| { | |
| "best_metric": 1.5968632698059082, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-130", | |
| "epoch": 0.04518178609248147, | |
| "eval_steps": 10, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002823861630780092, | |
| "grad_norm": 1.2056736946105957, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9521, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002823861630780092, | |
| "eval_loss": 2.352551221847534, | |
| "eval_runtime": 133.636, | |
| "eval_samples_per_second": 5.582, | |
| "eval_steps_per_second": 5.582, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005647723261560184, | |
| "grad_norm": 4.347576141357422, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1192, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008471584892340275, | |
| "grad_norm": 0.7937899231910706, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1903, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011295446523120368, | |
| "grad_norm": 3.9262712001800537, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5143, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014119308153900459, | |
| "grad_norm": 2.7941317558288574, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9205, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001694316978468055, | |
| "grad_norm": 0.9424725770950317, | |
| "learning_rate": 0.00012, | |
| "loss": 2.582, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001976703141546064, | |
| "grad_norm": 1.8026996850967407, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0555, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022590893046240735, | |
| "grad_norm": 1.0503661632537842, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6065, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025414754677020824, | |
| "grad_norm": 2.3215556144714355, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6192, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028238616307800918, | |
| "grad_norm": 1.60389244556427, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1819, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028238616307800918, | |
| "eval_loss": 2.1240005493164062, | |
| "eval_runtime": 133.7157, | |
| "eval_samples_per_second": 5.579, | |
| "eval_steps_per_second": 5.579, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003106247793858101, | |
| "grad_norm": 1.0237597227096558, | |
| "learning_rate": 0.0001999979446958366, | |
| "loss": 1.8844, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00338863395693611, | |
| "grad_norm": 4.726717472076416, | |
| "learning_rate": 0.00019999177886783194, | |
| "loss": 3.1172, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0036710201200141194, | |
| "grad_norm": 1.6403062343597412, | |
| "learning_rate": 0.00019998150276943902, | |
| "loss": 1.7007, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003953406283092128, | |
| "grad_norm": 2.1164722442626953, | |
| "learning_rate": 0.000199967116823068, | |
| "loss": 2.5321, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004235792446170138, | |
| "grad_norm": 3.5340867042541504, | |
| "learning_rate": 0.0001999486216200688, | |
| "loss": 2.3608, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004518178609248147, | |
| "grad_norm": 5.55496072769165, | |
| "learning_rate": 0.00019992601792070679, | |
| "loss": 1.6141, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004800564772326156, | |
| "grad_norm": 7.0048136711120605, | |
| "learning_rate": 0.00019989930665413147, | |
| "loss": 2.2728, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005082950935404165, | |
| "grad_norm": 1.7807990312576294, | |
| "learning_rate": 0.00019986848891833845, | |
| "loss": 1.6759, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005365337098482174, | |
| "grad_norm": 3.1774418354034424, | |
| "learning_rate": 0.0001998335659801241, | |
| "loss": 0.8362, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0056477232615601836, | |
| "grad_norm": 5.73573637008667, | |
| "learning_rate": 0.00019979453927503364, | |
| "loss": 2.7934, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0056477232615601836, | |
| "eval_loss": 1.7092158794403076, | |
| "eval_runtime": 133.3036, | |
| "eval_samples_per_second": 5.596, | |
| "eval_steps_per_second": 5.596, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005930109424638193, | |
| "grad_norm": 1.705460548400879, | |
| "learning_rate": 0.00019975141040730207, | |
| "loss": 1.3571, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006212495587716202, | |
| "grad_norm": 1.3597909212112427, | |
| "learning_rate": 0.0001997041811497882, | |
| "loss": 1.491, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006494881750794211, | |
| "grad_norm": 1.3038731813430786, | |
| "learning_rate": 0.00019965285344390184, | |
| "loss": 2.4389, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00677726791387222, | |
| "grad_norm": 2.3923144340515137, | |
| "learning_rate": 0.00019959742939952392, | |
| "loss": 1.3591, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0070596540769502295, | |
| "grad_norm": 2.964477300643921, | |
| "learning_rate": 0.00019953791129491983, | |
| "loss": 1.1022, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007342040240028239, | |
| "grad_norm": 3.184072732925415, | |
| "learning_rate": 0.00019947430157664576, | |
| "loss": 1.4837, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007624426403106248, | |
| "grad_norm": 1.576446294784546, | |
| "learning_rate": 0.00019940660285944803, | |
| "loss": 2.0992, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007906812566184257, | |
| "grad_norm": 2.878796100616455, | |
| "learning_rate": 0.00019933481792615583, | |
| "loss": 2.4712, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008189198729262267, | |
| "grad_norm": 2.5952467918395996, | |
| "learning_rate": 0.0001992589497275665, | |
| "loss": 1.6412, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008471584892340275, | |
| "grad_norm": 2.8451197147369385, | |
| "learning_rate": 0.0001991790013823246, | |
| "loss": 1.6372, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008471584892340275, | |
| "eval_loss": 1.6834224462509155, | |
| "eval_runtime": 133.2875, | |
| "eval_samples_per_second": 5.597, | |
| "eval_steps_per_second": 5.597, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008753971055418284, | |
| "grad_norm": 2.855771780014038, | |
| "learning_rate": 0.00019909497617679348, | |
| "loss": 2.608, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009036357218496294, | |
| "grad_norm": 2.0999650955200195, | |
| "learning_rate": 0.0001990068775649202, | |
| "loss": 1.6182, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009318743381574303, | |
| "grad_norm": 5.745433330535889, | |
| "learning_rate": 0.00019891470916809362, | |
| "loss": 1.6578, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009601129544652313, | |
| "grad_norm": 1.7802093029022217, | |
| "learning_rate": 0.00019881847477499557, | |
| "loss": 1.8047, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009883515707730321, | |
| "grad_norm": 3.094785451889038, | |
| "learning_rate": 0.00019871817834144504, | |
| "loss": 1.2005, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01016590187080833, | |
| "grad_norm": 2.3366200923919678, | |
| "learning_rate": 0.0001986138239902355, | |
| "loss": 2.0731, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01044828803388634, | |
| "grad_norm": 3.872102737426758, | |
| "learning_rate": 0.0001985054160109657, | |
| "loss": 1.301, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010730674196964348, | |
| "grad_norm": 1.3710724115371704, | |
| "learning_rate": 0.00019839295885986296, | |
| "loss": 1.4742, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.011013060360042359, | |
| "grad_norm": 2.481275796890259, | |
| "learning_rate": 0.0001982764571596004, | |
| "loss": 1.5866, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011295446523120367, | |
| "grad_norm": 1.8309324979782104, | |
| "learning_rate": 0.00019815591569910654, | |
| "loss": 2.644, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011295446523120367, | |
| "eval_loss": 1.6503487825393677, | |
| "eval_runtime": 133.397, | |
| "eval_samples_per_second": 5.592, | |
| "eval_steps_per_second": 5.592, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011577832686198376, | |
| "grad_norm": 1.9744967222213745, | |
| "learning_rate": 0.00019803133943336874, | |
| "loss": 2.3377, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011860218849276386, | |
| "grad_norm": 1.438886046409607, | |
| "learning_rate": 0.0001979027334832293, | |
| "loss": 1.4721, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.012142605012354394, | |
| "grad_norm": 3.23305082321167, | |
| "learning_rate": 0.00019777010313517518, | |
| "loss": 1.7882, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012424991175432405, | |
| "grad_norm": 5.8521013259887695, | |
| "learning_rate": 0.00019763345384112043, | |
| "loss": 1.2744, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012707377338510413, | |
| "grad_norm": 5.29448127746582, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 1.0265, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012989763501588421, | |
| "grad_norm": 3.448343515396118, | |
| "learning_rate": 0.00019734812104845047, | |
| "loss": 2.1143, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013272149664666432, | |
| "grad_norm": 2.209937810897827, | |
| "learning_rate": 0.00019719944927874881, | |
| "loss": 1.325, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01355453582774444, | |
| "grad_norm": 1.200800895690918, | |
| "learning_rate": 0.0001970467820203915, | |
| "loss": 1.8635, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01383692199082245, | |
| "grad_norm": 1.2242612838745117, | |
| "learning_rate": 0.00019689012554893154, | |
| "loss": 1.7063, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.014119308153900459, | |
| "grad_norm": 1.140673279762268, | |
| "learning_rate": 0.00019672948630390294, | |
| "loss": 1.315, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014119308153900459, | |
| "eval_loss": 1.6434087753295898, | |
| "eval_runtime": 133.392, | |
| "eval_samples_per_second": 5.593, | |
| "eval_steps_per_second": 5.593, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014401694316978467, | |
| "grad_norm": 2.5457074642181396, | |
| "learning_rate": 0.00019656487088855592, | |
| "loss": 1.5371, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.014684080480056478, | |
| "grad_norm": 2.4005753993988037, | |
| "learning_rate": 0.00019639628606958533, | |
| "loss": 1.0716, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.014966466643134486, | |
| "grad_norm": 2.4281392097473145, | |
| "learning_rate": 0.0001962237387768529, | |
| "loss": 2.1807, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.015248852806212496, | |
| "grad_norm": 2.5013136863708496, | |
| "learning_rate": 0.00019604723610310194, | |
| "loss": 1.0288, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.015531238969290505, | |
| "grad_norm": 2.0805702209472656, | |
| "learning_rate": 0.00019586678530366606, | |
| "loss": 1.1582, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.015813625132368513, | |
| "grad_norm": 7.539531707763672, | |
| "learning_rate": 0.00019568239379617088, | |
| "loss": 1.7791, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.016096011295446522, | |
| "grad_norm": 1.5069524049758911, | |
| "learning_rate": 0.00019549406916022905, | |
| "loss": 1.6449, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.016378397458524534, | |
| "grad_norm": 1.1627360582351685, | |
| "learning_rate": 0.00019530181913712872, | |
| "loss": 1.2881, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.016660783621602542, | |
| "grad_norm": 5.9471282958984375, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.6948, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.01694316978468055, | |
| "grad_norm": 1.4962432384490967, | |
| "learning_rate": 0.00019490557470106686, | |
| "loss": 1.3254, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01694316978468055, | |
| "eval_loss": 1.633779525756836, | |
| "eval_runtime": 133.2937, | |
| "eval_samples_per_second": 5.597, | |
| "eval_steps_per_second": 5.597, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01722555594775856, | |
| "grad_norm": 1.3225600719451904, | |
| "learning_rate": 0.00019470159657616215, | |
| "loss": 1.7811, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.017507942110836568, | |
| "grad_norm": 1.632053017616272, | |
| "learning_rate": 0.00019449372563954293, | |
| "loss": 1.8656, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.01779032827391458, | |
| "grad_norm": 1.7111440896987915, | |
| "learning_rate": 0.0001942819704359693, | |
| "loss": 0.8098, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.018072714436992588, | |
| "grad_norm": 1.5115035772323608, | |
| "learning_rate": 0.00019406633966986828, | |
| "loss": 1.0582, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.018355100600070597, | |
| "grad_norm": 2.999513626098633, | |
| "learning_rate": 0.00019384684220497605, | |
| "loss": 2.1569, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.018637486763148605, | |
| "grad_norm": 1.0796102285385132, | |
| "learning_rate": 0.00019362348706397373, | |
| "loss": 1.4516, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.018919872926226614, | |
| "grad_norm": 2.9733681678771973, | |
| "learning_rate": 0.00019339628342811632, | |
| "loss": 1.6857, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.019202259089304625, | |
| "grad_norm": 2.086916923522949, | |
| "learning_rate": 0.0001931652406368554, | |
| "loss": 0.7689, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.019484645252382634, | |
| "grad_norm": 1.511246919631958, | |
| "learning_rate": 0.0001929303681874552, | |
| "loss": 1.5469, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.019767031415460642, | |
| "grad_norm": 2.029017925262451, | |
| "learning_rate": 0.0001926916757346022, | |
| "loss": 1.3705, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.019767031415460642, | |
| "eval_loss": 1.6125953197479248, | |
| "eval_runtime": 133.426, | |
| "eval_samples_per_second": 5.591, | |
| "eval_steps_per_second": 5.591, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02004941757853865, | |
| "grad_norm": 2.52913761138916, | |
| "learning_rate": 0.00019244917309000817, | |
| "loss": 1.722, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.02033180374161666, | |
| "grad_norm": 7.770167350769043, | |
| "learning_rate": 0.00019220287022200707, | |
| "loss": 2.7036, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.02061418990469467, | |
| "grad_norm": 1.7608412504196167, | |
| "learning_rate": 0.0001919527772551451, | |
| "loss": 1.2768, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.02089657606777268, | |
| "grad_norm": 2.3405442237854004, | |
| "learning_rate": 0.00019169890446976454, | |
| "loss": 2.2241, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.02117896223085069, | |
| "grad_norm": 2.386042356491089, | |
| "learning_rate": 0.00019144126230158127, | |
| "loss": 1.3922, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.021461348393928697, | |
| "grad_norm": 2.280710458755493, | |
| "learning_rate": 0.0001911798613412557, | |
| "loss": 1.608, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.021743734557006705, | |
| "grad_norm": 1.2972298860549927, | |
| "learning_rate": 0.0001909147123339575, | |
| "loss": 2.1776, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.022026120720084717, | |
| "grad_norm": 1.4631404876708984, | |
| "learning_rate": 0.0001906458261789238, | |
| "loss": 3.1008, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.022308506883162726, | |
| "grad_norm": 1.0595492124557495, | |
| "learning_rate": 0.00019037321392901136, | |
| "loss": 1.3511, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.022590893046240734, | |
| "grad_norm": 0.9610152244567871, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 2.1504, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.022590893046240734, | |
| "eval_loss": 1.602448582649231, | |
| "eval_runtime": 133.5988, | |
| "eval_samples_per_second": 5.584, | |
| "eval_steps_per_second": 5.584, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.022873279209318743, | |
| "grad_norm": 1.699086308479309, | |
| "learning_rate": 0.0001898168561213419, | |
| "loss": 1.3892, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.02315566537239675, | |
| "grad_norm": 1.2091821432113647, | |
| "learning_rate": 0.0001895331334332753, | |
| "loss": 1.5162, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.023438051535474763, | |
| "grad_norm": 1.6631978750228882, | |
| "learning_rate": 0.0001892457303887706, | |
| "loss": 0.8076, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.02372043769855277, | |
| "grad_norm": 1.577644944190979, | |
| "learning_rate": 0.0001889546588018412, | |
| "loss": 1.4393, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.02400282386163078, | |
| "grad_norm": 1.207412838935852, | |
| "learning_rate": 0.00018865993063730004, | |
| "loss": 2.1015, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.02428521002470879, | |
| "grad_norm": 2.7810745239257812, | |
| "learning_rate": 0.00018836155801026753, | |
| "loss": 1.4547, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.024567596187786797, | |
| "grad_norm": 2.054161787033081, | |
| "learning_rate": 0.0001880595531856738, | |
| "loss": 1.3083, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.02484998235086481, | |
| "grad_norm": 3.753908634185791, | |
| "learning_rate": 0.00018775392857775432, | |
| "loss": 2.8305, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.025132368513942818, | |
| "grad_norm": 4.611723899841309, | |
| "learning_rate": 0.00018744469674953956, | |
| "loss": 1.7302, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.025414754677020826, | |
| "grad_norm": 2.27549409866333, | |
| "learning_rate": 0.00018713187041233896, | |
| "loss": 1.8115, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.025414754677020826, | |
| "eval_loss": 1.6072229146957397, | |
| "eval_runtime": 133.6033, | |
| "eval_samples_per_second": 5.584, | |
| "eval_steps_per_second": 5.584, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.025697140840098835, | |
| "grad_norm": 1.4146398305892944, | |
| "learning_rate": 0.00018681546242521786, | |
| "loss": 1.1993, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.025979527003176843, | |
| "grad_norm": 2.2005670070648193, | |
| "learning_rate": 0.00018649548579446936, | |
| "loss": 1.9517, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.026261913166254855, | |
| "grad_norm": 1.241758108139038, | |
| "learning_rate": 0.0001861719536730795, | |
| "loss": 2.0892, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.026544299329332863, | |
| "grad_norm": 1.4617339372634888, | |
| "learning_rate": 0.00018584487936018661, | |
| "loss": 2.2815, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.026826685492410872, | |
| "grad_norm": 1.677581548690796, | |
| "learning_rate": 0.00018551427630053463, | |
| "loss": 1.75, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.02710907165548888, | |
| "grad_norm": 3.2750422954559326, | |
| "learning_rate": 0.00018518015808392045, | |
| "loss": 1.8473, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.02739145781856689, | |
| "grad_norm": 1.7410293817520142, | |
| "learning_rate": 0.00018484253844463526, | |
| "loss": 1.2498, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.0276738439816449, | |
| "grad_norm": 1.0431251525878906, | |
| "learning_rate": 0.00018450143126090015, | |
| "loss": 2.3196, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.02795623014472291, | |
| "grad_norm": 2.758586883544922, | |
| "learning_rate": 0.00018415685055429533, | |
| "loss": 1.9701, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.028238616307800918, | |
| "grad_norm": 1.7685903310775757, | |
| "learning_rate": 0.00018380881048918405, | |
| "loss": 1.4758, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.028238616307800918, | |
| "eval_loss": 1.6011497974395752, | |
| "eval_runtime": 133.8006, | |
| "eval_samples_per_second": 5.575, | |
| "eval_steps_per_second": 5.575, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.028521002470878926, | |
| "grad_norm": 1.1203055381774902, | |
| "learning_rate": 0.00018345732537213027, | |
| "loss": 1.7475, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.028803388633956935, | |
| "grad_norm": 1.274515986442566, | |
| "learning_rate": 0.00018310240965131041, | |
| "loss": 2.6023, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.029085774797034947, | |
| "grad_norm": 2.5792765617370605, | |
| "learning_rate": 0.00018274407791591966, | |
| "loss": 1.1908, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.029368160960112955, | |
| "grad_norm": 1.466035008430481, | |
| "learning_rate": 0.00018238234489557215, | |
| "loss": 0.7359, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.029650547123190964, | |
| "grad_norm": 3.4681172370910645, | |
| "learning_rate": 0.0001820172254596956, | |
| "loss": 1.8144, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.029932933286268972, | |
| "grad_norm": 4.0510993003845215, | |
| "learning_rate": 0.00018164873461691986, | |
| "loss": 0.7832, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.03021531944934698, | |
| "grad_norm": 5.226031303405762, | |
| "learning_rate": 0.00018127688751446027, | |
| "loss": 1.7575, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.030497705612424993, | |
| "grad_norm": 1.0487242937088013, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.077, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.030780091775503, | |
| "grad_norm": 1.5338118076324463, | |
| "learning_rate": 0.0001805231858085356, | |
| "loss": 1.5191, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.03106247793858101, | |
| "grad_norm": 1.2566704750061035, | |
| "learning_rate": 0.00018014136218679567, | |
| "loss": 1.756, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03106247793858101, | |
| "eval_loss": 1.6045676469802856, | |
| "eval_runtime": 133.6566, | |
| "eval_samples_per_second": 5.581, | |
| "eval_steps_per_second": 5.581, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03134486410165902, | |
| "grad_norm": 0.7646064758300781, | |
| "learning_rate": 0.00017975624426754848, | |
| "loss": 1.6671, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.03162725026473703, | |
| "grad_norm": 2.133544445037842, | |
| "learning_rate": 0.00017936784788148328, | |
| "loss": 1.5909, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.03190963642781504, | |
| "grad_norm": 2.059943199157715, | |
| "learning_rate": 0.00017897618899405423, | |
| "loss": 1.7489, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.032192022590893044, | |
| "grad_norm": 0.8779903650283813, | |
| "learning_rate": 0.00017858128370482426, | |
| "loss": 1.4871, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.032474408753971055, | |
| "grad_norm": 1.5168753862380981, | |
| "learning_rate": 0.000178183148246803, | |
| "loss": 1.8045, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.03275679491704907, | |
| "grad_norm": 1.1241475343704224, | |
| "learning_rate": 0.00017778179898577973, | |
| "loss": 1.64, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.03303918108012707, | |
| "grad_norm": 9.078608512878418, | |
| "learning_rate": 0.00017737725241965069, | |
| "loss": 2.7736, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.033321567243205084, | |
| "grad_norm": 3.2590787410736084, | |
| "learning_rate": 0.00017696952517774062, | |
| "loss": 2.5064, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.03360395340628309, | |
| "grad_norm": 2.293269395828247, | |
| "learning_rate": 0.00017655863402011947, | |
| "loss": 2.146, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.0338863395693611, | |
| "grad_norm": 1.5803933143615723, | |
| "learning_rate": 0.00017614459583691346, | |
| "loss": 1.4979, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0338863395693611, | |
| "eval_loss": 1.603722095489502, | |
| "eval_runtime": 133.2987, | |
| "eval_samples_per_second": 5.596, | |
| "eval_steps_per_second": 5.596, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03416872573243911, | |
| "grad_norm": 1.4283939599990845, | |
| "learning_rate": 0.00017572742764761055, | |
| "loss": 1.4789, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.03445111189551712, | |
| "grad_norm": 1.3361456394195557, | |
| "learning_rate": 0.00017530714660036112, | |
| "loss": 0.784, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.03473349805859513, | |
| "grad_norm": 1.0861424207687378, | |
| "learning_rate": 0.00017488376997127283, | |
| "loss": 2.2809, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.035015884221673135, | |
| "grad_norm": 4.459283351898193, | |
| "learning_rate": 0.0001744573151637007, | |
| "loss": 1.4483, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.03529827038475115, | |
| "grad_norm": 1.324436902999878, | |
| "learning_rate": 0.00017402779970753155, | |
| "loss": 2.6136, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.03558065654782916, | |
| "grad_norm": 3.7964041233062744, | |
| "learning_rate": 0.0001735952412584635, | |
| "loss": 1.092, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.035863042710907164, | |
| "grad_norm": 2.560436725616455, | |
| "learning_rate": 0.00017315965759728014, | |
| "loss": 1.4307, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.036145428873985176, | |
| "grad_norm": 1.473990797996521, | |
| "learning_rate": 0.00017272106662911973, | |
| "loss": 1.1344, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.03642781503706318, | |
| "grad_norm": 3.3736298084259033, | |
| "learning_rate": 0.00017227948638273916, | |
| "loss": 1.5746, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.03671020120014119, | |
| "grad_norm": 1.5858126878738403, | |
| "learning_rate": 0.00017183493500977278, | |
| "loss": 1.3798, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03671020120014119, | |
| "eval_loss": 1.5968632698059082, | |
| "eval_runtime": 133.2364, | |
| "eval_samples_per_second": 5.599, | |
| "eval_steps_per_second": 5.599, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.036992587363219205, | |
| "grad_norm": 0.9281368851661682, | |
| "learning_rate": 0.0001713874307839863, | |
| "loss": 1.8154, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.03727497352629721, | |
| "grad_norm": 2.6511611938476562, | |
| "learning_rate": 0.0001709369921005258, | |
| "loss": 1.4, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.03755735968937522, | |
| "grad_norm": 1.9646121263504028, | |
| "learning_rate": 0.00017048363747516117, | |
| "loss": 1.4126, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.03783974585245323, | |
| "grad_norm": 1.7208032608032227, | |
| "learning_rate": 0.00017002738554352552, | |
| "loss": 0.5568, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.03812213201553124, | |
| "grad_norm": 2.9022722244262695, | |
| "learning_rate": 0.00016956825506034867, | |
| "loss": 1.6914, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.03840451817860925, | |
| "grad_norm": 1.368131160736084, | |
| "learning_rate": 0.00016910626489868649, | |
| "loss": 1.5647, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.038686904341687256, | |
| "grad_norm": 1.5058932304382324, | |
| "learning_rate": 0.00016864143404914504, | |
| "loss": 2.4011, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.03896929050476527, | |
| "grad_norm": 2.3039586544036865, | |
| "learning_rate": 0.00016817378161909996, | |
| "loss": 0.9973, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.03925167666784327, | |
| "grad_norm": 1.9210929870605469, | |
| "learning_rate": 0.00016770332683191096, | |
| "loss": 1.7679, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.039534062830921285, | |
| "grad_norm": 1.3414863348007202, | |
| "learning_rate": 0.0001672300890261317, | |
| "loss": 1.4788, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.039534062830921285, | |
| "eval_loss": 1.6231486797332764, | |
| "eval_runtime": 133.2243, | |
| "eval_samples_per_second": 5.6, | |
| "eval_steps_per_second": 5.6, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0398164489939993, | |
| "grad_norm": 1.8461261987686157, | |
| "learning_rate": 0.0001667540876547148, | |
| "loss": 2.1281, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.0400988351570773, | |
| "grad_norm": 3.0568318367004395, | |
| "learning_rate": 0.0001662753422842123, | |
| "loss": 1.476, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.040381221320155314, | |
| "grad_norm": 1.1168292760849, | |
| "learning_rate": 0.00016579387259397127, | |
| "loss": 0.9893, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.04066360748323332, | |
| "grad_norm": 2.078538417816162, | |
| "learning_rate": 0.00016530969837532487, | |
| "loss": 0.8452, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.04094599364631133, | |
| "grad_norm": 2.543635845184326, | |
| "learning_rate": 0.00016482283953077887, | |
| "loss": 1.5892, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.04122837980938934, | |
| "grad_norm": 1.8149226903915405, | |
| "learning_rate": 0.00016433331607319343, | |
| "loss": 1.4509, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.04151076597246735, | |
| "grad_norm": 1.4729820489883423, | |
| "learning_rate": 0.00016384114812496056, | |
| "loss": 1.5081, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.04179315213554536, | |
| "grad_norm": 2.2723262310028076, | |
| "learning_rate": 0.00016334635591717703, | |
| "loss": 2.19, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.042075538298623365, | |
| "grad_norm": 1.748171091079712, | |
| "learning_rate": 0.00016284895978881236, | |
| "loss": 2.2346, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.04235792446170138, | |
| "grad_norm": 1.4556044340133667, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 1.1614, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04235792446170138, | |
| "eval_loss": 1.6199051141738892, | |
| "eval_runtime": 133.3692, | |
| "eval_samples_per_second": 5.593, | |
| "eval_steps_per_second": 5.593, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04264031062477939, | |
| "grad_norm": 1.4214565753936768, | |
| "learning_rate": 0.00016184643766056317, | |
| "loss": 1.9267, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.042922696787857394, | |
| "grad_norm": 1.2661665678024292, | |
| "learning_rate": 0.00016134135287043669, | |
| "loss": 1.8779, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.043205082950935406, | |
| "grad_norm": 2.253584384918213, | |
| "learning_rate": 0.00016083374657755134, | |
| "loss": 1.2, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.04348746911401341, | |
| "grad_norm": 2.3451638221740723, | |
| "learning_rate": 0.00016032363964761363, | |
| "loss": 2.1057, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.04376985527709142, | |
| "grad_norm": 2.77101731300354, | |
| "learning_rate": 0.00015981105304912162, | |
| "loss": 1.8791, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.044052241440169435, | |
| "grad_norm": 1.678722620010376, | |
| "learning_rate": 0.00015929600785250257, | |
| "loss": 2.4479, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.04433462760324744, | |
| "grad_norm": 1.2198508977890015, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 2.3366, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.04461701376632545, | |
| "grad_norm": 5.628009796142578, | |
| "learning_rate": 0.0001582586264510396, | |
| "loss": 1.3177, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.04489939992940346, | |
| "grad_norm": 2.065458297729492, | |
| "learning_rate": 0.00015773633288888197, | |
| "loss": 2.0971, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.04518178609248147, | |
| "grad_norm": 0.9564564824104309, | |
| "learning_rate": 0.00015721166601221698, | |
| "loss": 1.3886, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04518178609248147, | |
| "eval_loss": 1.6064260005950928, | |
| "eval_runtime": 133.4242, | |
| "eval_samples_per_second": 5.591, | |
| "eval_steps_per_second": 5.591, | |
| "step": 160 | |
| } | |
| ], | |
| "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": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.566085736300544e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |