dpt-moses / trainer_state.json
Owen Huang
First commit
8043b60
raw
history blame
28.4 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 100.0,
"global_step": 113200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.44,
"learning_rate": 4.97791519434629e-05,
"loss": 0.9761,
"step": 500
},
{
"epoch": 0.88,
"learning_rate": 4.95583038869258e-05,
"loss": 0.6349,
"step": 1000
},
{
"epoch": 1.33,
"learning_rate": 4.93374558303887e-05,
"loss": 0.5803,
"step": 1500
},
{
"epoch": 1.77,
"learning_rate": 4.9116607773851593e-05,
"loss": 0.5568,
"step": 2000
},
{
"epoch": 2.21,
"learning_rate": 4.889575971731449e-05,
"loss": 0.5413,
"step": 2500
},
{
"epoch": 2.65,
"learning_rate": 4.867491166077739e-05,
"loss": 0.5304,
"step": 3000
},
{
"epoch": 3.09,
"learning_rate": 4.8454063604240283e-05,
"loss": 0.5222,
"step": 3500
},
{
"epoch": 3.53,
"learning_rate": 4.823321554770318e-05,
"loss": 0.5149,
"step": 4000
},
{
"epoch": 3.98,
"learning_rate": 4.8012367491166086e-05,
"loss": 0.5104,
"step": 4500
},
{
"epoch": 4.42,
"learning_rate": 4.779151943462898e-05,
"loss": 0.5041,
"step": 5000
},
{
"epoch": 4.86,
"learning_rate": 4.7570671378091875e-05,
"loss": 0.5012,
"step": 5500
},
{
"epoch": 5.3,
"learning_rate": 4.734982332155477e-05,
"loss": 0.4968,
"step": 6000
},
{
"epoch": 5.74,
"learning_rate": 4.712897526501767e-05,
"loss": 0.4941,
"step": 6500
},
{
"epoch": 6.18,
"learning_rate": 4.690812720848057e-05,
"loss": 0.4911,
"step": 7000
},
{
"epoch": 6.63,
"learning_rate": 4.6687279151943466e-05,
"loss": 0.488,
"step": 7500
},
{
"epoch": 7.07,
"learning_rate": 4.646643109540637e-05,
"loss": 0.4861,
"step": 8000
},
{
"epoch": 7.51,
"learning_rate": 4.624558303886926e-05,
"loss": 0.4828,
"step": 8500
},
{
"epoch": 7.95,
"learning_rate": 4.6024734982332156e-05,
"loss": 0.4821,
"step": 9000
},
{
"epoch": 8.39,
"learning_rate": 4.580388692579505e-05,
"loss": 0.4785,
"step": 9500
},
{
"epoch": 8.83,
"learning_rate": 4.558303886925796e-05,
"loss": 0.4781,
"step": 10000
},
{
"epoch": 9.28,
"learning_rate": 4.536219081272085e-05,
"loss": 0.4754,
"step": 10500
},
{
"epoch": 9.72,
"learning_rate": 4.514134275618375e-05,
"loss": 0.4745,
"step": 11000
},
{
"epoch": 10.16,
"learning_rate": 4.492049469964665e-05,
"loss": 0.4726,
"step": 11500
},
{
"epoch": 10.6,
"learning_rate": 4.469964664310954e-05,
"loss": 0.471,
"step": 12000
},
{
"epoch": 11.04,
"learning_rate": 4.4478798586572437e-05,
"loss": 0.4704,
"step": 12500
},
{
"epoch": 11.48,
"learning_rate": 4.425795053003534e-05,
"loss": 0.4678,
"step": 13000
},
{
"epoch": 11.93,
"learning_rate": 4.403710247349824e-05,
"loss": 0.4681,
"step": 13500
},
{
"epoch": 12.37,
"learning_rate": 4.381625441696113e-05,
"loss": 0.4649,
"step": 14000
},
{
"epoch": 12.81,
"learning_rate": 4.359540636042403e-05,
"loss": 0.4654,
"step": 14500
},
{
"epoch": 13.25,
"learning_rate": 4.337455830388692e-05,
"loss": 0.4632,
"step": 15000
},
{
"epoch": 13.69,
"learning_rate": 4.315371024734983e-05,
"loss": 0.4627,
"step": 15500
},
{
"epoch": 14.13,
"learning_rate": 4.2932862190812724e-05,
"loss": 0.4616,
"step": 16000
},
{
"epoch": 14.58,
"learning_rate": 4.271201413427562e-05,
"loss": 0.4601,
"step": 16500
},
{
"epoch": 15.02,
"learning_rate": 4.249116607773852e-05,
"loss": 0.4607,
"step": 17000
},
{
"epoch": 15.46,
"learning_rate": 4.2270318021201414e-05,
"loss": 0.4572,
"step": 17500
},
{
"epoch": 15.9,
"learning_rate": 4.204946996466431e-05,
"loss": 0.4587,
"step": 18000
},
{
"epoch": 16.34,
"learning_rate": 4.182862190812721e-05,
"loss": 0.4557,
"step": 18500
},
{
"epoch": 16.78,
"learning_rate": 4.160777385159011e-05,
"loss": 0.4565,
"step": 19000
},
{
"epoch": 17.23,
"learning_rate": 4.1386925795053005e-05,
"loss": 0.4547,
"step": 19500
},
{
"epoch": 17.67,
"learning_rate": 4.11660777385159e-05,
"loss": 0.4541,
"step": 20000
},
{
"epoch": 18.11,
"learning_rate": 4.09452296819788e-05,
"loss": 0.4539,
"step": 20500
},
{
"epoch": 18.55,
"learning_rate": 4.07243816254417e-05,
"loss": 0.452,
"step": 21000
},
{
"epoch": 18.99,
"learning_rate": 4.0503533568904596e-05,
"loss": 0.4531,
"step": 21500
},
{
"epoch": 19.43,
"learning_rate": 4.028268551236749e-05,
"loss": 0.4496,
"step": 22000
},
{
"epoch": 19.88,
"learning_rate": 4.006183745583039e-05,
"loss": 0.4513,
"step": 22500
},
{
"epoch": 20.32,
"learning_rate": 3.9840989399293286e-05,
"loss": 0.4488,
"step": 23000
},
{
"epoch": 20.76,
"learning_rate": 3.962014134275618e-05,
"loss": 0.4493,
"step": 23500
},
{
"epoch": 21.2,
"learning_rate": 3.939929328621909e-05,
"loss": 0.4481,
"step": 24000
},
{
"epoch": 21.64,
"learning_rate": 3.917844522968198e-05,
"loss": 0.4475,
"step": 24500
},
{
"epoch": 22.08,
"learning_rate": 3.895759717314488e-05,
"loss": 0.4475,
"step": 25000
},
{
"epoch": 22.53,
"learning_rate": 3.873674911660777e-05,
"loss": 0.4453,
"step": 25500
},
{
"epoch": 22.97,
"learning_rate": 3.851590106007067e-05,
"loss": 0.447,
"step": 26000
},
{
"epoch": 23.41,
"learning_rate": 3.8295053003533574e-05,
"loss": 0.4435,
"step": 26500
},
{
"epoch": 23.85,
"learning_rate": 3.807420494699647e-05,
"loss": 0.4454,
"step": 27000
},
{
"epoch": 24.29,
"learning_rate": 3.785335689045937e-05,
"loss": 0.443,
"step": 27500
},
{
"epoch": 24.73,
"learning_rate": 3.7632508833922264e-05,
"loss": 0.4436,
"step": 28000
},
{
"epoch": 25.18,
"learning_rate": 3.741166077738516e-05,
"loss": 0.4427,
"step": 28500
},
{
"epoch": 25.62,
"learning_rate": 3.719081272084805e-05,
"loss": 0.4418,
"step": 29000
},
{
"epoch": 26.06,
"learning_rate": 3.696996466431096e-05,
"loss": 0.4426,
"step": 29500
},
{
"epoch": 26.5,
"learning_rate": 3.6749116607773855e-05,
"loss": 0.4398,
"step": 30000
},
{
"epoch": 26.94,
"learning_rate": 3.652826855123675e-05,
"loss": 0.4417,
"step": 30500
},
{
"epoch": 27.39,
"learning_rate": 3.630742049469965e-05,
"loss": 0.4386,
"step": 31000
},
{
"epoch": 27.83,
"learning_rate": 3.6086572438162545e-05,
"loss": 0.4401,
"step": 31500
},
{
"epoch": 28.27,
"learning_rate": 3.586572438162544e-05,
"loss": 0.4382,
"step": 32000
},
{
"epoch": 28.71,
"learning_rate": 3.564487632508834e-05,
"loss": 0.4386,
"step": 32500
},
{
"epoch": 29.15,
"learning_rate": 3.542402826855124e-05,
"loss": 0.4381,
"step": 33000
},
{
"epoch": 29.59,
"learning_rate": 3.5203180212014136e-05,
"loss": 0.4369,
"step": 33500
},
{
"epoch": 30.04,
"learning_rate": 3.498233215547703e-05,
"loss": 0.438,
"step": 34000
},
{
"epoch": 30.48,
"learning_rate": 3.476148409893993e-05,
"loss": 0.435,
"step": 34500
},
{
"epoch": 30.92,
"learning_rate": 3.454063604240283e-05,
"loss": 0.4372,
"step": 35000
},
{
"epoch": 31.36,
"learning_rate": 3.431978798586573e-05,
"loss": 0.4343,
"step": 35500
},
{
"epoch": 31.8,
"learning_rate": 3.409893992932862e-05,
"loss": 0.4358,
"step": 36000
},
{
"epoch": 32.24,
"learning_rate": 3.387809187279152e-05,
"loss": 0.4341,
"step": 36500
},
{
"epoch": 32.69,
"learning_rate": 3.365724381625442e-05,
"loss": 0.4343,
"step": 37000
},
{
"epoch": 33.13,
"learning_rate": 3.343639575971731e-05,
"loss": 0.4343,
"step": 37500
},
{
"epoch": 33.57,
"learning_rate": 3.321554770318021e-05,
"loss": 0.4326,
"step": 38000
},
{
"epoch": 34.01,
"learning_rate": 3.2994699646643114e-05,
"loss": 0.4343,
"step": 38500
},
{
"epoch": 34.45,
"learning_rate": 3.277385159010601e-05,
"loss": 0.4309,
"step": 39000
},
{
"epoch": 34.89,
"learning_rate": 3.25530035335689e-05,
"loss": 0.4332,
"step": 39500
},
{
"epoch": 35.34,
"learning_rate": 3.2332155477031804e-05,
"loss": 0.4306,
"step": 40000
},
{
"epoch": 35.78,
"learning_rate": 3.2111307420494705e-05,
"loss": 0.4318,
"step": 40500
},
{
"epoch": 36.22,
"learning_rate": 3.18904593639576e-05,
"loss": 0.4306,
"step": 41000
},
{
"epoch": 36.66,
"learning_rate": 3.1669611307420494e-05,
"loss": 0.4304,
"step": 41500
},
{
"epoch": 37.1,
"learning_rate": 3.1448763250883395e-05,
"loss": 0.4307,
"step": 42000
},
{
"epoch": 37.54,
"learning_rate": 3.122791519434629e-05,
"loss": 0.4289,
"step": 42500
},
{
"epoch": 37.99,
"learning_rate": 3.1007067137809184e-05,
"loss": 0.431,
"step": 43000
},
{
"epoch": 38.43,
"learning_rate": 3.078621908127209e-05,
"loss": 0.4276,
"step": 43500
},
{
"epoch": 38.87,
"learning_rate": 3.0565371024734986e-05,
"loss": 0.4296,
"step": 44000
},
{
"epoch": 39.31,
"learning_rate": 3.034452296819788e-05,
"loss": 0.4274,
"step": 44500
},
{
"epoch": 39.75,
"learning_rate": 3.0123674911660775e-05,
"loss": 0.4285,
"step": 45000
},
{
"epoch": 40.19,
"learning_rate": 2.990282685512368e-05,
"loss": 0.4276,
"step": 45500
},
{
"epoch": 40.64,
"learning_rate": 2.9681978798586574e-05,
"loss": 0.427,
"step": 46000
},
{
"epoch": 41.08,
"learning_rate": 2.9461130742049468e-05,
"loss": 0.4278,
"step": 46500
},
{
"epoch": 41.52,
"learning_rate": 2.9240282685512373e-05,
"loss": 0.4256,
"step": 47000
},
{
"epoch": 41.96,
"learning_rate": 2.9019434628975267e-05,
"loss": 0.4277,
"step": 47500
},
{
"epoch": 42.4,
"learning_rate": 2.879858657243816e-05,
"loss": 0.4246,
"step": 48000
},
{
"epoch": 42.84,
"learning_rate": 2.857773851590106e-05,
"loss": 0.4266,
"step": 48500
},
{
"epoch": 43.29,
"learning_rate": 2.835689045936396e-05,
"loss": 0.4246,
"step": 49000
},
{
"epoch": 43.73,
"learning_rate": 2.8136042402826858e-05,
"loss": 0.4254,
"step": 49500
},
{
"epoch": 44.17,
"learning_rate": 2.7915194346289753e-05,
"loss": 0.4248,
"step": 50000
},
{
"epoch": 44.61,
"learning_rate": 2.7694346289752654e-05,
"loss": 0.424,
"step": 50500
},
{
"epoch": 45.05,
"learning_rate": 2.747349823321555e-05,
"loss": 0.4251,
"step": 51000
},
{
"epoch": 45.49,
"learning_rate": 2.7252650176678446e-05,
"loss": 0.4227,
"step": 51500
},
{
"epoch": 45.94,
"learning_rate": 2.703180212014134e-05,
"loss": 0.4248,
"step": 52000
},
{
"epoch": 46.38,
"learning_rate": 2.6810954063604245e-05,
"loss": 0.4221,
"step": 52500
},
{
"epoch": 46.82,
"learning_rate": 2.659010600706714e-05,
"loss": 0.4237,
"step": 53000
},
{
"epoch": 47.26,
"learning_rate": 2.6369257950530034e-05,
"loss": 0.4221,
"step": 53500
},
{
"epoch": 47.7,
"learning_rate": 2.6148409893992938e-05,
"loss": 0.4225,
"step": 54000
},
{
"epoch": 48.14,
"learning_rate": 2.5927561837455833e-05,
"loss": 0.4225,
"step": 54500
},
{
"epoch": 48.59,
"learning_rate": 2.5706713780918727e-05,
"loss": 0.4214,
"step": 55000
},
{
"epoch": 49.03,
"learning_rate": 2.5485865724381625e-05,
"loss": 0.4228,
"step": 55500
},
{
"epoch": 49.47,
"learning_rate": 2.5265017667844526e-05,
"loss": 0.42,
"step": 56000
},
{
"epoch": 49.91,
"learning_rate": 2.5044169611307424e-05,
"loss": 0.4222,
"step": 56500
},
{
"epoch": 50.35,
"learning_rate": 2.4823321554770318e-05,
"loss": 0.4197,
"step": 57000
},
{
"epoch": 50.8,
"learning_rate": 2.4602473498233216e-05,
"loss": 0.4211,
"step": 57500
},
{
"epoch": 51.24,
"learning_rate": 2.4381625441696117e-05,
"loss": 0.42,
"step": 58000
},
{
"epoch": 51.68,
"learning_rate": 2.416077738515901e-05,
"loss": 0.4201,
"step": 58500
},
{
"epoch": 52.12,
"learning_rate": 2.393992932862191e-05,
"loss": 0.4203,
"step": 59000
},
{
"epoch": 52.56,
"learning_rate": 2.3719081272084807e-05,
"loss": 0.419,
"step": 59500
},
{
"epoch": 53.0,
"learning_rate": 2.3498233215547705e-05,
"loss": 0.4207,
"step": 60000
},
{
"epoch": 53.45,
"learning_rate": 2.32773851590106e-05,
"loss": 0.4176,
"step": 60500
},
{
"epoch": 53.89,
"learning_rate": 2.30565371024735e-05,
"loss": 0.4199,
"step": 61000
},
{
"epoch": 54.33,
"learning_rate": 2.2835689045936398e-05,
"loss": 0.4179,
"step": 61500
},
{
"epoch": 54.77,
"learning_rate": 2.2614840989399292e-05,
"loss": 0.4188,
"step": 62000
},
{
"epoch": 55.21,
"learning_rate": 2.2393992932862194e-05,
"loss": 0.4181,
"step": 62500
},
{
"epoch": 55.65,
"learning_rate": 2.2173144876325088e-05,
"loss": 0.4178,
"step": 63000
},
{
"epoch": 56.1,
"learning_rate": 2.195229681978799e-05,
"loss": 0.4184,
"step": 63500
},
{
"epoch": 56.54,
"learning_rate": 2.1731448763250883e-05,
"loss": 0.4169,
"step": 64000
},
{
"epoch": 56.98,
"learning_rate": 2.151060070671378e-05,
"loss": 0.4185,
"step": 64500
},
{
"epoch": 57.42,
"learning_rate": 2.128975265017668e-05,
"loss": 0.4159,
"step": 65000
},
{
"epoch": 57.86,
"learning_rate": 2.1068904593639577e-05,
"loss": 0.4177,
"step": 65500
},
{
"epoch": 58.3,
"learning_rate": 2.0848056537102475e-05,
"loss": 0.4159,
"step": 66000
},
{
"epoch": 58.75,
"learning_rate": 2.0627208480565372e-05,
"loss": 0.4169,
"step": 66500
},
{
"epoch": 59.19,
"learning_rate": 2.040636042402827e-05,
"loss": 0.4163,
"step": 67000
},
{
"epoch": 59.63,
"learning_rate": 2.0185512367491165e-05,
"loss": 0.4159,
"step": 67500
},
{
"epoch": 60.07,
"learning_rate": 1.9964664310954066e-05,
"loss": 0.4167,
"step": 68000
},
{
"epoch": 60.51,
"learning_rate": 1.974381625441696e-05,
"loss": 0.4148,
"step": 68500
},
{
"epoch": 60.95,
"learning_rate": 1.9522968197879858e-05,
"loss": 0.4165,
"step": 69000
},
{
"epoch": 61.4,
"learning_rate": 1.930212014134276e-05,
"loss": 0.4142,
"step": 69500
},
{
"epoch": 61.84,
"learning_rate": 1.9081272084805653e-05,
"loss": 0.4157,
"step": 70000
},
{
"epoch": 62.28,
"learning_rate": 1.8860424028268555e-05,
"loss": 0.4144,
"step": 70500
},
{
"epoch": 62.72,
"learning_rate": 1.863957597173145e-05,
"loss": 0.4149,
"step": 71000
},
{
"epoch": 63.16,
"learning_rate": 1.8418727915194347e-05,
"loss": 0.4147,
"step": 71500
},
{
"epoch": 63.6,
"learning_rate": 1.8197879858657244e-05,
"loss": 0.4139,
"step": 72000
},
{
"epoch": 64.05,
"learning_rate": 1.7977031802120142e-05,
"loss": 0.4151,
"step": 72500
},
{
"epoch": 64.49,
"learning_rate": 1.775618374558304e-05,
"loss": 0.413,
"step": 73000
},
{
"epoch": 64.93,
"learning_rate": 1.7535335689045938e-05,
"loss": 0.4147,
"step": 73500
},
{
"epoch": 65.37,
"learning_rate": 1.7314487632508836e-05,
"loss": 0.4127,
"step": 74000
},
{
"epoch": 65.81,
"learning_rate": 1.709363957597173e-05,
"loss": 0.4139,
"step": 74500
},
{
"epoch": 66.25,
"learning_rate": 1.687279151943463e-05,
"loss": 0.4128,
"step": 75000
},
{
"epoch": 66.7,
"learning_rate": 1.6651943462897526e-05,
"loss": 0.4131,
"step": 75500
},
{
"epoch": 67.14,
"learning_rate": 1.6431095406360427e-05,
"loss": 0.4133,
"step": 76000
},
{
"epoch": 67.58,
"learning_rate": 1.6210247349823324e-05,
"loss": 0.4123,
"step": 76500
},
{
"epoch": 68.02,
"learning_rate": 1.598939929328622e-05,
"loss": 0.4136,
"step": 77000
},
{
"epoch": 68.46,
"learning_rate": 1.576855123674912e-05,
"loss": 0.4114,
"step": 77500
},
{
"epoch": 68.9,
"learning_rate": 1.5547703180212014e-05,
"loss": 0.413,
"step": 78000
},
{
"epoch": 69.35,
"learning_rate": 1.5326855123674912e-05,
"loss": 0.4113,
"step": 78500
},
{
"epoch": 69.79,
"learning_rate": 1.5106007067137808e-05,
"loss": 0.4123,
"step": 79000
},
{
"epoch": 70.23,
"learning_rate": 1.4885159010600708e-05,
"loss": 0.4116,
"step": 79500
},
{
"epoch": 70.67,
"learning_rate": 1.4664310954063604e-05,
"loss": 0.4116,
"step": 80000
},
{
"epoch": 71.11,
"learning_rate": 1.4443462897526502e-05,
"loss": 0.412,
"step": 80500
},
{
"epoch": 71.55,
"learning_rate": 1.4222614840989401e-05,
"loss": 0.4107,
"step": 81000
},
{
"epoch": 72.0,
"learning_rate": 1.4001766784452297e-05,
"loss": 0.4122,
"step": 81500
},
{
"epoch": 72.44,
"learning_rate": 1.3780918727915197e-05,
"loss": 0.41,
"step": 82000
},
{
"epoch": 72.88,
"learning_rate": 1.3560070671378091e-05,
"loss": 0.4114,
"step": 82500
},
{
"epoch": 73.32,
"learning_rate": 1.333922261484099e-05,
"loss": 0.4102,
"step": 83000
},
{
"epoch": 73.76,
"learning_rate": 1.3118374558303886e-05,
"loss": 0.4108,
"step": 83500
},
{
"epoch": 74.2,
"learning_rate": 1.2897526501766786e-05,
"loss": 0.4104,
"step": 84000
},
{
"epoch": 74.65,
"learning_rate": 1.2676678445229684e-05,
"loss": 0.4101,
"step": 84500
},
{
"epoch": 75.09,
"learning_rate": 1.245583038869258e-05,
"loss": 0.4106,
"step": 85000
},
{
"epoch": 75.53,
"learning_rate": 1.2234982332155478e-05,
"loss": 0.4094,
"step": 85500
},
{
"epoch": 75.97,
"learning_rate": 1.2014134275618374e-05,
"loss": 0.4107,
"step": 86000
},
{
"epoch": 76.41,
"learning_rate": 1.1793286219081273e-05,
"loss": 0.4088,
"step": 86500
},
{
"epoch": 76.86,
"learning_rate": 1.1572438162544171e-05,
"loss": 0.4101,
"step": 87000
},
{
"epoch": 77.3,
"learning_rate": 1.1351590106007069e-05,
"loss": 0.4089,
"step": 87500
},
{
"epoch": 77.74,
"learning_rate": 1.1130742049469965e-05,
"loss": 0.4095,
"step": 88000
},
{
"epoch": 78.18,
"learning_rate": 1.0909893992932863e-05,
"loss": 0.4092,
"step": 88500
},
{
"epoch": 78.62,
"learning_rate": 1.068904593639576e-05,
"loss": 0.4087,
"step": 89000
},
{
"epoch": 79.06,
"learning_rate": 1.0468197879858656e-05,
"loss": 0.4094,
"step": 89500
},
{
"epoch": 79.51,
"learning_rate": 1.0247349823321556e-05,
"loss": 0.4081,
"step": 90000
},
{
"epoch": 79.95,
"learning_rate": 1.0026501766784454e-05,
"loss": 0.4092,
"step": 90500
},
{
"epoch": 80.39,
"learning_rate": 9.805653710247351e-06,
"loss": 0.4078,
"step": 91000
},
{
"epoch": 80.83,
"learning_rate": 9.584805653710247e-06,
"loss": 0.4087,
"step": 91500
},
{
"epoch": 81.27,
"learning_rate": 9.363957597173145e-06,
"loss": 0.4078,
"step": 92000
},
{
"epoch": 81.71,
"learning_rate": 9.143109540636043e-06,
"loss": 0.4081,
"step": 92500
},
{
"epoch": 82.16,
"learning_rate": 8.922261484098939e-06,
"loss": 0.4082,
"step": 93000
},
{
"epoch": 82.6,
"learning_rate": 8.701413427561837e-06,
"loss": 0.4075,
"step": 93500
},
{
"epoch": 83.04,
"learning_rate": 8.480565371024736e-06,
"loss": 0.4082,
"step": 94000
},
{
"epoch": 83.48,
"learning_rate": 8.259717314487634e-06,
"loss": 0.4069,
"step": 94500
},
{
"epoch": 83.92,
"learning_rate": 8.03886925795053e-06,
"loss": 0.4081,
"step": 95000
},
{
"epoch": 84.36,
"learning_rate": 7.818021201413428e-06,
"loss": 0.4068,
"step": 95500
},
{
"epoch": 84.81,
"learning_rate": 7.597173144876325e-06,
"loss": 0.4075,
"step": 96000
},
{
"epoch": 85.25,
"learning_rate": 7.376325088339223e-06,
"loss": 0.407,
"step": 96500
},
{
"epoch": 85.69,
"learning_rate": 7.15547703180212e-06,
"loss": 0.407,
"step": 97000
},
{
"epoch": 86.13,
"learning_rate": 6.934628975265017e-06,
"loss": 0.4071,
"step": 97500
},
{
"epoch": 86.57,
"learning_rate": 6.713780918727916e-06,
"loss": 0.4064,
"step": 98000
},
{
"epoch": 87.01,
"learning_rate": 6.492932862190814e-06,
"loss": 0.4073,
"step": 98500
},
{
"epoch": 87.46,
"learning_rate": 6.272084805653711e-06,
"loss": 0.406,
"step": 99000
},
{
"epoch": 87.9,
"learning_rate": 6.051236749116608e-06,
"loss": 0.4068,
"step": 99500
},
{
"epoch": 88.34,
"learning_rate": 5.830388692579505e-06,
"loss": 0.4059,
"step": 100000
},
{
"epoch": 88.78,
"learning_rate": 5.609540636042403e-06,
"loss": 0.4063,
"step": 100500
},
{
"epoch": 89.22,
"learning_rate": 5.388692579505301e-06,
"loss": 0.4061,
"step": 101000
},
{
"epoch": 89.66,
"learning_rate": 5.167844522968198e-06,
"loss": 0.4059,
"step": 101500
},
{
"epoch": 90.11,
"learning_rate": 4.946996466431096e-06,
"loss": 0.4061,
"step": 102000
},
{
"epoch": 90.55,
"learning_rate": 4.726148409893993e-06,
"loss": 0.4056,
"step": 102500
},
{
"epoch": 90.99,
"learning_rate": 4.505300353356891e-06,
"loss": 0.406,
"step": 103000
},
{
"epoch": 91.43,
"learning_rate": 4.284452296819788e-06,
"loss": 0.4051,
"step": 103500
},
{
"epoch": 91.87,
"learning_rate": 4.063604240282685e-06,
"loss": 0.4057,
"step": 104000
},
{
"epoch": 92.31,
"learning_rate": 3.842756183745584e-06,
"loss": 0.4052,
"step": 104500
},
{
"epoch": 92.76,
"learning_rate": 3.621908127208481e-06,
"loss": 0.4054,
"step": 105000
},
{
"epoch": 93.2,
"learning_rate": 3.401060070671378e-06,
"loss": 0.4051,
"step": 105500
},
{
"epoch": 93.64,
"learning_rate": 3.1802120141342753e-06,
"loss": 0.4049,
"step": 106000
},
{
"epoch": 94.08,
"learning_rate": 2.959363957597173e-06,
"loss": 0.4053,
"step": 106500
},
{
"epoch": 94.52,
"learning_rate": 2.738515901060071e-06,
"loss": 0.4047,
"step": 107000
},
{
"epoch": 94.96,
"learning_rate": 2.517667844522968e-06,
"loss": 0.405,
"step": 107500
},
{
"epoch": 95.41,
"learning_rate": 2.296819787985866e-06,
"loss": 0.4044,
"step": 108000
},
{
"epoch": 95.85,
"learning_rate": 2.0759717314487633e-06,
"loss": 0.4047,
"step": 108500
},
{
"epoch": 96.29,
"learning_rate": 1.8551236749116609e-06,
"loss": 0.4044,
"step": 109000
},
{
"epoch": 96.73,
"learning_rate": 1.6342756183745586e-06,
"loss": 0.4044,
"step": 109500
},
{
"epoch": 97.17,
"learning_rate": 1.4134275618374558e-06,
"loss": 0.4044,
"step": 110000
},
{
"epoch": 97.61,
"learning_rate": 1.1925795053003533e-06,
"loss": 0.4042,
"step": 110500
},
{
"epoch": 98.06,
"learning_rate": 9.71731448763251e-07,
"loss": 0.4044,
"step": 111000
},
{
"epoch": 98.5,
"learning_rate": 7.508833922261484e-07,
"loss": 0.404,
"step": 111500
},
{
"epoch": 98.94,
"learning_rate": 5.30035335689046e-07,
"loss": 0.4041,
"step": 112000
},
{
"epoch": 99.38,
"learning_rate": 3.091872791519435e-07,
"loss": 0.4039,
"step": 112500
},
{
"epoch": 99.82,
"learning_rate": 8.833922261484099e-08,
"loss": 0.4039,
"step": 113000
},
{
"epoch": 100.0,
"step": 113200,
"total_flos": 8.087110710389113e+18,
"train_loss": 0.43426066813115094,
"train_runtime": 194605.8141,
"train_samples_per_second": 814.294,
"train_steps_per_second": 0.582
}
],
"max_steps": 113200,
"num_train_epochs": 100,
"total_flos": 8.087110710389113e+18,
"trial_name": null,
"trial_params": null
}