es_financial / trainer_state.json
huranokuma's picture
End of training
c610a31
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"global_step": 182810,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 4.98632459931076e-05,
"loss": 2.0893,
"step": 500
},
{
"epoch": 0.05,
"learning_rate": 4.97264919862152e-05,
"loss": 2.0282,
"step": 1000
},
{
"epoch": 0.08,
"learning_rate": 4.9589737979322795e-05,
"loss": 2.0359,
"step": 1500
},
{
"epoch": 0.11,
"learning_rate": 4.94529839724304e-05,
"loss": 2.0573,
"step": 2000
},
{
"epoch": 0.14,
"learning_rate": 4.931622996553799e-05,
"loss": 2.0498,
"step": 2500
},
{
"epoch": 0.16,
"learning_rate": 4.9179475958645595e-05,
"loss": 1.9906,
"step": 3000
},
{
"epoch": 0.19,
"learning_rate": 4.904272195175319e-05,
"loss": 2.0297,
"step": 3500
},
{
"epoch": 0.22,
"learning_rate": 4.8905967944860786e-05,
"loss": 1.9994,
"step": 4000
},
{
"epoch": 0.25,
"learning_rate": 4.876921393796838e-05,
"loss": 2.0443,
"step": 4500
},
{
"epoch": 0.27,
"learning_rate": 4.863245993107598e-05,
"loss": 1.9891,
"step": 5000
},
{
"epoch": 0.3,
"learning_rate": 4.849570592418358e-05,
"loss": 1.9978,
"step": 5500
},
{
"epoch": 0.33,
"learning_rate": 4.835895191729118e-05,
"loss": 2.0001,
"step": 6000
},
{
"epoch": 0.36,
"learning_rate": 4.8222197910398776e-05,
"loss": 1.9579,
"step": 6500
},
{
"epoch": 0.38,
"learning_rate": 4.808544390350638e-05,
"loss": 1.9862,
"step": 7000
},
{
"epoch": 0.41,
"learning_rate": 4.7948689896613974e-05,
"loss": 1.959,
"step": 7500
},
{
"epoch": 0.44,
"learning_rate": 4.781193588972157e-05,
"loss": 1.9861,
"step": 8000
},
{
"epoch": 0.46,
"learning_rate": 4.7675181882829165e-05,
"loss": 1.9626,
"step": 8500
},
{
"epoch": 0.49,
"learning_rate": 4.753842787593677e-05,
"loss": 1.9609,
"step": 9000
},
{
"epoch": 0.52,
"learning_rate": 4.740167386904437e-05,
"loss": 1.9949,
"step": 9500
},
{
"epoch": 0.55,
"learning_rate": 4.7264919862151964e-05,
"loss": 1.9398,
"step": 10000
},
{
"epoch": 0.57,
"learning_rate": 4.712816585525956e-05,
"loss": 1.9657,
"step": 10500
},
{
"epoch": 0.6,
"learning_rate": 4.699141184836716e-05,
"loss": 1.9369,
"step": 11000
},
{
"epoch": 0.63,
"learning_rate": 4.685465784147476e-05,
"loss": 1.9916,
"step": 11500
},
{
"epoch": 0.66,
"learning_rate": 4.671790383458235e-05,
"loss": 1.9725,
"step": 12000
},
{
"epoch": 0.68,
"learning_rate": 4.6581149827689955e-05,
"loss": 1.9161,
"step": 12500
},
{
"epoch": 0.71,
"learning_rate": 4.644439582079756e-05,
"loss": 1.9733,
"step": 13000
},
{
"epoch": 0.74,
"learning_rate": 4.630764181390515e-05,
"loss": 1.952,
"step": 13500
},
{
"epoch": 0.77,
"learning_rate": 4.617088780701275e-05,
"loss": 1.9321,
"step": 14000
},
{
"epoch": 0.79,
"learning_rate": 4.603413380012034e-05,
"loss": 1.935,
"step": 14500
},
{
"epoch": 0.82,
"learning_rate": 4.5897379793227945e-05,
"loss": 1.9755,
"step": 15000
},
{
"epoch": 0.85,
"learning_rate": 4.576062578633554e-05,
"loss": 1.9573,
"step": 15500
},
{
"epoch": 0.88,
"learning_rate": 4.5623871779443136e-05,
"loss": 1.9531,
"step": 16000
},
{
"epoch": 0.9,
"learning_rate": 4.548711777255074e-05,
"loss": 1.9465,
"step": 16500
},
{
"epoch": 0.93,
"learning_rate": 4.535036376565834e-05,
"loss": 1.9641,
"step": 17000
},
{
"epoch": 0.96,
"learning_rate": 4.5213609758765936e-05,
"loss": 1.9157,
"step": 17500
},
{
"epoch": 0.98,
"learning_rate": 4.507685575187353e-05,
"loss": 1.9518,
"step": 18000
},
{
"epoch": 1.01,
"learning_rate": 4.4940101744981127e-05,
"loss": 1.7654,
"step": 18500
},
{
"epoch": 1.04,
"learning_rate": 4.480334773808873e-05,
"loss": 1.6299,
"step": 19000
},
{
"epoch": 1.07,
"learning_rate": 4.4666593731196324e-05,
"loss": 1.6508,
"step": 19500
},
{
"epoch": 1.09,
"learning_rate": 4.4529839724303926e-05,
"loss": 1.6008,
"step": 20000
},
{
"epoch": 1.12,
"learning_rate": 4.439308571741152e-05,
"loss": 1.6127,
"step": 20500
},
{
"epoch": 1.15,
"learning_rate": 4.4256331710519124e-05,
"loss": 1.5774,
"step": 21000
},
{
"epoch": 1.18,
"learning_rate": 4.411957770362672e-05,
"loss": 1.6349,
"step": 21500
},
{
"epoch": 1.2,
"learning_rate": 4.3982823696734315e-05,
"loss": 1.6484,
"step": 22000
},
{
"epoch": 1.23,
"learning_rate": 4.384606968984191e-05,
"loss": 1.6607,
"step": 22500
},
{
"epoch": 1.26,
"learning_rate": 4.370931568294951e-05,
"loss": 1.6338,
"step": 23000
},
{
"epoch": 1.29,
"learning_rate": 4.3572561676057114e-05,
"loss": 1.6342,
"step": 23500
},
{
"epoch": 1.31,
"learning_rate": 4.343580766916471e-05,
"loss": 1.6453,
"step": 24000
},
{
"epoch": 1.34,
"learning_rate": 4.3299053662272305e-05,
"loss": 1.6547,
"step": 24500
},
{
"epoch": 1.37,
"learning_rate": 4.316229965537991e-05,
"loss": 1.6587,
"step": 25000
},
{
"epoch": 1.39,
"learning_rate": 4.30255456484875e-05,
"loss": 1.6449,
"step": 25500
},
{
"epoch": 1.42,
"learning_rate": 4.28887916415951e-05,
"loss": 1.6473,
"step": 26000
},
{
"epoch": 1.45,
"learning_rate": 4.275203763470269e-05,
"loss": 1.6378,
"step": 26500
},
{
"epoch": 1.48,
"learning_rate": 4.2615283627810296e-05,
"loss": 1.6495,
"step": 27000
},
{
"epoch": 1.5,
"learning_rate": 4.24785296209179e-05,
"loss": 1.695,
"step": 27500
},
{
"epoch": 1.53,
"learning_rate": 4.234177561402549e-05,
"loss": 1.7073,
"step": 28000
},
{
"epoch": 1.56,
"learning_rate": 4.220502160713309e-05,
"loss": 1.7791,
"step": 28500
},
{
"epoch": 1.59,
"learning_rate": 4.206826760024069e-05,
"loss": 1.7924,
"step": 29000
},
{
"epoch": 1.61,
"learning_rate": 4.1931513593348286e-05,
"loss": 1.8115,
"step": 29500
},
{
"epoch": 1.64,
"learning_rate": 4.179475958645588e-05,
"loss": 1.7199,
"step": 30000
},
{
"epoch": 1.67,
"learning_rate": 4.1658005579563484e-05,
"loss": 1.7923,
"step": 30500
},
{
"epoch": 1.7,
"learning_rate": 4.1521251572671086e-05,
"loss": 1.6858,
"step": 31000
},
{
"epoch": 1.72,
"learning_rate": 4.138449756577868e-05,
"loss": 1.6759,
"step": 31500
},
{
"epoch": 1.75,
"learning_rate": 4.1247743558886276e-05,
"loss": 1.6905,
"step": 32000
},
{
"epoch": 1.78,
"learning_rate": 4.111098955199388e-05,
"loss": 1.6696,
"step": 32500
},
{
"epoch": 1.81,
"learning_rate": 4.0974235545101474e-05,
"loss": 1.7242,
"step": 33000
},
{
"epoch": 1.83,
"learning_rate": 4.083748153820907e-05,
"loss": 1.7341,
"step": 33500
},
{
"epoch": 1.86,
"learning_rate": 4.0700727531316665e-05,
"loss": 1.7026,
"step": 34000
},
{
"epoch": 1.89,
"learning_rate": 4.056397352442427e-05,
"loss": 1.7249,
"step": 34500
},
{
"epoch": 1.91,
"learning_rate": 4.042721951753187e-05,
"loss": 1.6447,
"step": 35000
},
{
"epoch": 1.94,
"learning_rate": 4.0290465510639464e-05,
"loss": 1.6748,
"step": 35500
},
{
"epoch": 1.97,
"learning_rate": 4.015371150374706e-05,
"loss": 1.6952,
"step": 36000
},
{
"epoch": 2.0,
"learning_rate": 4.001695749685466e-05,
"loss": 1.6569,
"step": 36500
},
{
"epoch": 2.02,
"learning_rate": 3.988020348996226e-05,
"loss": 1.4236,
"step": 37000
},
{
"epoch": 2.05,
"learning_rate": 3.974344948306985e-05,
"loss": 1.4146,
"step": 37500
},
{
"epoch": 2.08,
"learning_rate": 3.9606695476177455e-05,
"loss": 1.4398,
"step": 38000
},
{
"epoch": 2.11,
"learning_rate": 3.946994146928506e-05,
"loss": 1.433,
"step": 38500
},
{
"epoch": 2.13,
"learning_rate": 3.933318746239265e-05,
"loss": 1.4019,
"step": 39000
},
{
"epoch": 2.16,
"learning_rate": 3.919643345550025e-05,
"loss": 1.4358,
"step": 39500
},
{
"epoch": 2.19,
"learning_rate": 3.905967944860784e-05,
"loss": 1.4445,
"step": 40000
},
{
"epoch": 2.22,
"learning_rate": 3.8922925441715445e-05,
"loss": 1.3795,
"step": 40500
},
{
"epoch": 2.24,
"learning_rate": 3.878617143482304e-05,
"loss": 1.4617,
"step": 41000
},
{
"epoch": 2.27,
"learning_rate": 3.864941742793064e-05,
"loss": 1.399,
"step": 41500
},
{
"epoch": 2.3,
"learning_rate": 3.851266342103824e-05,
"loss": 1.4227,
"step": 42000
},
{
"epoch": 2.32,
"learning_rate": 3.837590941414584e-05,
"loss": 1.406,
"step": 42500
},
{
"epoch": 2.35,
"learning_rate": 3.8239155407253436e-05,
"loss": 1.4229,
"step": 43000
},
{
"epoch": 2.38,
"learning_rate": 3.810240140036103e-05,
"loss": 1.4309,
"step": 43500
},
{
"epoch": 2.41,
"learning_rate": 3.796564739346863e-05,
"loss": 1.4129,
"step": 44000
},
{
"epoch": 2.43,
"learning_rate": 3.782889338657623e-05,
"loss": 1.4409,
"step": 44500
},
{
"epoch": 2.46,
"learning_rate": 3.7692139379683824e-05,
"loss": 1.3927,
"step": 45000
},
{
"epoch": 2.49,
"learning_rate": 3.7555385372791426e-05,
"loss": 1.4553,
"step": 45500
},
{
"epoch": 2.52,
"learning_rate": 3.741863136589902e-05,
"loss": 1.4204,
"step": 46000
},
{
"epoch": 2.54,
"learning_rate": 3.7281877359006624e-05,
"loss": 1.4391,
"step": 46500
},
{
"epoch": 2.57,
"learning_rate": 3.714512335211422e-05,
"loss": 1.4732,
"step": 47000
},
{
"epoch": 2.6,
"learning_rate": 3.7008369345221815e-05,
"loss": 1.4435,
"step": 47500
},
{
"epoch": 2.63,
"learning_rate": 3.687161533832941e-05,
"loss": 1.4206,
"step": 48000
},
{
"epoch": 2.65,
"learning_rate": 3.673486133143701e-05,
"loss": 1.4552,
"step": 48500
},
{
"epoch": 2.68,
"learning_rate": 3.6598107324544614e-05,
"loss": 1.4611,
"step": 49000
},
{
"epoch": 2.71,
"learning_rate": 3.646135331765221e-05,
"loss": 1.4487,
"step": 49500
},
{
"epoch": 2.74,
"learning_rate": 3.6324599310759805e-05,
"loss": 1.4679,
"step": 50000
},
{
"epoch": 2.76,
"learning_rate": 3.618784530386741e-05,
"loss": 1.4245,
"step": 50500
},
{
"epoch": 2.79,
"learning_rate": 3.6051091296975e-05,
"loss": 1.4871,
"step": 51000
},
{
"epoch": 2.82,
"learning_rate": 3.59143372900826e-05,
"loss": 1.4553,
"step": 51500
},
{
"epoch": 2.84,
"learning_rate": 3.57775832831902e-05,
"loss": 1.4775,
"step": 52000
},
{
"epoch": 2.87,
"learning_rate": 3.56408292762978e-05,
"loss": 1.4399,
"step": 52500
},
{
"epoch": 2.9,
"learning_rate": 3.55040752694054e-05,
"loss": 1.4695,
"step": 53000
},
{
"epoch": 2.93,
"learning_rate": 3.536732126251299e-05,
"loss": 1.4722,
"step": 53500
},
{
"epoch": 2.95,
"learning_rate": 3.523056725562059e-05,
"loss": 1.4315,
"step": 54000
},
{
"epoch": 2.98,
"learning_rate": 3.509381324872819e-05,
"loss": 1.4428,
"step": 54500
},
{
"epoch": 3.01,
"learning_rate": 3.4957059241835786e-05,
"loss": 1.4064,
"step": 55000
},
{
"epoch": 3.04,
"learning_rate": 3.482030523494338e-05,
"loss": 1.216,
"step": 55500
},
{
"epoch": 3.06,
"learning_rate": 3.4683551228050984e-05,
"loss": 1.2302,
"step": 56000
},
{
"epoch": 3.09,
"learning_rate": 3.4546797221158586e-05,
"loss": 1.217,
"step": 56500
},
{
"epoch": 3.12,
"learning_rate": 3.441004321426618e-05,
"loss": 1.2273,
"step": 57000
},
{
"epoch": 3.15,
"learning_rate": 3.427328920737378e-05,
"loss": 1.2445,
"step": 57500
},
{
"epoch": 3.17,
"learning_rate": 3.413653520048137e-05,
"loss": 1.276,
"step": 58000
},
{
"epoch": 3.2,
"learning_rate": 3.3999781193588974e-05,
"loss": 1.2173,
"step": 58500
},
{
"epoch": 3.23,
"learning_rate": 3.386302718669657e-05,
"loss": 1.2329,
"step": 59000
},
{
"epoch": 3.25,
"learning_rate": 3.372627317980417e-05,
"loss": 1.2375,
"step": 59500
},
{
"epoch": 3.28,
"learning_rate": 3.358951917291177e-05,
"loss": 1.231,
"step": 60000
},
{
"epoch": 3.31,
"learning_rate": 3.345276516601937e-05,
"loss": 1.2456,
"step": 60500
},
{
"epoch": 3.34,
"learning_rate": 3.3316011159126965e-05,
"loss": 1.2182,
"step": 61000
},
{
"epoch": 3.36,
"learning_rate": 3.317925715223456e-05,
"loss": 1.2585,
"step": 61500
},
{
"epoch": 3.39,
"learning_rate": 3.3042503145342155e-05,
"loss": 1.2544,
"step": 62000
},
{
"epoch": 3.42,
"learning_rate": 3.290574913844976e-05,
"loss": 1.2676,
"step": 62500
},
{
"epoch": 3.45,
"learning_rate": 3.276899513155735e-05,
"loss": 1.2598,
"step": 63000
},
{
"epoch": 3.47,
"learning_rate": 3.2632241124664955e-05,
"loss": 1.235,
"step": 63500
},
{
"epoch": 3.5,
"learning_rate": 3.249548711777256e-05,
"loss": 1.2327,
"step": 64000
},
{
"epoch": 3.53,
"learning_rate": 3.235873311088015e-05,
"loss": 1.2675,
"step": 64500
},
{
"epoch": 3.56,
"learning_rate": 3.222197910398775e-05,
"loss": 1.2959,
"step": 65000
},
{
"epoch": 3.58,
"learning_rate": 3.2085225097095343e-05,
"loss": 1.259,
"step": 65500
},
{
"epoch": 3.61,
"learning_rate": 3.1948471090202946e-05,
"loss": 1.2785,
"step": 66000
},
{
"epoch": 3.64,
"learning_rate": 3.181171708331054e-05,
"loss": 1.2611,
"step": 66500
},
{
"epoch": 3.67,
"learning_rate": 3.167496307641814e-05,
"loss": 1.2528,
"step": 67000
},
{
"epoch": 3.69,
"learning_rate": 3.153820906952574e-05,
"loss": 1.2584,
"step": 67500
},
{
"epoch": 3.72,
"learning_rate": 3.140145506263334e-05,
"loss": 1.2675,
"step": 68000
},
{
"epoch": 3.75,
"learning_rate": 3.1264701055740936e-05,
"loss": 1.2754,
"step": 68500
},
{
"epoch": 3.77,
"learning_rate": 3.112794704884853e-05,
"loss": 1.2927,
"step": 69000
},
{
"epoch": 3.8,
"learning_rate": 3.099119304195613e-05,
"loss": 1.2775,
"step": 69500
},
{
"epoch": 3.83,
"learning_rate": 3.085443903506373e-05,
"loss": 1.2686,
"step": 70000
},
{
"epoch": 3.86,
"learning_rate": 3.071768502817133e-05,
"loss": 1.2631,
"step": 70500
},
{
"epoch": 3.88,
"learning_rate": 3.0580931021278927e-05,
"loss": 1.2756,
"step": 71000
},
{
"epoch": 3.91,
"learning_rate": 3.0444177014386522e-05,
"loss": 1.2529,
"step": 71500
},
{
"epoch": 3.94,
"learning_rate": 3.0307423007494124e-05,
"loss": 1.2656,
"step": 72000
},
{
"epoch": 3.97,
"learning_rate": 3.017066900060172e-05,
"loss": 1.2597,
"step": 72500
},
{
"epoch": 3.99,
"learning_rate": 3.0033914993709318e-05,
"loss": 1.2928,
"step": 73000
},
{
"epoch": 4.02,
"learning_rate": 2.9897160986816914e-05,
"loss": 1.1113,
"step": 73500
},
{
"epoch": 4.05,
"learning_rate": 2.9760406979924516e-05,
"loss": 1.0677,
"step": 74000
},
{
"epoch": 4.08,
"learning_rate": 2.962365297303211e-05,
"loss": 1.054,
"step": 74500
},
{
"epoch": 4.1,
"learning_rate": 2.948689896613971e-05,
"loss": 1.0708,
"step": 75000
},
{
"epoch": 4.13,
"learning_rate": 2.9350144959247305e-05,
"loss": 1.0741,
"step": 75500
},
{
"epoch": 4.16,
"learning_rate": 2.9213390952354908e-05,
"loss": 1.0736,
"step": 76000
},
{
"epoch": 4.18,
"learning_rate": 2.9076636945462503e-05,
"loss": 1.0618,
"step": 76500
},
{
"epoch": 4.21,
"learning_rate": 2.8939882938570102e-05,
"loss": 1.1291,
"step": 77000
},
{
"epoch": 4.24,
"learning_rate": 2.8803128931677697e-05,
"loss": 1.0901,
"step": 77500
},
{
"epoch": 4.27,
"learning_rate": 2.86663749247853e-05,
"loss": 1.0895,
"step": 78000
},
{
"epoch": 4.29,
"learning_rate": 2.8529620917892898e-05,
"loss": 1.0702,
"step": 78500
},
{
"epoch": 4.32,
"learning_rate": 2.8392866911000493e-05,
"loss": 1.0729,
"step": 79000
},
{
"epoch": 4.35,
"learning_rate": 2.825611290410809e-05,
"loss": 1.0829,
"step": 79500
},
{
"epoch": 4.38,
"learning_rate": 2.811935889721569e-05,
"loss": 1.105,
"step": 80000
},
{
"epoch": 4.4,
"learning_rate": 2.798260489032329e-05,
"loss": 1.1153,
"step": 80500
},
{
"epoch": 4.43,
"learning_rate": 2.7845850883430885e-05,
"loss": 1.0886,
"step": 81000
},
{
"epoch": 4.46,
"learning_rate": 2.770909687653848e-05,
"loss": 1.112,
"step": 81500
},
{
"epoch": 4.49,
"learning_rate": 2.7572342869646083e-05,
"loss": 1.1041,
"step": 82000
},
{
"epoch": 4.51,
"learning_rate": 2.743558886275368e-05,
"loss": 1.096,
"step": 82500
},
{
"epoch": 4.54,
"learning_rate": 2.7298834855861277e-05,
"loss": 1.1532,
"step": 83000
},
{
"epoch": 4.57,
"learning_rate": 2.7162080848968872e-05,
"loss": 1.127,
"step": 83500
},
{
"epoch": 4.59,
"learning_rate": 2.7025326842076474e-05,
"loss": 1.1254,
"step": 84000
},
{
"epoch": 4.62,
"learning_rate": 2.6888572835184073e-05,
"loss": 1.1162,
"step": 84500
},
{
"epoch": 4.65,
"learning_rate": 2.675181882829167e-05,
"loss": 1.0954,
"step": 85000
},
{
"epoch": 4.68,
"learning_rate": 2.6615064821399267e-05,
"loss": 1.1377,
"step": 85500
},
{
"epoch": 4.7,
"learning_rate": 2.647831081450687e-05,
"loss": 1.1012,
"step": 86000
},
{
"epoch": 4.73,
"learning_rate": 2.6341556807614465e-05,
"loss": 1.1177,
"step": 86500
},
{
"epoch": 4.76,
"learning_rate": 2.620480280072206e-05,
"loss": 1.1125,
"step": 87000
},
{
"epoch": 4.79,
"learning_rate": 2.606804879382966e-05,
"loss": 1.1555,
"step": 87500
},
{
"epoch": 4.81,
"learning_rate": 2.593129478693726e-05,
"loss": 1.1127,
"step": 88000
},
{
"epoch": 4.84,
"learning_rate": 2.5794540780044857e-05,
"loss": 1.1456,
"step": 88500
},
{
"epoch": 4.87,
"learning_rate": 2.5657786773152452e-05,
"loss": 1.1249,
"step": 89000
},
{
"epoch": 4.9,
"learning_rate": 2.552103276626005e-05,
"loss": 1.1422,
"step": 89500
},
{
"epoch": 4.92,
"learning_rate": 2.5384278759367653e-05,
"loss": 1.1422,
"step": 90000
},
{
"epoch": 4.95,
"learning_rate": 2.5247524752475248e-05,
"loss": 1.1592,
"step": 90500
},
{
"epoch": 4.98,
"learning_rate": 2.5110770745582847e-05,
"loss": 1.1493,
"step": 91000
},
{
"epoch": 5.01,
"learning_rate": 2.4974016738690446e-05,
"loss": 1.0908,
"step": 91500
},
{
"epoch": 5.03,
"learning_rate": 2.483726273179804e-05,
"loss": 0.9386,
"step": 92000
},
{
"epoch": 5.06,
"learning_rate": 2.470050872490564e-05,
"loss": 0.9452,
"step": 92500
},
{
"epoch": 5.09,
"learning_rate": 2.456375471801324e-05,
"loss": 0.98,
"step": 93000
},
{
"epoch": 5.11,
"learning_rate": 2.4427000711120838e-05,
"loss": 0.9672,
"step": 93500
},
{
"epoch": 5.14,
"learning_rate": 2.4290246704228433e-05,
"loss": 0.9567,
"step": 94000
},
{
"epoch": 5.17,
"learning_rate": 2.415349269733603e-05,
"loss": 0.9555,
"step": 94500
},
{
"epoch": 5.2,
"learning_rate": 2.401673869044363e-05,
"loss": 0.9843,
"step": 95000
},
{
"epoch": 5.22,
"learning_rate": 2.387998468355123e-05,
"loss": 0.977,
"step": 95500
},
{
"epoch": 5.25,
"learning_rate": 2.3743230676658828e-05,
"loss": 0.9672,
"step": 96000
},
{
"epoch": 5.28,
"learning_rate": 2.3606476669766427e-05,
"loss": 0.9683,
"step": 96500
},
{
"epoch": 5.31,
"learning_rate": 2.3469722662874026e-05,
"loss": 0.9976,
"step": 97000
},
{
"epoch": 5.33,
"learning_rate": 2.333296865598162e-05,
"loss": 0.9912,
"step": 97500
},
{
"epoch": 5.36,
"learning_rate": 2.319621464908922e-05,
"loss": 0.9843,
"step": 98000
},
{
"epoch": 5.39,
"learning_rate": 2.305946064219682e-05,
"loss": 0.9622,
"step": 98500
},
{
"epoch": 5.42,
"learning_rate": 2.2922706635304417e-05,
"loss": 0.9723,
"step": 99000
},
{
"epoch": 5.44,
"learning_rate": 2.2785952628412013e-05,
"loss": 0.9783,
"step": 99500
},
{
"epoch": 5.47,
"learning_rate": 2.264919862151961e-05,
"loss": 0.956,
"step": 100000
},
{
"epoch": 5.5,
"learning_rate": 2.251244461462721e-05,
"loss": 0.9982,
"step": 100500
},
{
"epoch": 5.52,
"learning_rate": 2.237569060773481e-05,
"loss": 0.9763,
"step": 101000
},
{
"epoch": 5.55,
"learning_rate": 2.2238936600842404e-05,
"loss": 0.9901,
"step": 101500
},
{
"epoch": 5.58,
"learning_rate": 2.2102182593950007e-05,
"loss": 0.966,
"step": 102000
},
{
"epoch": 5.61,
"learning_rate": 2.1965428587057602e-05,
"loss": 0.9847,
"step": 102500
},
{
"epoch": 5.63,
"learning_rate": 2.18286745801652e-05,
"loss": 0.9981,
"step": 103000
},
{
"epoch": 5.66,
"learning_rate": 2.1691920573272796e-05,
"loss": 0.9539,
"step": 103500
},
{
"epoch": 5.69,
"learning_rate": 2.1555166566380398e-05,
"loss": 0.9897,
"step": 104000
},
{
"epoch": 5.72,
"learning_rate": 2.1418412559487994e-05,
"loss": 1.0071,
"step": 104500
},
{
"epoch": 5.74,
"learning_rate": 2.1281658552595592e-05,
"loss": 0.9948,
"step": 105000
},
{
"epoch": 5.77,
"learning_rate": 2.114490454570319e-05,
"loss": 1.0028,
"step": 105500
},
{
"epoch": 5.8,
"learning_rate": 2.100815053881079e-05,
"loss": 1.0115,
"step": 106000
},
{
"epoch": 5.83,
"learning_rate": 2.0871396531918385e-05,
"loss": 0.978,
"step": 106500
},
{
"epoch": 5.85,
"learning_rate": 2.0734642525025984e-05,
"loss": 0.9922,
"step": 107000
},
{
"epoch": 5.88,
"learning_rate": 2.0597888518133583e-05,
"loss": 1.0203,
"step": 107500
},
{
"epoch": 5.91,
"learning_rate": 2.046113451124118e-05,
"loss": 1.0288,
"step": 108000
},
{
"epoch": 5.94,
"learning_rate": 2.0324380504348777e-05,
"loss": 0.9899,
"step": 108500
},
{
"epoch": 5.96,
"learning_rate": 2.0187626497456376e-05,
"loss": 0.9988,
"step": 109000
},
{
"epoch": 5.99,
"learning_rate": 2.0050872490563975e-05,
"loss": 1.0026,
"step": 109500
},
{
"epoch": 6.02,
"learning_rate": 1.9914118483671573e-05,
"loss": 0.9024,
"step": 110000
},
{
"epoch": 6.04,
"learning_rate": 1.977736447677917e-05,
"loss": 0.849,
"step": 110500
},
{
"epoch": 6.07,
"learning_rate": 1.964061046988677e-05,
"loss": 0.8861,
"step": 111000
},
{
"epoch": 6.1,
"learning_rate": 1.9503856462994366e-05,
"loss": 0.8508,
"step": 111500
},
{
"epoch": 6.13,
"learning_rate": 1.9367102456101965e-05,
"loss": 0.8596,
"step": 112000
},
{
"epoch": 6.15,
"learning_rate": 1.923034844920956e-05,
"loss": 0.8596,
"step": 112500
},
{
"epoch": 6.18,
"learning_rate": 1.9093594442317163e-05,
"loss": 0.8316,
"step": 113000
},
{
"epoch": 6.21,
"learning_rate": 1.8956840435424758e-05,
"loss": 0.8432,
"step": 113500
},
{
"epoch": 6.24,
"learning_rate": 1.8820086428532357e-05,
"loss": 0.8965,
"step": 114000
},
{
"epoch": 6.26,
"learning_rate": 1.8683332421639956e-05,
"loss": 0.8633,
"step": 114500
},
{
"epoch": 6.29,
"learning_rate": 1.8546578414747554e-05,
"loss": 0.8741,
"step": 115000
},
{
"epoch": 6.32,
"learning_rate": 1.840982440785515e-05,
"loss": 0.859,
"step": 115500
},
{
"epoch": 6.35,
"learning_rate": 1.827307040096275e-05,
"loss": 0.8788,
"step": 116000
},
{
"epoch": 6.37,
"learning_rate": 1.8136316394070347e-05,
"loss": 0.8782,
"step": 116500
},
{
"epoch": 6.4,
"learning_rate": 1.7999562387177946e-05,
"loss": 0.8872,
"step": 117000
},
{
"epoch": 6.43,
"learning_rate": 1.786280838028554e-05,
"loss": 0.9024,
"step": 117500
},
{
"epoch": 6.45,
"learning_rate": 1.772605437339314e-05,
"loss": 0.8986,
"step": 118000
},
{
"epoch": 6.48,
"learning_rate": 1.758930036650074e-05,
"loss": 0.8831,
"step": 118500
},
{
"epoch": 6.51,
"learning_rate": 1.7452546359608338e-05,
"loss": 0.8677,
"step": 119000
},
{
"epoch": 6.54,
"learning_rate": 1.7315792352715933e-05,
"loss": 0.8984,
"step": 119500
},
{
"epoch": 6.56,
"learning_rate": 1.7179038345823535e-05,
"loss": 0.8661,
"step": 120000
},
{
"epoch": 6.59,
"learning_rate": 1.704228433893113e-05,
"loss": 0.9107,
"step": 120500
},
{
"epoch": 6.62,
"learning_rate": 1.690553033203873e-05,
"loss": 0.9041,
"step": 121000
},
{
"epoch": 6.65,
"learning_rate": 1.6768776325146325e-05,
"loss": 0.8869,
"step": 121500
},
{
"epoch": 6.67,
"learning_rate": 1.6632022318253927e-05,
"loss": 0.9012,
"step": 122000
},
{
"epoch": 6.7,
"learning_rate": 1.6495268311361522e-05,
"loss": 0.8737,
"step": 122500
},
{
"epoch": 6.73,
"learning_rate": 1.635851430446912e-05,
"loss": 0.8927,
"step": 123000
},
{
"epoch": 6.76,
"learning_rate": 1.622176029757672e-05,
"loss": 0.8836,
"step": 123500
},
{
"epoch": 6.78,
"learning_rate": 1.608500629068432e-05,
"loss": 0.8753,
"step": 124000
},
{
"epoch": 6.81,
"learning_rate": 1.5948252283791914e-05,
"loss": 0.885,
"step": 124500
},
{
"epoch": 6.84,
"learning_rate": 1.5811498276899513e-05,
"loss": 0.8998,
"step": 125000
},
{
"epoch": 6.87,
"learning_rate": 1.567474427000711e-05,
"loss": 0.916,
"step": 125500
},
{
"epoch": 6.89,
"learning_rate": 1.553799026311471e-05,
"loss": 0.8755,
"step": 126000
},
{
"epoch": 6.92,
"learning_rate": 1.5401236256222306e-05,
"loss": 0.8842,
"step": 126500
},
{
"epoch": 6.95,
"learning_rate": 1.5264482249329905e-05,
"loss": 0.905,
"step": 127000
},
{
"epoch": 6.97,
"learning_rate": 1.5127728242437505e-05,
"loss": 0.9004,
"step": 127500
},
{
"epoch": 7.0,
"learning_rate": 1.4990974235545102e-05,
"loss": 0.8866,
"step": 128000
},
{
"epoch": 7.03,
"learning_rate": 1.48542202286527e-05,
"loss": 0.7771,
"step": 128500
},
{
"epoch": 7.06,
"learning_rate": 1.4717466221760298e-05,
"loss": 0.8103,
"step": 129000
},
{
"epoch": 7.08,
"learning_rate": 1.4580712214867898e-05,
"loss": 0.8078,
"step": 129500
},
{
"epoch": 7.11,
"learning_rate": 1.4443958207975494e-05,
"loss": 0.7961,
"step": 130000
},
{
"epoch": 7.14,
"learning_rate": 1.4307204201083094e-05,
"loss": 0.7902,
"step": 130500
},
{
"epoch": 7.17,
"learning_rate": 1.417045019419069e-05,
"loss": 0.8105,
"step": 131000
},
{
"epoch": 7.19,
"learning_rate": 1.403369618729829e-05,
"loss": 0.7907,
"step": 131500
},
{
"epoch": 7.22,
"learning_rate": 1.3896942180405887e-05,
"loss": 0.792,
"step": 132000
},
{
"epoch": 7.25,
"learning_rate": 1.3760188173513486e-05,
"loss": 0.7866,
"step": 132500
},
{
"epoch": 7.28,
"learning_rate": 1.3623434166621083e-05,
"loss": 0.8102,
"step": 133000
},
{
"epoch": 7.3,
"learning_rate": 1.3486680159728682e-05,
"loss": 0.7984,
"step": 133500
},
{
"epoch": 7.33,
"learning_rate": 1.3349926152836279e-05,
"loss": 0.8041,
"step": 134000
},
{
"epoch": 7.36,
"learning_rate": 1.3213172145943878e-05,
"loss": 0.8205,
"step": 134500
},
{
"epoch": 7.38,
"learning_rate": 1.3076418139051475e-05,
"loss": 0.7662,
"step": 135000
},
{
"epoch": 7.41,
"learning_rate": 1.2939664132159074e-05,
"loss": 0.7829,
"step": 135500
},
{
"epoch": 7.44,
"learning_rate": 1.280291012526667e-05,
"loss": 0.7997,
"step": 136000
},
{
"epoch": 7.47,
"learning_rate": 1.266615611837427e-05,
"loss": 0.8083,
"step": 136500
},
{
"epoch": 7.49,
"learning_rate": 1.2529402111481866e-05,
"loss": 0.8018,
"step": 137000
},
{
"epoch": 7.52,
"learning_rate": 1.2392648104589465e-05,
"loss": 0.789,
"step": 137500
},
{
"epoch": 7.55,
"learning_rate": 1.2255894097697062e-05,
"loss": 0.7978,
"step": 138000
},
{
"epoch": 7.58,
"learning_rate": 1.2119140090804661e-05,
"loss": 0.7952,
"step": 138500
},
{
"epoch": 7.6,
"learning_rate": 1.1982386083912258e-05,
"loss": 0.7908,
"step": 139000
},
{
"epoch": 7.63,
"learning_rate": 1.1845632077019857e-05,
"loss": 0.8163,
"step": 139500
},
{
"epoch": 7.66,
"learning_rate": 1.1708878070127454e-05,
"loss": 0.7917,
"step": 140000
},
{
"epoch": 7.69,
"learning_rate": 1.1572124063235053e-05,
"loss": 0.7945,
"step": 140500
},
{
"epoch": 7.71,
"learning_rate": 1.1435370056342652e-05,
"loss": 0.8289,
"step": 141000
},
{
"epoch": 7.74,
"learning_rate": 1.1298616049450249e-05,
"loss": 0.7807,
"step": 141500
},
{
"epoch": 7.77,
"learning_rate": 1.1161862042557847e-05,
"loss": 0.8143,
"step": 142000
},
{
"epoch": 7.79,
"learning_rate": 1.1025108035665444e-05,
"loss": 0.79,
"step": 142500
},
{
"epoch": 7.82,
"learning_rate": 1.0888354028773043e-05,
"loss": 0.7928,
"step": 143000
},
{
"epoch": 7.85,
"learning_rate": 1.0751600021880642e-05,
"loss": 0.8083,
"step": 143500
},
{
"epoch": 7.88,
"learning_rate": 1.061484601498824e-05,
"loss": 0.8019,
"step": 144000
},
{
"epoch": 7.9,
"learning_rate": 1.0478092008095838e-05,
"loss": 0.7891,
"step": 144500
},
{
"epoch": 7.93,
"learning_rate": 1.0341338001203437e-05,
"loss": 0.8143,
"step": 145000
},
{
"epoch": 7.96,
"learning_rate": 1.0204583994311034e-05,
"loss": 0.82,
"step": 145500
},
{
"epoch": 7.99,
"learning_rate": 1.0067829987418633e-05,
"loss": 0.8235,
"step": 146000
},
{
"epoch": 8.01,
"learning_rate": 9.931075980526231e-06,
"loss": 0.7471,
"step": 146500
},
{
"epoch": 8.04,
"learning_rate": 9.794321973633828e-06,
"loss": 0.7027,
"step": 147000
},
{
"epoch": 8.07,
"learning_rate": 9.657567966741427e-06,
"loss": 0.7308,
"step": 147500
},
{
"epoch": 8.1,
"learning_rate": 9.520813959849024e-06,
"loss": 0.726,
"step": 148000
},
{
"epoch": 8.12,
"learning_rate": 9.384059952956623e-06,
"loss": 0.7165,
"step": 148500
},
{
"epoch": 8.15,
"learning_rate": 9.24730594606422e-06,
"loss": 0.7214,
"step": 149000
},
{
"epoch": 8.18,
"learning_rate": 9.110551939171819e-06,
"loss": 0.7191,
"step": 149500
},
{
"epoch": 8.21,
"learning_rate": 8.973797932279416e-06,
"loss": 0.7499,
"step": 150000
},
{
"epoch": 8.23,
"learning_rate": 8.837043925387015e-06,
"loss": 0.7111,
"step": 150500
},
{
"epoch": 8.26,
"learning_rate": 8.700289918494613e-06,
"loss": 0.7301,
"step": 151000
},
{
"epoch": 8.29,
"learning_rate": 8.56353591160221e-06,
"loss": 0.7363,
"step": 151500
},
{
"epoch": 8.31,
"learning_rate": 8.42678190470981e-06,
"loss": 0.7207,
"step": 152000
},
{
"epoch": 8.34,
"learning_rate": 8.290027897817406e-06,
"loss": 0.7344,
"step": 152500
},
{
"epoch": 8.37,
"learning_rate": 8.153273890925005e-06,
"loss": 0.7097,
"step": 153000
},
{
"epoch": 8.4,
"learning_rate": 8.016519884032602e-06,
"loss": 0.7385,
"step": 153500
},
{
"epoch": 8.42,
"learning_rate": 7.879765877140201e-06,
"loss": 0.7314,
"step": 154000
},
{
"epoch": 8.45,
"learning_rate": 7.743011870247798e-06,
"loss": 0.7595,
"step": 154500
},
{
"epoch": 8.48,
"learning_rate": 7.606257863355397e-06,
"loss": 0.7482,
"step": 155000
},
{
"epoch": 8.51,
"learning_rate": 7.469503856462995e-06,
"loss": 0.7449,
"step": 155500
},
{
"epoch": 8.53,
"learning_rate": 7.332749849570593e-06,
"loss": 0.7366,
"step": 156000
},
{
"epoch": 8.56,
"learning_rate": 7.195995842678191e-06,
"loss": 0.7261,
"step": 156500
},
{
"epoch": 8.59,
"learning_rate": 7.059241835785789e-06,
"loss": 0.7209,
"step": 157000
},
{
"epoch": 8.62,
"learning_rate": 6.922487828893387e-06,
"loss": 0.7439,
"step": 157500
},
{
"epoch": 8.64,
"learning_rate": 6.785733822000985e-06,
"loss": 0.7301,
"step": 158000
},
{
"epoch": 8.67,
"learning_rate": 6.648979815108583e-06,
"loss": 0.7198,
"step": 158500
},
{
"epoch": 8.7,
"learning_rate": 6.512225808216181e-06,
"loss": 0.7509,
"step": 159000
},
{
"epoch": 8.72,
"learning_rate": 6.375471801323779e-06,
"loss": 0.749,
"step": 159500
},
{
"epoch": 8.75,
"learning_rate": 6.238717794431377e-06,
"loss": 0.7126,
"step": 160000
},
{
"epoch": 8.78,
"learning_rate": 6.101963787538975e-06,
"loss": 0.7409,
"step": 160500
},
{
"epoch": 8.81,
"learning_rate": 5.965209780646573e-06,
"loss": 0.7593,
"step": 161000
},
{
"epoch": 8.83,
"learning_rate": 5.828455773754171e-06,
"loss": 0.7404,
"step": 161500
},
{
"epoch": 8.86,
"learning_rate": 5.6917017668617695e-06,
"loss": 0.7502,
"step": 162000
},
{
"epoch": 8.89,
"learning_rate": 5.5549477599693675e-06,
"loss": 0.7489,
"step": 162500
},
{
"epoch": 8.92,
"learning_rate": 5.418193753076965e-06,
"loss": 0.7303,
"step": 163000
},
{
"epoch": 8.94,
"learning_rate": 5.281439746184563e-06,
"loss": 0.7215,
"step": 163500
},
{
"epoch": 8.97,
"learning_rate": 5.144685739292161e-06,
"loss": 0.7592,
"step": 164000
},
{
"epoch": 9.0,
"learning_rate": 5.007931732399759e-06,
"loss": 0.7516,
"step": 164500
},
{
"epoch": 9.03,
"learning_rate": 4.871177725507357e-06,
"loss": 0.6963,
"step": 165000
},
{
"epoch": 9.05,
"learning_rate": 4.734423718614955e-06,
"loss": 0.7041,
"step": 165500
},
{
"epoch": 9.08,
"learning_rate": 4.597669711722554e-06,
"loss": 0.6961,
"step": 166000
},
{
"epoch": 9.11,
"learning_rate": 4.460915704830152e-06,
"loss": 0.6921,
"step": 166500
},
{
"epoch": 9.14,
"learning_rate": 4.32416169793775e-06,
"loss": 0.6988,
"step": 167000
},
{
"epoch": 9.16,
"learning_rate": 4.1874076910453484e-06,
"loss": 0.676,
"step": 167500
},
{
"epoch": 9.19,
"learning_rate": 4.050653684152946e-06,
"loss": 0.6658,
"step": 168000
},
{
"epoch": 9.22,
"learning_rate": 3.913899677260544e-06,
"loss": 0.6926,
"step": 168500
},
{
"epoch": 9.24,
"learning_rate": 3.777145670368142e-06,
"loss": 0.68,
"step": 169000
},
{
"epoch": 9.27,
"learning_rate": 3.64039166347574e-06,
"loss": 0.6911,
"step": 169500
},
{
"epoch": 9.3,
"learning_rate": 3.5036376565833385e-06,
"loss": 0.7205,
"step": 170000
},
{
"epoch": 9.33,
"learning_rate": 3.3668836496909364e-06,
"loss": 0.711,
"step": 170500
},
{
"epoch": 9.35,
"learning_rate": 3.2301296427985343e-06,
"loss": 0.6982,
"step": 171000
},
{
"epoch": 9.38,
"learning_rate": 3.0933756359061323e-06,
"loss": 0.677,
"step": 171500
},
{
"epoch": 9.41,
"learning_rate": 2.95662162901373e-06,
"loss": 0.6964,
"step": 172000
},
{
"epoch": 9.44,
"learning_rate": 2.8198676221213285e-06,
"loss": 0.6738,
"step": 172500
},
{
"epoch": 9.46,
"learning_rate": 2.6831136152289265e-06,
"loss": 0.6774,
"step": 173000
},
{
"epoch": 9.49,
"learning_rate": 2.5463596083365244e-06,
"loss": 0.6757,
"step": 173500
},
{
"epoch": 9.52,
"learning_rate": 2.4096056014441223e-06,
"loss": 0.6856,
"step": 174000
},
{
"epoch": 9.55,
"learning_rate": 2.2728515945517207e-06,
"loss": 0.6794,
"step": 174500
},
{
"epoch": 9.57,
"learning_rate": 2.1360975876593186e-06,
"loss": 0.6813,
"step": 175000
},
{
"epoch": 9.6,
"learning_rate": 1.9993435807669165e-06,
"loss": 0.7041,
"step": 175500
},
{
"epoch": 9.63,
"learning_rate": 1.8625895738745147e-06,
"loss": 0.7096,
"step": 176000
},
{
"epoch": 9.65,
"learning_rate": 1.7258355669821126e-06,
"loss": 0.6898,
"step": 176500
},
{
"epoch": 9.68,
"learning_rate": 1.5890815600897107e-06,
"loss": 0.685,
"step": 177000
},
{
"epoch": 9.71,
"learning_rate": 1.4523275531973089e-06,
"loss": 0.7295,
"step": 177500
},
{
"epoch": 9.74,
"learning_rate": 1.3155735463049068e-06,
"loss": 0.6815,
"step": 178000
},
{
"epoch": 9.76,
"learning_rate": 1.178819539412505e-06,
"loss": 0.6813,
"step": 178500
},
{
"epoch": 9.79,
"learning_rate": 1.0420655325201029e-06,
"loss": 0.6895,
"step": 179000
},
{
"epoch": 9.82,
"learning_rate": 9.053115256277009e-07,
"loss": 0.6738,
"step": 179500
},
{
"epoch": 9.85,
"learning_rate": 7.685575187352989e-07,
"loss": 0.6672,
"step": 180000
},
{
"epoch": 9.87,
"learning_rate": 6.318035118428971e-07,
"loss": 0.7159,
"step": 180500
},
{
"epoch": 9.9,
"learning_rate": 4.950495049504951e-07,
"loss": 0.6866,
"step": 181000
},
{
"epoch": 9.93,
"learning_rate": 3.582954980580931e-07,
"loss": 0.6515,
"step": 181500
},
{
"epoch": 9.96,
"learning_rate": 2.2154149116569118e-07,
"loss": 0.6941,
"step": 182000
},
{
"epoch": 9.98,
"learning_rate": 8.478748427328921e-08,
"loss": 0.6977,
"step": 182500
},
{
"epoch": 10.0,
"step": 182810,
"total_flos": 1.6977577396666368e+17,
"train_loss": 1.1540878025462047,
"train_runtime": 36258.7506,
"train_samples_per_second": 5.042,
"train_steps_per_second": 5.042
}
],
"max_steps": 182810,
"num_train_epochs": 10,
"total_flos": 1.6977577396666368e+17,
"trial_name": null,
"trial_params": null
}