mbart-summarization-mlsum / trainer_state.json
artelabsuper
trained model
6424b22
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"global_step": 127988,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.980466918773635e-05,
"loss": 3.8391,
"step": 500
},
{
"epoch": 0.03,
"learning_rate": 4.96093383754727e-05,
"loss": 3.5549,
"step": 1000
},
{
"epoch": 0.05,
"learning_rate": 4.941400756320905e-05,
"loss": 3.5792,
"step": 1500
},
{
"epoch": 0.06,
"learning_rate": 4.9218676750945406e-05,
"loss": 3.4807,
"step": 2000
},
{
"epoch": 0.08,
"learning_rate": 4.9023345938681755e-05,
"loss": 5.5711,
"step": 2500
},
{
"epoch": 0.09,
"learning_rate": 4.8828015126418104e-05,
"loss": 3.4924,
"step": 3000
},
{
"epoch": 0.11,
"learning_rate": 4.863268431415445e-05,
"loss": 3.3686,
"step": 3500
},
{
"epoch": 0.13,
"learning_rate": 4.84373535018908e-05,
"loss": 3.3857,
"step": 4000
},
{
"epoch": 0.14,
"learning_rate": 4.824202268962715e-05,
"loss": 3.3547,
"step": 4500
},
{
"epoch": 0.16,
"learning_rate": 4.80466918773635e-05,
"loss": 3.3625,
"step": 5000
},
{
"epoch": 0.17,
"learning_rate": 4.7851361065099856e-05,
"loss": 3.3164,
"step": 5500
},
{
"epoch": 0.19,
"learning_rate": 4.7656030252836205e-05,
"loss": 3.301,
"step": 6000
},
{
"epoch": 0.2,
"learning_rate": 4.7460699440572554e-05,
"loss": 3.1746,
"step": 6500
},
{
"epoch": 0.22,
"learning_rate": 4.7265368628308904e-05,
"loss": 3.2548,
"step": 7000
},
{
"epoch": 0.23,
"learning_rate": 4.707003781604525e-05,
"loss": 3.1595,
"step": 7500
},
{
"epoch": 0.25,
"learning_rate": 4.687470700378161e-05,
"loss": 3.2356,
"step": 8000
},
{
"epoch": 0.27,
"learning_rate": 4.667937619151796e-05,
"loss": 3.2533,
"step": 8500
},
{
"epoch": 0.28,
"learning_rate": 4.648404537925431e-05,
"loss": 3.2142,
"step": 9000
},
{
"epoch": 0.3,
"learning_rate": 4.628871456699066e-05,
"loss": 3.1645,
"step": 9500
},
{
"epoch": 0.31,
"learning_rate": 4.609338375472701e-05,
"loss": 3.2479,
"step": 10000
},
{
"epoch": 0.33,
"learning_rate": 4.589805294246336e-05,
"loss": 3.2195,
"step": 10500
},
{
"epoch": 0.34,
"learning_rate": 4.570272213019971e-05,
"loss": 3.1258,
"step": 11000
},
{
"epoch": 0.36,
"learning_rate": 4.550739131793606e-05,
"loss": 3.1771,
"step": 11500
},
{
"epoch": 0.38,
"learning_rate": 4.531206050567241e-05,
"loss": 3.2118,
"step": 12000
},
{
"epoch": 0.39,
"learning_rate": 4.511672969340876e-05,
"loss": 3.101,
"step": 12500
},
{
"epoch": 0.41,
"learning_rate": 4.492139888114511e-05,
"loss": 3.129,
"step": 13000
},
{
"epoch": 0.42,
"learning_rate": 4.472606806888146e-05,
"loss": 3.1021,
"step": 13500
},
{
"epoch": 0.44,
"learning_rate": 4.453073725661781e-05,
"loss": 3.1185,
"step": 14000
},
{
"epoch": 0.45,
"learning_rate": 4.433540644435416e-05,
"loss": 3.1291,
"step": 14500
},
{
"epoch": 0.47,
"learning_rate": 4.414007563209051e-05,
"loss": 3.0354,
"step": 15000
},
{
"epoch": 0.48,
"learning_rate": 4.394474481982686e-05,
"loss": 3.0164,
"step": 15500
},
{
"epoch": 0.5,
"learning_rate": 4.374941400756321e-05,
"loss": 3.0837,
"step": 16000
},
{
"epoch": 0.52,
"learning_rate": 4.3554083195299564e-05,
"loss": 3.0235,
"step": 16500
},
{
"epoch": 0.53,
"learning_rate": 4.335875238303591e-05,
"loss": 3.0046,
"step": 17000
},
{
"epoch": 0.55,
"learning_rate": 4.316342157077226e-05,
"loss": 3.0702,
"step": 17500
},
{
"epoch": 0.56,
"learning_rate": 4.296809075850861e-05,
"loss": 3.0582,
"step": 18000
},
{
"epoch": 0.58,
"learning_rate": 4.277275994624496e-05,
"loss": 3.039,
"step": 18500
},
{
"epoch": 0.59,
"learning_rate": 4.257742913398131e-05,
"loss": 3.1094,
"step": 19000
},
{
"epoch": 0.61,
"learning_rate": 4.238209832171766e-05,
"loss": 2.9548,
"step": 19500
},
{
"epoch": 0.63,
"learning_rate": 4.2186767509454014e-05,
"loss": 3.0493,
"step": 20000
},
{
"epoch": 0.64,
"learning_rate": 4.1991436697190363e-05,
"loss": 3.0473,
"step": 20500
},
{
"epoch": 0.66,
"learning_rate": 4.179610588492671e-05,
"loss": 3.0363,
"step": 21000
},
{
"epoch": 0.67,
"learning_rate": 4.160077507266306e-05,
"loss": 2.9445,
"step": 21500
},
{
"epoch": 0.69,
"learning_rate": 4.140544426039941e-05,
"loss": 2.9368,
"step": 22000
},
{
"epoch": 0.7,
"learning_rate": 4.121011344813576e-05,
"loss": 2.9829,
"step": 22500
},
{
"epoch": 0.72,
"learning_rate": 4.1014782635872116e-05,
"loss": 3.0427,
"step": 23000
},
{
"epoch": 0.73,
"learning_rate": 4.0819451823608465e-05,
"loss": 2.974,
"step": 23500
},
{
"epoch": 0.75,
"learning_rate": 4.062412101134482e-05,
"loss": 2.9314,
"step": 24000
},
{
"epoch": 0.77,
"learning_rate": 4.042879019908117e-05,
"loss": 2.9788,
"step": 24500
},
{
"epoch": 0.78,
"learning_rate": 4.023345938681752e-05,
"loss": 2.9794,
"step": 25000
},
{
"epoch": 0.8,
"learning_rate": 4.003812857455387e-05,
"loss": 2.9851,
"step": 25500
},
{
"epoch": 0.81,
"learning_rate": 3.984279776229022e-05,
"loss": 2.9453,
"step": 26000
},
{
"epoch": 0.83,
"learning_rate": 3.9647466950026566e-05,
"loss": 3.0433,
"step": 26500
},
{
"epoch": 0.84,
"learning_rate": 3.9452136137762916e-05,
"loss": 2.956,
"step": 27000
},
{
"epoch": 0.86,
"learning_rate": 3.925680532549927e-05,
"loss": 2.9388,
"step": 27500
},
{
"epoch": 0.88,
"learning_rate": 3.906147451323562e-05,
"loss": 2.9308,
"step": 28000
},
{
"epoch": 0.89,
"learning_rate": 3.886614370097197e-05,
"loss": 2.9588,
"step": 28500
},
{
"epoch": 0.91,
"learning_rate": 3.867081288870832e-05,
"loss": 2.9588,
"step": 29000
},
{
"epoch": 0.92,
"learning_rate": 3.847548207644467e-05,
"loss": 2.8812,
"step": 29500
},
{
"epoch": 0.94,
"learning_rate": 3.828015126418102e-05,
"loss": 2.9103,
"step": 30000
},
{
"epoch": 0.95,
"learning_rate": 3.8084820451917366e-05,
"loss": 2.8671,
"step": 30500
},
{
"epoch": 0.97,
"learning_rate": 3.788948963965372e-05,
"loss": 2.868,
"step": 31000
},
{
"epoch": 0.98,
"learning_rate": 3.769415882739007e-05,
"loss": 2.9499,
"step": 31500
},
{
"epoch": 1.0,
"learning_rate": 3.749882801512642e-05,
"loss": 2.9272,
"step": 32000
},
{
"epoch": 1.02,
"learning_rate": 3.730349720286277e-05,
"loss": 2.3079,
"step": 32500
},
{
"epoch": 1.03,
"learning_rate": 3.710816639059912e-05,
"loss": 2.3296,
"step": 33000
},
{
"epoch": 1.05,
"learning_rate": 3.691283557833547e-05,
"loss": 2.3636,
"step": 33500
},
{
"epoch": 1.06,
"learning_rate": 3.671750476607182e-05,
"loss": 2.3879,
"step": 34000
},
{
"epoch": 1.08,
"learning_rate": 3.652217395380817e-05,
"loss": 2.3653,
"step": 34500
},
{
"epoch": 1.09,
"learning_rate": 3.632684314154452e-05,
"loss": 2.2813,
"step": 35000
},
{
"epoch": 1.11,
"learning_rate": 3.613151232928087e-05,
"loss": 2.3776,
"step": 35500
},
{
"epoch": 1.13,
"learning_rate": 3.593618151701722e-05,
"loss": 2.3478,
"step": 36000
},
{
"epoch": 1.14,
"learning_rate": 3.574085070475357e-05,
"loss": 2.3453,
"step": 36500
},
{
"epoch": 1.16,
"learning_rate": 3.554551989248992e-05,
"loss": 2.3145,
"step": 37000
},
{
"epoch": 1.17,
"learning_rate": 3.535018908022627e-05,
"loss": 2.3296,
"step": 37500
},
{
"epoch": 1.19,
"learning_rate": 3.515485826796262e-05,
"loss": 2.3543,
"step": 38000
},
{
"epoch": 1.2,
"learning_rate": 3.495952745569898e-05,
"loss": 2.289,
"step": 38500
},
{
"epoch": 1.22,
"learning_rate": 3.476419664343533e-05,
"loss": 2.4305,
"step": 39000
},
{
"epoch": 1.23,
"learning_rate": 3.456886583117168e-05,
"loss": 2.3672,
"step": 39500
},
{
"epoch": 1.25,
"learning_rate": 3.4373535018908026e-05,
"loss": 2.3041,
"step": 40000
},
{
"epoch": 1.27,
"learning_rate": 3.4178204206644375e-05,
"loss": 2.3282,
"step": 40500
},
{
"epoch": 1.28,
"learning_rate": 3.3982873394380725e-05,
"loss": 2.3631,
"step": 41000
},
{
"epoch": 1.3,
"learning_rate": 3.3787542582117074e-05,
"loss": 2.2899,
"step": 41500
},
{
"epoch": 1.31,
"learning_rate": 3.359221176985343e-05,
"loss": 2.3022,
"step": 42000
},
{
"epoch": 1.33,
"learning_rate": 3.339688095758978e-05,
"loss": 2.3512,
"step": 42500
},
{
"epoch": 1.34,
"learning_rate": 3.320155014532613e-05,
"loss": 2.3304,
"step": 43000
},
{
"epoch": 1.36,
"learning_rate": 3.300621933306248e-05,
"loss": 2.3307,
"step": 43500
},
{
"epoch": 1.38,
"learning_rate": 3.2810888520798826e-05,
"loss": 2.3752,
"step": 44000
},
{
"epoch": 1.39,
"learning_rate": 3.2615557708535175e-05,
"loss": 2.2553,
"step": 44500
},
{
"epoch": 1.41,
"learning_rate": 3.2420226896271524e-05,
"loss": 2.3906,
"step": 45000
},
{
"epoch": 1.42,
"learning_rate": 3.222489608400788e-05,
"loss": 2.3277,
"step": 45500
},
{
"epoch": 1.44,
"learning_rate": 3.202956527174423e-05,
"loss": 2.3515,
"step": 46000
},
{
"epoch": 1.45,
"learning_rate": 3.183423445948058e-05,
"loss": 2.3409,
"step": 46500
},
{
"epoch": 1.47,
"learning_rate": 3.163890364721693e-05,
"loss": 2.3093,
"step": 47000
},
{
"epoch": 1.48,
"learning_rate": 3.1443572834953277e-05,
"loss": 2.2961,
"step": 47500
},
{
"epoch": 1.5,
"learning_rate": 3.1248242022689626e-05,
"loss": 2.2775,
"step": 48000
},
{
"epoch": 1.52,
"learning_rate": 3.1052911210425975e-05,
"loss": 2.2714,
"step": 48500
},
{
"epoch": 1.53,
"learning_rate": 3.085758039816233e-05,
"loss": 2.3634,
"step": 49000
},
{
"epoch": 1.55,
"learning_rate": 3.066224958589868e-05,
"loss": 2.353,
"step": 49500
},
{
"epoch": 1.56,
"learning_rate": 3.046691877363503e-05,
"loss": 2.3295,
"step": 50000
},
{
"epoch": 1.58,
"learning_rate": 3.0271587961371378e-05,
"loss": 2.3014,
"step": 50500
},
{
"epoch": 1.59,
"learning_rate": 3.0076257149107727e-05,
"loss": 2.319,
"step": 51000
},
{
"epoch": 1.61,
"learning_rate": 2.988092633684408e-05,
"loss": 2.3364,
"step": 51500
},
{
"epoch": 1.63,
"learning_rate": 2.968559552458043e-05,
"loss": 2.3935,
"step": 52000
},
{
"epoch": 1.64,
"learning_rate": 2.9490264712316778e-05,
"loss": 2.379,
"step": 52500
},
{
"epoch": 1.66,
"learning_rate": 2.9294933900053127e-05,
"loss": 2.284,
"step": 53000
},
{
"epoch": 1.67,
"learning_rate": 2.9099603087789483e-05,
"loss": 2.317,
"step": 53500
},
{
"epoch": 1.69,
"learning_rate": 2.8904272275525835e-05,
"loss": 2.3177,
"step": 54000
},
{
"epoch": 1.7,
"learning_rate": 2.8708941463262185e-05,
"loss": 2.3619,
"step": 54500
},
{
"epoch": 1.72,
"learning_rate": 2.8513610650998534e-05,
"loss": 2.3052,
"step": 55000
},
{
"epoch": 1.73,
"learning_rate": 2.8318279838734886e-05,
"loss": 2.3617,
"step": 55500
},
{
"epoch": 1.75,
"learning_rate": 2.8122949026471235e-05,
"loss": 2.3074,
"step": 56000
},
{
"epoch": 1.77,
"learning_rate": 2.7927618214207584e-05,
"loss": 2.3894,
"step": 56500
},
{
"epoch": 1.78,
"learning_rate": 2.7732287401943933e-05,
"loss": 2.3208,
"step": 57000
},
{
"epoch": 1.8,
"learning_rate": 2.7536956589680286e-05,
"loss": 2.3569,
"step": 57500
},
{
"epoch": 1.81,
"learning_rate": 2.7341625777416635e-05,
"loss": 2.4341,
"step": 58000
},
{
"epoch": 1.83,
"learning_rate": 2.7146294965152984e-05,
"loss": 2.246,
"step": 58500
},
{
"epoch": 1.84,
"learning_rate": 2.6950964152889337e-05,
"loss": 2.2938,
"step": 59000
},
{
"epoch": 1.86,
"learning_rate": 2.6755633340625686e-05,
"loss": 2.3378,
"step": 59500
},
{
"epoch": 1.88,
"learning_rate": 2.6560302528362035e-05,
"loss": 2.297,
"step": 60000
},
{
"epoch": 1.89,
"learning_rate": 2.6364971716098384e-05,
"loss": 2.3859,
"step": 60500
},
{
"epoch": 1.91,
"learning_rate": 2.6169640903834737e-05,
"loss": 2.4035,
"step": 61000
},
{
"epoch": 1.92,
"learning_rate": 2.5974310091571086e-05,
"loss": 2.3027,
"step": 61500
},
{
"epoch": 1.94,
"learning_rate": 2.5778979279307435e-05,
"loss": 2.2821,
"step": 62000
},
{
"epoch": 1.95,
"learning_rate": 2.5583648467043787e-05,
"loss": 2.3267,
"step": 62500
},
{
"epoch": 1.97,
"learning_rate": 2.5388317654780136e-05,
"loss": 2.3205,
"step": 63000
},
{
"epoch": 1.98,
"learning_rate": 2.5192986842516485e-05,
"loss": 2.3695,
"step": 63500
},
{
"epoch": 2.0,
"learning_rate": 2.4997656030252835e-05,
"loss": 2.3184,
"step": 64000
},
{
"epoch": 2.02,
"learning_rate": 2.4802325217989187e-05,
"loss": 1.6629,
"step": 64500
},
{
"epoch": 2.03,
"learning_rate": 2.460699440572554e-05,
"loss": 1.6359,
"step": 65000
},
{
"epoch": 2.05,
"learning_rate": 2.441166359346189e-05,
"loss": 1.5733,
"step": 65500
},
{
"epoch": 2.06,
"learning_rate": 2.4216332781198238e-05,
"loss": 1.5338,
"step": 66000
},
{
"epoch": 2.08,
"learning_rate": 2.402100196893459e-05,
"loss": 1.5802,
"step": 66500
},
{
"epoch": 2.09,
"learning_rate": 2.382567115667094e-05,
"loss": 1.5904,
"step": 67000
},
{
"epoch": 2.11,
"learning_rate": 2.363034034440729e-05,
"loss": 1.6188,
"step": 67500
},
{
"epoch": 2.13,
"learning_rate": 2.343500953214364e-05,
"loss": 1.6242,
"step": 68000
},
{
"epoch": 2.14,
"learning_rate": 2.323967871987999e-05,
"loss": 1.6195,
"step": 68500
},
{
"epoch": 2.16,
"learning_rate": 2.304434790761634e-05,
"loss": 1.5721,
"step": 69000
},
{
"epoch": 2.17,
"learning_rate": 2.284901709535269e-05,
"loss": 1.6324,
"step": 69500
},
{
"epoch": 2.19,
"learning_rate": 2.265368628308904e-05,
"loss": 1.5727,
"step": 70000
},
{
"epoch": 2.2,
"learning_rate": 2.245835547082539e-05,
"loss": 1.5782,
"step": 70500
},
{
"epoch": 2.22,
"learning_rate": 2.226302465856174e-05,
"loss": 1.5516,
"step": 71000
},
{
"epoch": 2.23,
"learning_rate": 2.206769384629809e-05,
"loss": 1.6206,
"step": 71500
},
{
"epoch": 2.25,
"learning_rate": 2.187236303403444e-05,
"loss": 1.6315,
"step": 72000
},
{
"epoch": 2.27,
"learning_rate": 2.1677032221770793e-05,
"loss": 1.6529,
"step": 72500
},
{
"epoch": 2.28,
"learning_rate": 2.1481701409507142e-05,
"loss": 1.5855,
"step": 73000
},
{
"epoch": 2.3,
"learning_rate": 2.1286370597243495e-05,
"loss": 1.565,
"step": 73500
},
{
"epoch": 2.31,
"learning_rate": 2.1091039784979844e-05,
"loss": 1.621,
"step": 74000
},
{
"epoch": 2.33,
"learning_rate": 2.0895708972716193e-05,
"loss": 1.6038,
"step": 74500
},
{
"epoch": 2.34,
"learning_rate": 2.0700378160452542e-05,
"loss": 1.6686,
"step": 75000
},
{
"epoch": 2.36,
"learning_rate": 2.0505047348188895e-05,
"loss": 1.6477,
"step": 75500
},
{
"epoch": 2.38,
"learning_rate": 2.0309716535925244e-05,
"loss": 1.6113,
"step": 76000
},
{
"epoch": 2.39,
"learning_rate": 2.0114385723661593e-05,
"loss": 1.6444,
"step": 76500
},
{
"epoch": 2.41,
"learning_rate": 1.9919054911397945e-05,
"loss": 1.5774,
"step": 77000
},
{
"epoch": 2.42,
"learning_rate": 1.9723724099134295e-05,
"loss": 1.6326,
"step": 77500
},
{
"epoch": 2.44,
"learning_rate": 1.9528393286870644e-05,
"loss": 1.689,
"step": 78000
},
{
"epoch": 2.45,
"learning_rate": 1.9333062474606993e-05,
"loss": 1.5713,
"step": 78500
},
{
"epoch": 2.47,
"learning_rate": 1.9137731662343345e-05,
"loss": 1.6681,
"step": 79000
},
{
"epoch": 2.48,
"learning_rate": 1.8942400850079694e-05,
"loss": 1.6577,
"step": 79500
},
{
"epoch": 2.5,
"learning_rate": 1.8747070037816047e-05,
"loss": 1.6331,
"step": 80000
},
{
"epoch": 2.52,
"learning_rate": 1.8551739225552396e-05,
"loss": 1.6913,
"step": 80500
},
{
"epoch": 2.53,
"learning_rate": 1.835640841328875e-05,
"loss": 1.5789,
"step": 81000
},
{
"epoch": 2.55,
"learning_rate": 1.8161077601025098e-05,
"loss": 1.6053,
"step": 81500
},
{
"epoch": 2.56,
"learning_rate": 1.7965746788761447e-05,
"loss": 1.6313,
"step": 82000
},
{
"epoch": 2.58,
"learning_rate": 1.77704159764978e-05,
"loss": 1.6604,
"step": 82500
},
{
"epoch": 2.59,
"learning_rate": 1.757508516423415e-05,
"loss": 1.6661,
"step": 83000
},
{
"epoch": 2.61,
"learning_rate": 1.7379754351970497e-05,
"loss": 1.7325,
"step": 83500
},
{
"epoch": 2.63,
"learning_rate": 1.7184423539706847e-05,
"loss": 1.6432,
"step": 84000
},
{
"epoch": 2.64,
"learning_rate": 1.69890927274432e-05,
"loss": 1.6206,
"step": 84500
},
{
"epoch": 2.66,
"learning_rate": 1.6793761915179548e-05,
"loss": 1.5495,
"step": 85000
},
{
"epoch": 2.67,
"learning_rate": 1.6598431102915897e-05,
"loss": 1.6021,
"step": 85500
},
{
"epoch": 2.69,
"learning_rate": 1.640310029065225e-05,
"loss": 1.6682,
"step": 86000
},
{
"epoch": 2.7,
"learning_rate": 1.62077694783886e-05,
"loss": 1.6304,
"step": 86500
},
{
"epoch": 2.72,
"learning_rate": 1.6012438666124948e-05,
"loss": 1.6224,
"step": 87000
},
{
"epoch": 2.73,
"learning_rate": 1.58171078538613e-05,
"loss": 1.5918,
"step": 87500
},
{
"epoch": 2.75,
"learning_rate": 1.5621777041597653e-05,
"loss": 1.6452,
"step": 88000
},
{
"epoch": 2.77,
"learning_rate": 1.5426446229334002e-05,
"loss": 1.5782,
"step": 88500
},
{
"epoch": 2.78,
"learning_rate": 1.5231115417070351e-05,
"loss": 1.5876,
"step": 89000
},
{
"epoch": 2.8,
"learning_rate": 1.5035784604806702e-05,
"loss": 1.6174,
"step": 89500
},
{
"epoch": 2.81,
"learning_rate": 1.4840453792543051e-05,
"loss": 1.6148,
"step": 90000
},
{
"epoch": 2.83,
"learning_rate": 1.4645122980279402e-05,
"loss": 1.6081,
"step": 90500
},
{
"epoch": 2.84,
"learning_rate": 1.4449792168015753e-05,
"loss": 1.5744,
"step": 91000
},
{
"epoch": 2.86,
"learning_rate": 1.4254461355752102e-05,
"loss": 1.6439,
"step": 91500
},
{
"epoch": 2.88,
"learning_rate": 1.4059130543488453e-05,
"loss": 1.665,
"step": 92000
},
{
"epoch": 2.89,
"learning_rate": 1.3863799731224802e-05,
"loss": 1.5745,
"step": 92500
},
{
"epoch": 2.91,
"learning_rate": 1.3668468918961153e-05,
"loss": 1.6089,
"step": 93000
},
{
"epoch": 2.92,
"learning_rate": 1.3473138106697503e-05,
"loss": 1.586,
"step": 93500
},
{
"epoch": 2.94,
"learning_rate": 1.3277807294433853e-05,
"loss": 1.6731,
"step": 94000
},
{
"epoch": 2.95,
"learning_rate": 1.3082476482170203e-05,
"loss": 1.5726,
"step": 94500
},
{
"epoch": 2.97,
"learning_rate": 1.2887145669906556e-05,
"loss": 1.5644,
"step": 95000
},
{
"epoch": 2.98,
"learning_rate": 1.2691814857642905e-05,
"loss": 1.5762,
"step": 95500
},
{
"epoch": 3.0,
"learning_rate": 1.2496484045379254e-05,
"loss": 1.5657,
"step": 96000
},
{
"epoch": 3.02,
"learning_rate": 1.2301153233115605e-05,
"loss": 0.9433,
"step": 96500
},
{
"epoch": 3.03,
"learning_rate": 1.2105822420851956e-05,
"loss": 0.946,
"step": 97000
},
{
"epoch": 3.05,
"learning_rate": 1.1910491608588307e-05,
"loss": 0.9428,
"step": 97500
},
{
"epoch": 3.06,
"learning_rate": 1.1715160796324656e-05,
"loss": 0.8946,
"step": 98000
},
{
"epoch": 3.08,
"learning_rate": 1.1519829984061006e-05,
"loss": 0.9151,
"step": 98500
},
{
"epoch": 3.09,
"learning_rate": 1.1324499171797357e-05,
"loss": 0.9333,
"step": 99000
},
{
"epoch": 3.11,
"learning_rate": 1.1129168359533706e-05,
"loss": 0.9164,
"step": 99500
},
{
"epoch": 3.13,
"learning_rate": 1.0933837547270057e-05,
"loss": 0.9953,
"step": 100000
},
{
"epoch": 3.14,
"learning_rate": 1.0738506735006406e-05,
"loss": 0.9017,
"step": 100500
},
{
"epoch": 3.16,
"learning_rate": 1.0543175922742759e-05,
"loss": 0.9446,
"step": 101000
},
{
"epoch": 3.17,
"learning_rate": 1.0347845110479108e-05,
"loss": 0.9605,
"step": 101500
},
{
"epoch": 3.19,
"learning_rate": 1.0152514298215459e-05,
"loss": 0.9269,
"step": 102000
},
{
"epoch": 3.2,
"learning_rate": 9.957183485951808e-06,
"loss": 0.9677,
"step": 102500
},
{
"epoch": 3.22,
"learning_rate": 9.761852673688159e-06,
"loss": 0.9406,
"step": 103000
},
{
"epoch": 3.23,
"learning_rate": 9.56652186142451e-06,
"loss": 0.9382,
"step": 103500
},
{
"epoch": 3.25,
"learning_rate": 9.371191049160859e-06,
"loss": 0.9711,
"step": 104000
},
{
"epoch": 3.27,
"learning_rate": 9.175860236897211e-06,
"loss": 0.9505,
"step": 104500
},
{
"epoch": 3.28,
"learning_rate": 8.98052942463356e-06,
"loss": 0.9686,
"step": 105000
},
{
"epoch": 3.3,
"learning_rate": 8.785198612369911e-06,
"loss": 0.9394,
"step": 105500
},
{
"epoch": 3.31,
"learning_rate": 8.58986780010626e-06,
"loss": 0.9612,
"step": 106000
},
{
"epoch": 3.33,
"learning_rate": 8.394536987842611e-06,
"loss": 0.968,
"step": 106500
},
{
"epoch": 3.34,
"learning_rate": 8.19920617557896e-06,
"loss": 0.9907,
"step": 107000
},
{
"epoch": 3.36,
"learning_rate": 8.00387536331531e-06,
"loss": 0.964,
"step": 107500
},
{
"epoch": 3.38,
"learning_rate": 7.808544551051662e-06,
"loss": 0.9707,
"step": 108000
},
{
"epoch": 3.39,
"learning_rate": 7.613213738788012e-06,
"loss": 0.9111,
"step": 108500
},
{
"epoch": 3.41,
"learning_rate": 7.417882926524362e-06,
"loss": 0.9294,
"step": 109000
},
{
"epoch": 3.42,
"learning_rate": 7.222552114260712e-06,
"loss": 0.9288,
"step": 109500
},
{
"epoch": 3.44,
"learning_rate": 7.027221301997062e-06,
"loss": 0.9456,
"step": 110000
},
{
"epoch": 3.45,
"learning_rate": 6.831890489733412e-06,
"loss": 0.9388,
"step": 110500
},
{
"epoch": 3.47,
"learning_rate": 6.636559677469763e-06,
"loss": 0.9385,
"step": 111000
},
{
"epoch": 3.48,
"learning_rate": 6.441228865206113e-06,
"loss": 0.9457,
"step": 111500
},
{
"epoch": 3.5,
"learning_rate": 6.245898052942464e-06,
"loss": 0.9371,
"step": 112000
},
{
"epoch": 3.52,
"learning_rate": 6.050567240678814e-06,
"loss": 0.892,
"step": 112500
},
{
"epoch": 3.53,
"learning_rate": 5.855236428415165e-06,
"loss": 0.9104,
"step": 113000
},
{
"epoch": 3.55,
"learning_rate": 5.6599056161515146e-06,
"loss": 0.9317,
"step": 113500
},
{
"epoch": 3.56,
"learning_rate": 5.4645748038878645e-06,
"loss": 0.8673,
"step": 114000
},
{
"epoch": 3.58,
"learning_rate": 5.2692439916242145e-06,
"loss": 0.9329,
"step": 114500
},
{
"epoch": 3.59,
"learning_rate": 5.073913179360565e-06,
"loss": 0.9171,
"step": 115000
},
{
"epoch": 3.61,
"learning_rate": 4.878582367096915e-06,
"loss": 0.8971,
"step": 115500
},
{
"epoch": 3.63,
"learning_rate": 4.683251554833266e-06,
"loss": 0.9205,
"step": 116000
},
{
"epoch": 3.64,
"learning_rate": 4.487920742569616e-06,
"loss": 0.9046,
"step": 116500
},
{
"epoch": 3.66,
"learning_rate": 4.292589930305967e-06,
"loss": 0.9163,
"step": 117000
},
{
"epoch": 3.67,
"learning_rate": 4.097259118042317e-06,
"loss": 0.9241,
"step": 117500
},
{
"epoch": 3.69,
"learning_rate": 3.901928305778667e-06,
"loss": 0.8993,
"step": 118000
},
{
"epoch": 3.7,
"learning_rate": 3.7065974935150167e-06,
"loss": 0.8975,
"step": 118500
},
{
"epoch": 3.72,
"learning_rate": 3.5112666812513675e-06,
"loss": 0.9508,
"step": 119000
},
{
"epoch": 3.73,
"learning_rate": 3.315935868987718e-06,
"loss": 0.8833,
"step": 119500
},
{
"epoch": 3.75,
"learning_rate": 3.120605056724068e-06,
"loss": 0.941,
"step": 120000
},
{
"epoch": 3.77,
"learning_rate": 2.9252742444604182e-06,
"loss": 0.9286,
"step": 120500
},
{
"epoch": 3.78,
"learning_rate": 2.7299434321967686e-06,
"loss": 0.9103,
"step": 121000
},
{
"epoch": 3.8,
"learning_rate": 2.534612619933119e-06,
"loss": 0.9002,
"step": 121500
},
{
"epoch": 3.81,
"learning_rate": 2.3392818076694694e-06,
"loss": 0.8605,
"step": 122000
},
{
"epoch": 3.83,
"learning_rate": 2.1439509954058193e-06,
"loss": 0.8555,
"step": 122500
},
{
"epoch": 3.84,
"learning_rate": 1.9486201831421697e-06,
"loss": 0.8961,
"step": 123000
},
{
"epoch": 3.86,
"learning_rate": 1.75328937087852e-06,
"loss": 0.9079,
"step": 123500
},
{
"epoch": 3.88,
"learning_rate": 1.55795855861487e-06,
"loss": 0.9456,
"step": 124000
},
{
"epoch": 3.89,
"learning_rate": 1.3626277463512205e-06,
"loss": 0.905,
"step": 124500
},
{
"epoch": 3.91,
"learning_rate": 1.1672969340875708e-06,
"loss": 0.8558,
"step": 125000
},
{
"epoch": 3.92,
"learning_rate": 9.71966121823921e-07,
"loss": 0.9055,
"step": 125500
},
{
"epoch": 3.94,
"learning_rate": 7.766353095602713e-07,
"loss": 0.9165,
"step": 126000
},
{
"epoch": 3.95,
"learning_rate": 5.813044972966216e-07,
"loss": 0.9449,
"step": 126500
},
{
"epoch": 3.97,
"learning_rate": 3.8597368503297185e-07,
"loss": 0.8955,
"step": 127000
},
{
"epoch": 3.98,
"learning_rate": 1.9064287276932213e-07,
"loss": 0.9181,
"step": 127500
},
{
"epoch": 4.0,
"step": 127988,
"total_flos": 7.906061868859392e+16,
"train_loss": 2.0082999333540426,
"train_runtime": 37501.9411,
"train_samples_per_second": 3.413,
"train_steps_per_second": 3.413
}
],
"max_steps": 127988,
"num_train_epochs": 4,
"total_flos": 7.906061868859392e+16,
"trial_name": null,
"trial_params": null
}