| { | |
| "best_metric": 1.6035598516464233, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.0338863395693611, | |
| "eval_steps": 10, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002823861630780092, | |
| "grad_norm": 1.2318695783615112, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0472, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002823861630780092, | |
| "eval_loss": 2.352551221847534, | |
| "eval_runtime": 134.4924, | |
| "eval_samples_per_second": 5.547, | |
| "eval_steps_per_second": 5.547, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005647723261560184, | |
| "grad_norm": 3.381352663040161, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7995, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008471584892340275, | |
| "grad_norm": 0.7312057018280029, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1274, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011295446523120368, | |
| "grad_norm": 1.382169485092163, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0301, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014119308153900459, | |
| "grad_norm": 1.6353622674942017, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7291, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001694316978468055, | |
| "grad_norm": 0.6910256147384644, | |
| "learning_rate": 0.00012, | |
| "loss": 2.8307, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001976703141546064, | |
| "grad_norm": 1.4815878868103027, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0774, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022590893046240735, | |
| "grad_norm": 1.042596459388733, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6145, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025414754677020824, | |
| "grad_norm": 0.8719121217727661, | |
| "learning_rate": 0.00018, | |
| "loss": 2.9212, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028238616307800918, | |
| "grad_norm": 1.0421559810638428, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3507, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028238616307800918, | |
| "eval_loss": 2.1853621006011963, | |
| "eval_runtime": 133.969, | |
| "eval_samples_per_second": 5.568, | |
| "eval_steps_per_second": 5.568, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003106247793858101, | |
| "grad_norm": 0.9601467847824097, | |
| "learning_rate": 0.0001999979446958366, | |
| "loss": 1.9811, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00338863395693611, | |
| "grad_norm": 1.353819489479065, | |
| "learning_rate": 0.00019999177886783194, | |
| "loss": 2.373, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0036710201200141194, | |
| "grad_norm": 0.897077202796936, | |
| "learning_rate": 0.00019998150276943902, | |
| "loss": 1.696, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003953406283092128, | |
| "grad_norm": 1.358173131942749, | |
| "learning_rate": 0.000199967116823068, | |
| "loss": 2.3396, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004235792446170138, | |
| "grad_norm": 1.0444282293319702, | |
| "learning_rate": 0.0001999486216200688, | |
| "loss": 1.482, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004518178609248147, | |
| "grad_norm": 3.5194482803344727, | |
| "learning_rate": 0.00019992601792070679, | |
| "loss": 1.6677, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004800564772326156, | |
| "grad_norm": 3.523196220397949, | |
| "learning_rate": 0.00019989930665413147, | |
| "loss": 2.393, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005082950935404165, | |
| "grad_norm": 0.9800947904586792, | |
| "learning_rate": 0.00019986848891833845, | |
| "loss": 1.6947, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005365337098482174, | |
| "grad_norm": 1.540337324142456, | |
| "learning_rate": 0.0001998335659801241, | |
| "loss": 0.563, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0056477232615601836, | |
| "grad_norm": 1.577869176864624, | |
| "learning_rate": 0.00019979453927503364, | |
| "loss": 2.0525, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0056477232615601836, | |
| "eval_loss": 1.7350926399230957, | |
| "eval_runtime": 133.9613, | |
| "eval_samples_per_second": 5.569, | |
| "eval_steps_per_second": 5.569, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005930109424638193, | |
| "grad_norm": 0.876990020275116, | |
| "learning_rate": 0.00019975141040730207, | |
| "loss": 1.2469, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006212495587716202, | |
| "grad_norm": 1.1722772121429443, | |
| "learning_rate": 0.0001997041811497882, | |
| "loss": 2.2798, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006494881750794211, | |
| "grad_norm": 0.9232650995254517, | |
| "learning_rate": 0.00019965285344390184, | |
| "loss": 2.5319, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00677726791387222, | |
| "grad_norm": 1.6948198080062866, | |
| "learning_rate": 0.00019959742939952392, | |
| "loss": 1.6864, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0070596540769502295, | |
| "grad_norm": 1.277117133140564, | |
| "learning_rate": 0.00019953791129491983, | |
| "loss": 2.1785, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007342040240028239, | |
| "grad_norm": 3.347221851348877, | |
| "learning_rate": 0.00019947430157664576, | |
| "loss": 1.5917, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007624426403106248, | |
| "grad_norm": 1.2190711498260498, | |
| "learning_rate": 0.00019940660285944803, | |
| "loss": 2.3655, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007906812566184257, | |
| "grad_norm": 1.9080499410629272, | |
| "learning_rate": 0.00019933481792615583, | |
| "loss": 2.0602, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008189198729262267, | |
| "grad_norm": 1.5589416027069092, | |
| "learning_rate": 0.0001992589497275665, | |
| "loss": 1.9817, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008471584892340275, | |
| "grad_norm": 2.701538562774658, | |
| "learning_rate": 0.0001991790013823246, | |
| "loss": 1.434, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008471584892340275, | |
| "eval_loss": 1.6901509761810303, | |
| "eval_runtime": 134.7409, | |
| "eval_samples_per_second": 5.537, | |
| "eval_steps_per_second": 5.537, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008753971055418284, | |
| "grad_norm": 1.0493268966674805, | |
| "learning_rate": 0.00019909497617679348, | |
| "loss": 2.413, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009036357218496294, | |
| "grad_norm": 1.5526515245437622, | |
| "learning_rate": 0.0001990068775649202, | |
| "loss": 2.2275, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009318743381574303, | |
| "grad_norm": 1.4149539470672607, | |
| "learning_rate": 0.00019891470916809362, | |
| "loss": 2.4908, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009601129544652313, | |
| "grad_norm": 1.2589884996414185, | |
| "learning_rate": 0.00019881847477499557, | |
| "loss": 1.7045, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009883515707730321, | |
| "grad_norm": 2.9048409461975098, | |
| "learning_rate": 0.00019871817834144504, | |
| "loss": 1.6211, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01016590187080833, | |
| "grad_norm": 1.029226303100586, | |
| "learning_rate": 0.0001986138239902355, | |
| "loss": 2.1988, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01044828803388634, | |
| "grad_norm": 1.716841697692871, | |
| "learning_rate": 0.0001985054160109657, | |
| "loss": 1.7938, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010730674196964348, | |
| "grad_norm": 1.0365818738937378, | |
| "learning_rate": 0.00019839295885986296, | |
| "loss": 1.896, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.011013060360042359, | |
| "grad_norm": 1.4247523546218872, | |
| "learning_rate": 0.0001982764571596004, | |
| "loss": 2.0023, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011295446523120367, | |
| "grad_norm": 1.0945035219192505, | |
| "learning_rate": 0.00019815591569910654, | |
| "loss": 2.4118, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011295446523120367, | |
| "eval_loss": 1.651785135269165, | |
| "eval_runtime": 134.7054, | |
| "eval_samples_per_second": 5.538, | |
| "eval_steps_per_second": 5.538, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011577832686198376, | |
| "grad_norm": 1.3919488191604614, | |
| "learning_rate": 0.00019803133943336874, | |
| "loss": 2.096, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011860218849276386, | |
| "grad_norm": 1.0962899923324585, | |
| "learning_rate": 0.0001979027334832293, | |
| "loss": 2.0469, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.012142605012354394, | |
| "grad_norm": 1.147463083267212, | |
| "learning_rate": 0.00019777010313517518, | |
| "loss": 2.0405, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012424991175432405, | |
| "grad_norm": 2.677388906478882, | |
| "learning_rate": 0.00019763345384112043, | |
| "loss": 1.0599, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012707377338510413, | |
| "grad_norm": 1.20905339717865, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 0.6549, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012989763501588421, | |
| "grad_norm": 1.109489917755127, | |
| "learning_rate": 0.00019734812104845047, | |
| "loss": 1.9309, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013272149664666432, | |
| "grad_norm": 1.518839955329895, | |
| "learning_rate": 0.00019719944927874881, | |
| "loss": 1.8122, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01355453582774444, | |
| "grad_norm": 0.8112537860870361, | |
| "learning_rate": 0.0001970467820203915, | |
| "loss": 1.8915, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01383692199082245, | |
| "grad_norm": 0.7357921004295349, | |
| "learning_rate": 0.00019689012554893154, | |
| "loss": 2.1672, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.014119308153900459, | |
| "grad_norm": 0.7238839268684387, | |
| "learning_rate": 0.00019672948630390294, | |
| "loss": 0.9114, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014119308153900459, | |
| "eval_loss": 1.624532699584961, | |
| "eval_runtime": 134.5228, | |
| "eval_samples_per_second": 5.546, | |
| "eval_steps_per_second": 5.546, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014401694316978467, | |
| "grad_norm": 4.2082200050354, | |
| "learning_rate": 0.00019656487088855592, | |
| "loss": 1.5288, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.014684080480056478, | |
| "grad_norm": 0.6968432068824768, | |
| "learning_rate": 0.00019639628606958533, | |
| "loss": 1.4653, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.014966466643134486, | |
| "grad_norm": 1.9569013118743896, | |
| "learning_rate": 0.0001962237387768529, | |
| "loss": 1.7478, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.015248852806212496, | |
| "grad_norm": 1.2472929954528809, | |
| "learning_rate": 0.00019604723610310194, | |
| "loss": 1.1666, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.015531238969290505, | |
| "grad_norm": 0.7596736550331116, | |
| "learning_rate": 0.00019586678530366606, | |
| "loss": 1.7902, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.015813625132368513, | |
| "grad_norm": 1.2892470359802246, | |
| "learning_rate": 0.00019568239379617088, | |
| "loss": 1.8049, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.016096011295446522, | |
| "grad_norm": 1.5124154090881348, | |
| "learning_rate": 0.00019549406916022905, | |
| "loss": 1.7232, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.016378397458524534, | |
| "grad_norm": 1.0523513555526733, | |
| "learning_rate": 0.00019530181913712872, | |
| "loss": 1.772, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.016660783621602542, | |
| "grad_norm": 2.185861825942993, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.3071, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.01694316978468055, | |
| "grad_norm": 0.6275917887687683, | |
| "learning_rate": 0.00019490557470106686, | |
| "loss": 2.0081, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01694316978468055, | |
| "eval_loss": 1.624603033065796, | |
| "eval_runtime": 134.5052, | |
| "eval_samples_per_second": 5.546, | |
| "eval_steps_per_second": 5.546, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01722555594775856, | |
| "grad_norm": 0.9301966428756714, | |
| "learning_rate": 0.00019470159657616215, | |
| "loss": 1.7401, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.017507942110836568, | |
| "grad_norm": 1.2353283166885376, | |
| "learning_rate": 0.00019449372563954293, | |
| "loss": 1.7241, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.01779032827391458, | |
| "grad_norm": 1.0061556100845337, | |
| "learning_rate": 0.0001942819704359693, | |
| "loss": 0.5784, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.018072714436992588, | |
| "grad_norm": 1.062904953956604, | |
| "learning_rate": 0.00019406633966986828, | |
| "loss": 2.1718, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.018355100600070597, | |
| "grad_norm": 1.897362470626831, | |
| "learning_rate": 0.00019384684220497605, | |
| "loss": 1.9466, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.018637486763148605, | |
| "grad_norm": 1.1101641654968262, | |
| "learning_rate": 0.00019362348706397373, | |
| "loss": 1.8438, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.018919872926226614, | |
| "grad_norm": 0.8784818649291992, | |
| "learning_rate": 0.00019339628342811632, | |
| "loss": 0.844, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.019202259089304625, | |
| "grad_norm": 1.256935477256775, | |
| "learning_rate": 0.0001931652406368554, | |
| "loss": 0.9449, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.019484645252382634, | |
| "grad_norm": 1.1505467891693115, | |
| "learning_rate": 0.0001929303681874552, | |
| "loss": 1.9627, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.019767031415460642, | |
| "grad_norm": 1.6793428659439087, | |
| "learning_rate": 0.0001926916757346022, | |
| "loss": 2.6109, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.019767031415460642, | |
| "eval_loss": 1.6243711709976196, | |
| "eval_runtime": 134.6115, | |
| "eval_samples_per_second": 5.542, | |
| "eval_steps_per_second": 5.542, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02004941757853865, | |
| "grad_norm": 2.2794175148010254, | |
| "learning_rate": 0.00019244917309000817, | |
| "loss": 1.624, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.02033180374161666, | |
| "grad_norm": 1.5373339653015137, | |
| "learning_rate": 0.00019220287022200707, | |
| "loss": 1.8068, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.02061418990469467, | |
| "grad_norm": 0.9991006255149841, | |
| "learning_rate": 0.0001919527772551451, | |
| "loss": 1.6704, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.02089657606777268, | |
| "grad_norm": 1.392340064048767, | |
| "learning_rate": 0.00019169890446976454, | |
| "loss": 2.378, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.02117896223085069, | |
| "grad_norm": 1.1224641799926758, | |
| "learning_rate": 0.00019144126230158127, | |
| "loss": 1.6227, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.021461348393928697, | |
| "grad_norm": 1.2003456354141235, | |
| "learning_rate": 0.0001911798613412557, | |
| "loss": 2.4362, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.021743734557006705, | |
| "grad_norm": 1.102264642715454, | |
| "learning_rate": 0.0001909147123339575, | |
| "loss": 2.3662, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.022026120720084717, | |
| "grad_norm": 0.7298341989517212, | |
| "learning_rate": 0.0001906458261789238, | |
| "loss": 2.8474, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.022308506883162726, | |
| "grad_norm": 1.0796235799789429, | |
| "learning_rate": 0.00019037321392901136, | |
| "loss": 1.5521, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.022590893046240734, | |
| "grad_norm": 0.7039556503295898, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 2.47, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.022590893046240734, | |
| "eval_loss": 1.617271900177002, | |
| "eval_runtime": 134.9383, | |
| "eval_samples_per_second": 5.528, | |
| "eval_steps_per_second": 5.528, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.022873279209318743, | |
| "grad_norm": 0.908437192440033, | |
| "learning_rate": 0.0001898168561213419, | |
| "loss": 1.9605, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.02315566537239675, | |
| "grad_norm": 0.8091934323310852, | |
| "learning_rate": 0.0001895331334332753, | |
| "loss": 1.5024, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.023438051535474763, | |
| "grad_norm": 1.5132545232772827, | |
| "learning_rate": 0.0001892457303887706, | |
| "loss": 1.0696, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.02372043769855277, | |
| "grad_norm": 1.2116718292236328, | |
| "learning_rate": 0.0001889546588018412, | |
| "loss": 1.7115, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.02400282386163078, | |
| "grad_norm": 0.8074257969856262, | |
| "learning_rate": 0.00018865993063730004, | |
| "loss": 2.7291, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.02428521002470879, | |
| "grad_norm": 1.1341824531555176, | |
| "learning_rate": 0.00018836155801026753, | |
| "loss": 1.8977, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.024567596187786797, | |
| "grad_norm": 1.9230746030807495, | |
| "learning_rate": 0.0001880595531856738, | |
| "loss": 1.5919, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.02484998235086481, | |
| "grad_norm": 0.9849350452423096, | |
| "learning_rate": 0.00018775392857775432, | |
| "loss": 2.8404, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.025132368513942818, | |
| "grad_norm": 2.4642324447631836, | |
| "learning_rate": 0.00018744469674953956, | |
| "loss": 1.2864, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.025414754677020826, | |
| "grad_norm": 1.7967941761016846, | |
| "learning_rate": 0.00018713187041233896, | |
| "loss": 1.8635, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.025414754677020826, | |
| "eval_loss": 1.6206018924713135, | |
| "eval_runtime": 134.6331, | |
| "eval_samples_per_second": 5.541, | |
| "eval_steps_per_second": 5.541, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.025697140840098835, | |
| "grad_norm": 1.2300053834915161, | |
| "learning_rate": 0.00018681546242521786, | |
| "loss": 2.5979, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.025979527003176843, | |
| "grad_norm": 1.4374971389770508, | |
| "learning_rate": 0.00018649548579446936, | |
| "loss": 1.9891, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.026261913166254855, | |
| "grad_norm": 1.0630384683609009, | |
| "learning_rate": 0.0001861719536730795, | |
| "loss": 2.2702, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.026544299329332863, | |
| "grad_norm": 1.124637246131897, | |
| "learning_rate": 0.00018584487936018661, | |
| "loss": 2.8282, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.026826685492410872, | |
| "grad_norm": 1.3020342588424683, | |
| "learning_rate": 0.00018551427630053463, | |
| "loss": 1.946, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.02710907165548888, | |
| "grad_norm": 1.0363761186599731, | |
| "learning_rate": 0.00018518015808392045, | |
| "loss": 1.4936, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.02739145781856689, | |
| "grad_norm": 1.612716794013977, | |
| "learning_rate": 0.00018484253844463526, | |
| "loss": 1.2949, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.0276738439816449, | |
| "grad_norm": 0.5706181526184082, | |
| "learning_rate": 0.00018450143126090015, | |
| "loss": 1.3093, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.02795623014472291, | |
| "grad_norm": 1.2899292707443237, | |
| "learning_rate": 0.00018415685055429533, | |
| "loss": 2.5082, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.028238616307800918, | |
| "grad_norm": 1.1273449659347534, | |
| "learning_rate": 0.00018380881048918405, | |
| "loss": 1.8346, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.028238616307800918, | |
| "eval_loss": 1.6035598516464233, | |
| "eval_runtime": 134.1623, | |
| "eval_samples_per_second": 5.56, | |
| "eval_steps_per_second": 5.56, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.028521002470878926, | |
| "grad_norm": 1.1187326908111572, | |
| "learning_rate": 0.00018345732537213027, | |
| "loss": 2.3691, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.028803388633956935, | |
| "grad_norm": 1.2883691787719727, | |
| "learning_rate": 0.00018310240965131041, | |
| "loss": 2.9992, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.029085774797034947, | |
| "grad_norm": 1.5844606161117554, | |
| "learning_rate": 0.00018274407791591966, | |
| "loss": 1.4277, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.029368160960112955, | |
| "grad_norm": 1.5807751417160034, | |
| "learning_rate": 0.00018238234489557215, | |
| "loss": 0.6992, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.029650547123190964, | |
| "grad_norm": 1.4340300559997559, | |
| "learning_rate": 0.0001820172254596956, | |
| "loss": 2.2425, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.029932933286268972, | |
| "grad_norm": 1.3567688465118408, | |
| "learning_rate": 0.00018164873461691986, | |
| "loss": 0.7425, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.03021531944934698, | |
| "grad_norm": 1.126590609550476, | |
| "learning_rate": 0.00018127688751446027, | |
| "loss": 1.8765, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.030497705612424993, | |
| "grad_norm": 0.9429426193237305, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.088, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.030780091775503, | |
| "grad_norm": 1.0398406982421875, | |
| "learning_rate": 0.0001805231858085356, | |
| "loss": 1.8745, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.03106247793858101, | |
| "grad_norm": 0.563444197177887, | |
| "learning_rate": 0.00018014136218679567, | |
| "loss": 2.4523, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03106247793858101, | |
| "eval_loss": 1.6250616312026978, | |
| "eval_runtime": 134.2663, | |
| "eval_samples_per_second": 5.556, | |
| "eval_steps_per_second": 5.556, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03134486410165902, | |
| "grad_norm": 0.664234459400177, | |
| "learning_rate": 0.00017975624426754848, | |
| "loss": 1.4157, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.03162725026473703, | |
| "grad_norm": 1.8084183931350708, | |
| "learning_rate": 0.00017936784788148328, | |
| "loss": 1.9874, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.03190963642781504, | |
| "grad_norm": 1.104672908782959, | |
| "learning_rate": 0.00017897618899405423, | |
| "loss": 2.7257, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.032192022590893044, | |
| "grad_norm": 0.7887753844261169, | |
| "learning_rate": 0.00017858128370482426, | |
| "loss": 2.7542, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.032474408753971055, | |
| "grad_norm": 1.3737729787826538, | |
| "learning_rate": 0.000178183148246803, | |
| "loss": 2.0767, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.03275679491704907, | |
| "grad_norm": 0.7426419258117676, | |
| "learning_rate": 0.00017778179898577973, | |
| "loss": 1.4909, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.03303918108012707, | |
| "grad_norm": 2.0367558002471924, | |
| "learning_rate": 0.00017737725241965069, | |
| "loss": 1.6603, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.033321567243205084, | |
| "grad_norm": 0.9449915289878845, | |
| "learning_rate": 0.00017696952517774062, | |
| "loss": 2.323, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.03360395340628309, | |
| "grad_norm": 2.1352381706237793, | |
| "learning_rate": 0.00017655863402011947, | |
| "loss": 1.9585, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.0338863395693611, | |
| "grad_norm": 1.0839155912399292, | |
| "learning_rate": 0.00017614459583691346, | |
| "loss": 1.5273, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0338863395693611, | |
| "eval_loss": 1.6136579513549805, | |
| "eval_runtime": 134.3244, | |
| "eval_samples_per_second": 5.554, | |
| "eval_steps_per_second": 5.554, | |
| "step": 120 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.174564302225408e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |