
| "grad_norm": 0.14385275542736053, | |
| "learning_rate": 0.00021, | |
| "loss": 1.0426, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0030554876558298704, | |
| "eval_loss": 0.9096205830574036, | |
| "eval_runtime": 283.3102, | |
| "eval_samples_per_second": 24.32, | |
| "eval_steps_per_second": 6.082, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0036665851869958446, | |
| "grad_norm": 0.1434783935546875, | |
| "learning_rate": 0.00020974422527728155, | |
| "loss": 0.8451, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.004277682718161819, | |
| "grad_norm": 0.13006432354450226, | |
| "learning_rate": 0.0002089781472178649, | |
| "loss": 0.8604, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0048887802493277925, | |
| "grad_norm": 0.13252924382686615, | |
| "learning_rate": 0.0002077054980770496, | |
| "loss": 0.8868, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005499877780493767, | |
| "grad_norm": 0.12162353843450546, | |
| "learning_rate": 0.00020593247807352348, | |
| "loss": 0.8893, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006110975311659741, | |
| "grad_norm": 0.1493881493806839, | |
| "learning_rate": 0.00020366772518252038, | |
| "loss": 0.9245, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006110975311659741, | |
| "eval_loss": 0.8621656894683838, | |
| "eval_runtime": 283.2071, | |
| "eval_samples_per_second": 24.328, | |
| "eval_steps_per_second": 6.084, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006722072842825715, | |
| "grad_norm": 0.12663449347019196, | |
| "learning_rate": 0.0002009222730524731, | |
| "loss": 0.8044, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.007333170373991689, | |
| "grad_norm": 0.13809515535831451, | |
| "learning_rate": 0.00019770949725018733, | |
| "loss": 0.852, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.007944267905157664, | |
| "grad_norm": 0.13587471842765808, | |
| "learning_rate": 0.00019404505009642473, | |
| "loss": 0.8401, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.008555365436323637, | |
| "grad_norm": 0.13504283130168915, | |
| "learning_rate": 0.0001899467844093695, | |
| "loss": 0.8743, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.009166462967489611, | |
| "grad_norm": 0.14619627594947815, | |
| "learning_rate": 0.00018543466652749268, | |
| "loss": 0.9113, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.009166462967489611, | |
| "eval_loss": 0.837764322757721, | |
| "eval_runtime": 283.8331, | |
| "eval_samples_per_second": 24.275, | |
| "eval_steps_per_second": 6.07, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.009777560498655585, | |
| "grad_norm": 0.12556147575378418, | |
| "learning_rate": 0.00018053067903555837, | |
| "loss": 0.7812, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.010388658029821559, | |
| "grad_norm": 0.13120540976524353, | |
| "learning_rate": 0.00017525871366768012, | |
| "loss": 0.8049, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.010999755560987534, | |
| "grad_norm": 0.1468738466501236, | |
| "learning_rate": 0.00016964445490919413, | |
| "loss": 0.8328, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.011610853092153508, | |
| "grad_norm": 0.13799065351486206, | |
| "learning_rate": 0.00016371525486442843, | |
| "loss": 0.8505, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.012221950623319482, | |
| "grad_norm": 0.1520494669675827, | |
| "learning_rate": 0.0001575, | |
| "loss": 0.8542, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.012221950623319482, | |
| "eval_loss": 0.8198666572570801, | |
| "eval_runtime": 284.1903, | |
| "eval_samples_per_second": 24.244, | |
| "eval_steps_per_second": 6.063, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.012833048154485455, | |
| "grad_norm": 0.13851197063922882, | |
| "learning_rate": 0.00015102897041285315, | |
| "loss": 0.8161, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.01344414568565143, | |
| "grad_norm": 0.14233830571174622, | |
| "learning_rate": 0.00014433369230867077, | |
| "loss": 0.7929, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.014055243216817405, | |
| "grad_norm": 0.13967365026474, | |
| "learning_rate": 0.0001374467844093695, | |
| "loss": 0.8082, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.014666340747983378, | |
| "grad_norm": 0.14153410494327545, | |
| "learning_rate": 0.0001304017990379651, | |
| "loss": 0.787, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.015277438279149352, | |
| "grad_norm": 0.15393155813217163, | |
| "learning_rate": 0.0001232330586550277, | |
| "loss": 0.8947, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.015277438279149352, | |
| "eval_loss": 0.8052677512168884, | |
| "eval_runtime": 283.3575, | |
| "eval_samples_per_second": 24.316, | |
| "eval_steps_per_second": 6.081, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.015888535810315327, | |
| "grad_norm": 0.15014930069446564, | |
| "learning_rate": 0.00011597548864310363, | |
| "loss": 0.7755, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.0164996333414813, | |
| "grad_norm": 0.14606203138828278, | |
| "learning_rate": 0.00010866444715376263, | |
| "loss": 0.7551, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.017110730872647275, | |
| "grad_norm": 0.14750610291957855, | |
| "learning_rate": 0.00010133555284623744, | |
| "loss": 0.81, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.01772182840381325, | |
| "grad_norm": 0.18205717206001282, | |
| "learning_rate": 9.402451135689641e-05, | |
| "loss": 0.804, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.018332925934979222, | |
| "grad_norm": 0.14796751737594604, | |
| "learning_rate": 8.676694134497232e-05, | |
| "loss": 0.872, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.018332925934979222, | |
| "eval_loss": 0.7966746091842651, | |
| "eval_runtime": 282.5751, | |
| "eval_samples_per_second": 24.383, | |
| "eval_steps_per_second": 6.097, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.018944023466145196, | |
| "grad_norm": 0.13817603886127472, | |
| "learning_rate": 7.95982009620349e-05, | |
| "loss": 0.746, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.01955512099731117, | |
| "grad_norm": 0.14924216270446777, | |
| "learning_rate": 7.255321559063053e-05, | |
| "loss": 0.7323, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.020166218528477144, | |
| "grad_norm": 0.14804905652999878, | |
| "learning_rate": 6.566630769132923e-05, | |
| "loss": 0.8057, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.020777316059643117, | |
| "grad_norm": 0.1513608694076538, | |
| "learning_rate": 5.897102958714686e-05, | |
| "loss": 0.781, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.021388413590809095, | |
| "grad_norm": 0.176563560962677, | |
| "learning_rate": 5.250000000000002e-05, | |
| "loss": 0.8638, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.021388413590809095, | |
| "eval_loss": 0.7875542640686035, | |
| "eval_runtime": 283.0303, | |
| "eval_samples_per_second": 24.344, | |
| "eval_steps_per_second": 6.088, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.02199951112197507, | |
| "grad_norm": 0.13537642359733582, | |
| "learning_rate": 4.62847451355716e-05, | |
| "loss": 0.7125, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.022610608653141042, | |
| "grad_norm": 0.15358619391918182, | |
| "learning_rate": 4.035554509080588e-05, | |
| "loss": 0.7337, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.023221706184307016, | |
| "grad_norm": 0.16124075651168823, | |
| "learning_rate": 3.474128633231992e-05, | |
| "loss": 0.7682, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.02383280371547299, | |
| "grad_norm": 0.15972477197647095, | |
| "learning_rate": 2.946932096444165e-05, | |
| "loss": 0.7327, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.024443901246638963, | |
| "grad_norm": 0.16827918589115143, | |
| "learning_rate": 2.456533347250732e-05, | |
| "loss": 0.819, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.024443901246638963, | |
| "eval_loss": 0.7825099229812622, | |
| "eval_runtime": 284.0898, | |
| "eval_samples_per_second": 24.253, | |
| "eval_steps_per_second": 6.065, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.025054998777804937, | |
| "grad_norm": 0.1699787676334381, | |
| "learning_rate": 2.005321559063053e-05, | |
| "loss": 0.7788, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.02566609630897091, | |
| "grad_norm": 0.16614125669002533, | |
| "learning_rate": 1.5954949903575276e-05, | |
| "loss": 0.7578, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.026277193840136884, | |
| "grad_norm": 0.1688673496246338, | |
| "learning_rate": 1.2290502749812666e-05, | |
| "loss": 0.7544, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.02688829137130286, | |
| "grad_norm": 0.16808409988880157, | |
| "learning_rate": 9.077726947526898e-06, | |
| "loss": 0.8112, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.027499388902468835, | |
| "grad_norm": 0.17651791870594025, | |
| "learning_rate": 6.332274817479627e-06, | |
| "loss": 0.8681, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.027499388902468835, | |
| "eval_loss": 0.7797022461891174, | |
| "eval_runtime": 283.4645, | |
| "eval_samples_per_second": 24.306, | |
| "eval_steps_per_second": 6.078, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.02811048643363481, | |
| "grad_norm": 0.15380319952964783, | |
| "learning_rate": 4.067521926476516e-06, | |
| "loss": 0.7337, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.028721583964800783, | |
| "grad_norm": 0.1493958830833435, | |
| "learning_rate": 2.294501922950403e-06, | |
| "loss": 0.7669, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.029332681495966757, | |
| "grad_norm": 0.1568552553653717, | |
| "learning_rate": 1.021852782135112e-06, | |
| "loss": 0.8023, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.02994377902713273, | |
| "grad_norm": 0.15516310930252075, | |
| "learning_rate": 2.5577472271845927e-07, | |
| "loss": 0.7542, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.030554876558298704, | |
| "grad_norm": 0.15687133371829987, | |
| "learning_rate": 0.0, | |
| "loss": 0.8238, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.030554876558298704, | |
| "eval_loss": 0.7794634103775024, | |
| "eval_runtime": 283.3578, | |
| "eval_samples_per_second": 24.316, | |
| "eval_steps_per_second": 6.081, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 4.130095680926515e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |