| { | |
| "best_metric": 11.921277046203613, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 2.008298755186722, | |
| "eval_steps": 25, | |
| "global_step": 121, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 0.008619977161288261, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 11.9327, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "eval_loss": 11.933255195617676, | |
| "eval_runtime": 0.0685, | |
| "eval_samples_per_second": 729.868, | |
| "eval_steps_per_second": 29.195, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 0.007508904207497835, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 11.9321, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04979253112033195, | |
| "grad_norm": 0.007870020344853401, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 11.9325, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06639004149377593, | |
| "grad_norm": 0.008674144744873047, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 11.9323, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08298755186721991, | |
| "grad_norm": 0.00782778114080429, | |
| "learning_rate": 0.00015, | |
| "loss": 11.9326, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0995850622406639, | |
| "grad_norm": 0.007341116201132536, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 11.9326, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11618257261410789, | |
| "grad_norm": 0.00769679993391037, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 11.9325, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13278008298755187, | |
| "grad_norm": 0.008552188985049725, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 11.9325, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14937759336099585, | |
| "grad_norm": 0.0071903131902217865, | |
| "learning_rate": 0.00027, | |
| "loss": 11.9329, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16597510373443983, | |
| "grad_norm": 0.006793375127017498, | |
| "learning_rate": 0.0003, | |
| "loss": 11.9332, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1825726141078838, | |
| "grad_norm": 0.006766727194190025, | |
| "learning_rate": 0.00029993992606774825, | |
| "loss": 11.9326, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1991701244813278, | |
| "grad_norm": 0.006954336538910866, | |
| "learning_rate": 0.00029975975238935744, | |
| "loss": 11.9319, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2157676348547718, | |
| "grad_norm": 0.008698610588908195, | |
| "learning_rate": 0.00029945962328137895, | |
| "loss": 11.9319, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23236514522821577, | |
| "grad_norm": 0.008457913063466549, | |
| "learning_rate": 0.0002990397791429554, | |
| "loss": 11.9322, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24896265560165975, | |
| "grad_norm": 0.008619188331067562, | |
| "learning_rate": 0.0002985005562632645, | |
| "loss": 11.9318, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26556016597510373, | |
| "grad_norm": 0.009035887196660042, | |
| "learning_rate": 0.00029784238655215626, | |
| "loss": 11.9322, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2821576763485477, | |
| "grad_norm": 0.010372682474553585, | |
| "learning_rate": 0.000297065797194199, | |
| "loss": 11.9315, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2987551867219917, | |
| "grad_norm": 0.009721986949443817, | |
| "learning_rate": 0.00029617141022641243, | |
| "loss": 11.932, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3153526970954357, | |
| "grad_norm": 0.011710022576153278, | |
| "learning_rate": 0.00029515994204002484, | |
| "loss": 11.9316, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.33195020746887965, | |
| "grad_norm": 0.011379418894648552, | |
| "learning_rate": 0.00029403220280665337, | |
| "loss": 11.932, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34854771784232363, | |
| "grad_norm": 0.012264162302017212, | |
| "learning_rate": 0.0002927890958293689, | |
| "loss": 11.9319, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3651452282157676, | |
| "grad_norm": 0.012727621011435986, | |
| "learning_rate": 0.0002914316168191626, | |
| "loss": 11.9315, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3817427385892116, | |
| "grad_norm": 0.013410990126430988, | |
| "learning_rate": 0.0002899608530973956, | |
| "loss": 11.9308, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3983402489626556, | |
| "grad_norm": 0.014416859485208988, | |
| "learning_rate": 0.00028837798272487026, | |
| "loss": 11.932, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4149377593360996, | |
| "grad_norm": 0.01126072183251381, | |
| "learning_rate": 0.00028668427355822034, | |
| "loss": 11.9328, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4149377593360996, | |
| "eval_loss": 11.931723594665527, | |
| "eval_runtime": 0.0673, | |
| "eval_samples_per_second": 743.046, | |
| "eval_steps_per_second": 29.722, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4315352697095436, | |
| "grad_norm": 0.019695591181516647, | |
| "learning_rate": 0.0002848810822343755, | |
| "loss": 11.931, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.44813278008298757, | |
| "grad_norm": 0.01740470714867115, | |
| "learning_rate": 0.00028296985308391476, | |
| "loss": 11.9307, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.46473029045643155, | |
| "grad_norm": 0.021143503487110138, | |
| "learning_rate": 0.0002809521169741782, | |
| "loss": 11.9306, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.48132780082987553, | |
| "grad_norm": 0.023337863385677338, | |
| "learning_rate": 0.0002788294900830639, | |
| "loss": 11.9307, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4979253112033195, | |
| "grad_norm": 0.026668556034564972, | |
| "learning_rate": 0.00027660367260449255, | |
| "loss": 11.9305, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5145228215767634, | |
| "grad_norm": 0.02838689088821411, | |
| "learning_rate": 0.0002742764473865763, | |
| "loss": 11.9296, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5311203319502075, | |
| "grad_norm": 0.027914777398109436, | |
| "learning_rate": 0.00027184967850358286, | |
| "loss": 11.9302, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5477178423236515, | |
| "grad_norm": 0.028979269787669182, | |
| "learning_rate": 0.0002693253097628385, | |
| "loss": 11.9297, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5643153526970954, | |
| "grad_norm": 0.03429955616593361, | |
| "learning_rate": 0.00026670536314776593, | |
| "loss": 11.9294, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5809128630705395, | |
| "grad_norm": 0.026081860065460205, | |
| "learning_rate": 0.00026399193719830457, | |
| "loss": 11.9296, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5975103734439834, | |
| "grad_norm": 0.026742985472083092, | |
| "learning_rate": 0.00026118720533001, | |
| "loss": 11.9289, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6141078838174274, | |
| "grad_norm": 0.03144499287009239, | |
| "learning_rate": 0.0002582934140931786, | |
| "loss": 11.929, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6307053941908713, | |
| "grad_norm": 0.04750339314341545, | |
| "learning_rate": 0.0002553128813733934, | |
| "loss": 11.9278, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6473029045643154, | |
| "grad_norm": 0.044398147612810135, | |
| "learning_rate": 0.0002522479945349299, | |
| "loss": 11.9275, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6639004149377593, | |
| "grad_norm": 0.04385744780302048, | |
| "learning_rate": 0.00024910120850851216, | |
| "loss": 11.9278, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6804979253112033, | |
| "grad_norm": 0.05074305832386017, | |
| "learning_rate": 0.00024587504382494774, | |
| "loss": 11.9262, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6970954356846473, | |
| "grad_norm": 0.047362346202135086, | |
| "learning_rate": 0.00024257208459621828, | |
| "loss": 11.9268, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7136929460580913, | |
| "grad_norm": 0.04583980143070221, | |
| "learning_rate": 0.00023919497644564298, | |
| "loss": 11.9258, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7302904564315352, | |
| "grad_norm": 0.049639176577329636, | |
| "learning_rate": 0.0002357464243887718, | |
| "loss": 11.9255, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7468879668049793, | |
| "grad_norm": 0.04268966615200043, | |
| "learning_rate": 0.00023222919066670647, | |
| "loss": 11.9256, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7634854771784232, | |
| "grad_norm": 0.04423046112060547, | |
| "learning_rate": 0.00022864609253358474, | |
| "loss": 11.9251, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7800829875518672, | |
| "grad_norm": 0.03876250982284546, | |
| "learning_rate": 0.000225, | |
| "loss": 11.9259, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7966804979253111, | |
| "grad_norm": 0.031338173896074295, | |
| "learning_rate": 0.00022129383353416347, | |
| "loss": 11.9259, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8132780082987552, | |
| "grad_norm": 0.031210312619805336, | |
| "learning_rate": 0.00021753056172265096, | |
| "loss": 11.9261, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8298755186721992, | |
| "grad_norm": 0.03140793740749359, | |
| "learning_rate": 0.00021371319889260717, | |
| "loss": 11.926, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8298755186721992, | |
| "eval_loss": 11.924413681030273, | |
| "eval_runtime": 0.0674, | |
| "eval_samples_per_second": 742.066, | |
| "eval_steps_per_second": 29.683, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8464730290456431, | |
| "grad_norm": 0.043788015842437744, | |
| "learning_rate": 0.00020984480269731242, | |
| "loss": 11.9232, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8630705394190872, | |
| "grad_norm": 0.03660878911614418, | |
| "learning_rate": 0.0002059284716670463, | |
| "loss": 11.9244, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8796680497925311, | |
| "grad_norm": 0.03714355081319809, | |
| "learning_rate": 0.00020196734272720854, | |
| "loss": 11.923, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.8962655601659751, | |
| "grad_norm": 0.03057694435119629, | |
| "learning_rate": 0.00019796458868568678, | |
| "loss": 11.922, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9128630705394191, | |
| "grad_norm": 0.02990574575960636, | |
| "learning_rate": 0.00019392341569148252, | |
| "loss": 11.9218, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9294605809128631, | |
| "grad_norm": 0.025974757969379425, | |
| "learning_rate": 0.00018984706066663143, | |
| "loss": 11.9227, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.946058091286307, | |
| "grad_norm": 0.02820601500570774, | |
| "learning_rate": 0.00018573878871347473, | |
| "loss": 11.9225, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9626556016597511, | |
| "grad_norm": 0.028666473925113678, | |
| "learning_rate": 0.00018160189049935892, | |
| "loss": 11.9233, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.979253112033195, | |
| "grad_norm": 0.02322000451385975, | |
| "learning_rate": 0.00017743967962085798, | |
| "loss": 11.923, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.995850622406639, | |
| "grad_norm": 0.028861528262495995, | |
| "learning_rate": 0.00017325548994962965, | |
| "loss": 11.924, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.012448132780083, | |
| "grad_norm": 0.04327556490898132, | |
| "learning_rate": 0.0001690526729620318, | |
| "loss": 21.3788, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.0290456431535269, | |
| "grad_norm": 0.02456553652882576, | |
| "learning_rate": 0.00016483459505463747, | |
| "loss": 11.6539, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.045643153526971, | |
| "grad_norm": 0.02364276722073555, | |
| "learning_rate": 0.00016060463484779918, | |
| "loss": 11.83, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.062240663900415, | |
| "grad_norm": 0.02070525474846363, | |
| "learning_rate": 0.00015636618047942222, | |
| "loss": 11.9144, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.0788381742738589, | |
| "grad_norm": 0.0210164375603199, | |
| "learning_rate": 0.00015212262689111433, | |
| "loss": 11.9249, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.095435684647303, | |
| "grad_norm": 0.02003309689462185, | |
| "learning_rate": 0.0001478773731088857, | |
| "loss": 11.9061, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.112033195020747, | |
| "grad_norm": 0.01854197308421135, | |
| "learning_rate": 0.00014363381952057778, | |
| "loss": 11.938, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.1286307053941909, | |
| "grad_norm": 0.022063063457608223, | |
| "learning_rate": 0.0001393953651522008, | |
| "loss": 11.9017, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.1452282157676348, | |
| "grad_norm": 0.017270218580961227, | |
| "learning_rate": 0.00013516540494536253, | |
| "loss": 11.978, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.161825726141079, | |
| "grad_norm": 0.01767859421670437, | |
| "learning_rate": 0.00013094732703796818, | |
| "loss": 11.9076, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1784232365145229, | |
| "grad_norm": 0.01846623234450817, | |
| "learning_rate": 0.0001267445100503703, | |
| "loss": 11.9928, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.1950207468879668, | |
| "grad_norm": 0.02277253195643425, | |
| "learning_rate": 0.000122560320379142, | |
| "loss": 11.9957, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.2116182572614107, | |
| "grad_norm": 0.017460819333791733, | |
| "learning_rate": 0.00011839810950064109, | |
| "loss": 9.1042, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.2282157676348548, | |
| "grad_norm": 0.027226807549595833, | |
| "learning_rate": 0.00011426121128652526, | |
| "loss": 14.9039, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.2448132780082988, | |
| "grad_norm": 0.02005860209465027, | |
| "learning_rate": 0.00011015293933336857, | |
| "loss": 11.642, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2448132780082988, | |
| "eval_loss": 11.92165756225586, | |
| "eval_runtime": 0.0678, | |
| "eval_samples_per_second": 737.673, | |
| "eval_steps_per_second": 29.507, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2614107883817427, | |
| "grad_norm": 0.01866528019309044, | |
| "learning_rate": 0.00010607658430851744, | |
| "loss": 11.8735, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.2780082987551866, | |
| "grad_norm": 0.014573541469871998, | |
| "learning_rate": 0.0001020354113143132, | |
| "loss": 11.8891, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.2946058091286308, | |
| "grad_norm": 0.014832578599452972, | |
| "learning_rate": 9.803265727279149e-05, | |
| "loss": 11.9601, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.3112033195020747, | |
| "grad_norm": 0.010414165444672108, | |
| "learning_rate": 9.407152833295372e-05, | |
| "loss": 11.9166, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.3278008298755186, | |
| "grad_norm": 0.014295806176960468, | |
| "learning_rate": 9.015519730268754e-05, | |
| "loss": 11.883, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3443983402489628, | |
| "grad_norm": 0.011363668367266655, | |
| "learning_rate": 8.62868011073928e-05, | |
| "loss": 11.9823, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.3609958506224067, | |
| "grad_norm": 0.012058326043188572, | |
| "learning_rate": 8.246943827734897e-05, | |
| "loss": 11.9326, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.3775933609958506, | |
| "grad_norm": 0.013995883986353874, | |
| "learning_rate": 7.870616646583648e-05, | |
| "loss": 11.9321, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.3941908713692945, | |
| "grad_norm": 0.017102347686886787, | |
| "learning_rate": 7.500000000000002e-05, | |
| "loss": 11.9893, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.4107883817427385, | |
| "grad_norm": 0.019754430279135704, | |
| "learning_rate": 7.135390746641526e-05, | |
| "loss": 12.3581, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.4273858921161826, | |
| "grad_norm": 0.014634879305958748, | |
| "learning_rate": 6.777080933329354e-05, | |
| "loss": 11.5957, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.4439834024896265, | |
| "grad_norm": 0.01592666283249855, | |
| "learning_rate": 6.425357561122819e-05, | |
| "loss": 11.8704, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.4605809128630705, | |
| "grad_norm": 0.01606922596693039, | |
| "learning_rate": 6.080502355435701e-05, | |
| "loss": 11.7446, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.4771784232365146, | |
| "grad_norm": 0.017506958916783333, | |
| "learning_rate": 5.742791540378175e-05, | |
| "loss": 11.9198, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.4937759336099585, | |
| "grad_norm": 0.014228662475943565, | |
| "learning_rate": 5.4124956175052295e-05, | |
| "loss": 11.9523, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.5103734439834025, | |
| "grad_norm": 0.01120895054191351, | |
| "learning_rate": 5.089879149148781e-05, | |
| "loss": 11.8631, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.5269709543568464, | |
| "grad_norm": 0.01069362461566925, | |
| "learning_rate": 4.7752005465070094e-05, | |
| "loss": 11.9319, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.5435684647302903, | |
| "grad_norm": 0.011584184132516384, | |
| "learning_rate": 4.468711862660662e-05, | |
| "loss": 11.9276, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.5601659751037344, | |
| "grad_norm": 0.012647481635212898, | |
| "learning_rate": 4.1706585906821334e-05, | |
| "loss": 11.9491, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.5767634854771784, | |
| "grad_norm": 0.012272904627025127, | |
| "learning_rate": 3.881279466999001e-05, | |
| "loss": 11.9568, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.5933609958506225, | |
| "grad_norm": 0.016778666526079178, | |
| "learning_rate": 3.600806280169541e-05, | |
| "loss": 11.9439, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.6099585062240664, | |
| "grad_norm": 0.01830066554248333, | |
| "learning_rate": 3.3294636852234105e-05, | |
| "loss": 12.0261, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.6265560165975104, | |
| "grad_norm": 0.0076575614511966705, | |
| "learning_rate": 3.067469023716154e-05, | |
| "loss": 9.0989, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.6431535269709543, | |
| "grad_norm": 0.020825980231165886, | |
| "learning_rate": 2.8150321496417135e-05, | |
| "loss": 14.9122, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.6597510373443982, | |
| "grad_norm": 0.013375605456531048, | |
| "learning_rate": 2.5723552613423687e-05, | |
| "loss": 11.6177, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6597510373443982, | |
| "eval_loss": 11.921277046203613, | |
| "eval_runtime": 0.0676, | |
| "eval_samples_per_second": 739.82, | |
| "eval_steps_per_second": 29.593, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6763485477178424, | |
| "grad_norm": 0.01629016175866127, | |
| "learning_rate": 2.3396327395507448e-05, | |
| "loss": 11.9071, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.6929460580912863, | |
| "grad_norm": 0.015467053279280663, | |
| "learning_rate": 2.117050991693609e-05, | |
| "loss": 11.8865, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.7095435684647304, | |
| "grad_norm": 0.01504999864846468, | |
| "learning_rate": 1.9047883025821774e-05, | |
| "loss": 11.9293, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.7261410788381744, | |
| "grad_norm": 0.01039854995906353, | |
| "learning_rate": 1.7030146916085185e-05, | |
| "loss": 11.8954, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.7427385892116183, | |
| "grad_norm": 0.011301021091639996, | |
| "learning_rate": 1.5118917765624467e-05, | |
| "loss": 11.9575, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.7593360995850622, | |
| "grad_norm": 0.009601314552128315, | |
| "learning_rate": 1.3315726441779629e-05, | |
| "loss": 11.9122, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.7759336099585061, | |
| "grad_norm": 0.011440463364124298, | |
| "learning_rate": 1.1622017275129708e-05, | |
| "loss": 11.9329, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.79253112033195, | |
| "grad_norm": 0.013274903409183025, | |
| "learning_rate": 1.00391469026044e-05, | |
| "loss": 11.9641, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.8091286307053942, | |
| "grad_norm": 0.013196711428463459, | |
| "learning_rate": 8.568383180837368e-06, | |
| "loss": 12.013, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.8257261410788381, | |
| "grad_norm": 0.022849783301353455, | |
| "learning_rate": 7.210904170631021e-06, | |
| "loss": 12.3974, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.8423236514522823, | |
| "grad_norm": 0.015286913141608238, | |
| "learning_rate": 5.967797193346574e-06, | |
| "loss": 11.7548, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.8589211618257262, | |
| "grad_norm": 0.012541989795863628, | |
| "learning_rate": 4.840057959975169e-06, | |
| "loss": 11.5806, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.8755186721991701, | |
| "grad_norm": 0.013375689275562763, | |
| "learning_rate": 3.828589773587515e-06, | |
| "loss": 11.8641, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.892116182572614, | |
| "grad_norm": 0.01497753243893385, | |
| "learning_rate": 2.934202805800989e-06, | |
| "loss": 11.8974, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.908713692946058, | |
| "grad_norm": 0.010004348121583462, | |
| "learning_rate": 2.1576134478437313e-06, | |
| "loss": 11.8974, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.9253112033195021, | |
| "grad_norm": 0.009814193472266197, | |
| "learning_rate": 1.4994437367354339e-06, | |
| "loss": 11.9167, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.941908713692946, | |
| "grad_norm": 0.008285530842840672, | |
| "learning_rate": 9.602208570445636e-07, | |
| "loss": 12.0253, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.9585062240663902, | |
| "grad_norm": 0.01668418012559414, | |
| "learning_rate": 5.403767186210218e-07, | |
| "loss": 11.8426, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.9751037344398341, | |
| "grad_norm": 0.014265616424381733, | |
| "learning_rate": 2.402476106425466e-07, | |
| "loss": 12.0079, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.991701244813278, | |
| "grad_norm": 0.016387728974223137, | |
| "learning_rate": 6.007393225176404e-08, | |
| "loss": 12.1605, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.008298755186722, | |
| "grad_norm": 0.04243115335702896, | |
| "learning_rate": 0.0, | |
| "loss": 20.6424, | |
| "step": 121 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 121, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 774412984320.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |