| { | |
| "best_metric": 0.6350438594818115, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.48661800486618007, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006488240064882401, | |
| "grad_norm": 4.320489406585693, | |
| "learning_rate": 5e-06, | |
| "loss": 2.9741, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006488240064882401, | |
| "eval_loss": 3.211296558380127, | |
| "eval_runtime": 82.1902, | |
| "eval_samples_per_second": 6.315, | |
| "eval_steps_per_second": 0.791, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012976480129764802, | |
| "grad_norm": 4.5113701820373535, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0388, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019464720194647202, | |
| "grad_norm": 4.6927714347839355, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.9837, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.025952960259529603, | |
| "grad_norm": 4.680801868438721, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2726, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.032441200324412, | |
| "grad_norm": 5.522418022155762, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.4348, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.038929440389294405, | |
| "grad_norm": 4.993494987487793, | |
| "learning_rate": 3e-05, | |
| "loss": 3.0498, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0454176804541768, | |
| "grad_norm": 4.6689133644104, | |
| "learning_rate": 3.5e-05, | |
| "loss": 2.6851, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05190592051905921, | |
| "grad_norm": 5.748671054840088, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7684, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.058394160583941604, | |
| "grad_norm": 6.775564670562744, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.3901, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.064882400648824, | |
| "grad_norm": 6.568486213684082, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9956, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07137064071370641, | |
| "grad_norm": 4.80515718460083, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.5494, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07785888077858881, | |
| "grad_norm": 4.092294692993164, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2444, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08434712084347121, | |
| "grad_norm": 2.87087345123291, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.0718, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0908353609083536, | |
| "grad_norm": 4.096825122833252, | |
| "learning_rate": 7e-05, | |
| "loss": 1.0977, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09732360097323602, | |
| "grad_norm": 4.781303405761719, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.98, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10381184103811841, | |
| "grad_norm": 3.2860639095306396, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9196, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11030008110300081, | |
| "grad_norm": 2.540112257003784, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.7389, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11678832116788321, | |
| "grad_norm": 2.675224542617798, | |
| "learning_rate": 9e-05, | |
| "loss": 0.6798, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12327656123276562, | |
| "grad_norm": 2.5746631622314453, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.6886, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.129764801297648, | |
| "grad_norm": 2.6324894428253174, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8362, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1362530413625304, | |
| "grad_norm": 2.355058193206787, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 0.8848, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14274128142741282, | |
| "grad_norm": 2.648463010787964, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.6325, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1492295214922952, | |
| "grad_norm": 2.4602627754211426, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 0.7505, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15571776155717762, | |
| "grad_norm": 1.898608922958374, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 0.6155, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16220600162206, | |
| "grad_norm": 1.9833636283874512, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.5744, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16869424168694241, | |
| "grad_norm": 2.158081293106079, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 0.695, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.17518248175182483, | |
| "grad_norm": 1.8228775262832642, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 0.638, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1816707218167072, | |
| "grad_norm": 1.7093753814697266, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 0.6839, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18815896188158962, | |
| "grad_norm": 1.9845768213272095, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 0.6063, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.19464720194647203, | |
| "grad_norm": 2.0481371879577637, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.7076, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20113544201135442, | |
| "grad_norm": 1.6540613174438477, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.6592, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.20762368207623683, | |
| "grad_norm": 1.7876536846160889, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 0.6407, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2141119221411192, | |
| "grad_norm": 1.8859717845916748, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 0.7916, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.22060016220600162, | |
| "grad_norm": 1.7074021100997925, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 0.482, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22708840227088403, | |
| "grad_norm": 1.5708434581756592, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.5889, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23357664233576642, | |
| "grad_norm": 1.7154409885406494, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 0.8398, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24006488240064883, | |
| "grad_norm": 1.9261146783828735, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 0.8207, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24655312246553124, | |
| "grad_norm": 1.4875516891479492, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 0.5842, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.25304136253041365, | |
| "grad_norm": 1.426688551902771, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 0.5933, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.259529602595296, | |
| "grad_norm": 1.401323914527893, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.5723, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2660178426601784, | |
| "grad_norm": 1.319161057472229, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 0.5813, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2725060827250608, | |
| "grad_norm": 1.4045952558517456, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.5935, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.27899432278994324, | |
| "grad_norm": 1.974134087562561, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 0.6298, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.28548256285482565, | |
| "grad_norm": 1.4510246515274048, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 0.5674, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 1.4368536472320557, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.7143, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2984590429845904, | |
| "grad_norm": 1.5513255596160889, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 0.5459, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.30494728304947283, | |
| "grad_norm": 1.2531628608703613, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 0.6001, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.31143552311435524, | |
| "grad_norm": 1.6614936590194702, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 0.7361, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.31792376317923765, | |
| "grad_norm": 1.7235716581344604, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 0.7437, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.32441200324412, | |
| "grad_norm": 1.3541579246520996, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.6751, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32441200324412, | |
| "eval_loss": 0.6350438594818115, | |
| "eval_runtime": 82.5647, | |
| "eval_samples_per_second": 6.286, | |
| "eval_steps_per_second": 0.787, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3309002433090024, | |
| "grad_norm": 1.1093209981918335, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 0.4294, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.33738848337388483, | |
| "grad_norm": 1.7794939279556274, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 0.5775, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.34387672343876724, | |
| "grad_norm": 1.381375789642334, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.6621, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.35036496350364965, | |
| "grad_norm": 1.4836828708648682, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 0.7448, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.35685320356853206, | |
| "grad_norm": 1.253775954246521, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.5938, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3633414436334144, | |
| "grad_norm": 1.5513309240341187, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 0.6217, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.36982968369829683, | |
| "grad_norm": 1.777928352355957, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 0.5749, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.37631792376317924, | |
| "grad_norm": 1.605820655822754, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 0.6827, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.38280616382806165, | |
| "grad_norm": 1.2288376092910767, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 0.5258, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.38929440389294406, | |
| "grad_norm": 1.3616653680801392, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.5963, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3957826439578264, | |
| "grad_norm": 1.4875752925872803, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 0.6351, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.40227088402270883, | |
| "grad_norm": 1.4477332830429077, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 0.5471, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.40875912408759124, | |
| "grad_norm": 1.8846336603164673, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 0.7482, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.41524736415247365, | |
| "grad_norm": 1.851898431777954, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.6356, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.42173560421735606, | |
| "grad_norm": 1.6405341625213623, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.7012, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4282238442822384, | |
| "grad_norm": 1.5401231050491333, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 0.5817, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.43471208434712083, | |
| "grad_norm": 1.2834601402282715, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 0.6662, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.44120032441200324, | |
| "grad_norm": 1.7023755311965942, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 0.7074, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.44768856447688565, | |
| "grad_norm": 1.2349250316619873, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 0.5058, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.45417680454176806, | |
| "grad_norm": 1.5026576519012451, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.7246, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4606650446066504, | |
| "grad_norm": 1.2308121919631958, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 0.7091, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.46715328467153283, | |
| "grad_norm": 1.6818972826004028, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 0.6945, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.47364152473641524, | |
| "grad_norm": 1.253867268562317, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 0.5318, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.48012976480129765, | |
| "grad_norm": 1.5630402565002441, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 0.7055, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.48661800486618007, | |
| "grad_norm": 1.377374291419983, | |
| "learning_rate": 0.0, | |
| "loss": 0.5693, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.451323701362688e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |