| { | |
| "best_metric": 0.8565043210983276, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.009915470613023971, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001322062748403196, | |
| "grad_norm": 9.740524291992188, | |
| "learning_rate": 5e-06, | |
| "loss": 28.5912, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001322062748403196, | |
| "eval_loss": 1.562753677368164, | |
| "eval_runtime": 9999.8963, | |
| "eval_samples_per_second": 2.548, | |
| "eval_steps_per_second": 0.637, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002644125496806392, | |
| "grad_norm": 10.005927085876465, | |
| "learning_rate": 1e-05, | |
| "loss": 25.9699, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00039661882452095884, | |
| "grad_norm": 9.001063346862793, | |
| "learning_rate": 1.5e-05, | |
| "loss": 23.1696, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005288250993612784, | |
| "grad_norm": 9.349806785583496, | |
| "learning_rate": 2e-05, | |
| "loss": 25.9893, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006610313742015981, | |
| "grad_norm": 10.730752944946289, | |
| "learning_rate": 2.5e-05, | |
| "loss": 25.5698, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007932376490419177, | |
| "grad_norm": 9.830964088439941, | |
| "learning_rate": 3e-05, | |
| "loss": 25.1505, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009254439238822373, | |
| "grad_norm": 10.586780548095703, | |
| "learning_rate": 3.5e-05, | |
| "loss": 23.8969, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001057650198722557, | |
| "grad_norm": 10.991456985473633, | |
| "learning_rate": 4e-05, | |
| "loss": 21.7006, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011898564735628764, | |
| "grad_norm": 10.33070182800293, | |
| "learning_rate": 4.5e-05, | |
| "loss": 19.3531, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013220627484031961, | |
| "grad_norm": 11.994871139526367, | |
| "learning_rate": 5e-05, | |
| "loss": 20.8966, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014542690232435156, | |
| "grad_norm": 8.332467079162598, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 16.9087, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0015864752980838353, | |
| "grad_norm": 7.184693336486816, | |
| "learning_rate": 6e-05, | |
| "loss": 17.9883, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0017186815729241548, | |
| "grad_norm": 10.19297981262207, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 20.0634, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0018508878477644746, | |
| "grad_norm": 11.294490814208984, | |
| "learning_rate": 7e-05, | |
| "loss": 18.7819, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0019830941226047943, | |
| "grad_norm": 9.1318998336792, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 17.7652, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002115300397445114, | |
| "grad_norm": 8.196518898010254, | |
| "learning_rate": 8e-05, | |
| "loss": 17.3877, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0022475066722854333, | |
| "grad_norm": 7.292929172515869, | |
| "learning_rate": 8.5e-05, | |
| "loss": 15.1944, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002379712947125753, | |
| "grad_norm": 8.115635871887207, | |
| "learning_rate": 9e-05, | |
| "loss": 16.4276, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0025119192219660727, | |
| "grad_norm": 5.500359058380127, | |
| "learning_rate": 9.5e-05, | |
| "loss": 16.1685, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0026441254968063922, | |
| "grad_norm": 5.809587478637695, | |
| "learning_rate": 0.0001, | |
| "loss": 13.4936, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0027763317716467117, | |
| "grad_norm": 6.296661376953125, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 14.7314, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0029085380464870312, | |
| "grad_norm": 5.297625541687012, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 15.7083, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003040744321327351, | |
| "grad_norm": 5.627785682678223, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 13.4142, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0031729505961676707, | |
| "grad_norm": 5.334050178527832, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 13.8942, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00330515687100799, | |
| "grad_norm": 5.117323398590088, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 14.3471, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0034373631458483097, | |
| "grad_norm": 4.972148418426514, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 15.7968, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0035695694206886296, | |
| "grad_norm": 5.201072692871094, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 15.8741, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003701775695528949, | |
| "grad_norm": 5.539172172546387, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 15.6628, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0038339819703692686, | |
| "grad_norm": 5.0465779304504395, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 16.0894, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.003966188245209589, | |
| "grad_norm": 3.873826503753662, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 13.6148, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004098394520049908, | |
| "grad_norm": 5.14940881729126, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 14.1108, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004230600794890228, | |
| "grad_norm": 4.079708576202393, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 15.0809, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004362807069730547, | |
| "grad_norm": 4.550064563751221, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 15.0017, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004495013344570867, | |
| "grad_norm": 4.309603691101074, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 12.8122, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0046272196194111865, | |
| "grad_norm": 4.0590596199035645, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 16.4249, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004759425894251506, | |
| "grad_norm": 3.855443239212036, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 13.3902, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0048916321690918255, | |
| "grad_norm": 4.2185845375061035, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 14.7503, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0050238384439321455, | |
| "grad_norm": 3.751422166824341, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 13.5052, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0051560447187724645, | |
| "grad_norm": 4.427120685577393, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 14.5314, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0052882509936127845, | |
| "grad_norm": 3.970076084136963, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 11.716, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0054204572684531035, | |
| "grad_norm": 4.443355083465576, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 13.1136, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0055526635432934235, | |
| "grad_norm": 3.5732617378234863, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 13.5725, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005684869818133743, | |
| "grad_norm": 4.124619483947754, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 12.9581, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0058170760929740625, | |
| "grad_norm": 4.425747871398926, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 14.8279, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005949282367814382, | |
| "grad_norm": 3.609567403793335, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 14.1364, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006081488642654702, | |
| "grad_norm": 3.978991746902466, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 13.0212, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0062136949174950214, | |
| "grad_norm": 3.3201518058776855, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 13.4931, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006345901192335341, | |
| "grad_norm": 3.9002010822296143, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 15.1584, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0064781074671756604, | |
| "grad_norm": 5.216058254241943, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 13.2532, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.00661031374201598, | |
| "grad_norm": 4.110899925231934, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 15.4582, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00661031374201598, | |
| "eval_loss": 0.8565043210983276, | |
| "eval_runtime": 10039.4222, | |
| "eval_samples_per_second": 2.538, | |
| "eval_steps_per_second": 0.634, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0067425200168563, | |
| "grad_norm": 4.067450046539307, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 12.9902, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.006874726291696619, | |
| "grad_norm": 4.162344455718994, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 14.1395, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.007006932566536939, | |
| "grad_norm": 3.732872486114502, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 14.143, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.007139138841377259, | |
| "grad_norm": 3.6808900833129883, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 12.1621, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.007271345116217578, | |
| "grad_norm": 4.079517841339111, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 14.2904, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.007403551391057898, | |
| "grad_norm": 3.8573484420776367, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 11.8412, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.007535757665898217, | |
| "grad_norm": 4.240724086761475, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 15.1161, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.007667963940738537, | |
| "grad_norm": 4.519715785980225, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 12.7284, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.007800170215578857, | |
| "grad_norm": 3.937958240509033, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 13.8901, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.007932376490419177, | |
| "grad_norm": 4.240633010864258, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 16.1377, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.008064582765259495, | |
| "grad_norm": 3.8049137592315674, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 12.7364, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.008196789040099815, | |
| "grad_norm": 4.874120235443115, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 13.4756, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.008328995314940135, | |
| "grad_norm": 3.806867837905884, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 14.6096, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.008461201589780455, | |
| "grad_norm": 3.8149616718292236, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 13.8567, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.008593407864620775, | |
| "grad_norm": 3.4338436126708984, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 12.3285, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.008725614139461093, | |
| "grad_norm": 3.7605013847351074, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 12.8175, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.008857820414301413, | |
| "grad_norm": 3.6850969791412354, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 14.5401, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.008990026689141733, | |
| "grad_norm": 3.94093656539917, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 14.2592, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.009122232963982053, | |
| "grad_norm": 4.350830554962158, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 15.4778, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.009254439238822373, | |
| "grad_norm": 4.318081855773926, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 16.1385, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.009386645513662693, | |
| "grad_norm": 4.209683418273926, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 13.5816, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.009518851788503011, | |
| "grad_norm": 3.6689677238464355, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 13.6826, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.009651058063343331, | |
| "grad_norm": 3.67459774017334, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 12.583, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.009783264338183651, | |
| "grad_norm": 4.068629741668701, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 13.2489, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.009915470613023971, | |
| "grad_norm": 4.4557976722717285, | |
| "learning_rate": 0.0, | |
| "loss": 12.7368, | |
| "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": 7.72814168653824e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |