{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "global_step": 168252, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.9851413356156244e-05, "loss": 9.0623, "step": 500 }, { "epoch": 0.02, "learning_rate": 4.9702826712312485e-05, "loss": 8.8042, "step": 1000 }, { "epoch": 0.03, "learning_rate": 4.9554240068468726e-05, "loss": 8.6835, "step": 1500 }, { "epoch": 0.04, "learning_rate": 4.940565342462497e-05, "loss": 8.721, "step": 2000 }, { "epoch": 0.04, "learning_rate": 4.9257066780781215e-05, "loss": 8.7979, "step": 2500 }, { "epoch": 0.05, "learning_rate": 4.910848013693745e-05, "loss": 8.7957, "step": 3000 }, { "epoch": 0.06, "learning_rate": 4.89598934930937e-05, "loss": 8.7586, "step": 3500 }, { "epoch": 0.07, "learning_rate": 4.881130684924994e-05, "loss": 8.7277, "step": 4000 }, { "epoch": 0.08, "learning_rate": 4.866272020540618e-05, "loss": 8.754, "step": 4500 }, { "epoch": 0.09, "learning_rate": 4.851413356156242e-05, "loss": 8.6946, "step": 5000 }, { "epoch": 0.1, "learning_rate": 4.836554691771866e-05, "loss": 8.6201, "step": 5500 }, { "epoch": 0.11, "learning_rate": 4.82169602738749e-05, "loss": 8.7833, "step": 6000 }, { "epoch": 0.12, "learning_rate": 4.8068373630031144e-05, "loss": 8.5384, "step": 6500 }, { "epoch": 0.12, "learning_rate": 4.7919786986187386e-05, "loss": 8.6775, "step": 7000 }, { "epoch": 0.13, "learning_rate": 4.7771200342343634e-05, "loss": 8.5872, "step": 7500 }, { "epoch": 0.14, "learning_rate": 4.7622613698499875e-05, "loss": 8.7197, "step": 8000 }, { "epoch": 0.15, "learning_rate": 4.747402705465611e-05, "loss": 8.6843, "step": 8500 }, { "epoch": 0.16, "learning_rate": 4.732544041081236e-05, "loss": 8.466, "step": 9000 }, { "epoch": 0.17, "learning_rate": 4.71768537669686e-05, "loss": 8.8049, "step": 9500 }, { "epoch": 0.18, "learning_rate": 4.702826712312484e-05, "loss": 8.5617, "step": 10000 }, { "epoch": 0.19, "learning_rate": 4.687968047928108e-05, "loss": 8.4742, "step": 10500 }, { "epoch": 0.2, "learning_rate": 4.673109383543732e-05, "loss": 8.7015, "step": 11000 }, { "epoch": 0.21, "learning_rate": 4.658250719159356e-05, "loss": 8.5935, "step": 11500 }, { "epoch": 0.21, "learning_rate": 4.6433920547749804e-05, "loss": 8.5818, "step": 12000 }, { "epoch": 0.22, "learning_rate": 4.6285333903906045e-05, "loss": 8.594, "step": 12500 }, { "epoch": 0.23, "learning_rate": 4.613674726006229e-05, "loss": 8.5958, "step": 13000 }, { "epoch": 0.24, "learning_rate": 4.5988160616218534e-05, "loss": 8.6729, "step": 13500 }, { "epoch": 0.25, "learning_rate": 4.583957397237477e-05, "loss": 8.5583, "step": 14000 }, { "epoch": 0.26, "learning_rate": 4.569098732853102e-05, "loss": 8.4468, "step": 14500 }, { "epoch": 0.27, "learning_rate": 4.554240068468726e-05, "loss": 8.4181, "step": 15000 }, { "epoch": 0.28, "learning_rate": 4.53938140408435e-05, "loss": 8.549, "step": 15500 }, { "epoch": 0.29, "learning_rate": 4.524522739699974e-05, "loss": 8.4542, "step": 16000 }, { "epoch": 0.29, "learning_rate": 4.509664075315598e-05, "loss": 8.4954, "step": 16500 }, { "epoch": 0.3, "learning_rate": 4.494805410931223e-05, "loss": 8.3789, "step": 17000 }, { "epoch": 0.31, "learning_rate": 4.4799467465468464e-05, "loss": 8.4243, "step": 17500 }, { "epoch": 0.32, "learning_rate": 4.4650880821624705e-05, "loss": 8.5108, "step": 18000 }, { "epoch": 0.33, "learning_rate": 4.450229417778095e-05, "loss": 8.5746, "step": 18500 }, { "epoch": 0.34, "learning_rate": 4.435370753393719e-05, "loss": 8.5546, "step": 19000 }, { "epoch": 0.35, "learning_rate": 4.4205120890093435e-05, "loss": 8.5514, "step": 19500 }, { "epoch": 0.36, "learning_rate": 4.4056534246249676e-05, "loss": 8.4347, "step": 20000 }, { "epoch": 0.37, "learning_rate": 4.390794760240592e-05, "loss": 8.5224, "step": 20500 }, { "epoch": 0.37, "learning_rate": 4.375936095856216e-05, "loss": 8.4994, "step": 21000 }, { "epoch": 0.38, "learning_rate": 4.36107743147184e-05, "loss": 8.4593, "step": 21500 }, { "epoch": 0.39, "learning_rate": 4.346218767087464e-05, "loss": 8.4521, "step": 22000 }, { "epoch": 0.4, "learning_rate": 4.331360102703089e-05, "loss": 8.5219, "step": 22500 }, { "epoch": 0.41, "learning_rate": 4.3165014383187123e-05, "loss": 8.4422, "step": 23000 }, { "epoch": 0.42, "learning_rate": 4.3016427739343365e-05, "loss": 8.6163, "step": 23500 }, { "epoch": 0.43, "learning_rate": 4.286784109549961e-05, "loss": 8.5638, "step": 24000 }, { "epoch": 0.44, "learning_rate": 4.271925445165585e-05, "loss": 8.6115, "step": 24500 }, { "epoch": 0.45, "learning_rate": 4.2570667807812095e-05, "loss": 8.4891, "step": 25000 }, { "epoch": 0.45, "learning_rate": 4.2422081163968336e-05, "loss": 8.4262, "step": 25500 }, { "epoch": 0.46, "learning_rate": 4.227349452012458e-05, "loss": 8.477, "step": 26000 }, { "epoch": 0.47, "learning_rate": 4.212490787628082e-05, "loss": 8.4471, "step": 26500 }, { "epoch": 0.48, "learning_rate": 4.197632123243706e-05, "loss": 8.5222, "step": 27000 }, { "epoch": 0.49, "learning_rate": 4.18277345885933e-05, "loss": 8.5666, "step": 27500 }, { "epoch": 0.5, "learning_rate": 4.167914794474955e-05, "loss": 8.4356, "step": 28000 }, { "epoch": 0.51, "learning_rate": 4.153056130090578e-05, "loss": 8.4847, "step": 28500 }, { "epoch": 0.52, "learning_rate": 4.138197465706203e-05, "loss": 8.4716, "step": 29000 }, { "epoch": 0.53, "learning_rate": 4.123338801321827e-05, "loss": 8.5387, "step": 29500 }, { "epoch": 0.53, "learning_rate": 4.1084801369374507e-05, "loss": 8.5522, "step": 30000 }, { "epoch": 0.54, "learning_rate": 4.0936214725530755e-05, "loss": 8.6269, "step": 30500 }, { "epoch": 0.55, "learning_rate": 4.0787628081686996e-05, "loss": 8.4528, "step": 31000 }, { "epoch": 0.56, "learning_rate": 4.063904143784324e-05, "loss": 8.5515, "step": 31500 }, { "epoch": 0.57, "learning_rate": 4.049045479399948e-05, "loss": 8.3859, "step": 32000 }, { "epoch": 0.58, "learning_rate": 4.034186815015572e-05, "loss": 8.5035, "step": 32500 }, { "epoch": 0.59, "learning_rate": 4.019328150631197e-05, "loss": 8.3759, "step": 33000 }, { "epoch": 0.6, "learning_rate": 4.00446948624682e-05, "loss": 8.6423, "step": 33500 }, { "epoch": 0.61, "learning_rate": 3.989610821862444e-05, "loss": 8.4445, "step": 34000 }, { "epoch": 0.62, "learning_rate": 3.974752157478069e-05, "loss": 8.5676, "step": 34500 }, { "epoch": 0.62, "learning_rate": 3.959893493093693e-05, "loss": 8.558, "step": 35000 }, { "epoch": 0.63, "learning_rate": 3.9450348287093166e-05, "loss": 8.5935, "step": 35500 }, { "epoch": 0.64, "learning_rate": 3.9301761643249414e-05, "loss": 8.5513, "step": 36000 }, { "epoch": 0.65, "learning_rate": 3.9153174999405655e-05, "loss": 8.5013, "step": 36500 }, { "epoch": 0.66, "learning_rate": 3.9004588355561897e-05, "loss": 8.367, "step": 37000 }, { "epoch": 0.67, "learning_rate": 3.885600171171814e-05, "loss": 8.3926, "step": 37500 }, { "epoch": 0.68, "learning_rate": 3.870741506787438e-05, "loss": 8.5125, "step": 38000 }, { "epoch": 0.69, "learning_rate": 3.855882842403063e-05, "loss": 8.5391, "step": 38500 }, { "epoch": 0.7, "learning_rate": 3.841024178018686e-05, "loss": 8.6012, "step": 39000 }, { "epoch": 0.7, "learning_rate": 3.82616551363431e-05, "loss": 8.5837, "step": 39500 }, { "epoch": 0.71, "learning_rate": 3.811306849249935e-05, "loss": 8.4399, "step": 40000 }, { "epoch": 0.72, "learning_rate": 3.796448184865559e-05, "loss": 8.3717, "step": 40500 }, { "epoch": 0.73, "learning_rate": 3.781589520481183e-05, "loss": 8.3921, "step": 41000 }, { "epoch": 0.74, "learning_rate": 3.7667308560968074e-05, "loss": 8.6485, "step": 41500 }, { "epoch": 0.75, "learning_rate": 3.7518721917124315e-05, "loss": 8.6172, "step": 42000 }, { "epoch": 0.76, "learning_rate": 3.737013527328056e-05, "loss": 8.4443, "step": 42500 }, { "epoch": 0.77, "learning_rate": 3.72215486294368e-05, "loss": 8.5358, "step": 43000 }, { "epoch": 0.78, "learning_rate": 3.707296198559304e-05, "loss": 8.5569, "step": 43500 }, { "epoch": 0.78, "learning_rate": 3.6924375341749286e-05, "loss": 8.4957, "step": 44000 }, { "epoch": 0.79, "learning_rate": 3.677578869790552e-05, "loss": 8.6387, "step": 44500 }, { "epoch": 0.8, "learning_rate": 3.662720205406177e-05, "loss": 8.4732, "step": 45000 }, { "epoch": 0.81, "learning_rate": 3.647861541021801e-05, "loss": 8.4356, "step": 45500 }, { "epoch": 0.82, "learning_rate": 3.633002876637425e-05, "loss": 8.5194, "step": 46000 }, { "epoch": 0.83, "learning_rate": 3.618144212253049e-05, "loss": 8.5896, "step": 46500 }, { "epoch": 0.84, "learning_rate": 3.6032855478686734e-05, "loss": 8.5769, "step": 47000 }, { "epoch": 0.85, "learning_rate": 3.5884268834842975e-05, "loss": 8.4959, "step": 47500 }, { "epoch": 0.86, "learning_rate": 3.5735682190999216e-05, "loss": 8.4584, "step": 48000 }, { "epoch": 0.86, "learning_rate": 3.558709554715546e-05, "loss": 8.5566, "step": 48500 }, { "epoch": 0.87, "learning_rate": 3.54385089033117e-05, "loss": 8.4576, "step": 49000 }, { "epoch": 0.88, "learning_rate": 3.5289922259467946e-05, "loss": 8.6795, "step": 49500 }, { "epoch": 0.89, "learning_rate": 3.514133561562418e-05, "loss": 8.5897, "step": 50000 }, { "epoch": 0.9, "learning_rate": 3.499274897178043e-05, "loss": 8.576, "step": 50500 }, { "epoch": 0.91, "learning_rate": 3.484416232793667e-05, "loss": 8.5107, "step": 51000 }, { "epoch": 0.92, "learning_rate": 3.469557568409291e-05, "loss": 8.5208, "step": 51500 }, { "epoch": 0.93, "learning_rate": 3.454698904024915e-05, "loss": 8.523, "step": 52000 }, { "epoch": 0.94, "learning_rate": 3.439840239640539e-05, "loss": 8.6138, "step": 52500 }, { "epoch": 0.95, "learning_rate": 3.4249815752561634e-05, "loss": 8.5042, "step": 53000 }, { "epoch": 0.95, "learning_rate": 3.4101229108717876e-05, "loss": 8.6146, "step": 53500 }, { "epoch": 0.96, "learning_rate": 3.395264246487412e-05, "loss": 8.5214, "step": 54000 }, { "epoch": 0.97, "learning_rate": 3.3804055821030365e-05, "loss": 8.4696, "step": 54500 }, { "epoch": 0.98, "learning_rate": 3.3655469177186606e-05, "loss": 8.451, "step": 55000 }, { "epoch": 0.99, "learning_rate": 3.350688253334284e-05, "loss": 8.4613, "step": 55500 }, { "epoch": 1.0, "learning_rate": 3.335829588949909e-05, "loss": 8.4817, "step": 56000 }, { "epoch": 1.01, "learning_rate": 3.320970924565533e-05, "loss": 8.4691, "step": 56500 }, { "epoch": 1.02, "learning_rate": 3.306112260181157e-05, "loss": 8.5732, "step": 57000 }, { "epoch": 1.03, "learning_rate": 3.291253595796781e-05, "loss": 8.4901, "step": 57500 }, { "epoch": 1.03, "learning_rate": 3.276394931412405e-05, "loss": 8.4497, "step": 58000 }, { "epoch": 1.04, "learning_rate": 3.2615362670280294e-05, "loss": 8.5303, "step": 58500 }, { "epoch": 1.05, "learning_rate": 3.2466776026436535e-05, "loss": 8.6241, "step": 59000 }, { "epoch": 1.06, "learning_rate": 3.2318189382592776e-05, "loss": 8.4288, "step": 59500 }, { "epoch": 1.07, "learning_rate": 3.2169602738749024e-05, "loss": 8.4964, "step": 60000 }, { "epoch": 1.08, "learning_rate": 3.2021016094905265e-05, "loss": 8.446, "step": 60500 }, { "epoch": 1.09, "learning_rate": 3.18724294510615e-05, "loss": 8.4443, "step": 61000 }, { "epoch": 1.1, "learning_rate": 3.172384280721775e-05, "loss": 8.5108, "step": 61500 }, { "epoch": 1.11, "learning_rate": 3.157525616337399e-05, "loss": 8.6207, "step": 62000 }, { "epoch": 1.11, "learning_rate": 3.142666951953023e-05, "loss": 8.59, "step": 62500 }, { "epoch": 1.12, "learning_rate": 3.127808287568647e-05, "loss": 8.6877, "step": 63000 }, { "epoch": 1.13, "learning_rate": 3.112949623184271e-05, "loss": 8.4827, "step": 63500 }, { "epoch": 1.14, "learning_rate": 3.098090958799896e-05, "loss": 8.5279, "step": 64000 }, { "epoch": 1.15, "learning_rate": 3.0832322944155195e-05, "loss": 8.4369, "step": 64500 }, { "epoch": 1.16, "learning_rate": 3.0683736300311436e-05, "loss": 8.6061, "step": 65000 }, { "epoch": 1.17, "learning_rate": 3.0535149656467684e-05, "loss": 8.4595, "step": 65500 }, { "epoch": 1.18, "learning_rate": 3.0386563012623925e-05, "loss": 8.3962, "step": 66000 }, { "epoch": 1.19, "learning_rate": 3.0237976368780163e-05, "loss": 8.5392, "step": 66500 }, { "epoch": 1.19, "learning_rate": 3.0089389724936407e-05, "loss": 8.3932, "step": 67000 }, { "epoch": 1.2, "learning_rate": 2.994080308109265e-05, "loss": 8.4278, "step": 67500 }, { "epoch": 1.21, "learning_rate": 2.9792216437248886e-05, "loss": 8.372, "step": 68000 }, { "epoch": 1.22, "learning_rate": 2.964362979340513e-05, "loss": 8.4326, "step": 68500 }, { "epoch": 1.23, "learning_rate": 2.9495043149561376e-05, "loss": 8.394, "step": 69000 }, { "epoch": 1.24, "learning_rate": 2.9346456505717617e-05, "loss": 8.3595, "step": 69500 }, { "epoch": 1.25, "learning_rate": 2.9197869861873855e-05, "loss": 8.4364, "step": 70000 }, { "epoch": 1.26, "learning_rate": 2.90492832180301e-05, "loss": 8.4903, "step": 70500 }, { "epoch": 1.27, "learning_rate": 2.8900696574186344e-05, "loss": 8.5403, "step": 71000 }, { "epoch": 1.27, "learning_rate": 2.875210993034258e-05, "loss": 8.4901, "step": 71500 }, { "epoch": 1.28, "learning_rate": 2.8603523286498823e-05, "loss": 8.5069, "step": 72000 }, { "epoch": 1.29, "learning_rate": 2.8454936642655067e-05, "loss": 8.4554, "step": 72500 }, { "epoch": 1.3, "learning_rate": 2.8306349998811312e-05, "loss": 8.6517, "step": 73000 }, { "epoch": 1.31, "learning_rate": 2.815776335496755e-05, "loss": 8.4631, "step": 73500 }, { "epoch": 1.32, "learning_rate": 2.800917671112379e-05, "loss": 8.4751, "step": 74000 }, { "epoch": 1.33, "learning_rate": 2.7860590067280035e-05, "loss": 8.589, "step": 74500 }, { "epoch": 1.34, "learning_rate": 2.7712003423436276e-05, "loss": 8.515, "step": 75000 }, { "epoch": 1.35, "learning_rate": 2.7563416779592514e-05, "loss": 8.5457, "step": 75500 }, { "epoch": 1.36, "learning_rate": 2.741483013574876e-05, "loss": 8.4698, "step": 76000 }, { "epoch": 1.36, "learning_rate": 2.7266243491905003e-05, "loss": 8.5481, "step": 76500 }, { "epoch": 1.37, "learning_rate": 2.711765684806124e-05, "loss": 8.5733, "step": 77000 }, { "epoch": 1.38, "learning_rate": 2.6969070204217482e-05, "loss": 8.4624, "step": 77500 }, { "epoch": 1.39, "learning_rate": 2.6820483560373727e-05, "loss": 8.4875, "step": 78000 }, { "epoch": 1.4, "learning_rate": 2.667189691652997e-05, "loss": 8.4949, "step": 78500 }, { "epoch": 1.41, "learning_rate": 2.652331027268621e-05, "loss": 8.5104, "step": 79000 }, { "epoch": 1.42, "learning_rate": 2.637472362884245e-05, "loss": 8.6732, "step": 79500 }, { "epoch": 1.43, "learning_rate": 2.6226136984998695e-05, "loss": 8.6028, "step": 80000 }, { "epoch": 1.44, "learning_rate": 2.607755034115494e-05, "loss": 8.6293, "step": 80500 }, { "epoch": 1.44, "learning_rate": 2.5928963697311177e-05, "loss": 8.6331, "step": 81000 }, { "epoch": 1.45, "learning_rate": 2.578037705346742e-05, "loss": 8.4385, "step": 81500 }, { "epoch": 1.46, "learning_rate": 2.5631790409623663e-05, "loss": 8.4303, "step": 82000 }, { "epoch": 1.47, "learning_rate": 2.54832037657799e-05, "loss": 8.3661, "step": 82500 }, { "epoch": 1.48, "learning_rate": 2.5334617121936145e-05, "loss": 8.3943, "step": 83000 }, { "epoch": 1.49, "learning_rate": 2.5186030478092386e-05, "loss": 8.4089, "step": 83500 }, { "epoch": 1.5, "learning_rate": 2.503744383424863e-05, "loss": 8.4719, "step": 84000 }, { "epoch": 1.51, "learning_rate": 2.4888857190404872e-05, "loss": 8.5825, "step": 84500 }, { "epoch": 1.52, "learning_rate": 2.4740270546561113e-05, "loss": 8.4867, "step": 85000 }, { "epoch": 1.52, "learning_rate": 2.459168390271735e-05, "loss": 8.3653, "step": 85500 }, { "epoch": 1.53, "learning_rate": 2.4443097258873596e-05, "loss": 8.4881, "step": 86000 }, { "epoch": 1.54, "learning_rate": 2.4294510615029837e-05, "loss": 8.3916, "step": 86500 }, { "epoch": 1.55, "learning_rate": 2.4145923971186078e-05, "loss": 8.4061, "step": 87000 }, { "epoch": 1.56, "learning_rate": 2.399733732734232e-05, "loss": 8.5029, "step": 87500 }, { "epoch": 1.57, "learning_rate": 2.3848750683498564e-05, "loss": 8.3934, "step": 88000 }, { "epoch": 1.58, "learning_rate": 2.3700164039654805e-05, "loss": 8.4483, "step": 88500 }, { "epoch": 1.59, "learning_rate": 2.3551577395811046e-05, "loss": 8.4115, "step": 89000 }, { "epoch": 1.6, "learning_rate": 2.3402990751967287e-05, "loss": 8.599, "step": 89500 }, { "epoch": 1.6, "learning_rate": 2.3254404108123532e-05, "loss": 8.4504, "step": 90000 }, { "epoch": 1.61, "learning_rate": 2.3105817464279773e-05, "loss": 8.3569, "step": 90500 }, { "epoch": 1.62, "learning_rate": 2.2957230820436014e-05, "loss": 8.6043, "step": 91000 }, { "epoch": 1.63, "learning_rate": 2.2808644176592255e-05, "loss": 8.3064, "step": 91500 }, { "epoch": 1.64, "learning_rate": 2.2660057532748497e-05, "loss": 8.6221, "step": 92000 }, { "epoch": 1.65, "learning_rate": 2.251147088890474e-05, "loss": 8.4029, "step": 92500 }, { "epoch": 1.66, "learning_rate": 2.236288424506098e-05, "loss": 8.5238, "step": 93000 }, { "epoch": 1.67, "learning_rate": 2.2214297601217223e-05, "loss": 8.3069, "step": 93500 }, { "epoch": 1.68, "learning_rate": 2.2065710957373465e-05, "loss": 8.5189, "step": 94000 }, { "epoch": 1.68, "learning_rate": 2.191712431352971e-05, "loss": 8.5181, "step": 94500 }, { "epoch": 1.69, "learning_rate": 2.1768537669685947e-05, "loss": 8.586, "step": 95000 }, { "epoch": 1.7, "learning_rate": 2.1619951025842188e-05, "loss": 8.3729, "step": 95500 }, { "epoch": 1.71, "learning_rate": 2.1471364381998433e-05, "loss": 8.6504, "step": 96000 }, { "epoch": 1.72, "learning_rate": 2.1322777738154674e-05, "loss": 8.493, "step": 96500 }, { "epoch": 1.73, "learning_rate": 2.1174191094310915e-05, "loss": 8.3185, "step": 97000 }, { "epoch": 1.74, "learning_rate": 2.1025604450467156e-05, "loss": 8.439, "step": 97500 }, { "epoch": 1.75, "learning_rate": 2.08770178066234e-05, "loss": 8.5533, "step": 98000 }, { "epoch": 1.76, "learning_rate": 2.0728431162779642e-05, "loss": 8.3284, "step": 98500 }, { "epoch": 1.77, "learning_rate": 2.0579844518935883e-05, "loss": 8.315, "step": 99000 }, { "epoch": 1.77, "learning_rate": 2.0431257875092124e-05, "loss": 8.4237, "step": 99500 }, { "epoch": 1.78, "learning_rate": 2.0282671231248365e-05, "loss": 8.4191, "step": 100000 }, { "epoch": 1.79, "learning_rate": 2.013408458740461e-05, "loss": 8.4631, "step": 100500 }, { "epoch": 1.8, "learning_rate": 1.9985497943560848e-05, "loss": 8.2988, "step": 101000 }, { "epoch": 1.81, "learning_rate": 1.9836911299717092e-05, "loss": 8.3866, "step": 101500 }, { "epoch": 1.82, "learning_rate": 1.9688324655873334e-05, "loss": 8.4536, "step": 102000 }, { "epoch": 1.83, "learning_rate": 1.9539738012029578e-05, "loss": 8.5572, "step": 102500 }, { "epoch": 1.84, "learning_rate": 1.9391151368185816e-05, "loss": 8.366, "step": 103000 }, { "epoch": 1.85, "learning_rate": 1.924256472434206e-05, "loss": 8.3163, "step": 103500 }, { "epoch": 1.85, "learning_rate": 1.90939780804983e-05, "loss": 8.3835, "step": 104000 }, { "epoch": 1.86, "learning_rate": 1.8945391436654543e-05, "loss": 8.5343, "step": 104500 }, { "epoch": 1.87, "learning_rate": 1.8796804792810784e-05, "loss": 8.3379, "step": 105000 }, { "epoch": 1.88, "learning_rate": 1.8648218148967025e-05, "loss": 8.4609, "step": 105500 }, { "epoch": 1.89, "learning_rate": 1.849963150512327e-05, "loss": 8.5256, "step": 106000 }, { "epoch": 1.9, "learning_rate": 1.835104486127951e-05, "loss": 8.3157, "step": 106500 }, { "epoch": 1.91, "learning_rate": 1.8202458217435752e-05, "loss": 8.6021, "step": 107000 }, { "epoch": 1.92, "learning_rate": 1.8053871573591993e-05, "loss": 8.4711, "step": 107500 }, { "epoch": 1.93, "learning_rate": 1.7905284929748238e-05, "loss": 8.4117, "step": 108000 }, { "epoch": 1.93, "learning_rate": 1.775669828590448e-05, "loss": 8.3728, "step": 108500 }, { "epoch": 1.94, "learning_rate": 1.760811164206072e-05, "loss": 8.475, "step": 109000 }, { "epoch": 1.95, "learning_rate": 1.745952499821696e-05, "loss": 8.4445, "step": 109500 }, { "epoch": 1.96, "learning_rate": 1.7310938354373202e-05, "loss": 8.4425, "step": 110000 }, { "epoch": 1.97, "learning_rate": 1.7162351710529444e-05, "loss": 8.4416, "step": 110500 }, { "epoch": 1.98, "learning_rate": 1.7013765066685685e-05, "loss": 8.4447, "step": 111000 }, { "epoch": 1.99, "learning_rate": 1.686517842284193e-05, "loss": 8.5124, "step": 111500 }, { "epoch": 2.0, "learning_rate": 1.671659177899817e-05, "loss": 8.187, "step": 112000 }, { "epoch": 2.01, "learning_rate": 1.656800513515441e-05, "loss": 8.3755, "step": 112500 }, { "epoch": 2.01, "learning_rate": 1.6419418491310653e-05, "loss": 8.3418, "step": 113000 }, { "epoch": 2.02, "learning_rate": 1.6270831847466897e-05, "loss": 8.4131, "step": 113500 }, { "epoch": 2.03, "learning_rate": 1.612224520362314e-05, "loss": 8.3132, "step": 114000 }, { "epoch": 2.04, "learning_rate": 1.597365855977938e-05, "loss": 8.4248, "step": 114500 }, { "epoch": 2.05, "learning_rate": 1.582507191593562e-05, "loss": 8.3797, "step": 115000 }, { "epoch": 2.06, "learning_rate": 1.5676485272091862e-05, "loss": 8.3197, "step": 115500 }, { "epoch": 2.07, "learning_rate": 1.5527898628248107e-05, "loss": 8.3627, "step": 116000 }, { "epoch": 2.08, "learning_rate": 1.5379311984404344e-05, "loss": 8.3708, "step": 116500 }, { "epoch": 2.09, "learning_rate": 1.5230725340560589e-05, "loss": 8.3659, "step": 117000 }, { "epoch": 2.1, "learning_rate": 1.508213869671683e-05, "loss": 8.4066, "step": 117500 }, { "epoch": 2.1, "learning_rate": 1.4933552052873073e-05, "loss": 8.4507, "step": 118000 }, { "epoch": 2.11, "learning_rate": 1.4784965409029314e-05, "loss": 8.3325, "step": 118500 }, { "epoch": 2.12, "learning_rate": 1.4636378765185554e-05, "loss": 8.4277, "step": 119000 }, { "epoch": 2.13, "learning_rate": 1.4487792121341798e-05, "loss": 8.3021, "step": 119500 }, { "epoch": 2.14, "learning_rate": 1.4339205477498038e-05, "loss": 8.4499, "step": 120000 }, { "epoch": 2.15, "learning_rate": 1.4190618833654282e-05, "loss": 8.3656, "step": 120500 }, { "epoch": 2.16, "learning_rate": 1.4042032189810522e-05, "loss": 8.4882, "step": 121000 }, { "epoch": 2.17, "learning_rate": 1.3893445545966766e-05, "loss": 8.5041, "step": 121500 }, { "epoch": 2.18, "learning_rate": 1.3744858902123006e-05, "loss": 8.2957, "step": 122000 }, { "epoch": 2.18, "learning_rate": 1.359627225827925e-05, "loss": 8.3517, "step": 122500 }, { "epoch": 2.19, "learning_rate": 1.344768561443549e-05, "loss": 8.3476, "step": 123000 }, { "epoch": 2.2, "learning_rate": 1.3299098970591731e-05, "loss": 8.3239, "step": 123500 }, { "epoch": 2.21, "learning_rate": 1.3150512326747974e-05, "loss": 8.3705, "step": 124000 }, { "epoch": 2.22, "learning_rate": 1.3001925682904215e-05, "loss": 8.2817, "step": 124500 }, { "epoch": 2.23, "learning_rate": 1.2853339039060458e-05, "loss": 8.386, "step": 125000 }, { "epoch": 2.24, "learning_rate": 1.2704752395216699e-05, "loss": 8.3455, "step": 125500 }, { "epoch": 2.25, "learning_rate": 1.2556165751372942e-05, "loss": 8.3228, "step": 126000 }, { "epoch": 2.26, "learning_rate": 1.2407579107529183e-05, "loss": 8.3176, "step": 126500 }, { "epoch": 2.26, "learning_rate": 1.2258992463685424e-05, "loss": 8.4304, "step": 127000 }, { "epoch": 2.27, "learning_rate": 1.2110405819841667e-05, "loss": 8.4209, "step": 127500 }, { "epoch": 2.28, "learning_rate": 1.1961819175997908e-05, "loss": 8.3362, "step": 128000 }, { "epoch": 2.29, "learning_rate": 1.1813232532154151e-05, "loss": 8.3753, "step": 128500 }, { "epoch": 2.3, "learning_rate": 1.1664645888310392e-05, "loss": 8.2538, "step": 129000 }, { "epoch": 2.31, "learning_rate": 1.1516059244466634e-05, "loss": 8.1921, "step": 129500 }, { "epoch": 2.32, "learning_rate": 1.1367472600622876e-05, "loss": 8.3222, "step": 130000 }, { "epoch": 2.33, "learning_rate": 1.1218885956779118e-05, "loss": 8.2967, "step": 130500 }, { "epoch": 2.34, "learning_rate": 1.1070299312935359e-05, "loss": 8.33, "step": 131000 }, { "epoch": 2.34, "learning_rate": 1.0921712669091602e-05, "loss": 8.4005, "step": 131500 }, { "epoch": 2.35, "learning_rate": 1.0773126025247843e-05, "loss": 8.3699, "step": 132000 }, { "epoch": 2.36, "learning_rate": 1.0624539381404084e-05, "loss": 8.3546, "step": 132500 }, { "epoch": 2.37, "learning_rate": 1.0475952737560327e-05, "loss": 8.4229, "step": 133000 }, { "epoch": 2.38, "learning_rate": 1.0327366093716568e-05, "loss": 8.3003, "step": 133500 }, { "epoch": 2.39, "learning_rate": 1.0178779449872811e-05, "loss": 8.3456, "step": 134000 }, { "epoch": 2.4, "learning_rate": 1.0030192806029052e-05, "loss": 8.2217, "step": 134500 }, { "epoch": 2.41, "learning_rate": 9.881606162185295e-06, "loss": 8.3187, "step": 135000 }, { "epoch": 2.42, "learning_rate": 9.733019518341534e-06, "loss": 8.3815, "step": 135500 }, { "epoch": 2.42, "learning_rate": 9.584432874497777e-06, "loss": 8.2689, "step": 136000 }, { "epoch": 2.43, "learning_rate": 9.435846230654018e-06, "loss": 8.3191, "step": 136500 }, { "epoch": 2.44, "learning_rate": 9.287259586810261e-06, "loss": 8.4162, "step": 137000 }, { "epoch": 2.45, "learning_rate": 9.138672942966502e-06, "loss": 8.3997, "step": 137500 }, { "epoch": 2.46, "learning_rate": 8.990086299122745e-06, "loss": 8.3898, "step": 138000 }, { "epoch": 2.47, "learning_rate": 8.841499655278986e-06, "loss": 8.3515, "step": 138500 }, { "epoch": 2.48, "learning_rate": 8.69291301143523e-06, "loss": 8.402, "step": 139000 }, { "epoch": 2.49, "learning_rate": 8.54432636759147e-06, "loss": 8.5421, "step": 139500 }, { "epoch": 2.5, "learning_rate": 8.395739723747713e-06, "loss": 8.284, "step": 140000 }, { "epoch": 2.51, "learning_rate": 8.247153079903953e-06, "loss": 8.3907, "step": 140500 }, { "epoch": 2.51, "learning_rate": 8.098566436060196e-06, "loss": 8.2416, "step": 141000 }, { "epoch": 2.52, "learning_rate": 7.949979792216437e-06, "loss": 8.2786, "step": 141500 }, { "epoch": 2.53, "learning_rate": 7.80139314837268e-06, "loss": 8.218, "step": 142000 }, { "epoch": 2.54, "learning_rate": 7.652806504528921e-06, "loss": 8.3371, "step": 142500 }, { "epoch": 2.55, "learning_rate": 7.504219860685163e-06, "loss": 8.4112, "step": 143000 }, { "epoch": 2.56, "learning_rate": 7.355633216841405e-06, "loss": 8.3448, "step": 143500 }, { "epoch": 2.57, "learning_rate": 7.207046572997647e-06, "loss": 8.3472, "step": 144000 }, { "epoch": 2.58, "learning_rate": 7.058459929153889e-06, "loss": 8.256, "step": 144500 }, { "epoch": 2.59, "learning_rate": 6.909873285310129e-06, "loss": 8.362, "step": 145000 }, { "epoch": 2.59, "learning_rate": 6.761286641466371e-06, "loss": 8.3393, "step": 145500 }, { "epoch": 2.6, "learning_rate": 6.612699997622613e-06, "loss": 8.2448, "step": 146000 }, { "epoch": 2.61, "learning_rate": 6.464113353778855e-06, "loss": 8.3471, "step": 146500 }, { "epoch": 2.62, "learning_rate": 6.315526709935097e-06, "loss": 8.2684, "step": 147000 }, { "epoch": 2.63, "learning_rate": 6.1669400660913394e-06, "loss": 8.3226, "step": 147500 }, { "epoch": 2.64, "learning_rate": 6.0183534222475815e-06, "loss": 8.3493, "step": 148000 }, { "epoch": 2.65, "learning_rate": 5.869766778403823e-06, "loss": 8.3861, "step": 148500 }, { "epoch": 2.66, "learning_rate": 5.721180134560065e-06, "loss": 8.2889, "step": 149000 }, { "epoch": 2.67, "learning_rate": 5.572593490716307e-06, "loss": 8.3556, "step": 149500 }, { "epoch": 2.67, "learning_rate": 5.424006846872549e-06, "loss": 8.2095, "step": 150000 }, { "epoch": 2.68, "learning_rate": 5.275420203028791e-06, "loss": 8.1834, "step": 150500 }, { "epoch": 2.69, "learning_rate": 5.126833559185032e-06, "loss": 8.3183, "step": 151000 }, { "epoch": 2.7, "learning_rate": 4.978246915341274e-06, "loss": 8.2933, "step": 151500 }, { "epoch": 2.71, "learning_rate": 4.829660271497516e-06, "loss": 8.2567, "step": 152000 }, { "epoch": 2.72, "learning_rate": 4.681073627653758e-06, "loss": 8.3184, "step": 152500 }, { "epoch": 2.73, "learning_rate": 4.53248698381e-06, "loss": 8.4259, "step": 153000 }, { "epoch": 2.74, "learning_rate": 4.383900339966241e-06, "loss": 8.3777, "step": 153500 }, { "epoch": 2.75, "learning_rate": 4.235313696122483e-06, "loss": 8.2875, "step": 154000 }, { "epoch": 2.75, "learning_rate": 4.086727052278725e-06, "loss": 8.3118, "step": 154500 }, { "epoch": 2.76, "learning_rate": 3.938140408434967e-06, "loss": 8.2465, "step": 155000 }, { "epoch": 2.77, "learning_rate": 3.7895537645912088e-06, "loss": 8.4145, "step": 155500 }, { "epoch": 2.78, "learning_rate": 3.6409671207474504e-06, "loss": 8.1984, "step": 156000 }, { "epoch": 2.79, "learning_rate": 3.4923804769036924e-06, "loss": 8.3681, "step": 156500 }, { "epoch": 2.8, "learning_rate": 3.343793833059934e-06, "loss": 8.1982, "step": 157000 }, { "epoch": 2.81, "learning_rate": 3.195207189216176e-06, "loss": 8.303, "step": 157500 }, { "epoch": 2.82, "learning_rate": 3.0466205453724176e-06, "loss": 8.3355, "step": 158000 }, { "epoch": 2.83, "learning_rate": 2.898033901528659e-06, "loss": 8.3953, "step": 158500 }, { "epoch": 2.84, "learning_rate": 2.749447257684901e-06, "loss": 8.4069, "step": 159000 }, { "epoch": 2.84, "learning_rate": 2.6008606138411432e-06, "loss": 8.3092, "step": 159500 }, { "epoch": 2.85, "learning_rate": 2.452273969997385e-06, "loss": 8.3073, "step": 160000 }, { "epoch": 2.86, "learning_rate": 2.303687326153627e-06, "loss": 8.3872, "step": 160500 }, { "epoch": 2.87, "learning_rate": 2.1551006823098684e-06, "loss": 8.3404, "step": 161000 }, { "epoch": 2.88, "learning_rate": 2.0065140384661104e-06, "loss": 8.2552, "step": 161500 }, { "epoch": 2.89, "learning_rate": 1.8579273946223525e-06, "loss": 8.2809, "step": 162000 }, { "epoch": 2.9, "learning_rate": 1.709340750778594e-06, "loss": 8.3951, "step": 162500 }, { "epoch": 2.91, "learning_rate": 1.5607541069348359e-06, "loss": 8.3388, "step": 163000 }, { "epoch": 2.92, "learning_rate": 1.4121674630910779e-06, "loss": 8.2567, "step": 163500 }, { "epoch": 2.92, "learning_rate": 1.2635808192473197e-06, "loss": 8.4246, "step": 164000 }, { "epoch": 2.93, "learning_rate": 1.1149941754035615e-06, "loss": 8.2949, "step": 164500 }, { "epoch": 2.94, "learning_rate": 9.66407531559803e-07, "loss": 8.3421, "step": 165000 }, { "epoch": 2.95, "learning_rate": 8.17820887716045e-07, "loss": 8.1758, "step": 165500 }, { "epoch": 2.96, "learning_rate": 6.692342438722869e-07, "loss": 8.305, "step": 166000 }, { "epoch": 2.97, "learning_rate": 5.206476000285286e-07, "loss": 8.3029, "step": 166500 }, { "epoch": 2.98, "learning_rate": 3.720609561847705e-07, "loss": 8.2702, "step": 167000 }, { "epoch": 2.99, "learning_rate": 2.234743123410123e-07, "loss": 8.3746, "step": 167500 }, { "epoch": 3.0, "learning_rate": 7.488766849725412e-08, "loss": 8.2764, "step": 168000 }, { "epoch": 3.0, "step": 168252, "total_flos": 6046176456633600.0, "train_loss": 8.453391505526772, "train_runtime": 13355.768, "train_samples_per_second": 25.195, "train_steps_per_second": 12.598 } ], "max_steps": 168252, "num_train_epochs": 3, "total_flos": 6046176456633600.0, "trial_name": null, "trial_params": null }