| { | |
| "best_metric": 0.06158732250332832, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 1.4328358208955223, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00955223880597015, | |
| "grad_norm": 29.604724884033203, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 11.1334, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00955223880597015, | |
| "eval_loss": 10.308030128479004, | |
| "eval_runtime": 7.207, | |
| "eval_samples_per_second": 6.938, | |
| "eval_steps_per_second": 6.938, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0191044776119403, | |
| "grad_norm": 37.691951751708984, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 10.295, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028656716417910448, | |
| "grad_norm": 40.03203582763672, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 9.8773, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0382089552238806, | |
| "grad_norm": 37.06792068481445, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 7.4423, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04776119402985075, | |
| "grad_norm": 25.62007713317871, | |
| "learning_rate": 0.00015, | |
| "loss": 4.1197, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.057313432835820896, | |
| "grad_norm": 20.416719436645508, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.4344, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06686567164179104, | |
| "grad_norm": 13.990738868713379, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.6984, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0764179104477612, | |
| "grad_norm": 26.440662384033203, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.6423, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08597014925373134, | |
| "grad_norm": 1.5983080863952637, | |
| "learning_rate": 0.00027, | |
| "loss": 0.0198, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0955223880597015, | |
| "grad_norm": 0.14272946119308472, | |
| "learning_rate": 0.0003, | |
| "loss": 0.0022, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10507462686567164, | |
| "grad_norm": 3.5088140964508057, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.0129, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11462686567164179, | |
| "grad_norm": 0.5191304087638855, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.0023, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12417910447761193, | |
| "grad_norm": 0.00615344662219286, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.0002, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13373134328358208, | |
| "grad_norm": 0.007408325094729662, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.0002, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14328358208955225, | |
| "grad_norm": 0.013087390922009945, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.0004, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1528358208955224, | |
| "grad_norm": 0.020046714693307877, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.0005, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16238805970149253, | |
| "grad_norm": 4.9524407386779785, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.0049, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17194029850746267, | |
| "grad_norm": 0.02008659392595291, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.0005, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18149253731343284, | |
| "grad_norm": 0.022405585274100304, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.0005, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.191044776119403, | |
| "grad_norm": 0.015606110915541649, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.0004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20059701492537313, | |
| "grad_norm": 0.014573603868484497, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.0004, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21014925373134327, | |
| "grad_norm": 0.05520666390657425, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.0005, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21970149253731344, | |
| "grad_norm": 0.015050092712044716, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.0003, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22925373134328358, | |
| "grad_norm": 0.017276253551244736, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.0003, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 0.01385075319558382, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.0002, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "eval_loss": 0.5136697292327881, | |
| "eval_runtime": 7.3698, | |
| "eval_samples_per_second": 6.784, | |
| "eval_steps_per_second": 6.784, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24835820895522387, | |
| "grad_norm": 0.003815986216068268, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.0001, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.25791044776119404, | |
| "grad_norm": 132.7102813720703, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 10.3943, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.26746268656716415, | |
| "grad_norm": 1.9110982418060303, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.2244, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2770149253731343, | |
| "grad_norm": 2.235290288925171, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0308, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2865671641791045, | |
| "grad_norm": 0.061887867748737335, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.0014, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2961194029850746, | |
| "grad_norm": 0.09402349591255188, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.0016, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3056716417910448, | |
| "grad_norm": 0.2571331858634949, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.0029, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.31522388059701495, | |
| "grad_norm": 0.0307838823646307, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.0005, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.32477611940298506, | |
| "grad_norm": 0.016969487071037292, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.0003, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.33432835820895523, | |
| "grad_norm": 0.015743907541036606, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.0002, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.34388059701492535, | |
| "grad_norm": 0.010241161100566387, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.0002, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3534328358208955, | |
| "grad_norm": 0.007466515991836786, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.0002, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3629850746268657, | |
| "grad_norm": 0.005754731595516205, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.0002, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3725373134328358, | |
| "grad_norm": 0.004388387314975262, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.0001, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.382089552238806, | |
| "grad_norm": 0.0040399739518761635, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.0001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.39164179104477614, | |
| "grad_norm": 0.003504898166283965, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.0001, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.40119402985074626, | |
| "grad_norm": 0.00304769491776824, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.0001, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.41074626865671643, | |
| "grad_norm": 0.0027260910719633102, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.0001, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.42029850746268654, | |
| "grad_norm": 0.0024885141756385565, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.0001, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4298507462686567, | |
| "grad_norm": 0.002281956607475877, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.0001, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4394029850746269, | |
| "grad_norm": 0.0018665606621652842, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.0001, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.448955223880597, | |
| "grad_norm": 0.001674832310527563, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.0001, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.45850746268656717, | |
| "grad_norm": 0.0015318113146349788, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0001, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.46805970149253734, | |
| "grad_norm": 0.001571908826008439, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.0001, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 0.0012952347751706839, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.0001, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "eval_loss": 0.23288998007774353, | |
| "eval_runtime": 7.3594, | |
| "eval_samples_per_second": 6.794, | |
| "eval_steps_per_second": 6.794, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4871641791044776, | |
| "grad_norm": 0.0012007909826934338, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.49671641791044774, | |
| "grad_norm": 0.0011592863593250513, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.506268656716418, | |
| "grad_norm": 46.191253662109375, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 3.1583, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5158208955223881, | |
| "grad_norm": 74.40240478515625, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.9258, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5253731343283582, | |
| "grad_norm": 0.0414118617773056, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.0002, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5349253731343283, | |
| "grad_norm": 0.8846156001091003, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.0021, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5444776119402985, | |
| "grad_norm": 0.007200995460152626, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.0002, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5540298507462686, | |
| "grad_norm": 22.75172233581543, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.0938, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5635820895522388, | |
| "grad_norm": 0.020017998293042183, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.0004, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.573134328358209, | |
| "grad_norm": 0.039760664105415344, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.0006, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5826865671641791, | |
| "grad_norm": 0.019533224403858185, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.0004, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5922388059701492, | |
| "grad_norm": 0.03347967565059662, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.0005, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.6017910447761194, | |
| "grad_norm": 0.02993916906416416, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.0005, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6113432835820896, | |
| "grad_norm": 0.013049600645899773, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.0003, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6208955223880597, | |
| "grad_norm": 0.008280406706035137, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.0002, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6304477611940299, | |
| "grad_norm": 0.006376465316861868, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.0002, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.0055150194093585014, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.0002, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.6495522388059701, | |
| "grad_norm": 0.004492188338190317, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.0001, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.6591044776119404, | |
| "grad_norm": 0.0042125750333070755, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.0001, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6686567164179105, | |
| "grad_norm": 0.003604372963309288, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.0001, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6782089552238806, | |
| "grad_norm": 0.0029829898849129677, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.0001, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6877611940298507, | |
| "grad_norm": 0.0027445245068520308, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.0001, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6973134328358209, | |
| "grad_norm": 0.0025820331647992134, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.0001, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.706865671641791, | |
| "grad_norm": 0.0014186253538355231, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 0.0013180454261600971, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "eval_loss": 0.0724787563085556, | |
| "eval_runtime": 7.3644, | |
| "eval_samples_per_second": 6.789, | |
| "eval_steps_per_second": 6.789, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7259701492537314, | |
| "grad_norm": 0.0012341466499492526, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.7355223880597015, | |
| "grad_norm": 0.0008805791730992496, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.7450746268656716, | |
| "grad_norm": 0.0008222783799283206, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.7546268656716418, | |
| "grad_norm": 31.767019271850586, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 2.0511, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.764179104477612, | |
| "grad_norm": 3.381103754043579, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.1576, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7737313432835821, | |
| "grad_norm": 0.0009540443425066769, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7832835820895523, | |
| "grad_norm": 0.001079144305549562, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.7928358208955224, | |
| "grad_norm": 0.0013730615610256791, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.0001, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.8023880597014925, | |
| "grad_norm": 0.001953846774995327, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.0001, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.8119402985074626, | |
| "grad_norm": 0.012235262431204319, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.0001, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8214925373134329, | |
| "grad_norm": 0.017554378136992455, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.0002, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.831044776119403, | |
| "grad_norm": 0.025415591895580292, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.0002, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.8405970149253731, | |
| "grad_norm": 0.010554085485637188, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.0001, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.8501492537313433, | |
| "grad_norm": 0.012406528927385807, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.0001, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.8597014925373134, | |
| "grad_norm": 0.008424860425293446, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.0001, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8692537313432835, | |
| "grad_norm": 0.006642926950007677, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.0001, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.8788059701492538, | |
| "grad_norm": 0.003924868535250425, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.0001, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.8883582089552239, | |
| "grad_norm": 0.0025878618471324444, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.0001, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.897910447761194, | |
| "grad_norm": 0.002073967596516013, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.0001, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.9074626865671642, | |
| "grad_norm": 0.0016776231350377202, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.0001, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9170149253731343, | |
| "grad_norm": 0.0012397398240864277, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.9265671641791045, | |
| "grad_norm": 0.0012315617641434073, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.9361194029850747, | |
| "grad_norm": 0.0010754205286502838, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.9456716417910448, | |
| "grad_norm": 0.001088542165234685, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 0.000979114673100412, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "eval_loss": 0.09308185428380966, | |
| "eval_runtime": 7.3775, | |
| "eval_samples_per_second": 6.777, | |
| "eval_steps_per_second": 6.777, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.964776119402985, | |
| "grad_norm": 0.0009638951742090285, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.9743283582089552, | |
| "grad_norm": 0.0008584060706198215, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.9838805970149254, | |
| "grad_norm": 0.0009191096178255975, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.9934328358208955, | |
| "grad_norm": 0.0008119167177937925, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.0029850746268656, | |
| "grad_norm": 7.888625144958496, | |
| "learning_rate": 0.00015, | |
| "loss": 0.6371, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.012537313432836, | |
| "grad_norm": 11.907392501831055, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 1.7248, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.022089552238806, | |
| "grad_norm": 0.002705940045416355, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.0316417910447762, | |
| "grad_norm": 0.0012168614193797112, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.0411940298507463, | |
| "grad_norm": 0.0009762799018062651, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.0507462686567164, | |
| "grad_norm": 0.0009869365021586418, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0602985074626865, | |
| "grad_norm": 0.0013177823275327682, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.0698507462686566, | |
| "grad_norm": 0.0011474322527647018, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.079402985074627, | |
| "grad_norm": 0.0015544156776741147, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.0001, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.088955223880597, | |
| "grad_norm": 0.002088154200464487, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.0001, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.0985074626865672, | |
| "grad_norm": 0.002132783178240061, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.0001, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.1080597014925373, | |
| "grad_norm": 0.010075758211314678, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.0001, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.1176119402985074, | |
| "grad_norm": 0.004856719635426998, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.0001, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.1271641791044775, | |
| "grad_norm": 0.004902370739728212, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.0001, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.1367164179104479, | |
| "grad_norm": 0.0026889245491474867, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.0001, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.146268656716418, | |
| "grad_norm": 0.002710577566176653, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.0001, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.155820895522388, | |
| "grad_norm": 0.002412110799923539, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.0001, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.1653731343283582, | |
| "grad_norm": 0.0020358674228191376, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.0001, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.1749253731343283, | |
| "grad_norm": 0.0016259319381788373, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.0001, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.1844776119402984, | |
| "grad_norm": 0.0015004443703219295, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.0001, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 0.0015228495467454195, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.0001, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "eval_loss": 0.08212555944919586, | |
| "eval_runtime": 7.3806, | |
| "eval_samples_per_second": 6.775, | |
| "eval_steps_per_second": 6.775, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.2035820895522389, | |
| "grad_norm": 0.0013782400637865067, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.0001, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.213134328358209, | |
| "grad_norm": 0.0017314350698143244, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.0001, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.2226865671641791, | |
| "grad_norm": 0.0015217890031635761, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.0001, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.2322388059701492, | |
| "grad_norm": 0.0013981597730889916, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.0001, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.2417910447761193, | |
| "grad_norm": 0.0011965703452005982, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2513432835820897, | |
| "grad_norm": 6.166757583618164, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.5203, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.2608955223880596, | |
| "grad_norm": 7.15877103805542, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.7429, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.27044776119403, | |
| "grad_norm": 0.0012916004052385688, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.0012297456851229072, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.2895522388059701, | |
| "grad_norm": 0.002031672513112426, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.0001, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.2991044776119403, | |
| "grad_norm": 0.01505509577691555, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.0001, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.3086567164179104, | |
| "grad_norm": 0.005438692402094603, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.0001, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.3182089552238807, | |
| "grad_norm": 0.008575469255447388, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.0001, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.3277611940298508, | |
| "grad_norm": 0.025798721238970757, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.0002, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.337313432835821, | |
| "grad_norm": 0.014630038291215897, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.0001, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.346865671641791, | |
| "grad_norm": 0.01390786375850439, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.0001, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.3564179104477612, | |
| "grad_norm": 0.003279446391388774, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.0001, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.3659701492537313, | |
| "grad_norm": 0.0030151065438985825, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.0001, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.3755223880597014, | |
| "grad_norm": 0.007617350667715073, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.0001, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.3850746268656717, | |
| "grad_norm": 0.0024264988023787737, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.3946268656716418, | |
| "grad_norm": 0.004660547710955143, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.0001, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.404179104477612, | |
| "grad_norm": 0.0025053154677152634, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.413731343283582, | |
| "grad_norm": 0.0053937798365950584, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.0001, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.4232835820895522, | |
| "grad_norm": 0.001341644674539566, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 0.0014711751136928797, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "eval_loss": 0.06158732250332832, | |
| "eval_runtime": 7.3739, | |
| "eval_samples_per_second": 6.781, | |
| "eval_steps_per_second": 6.781, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.364806786973696e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |