roberta-base-wechsel-french / trainer_state.json
benjamin's picture
initial commit
e98c28b
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 69.38659543467703,
"global_step": 250000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.14,
"learning_rate": 2.0000000000000003e-06,
"loss": 5.442,
"step": 500
},
{
"epoch": 0.28,
"learning_rate": 4.000000000000001e-06,
"loss": 4.4503,
"step": 1000
},
{
"epoch": 0.42,
"learning_rate": 6e-06,
"loss": 3.9029,
"step": 1500
},
{
"epoch": 0.56,
"learning_rate": 8.000000000000001e-06,
"loss": 3.5541,
"step": 2000
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 3.3022,
"step": 2500
},
{
"epoch": 0.83,
"learning_rate": 1.2e-05,
"loss": 3.1008,
"step": 3000
},
{
"epoch": 0.97,
"learning_rate": 1.4000000000000001e-05,
"loss": 2.9456,
"step": 3500
},
{
"epoch": 1.11,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.816,
"step": 4000
},
{
"epoch": 1.25,
"learning_rate": 1.8e-05,
"loss": 2.7046,
"step": 4500
},
{
"epoch": 1.39,
"learning_rate": 2e-05,
"loss": 2.6054,
"step": 5000
},
{
"epoch": 1.53,
"learning_rate": 2.2000000000000003e-05,
"loss": 2.528,
"step": 5500
},
{
"epoch": 1.67,
"learning_rate": 2.4e-05,
"loss": 2.4576,
"step": 6000
},
{
"epoch": 1.8,
"learning_rate": 2.6000000000000002e-05,
"loss": 2.3952,
"step": 6500
},
{
"epoch": 1.94,
"learning_rate": 2.8000000000000003e-05,
"loss": 2.3405,
"step": 7000
},
{
"epoch": 2.08,
"learning_rate": 3e-05,
"loss": 2.2901,
"step": 7500
},
{
"epoch": 2.22,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.2414,
"step": 8000
},
{
"epoch": 2.36,
"learning_rate": 3.4000000000000007e-05,
"loss": 2.2004,
"step": 8500
},
{
"epoch": 2.5,
"learning_rate": 3.6e-05,
"loss": 2.1586,
"step": 9000
},
{
"epoch": 2.64,
"learning_rate": 3.8e-05,
"loss": 2.123,
"step": 9500
},
{
"epoch": 2.78,
"learning_rate": 4e-05,
"loss": 2.0858,
"step": 10000
},
{
"epoch": 2.91,
"learning_rate": 4.2e-05,
"loss": 2.0479,
"step": 10500
},
{
"epoch": 3.05,
"learning_rate": 4.4000000000000006e-05,
"loss": 2.0195,
"step": 11000
},
{
"epoch": 3.19,
"learning_rate": 4.600000000000001e-05,
"loss": 1.9842,
"step": 11500
},
{
"epoch": 3.33,
"learning_rate": 4.8e-05,
"loss": 1.9575,
"step": 12000
},
{
"epoch": 3.47,
"learning_rate": 5e-05,
"loss": 1.9303,
"step": 12500
},
{
"epoch": 3.47,
"eval_loss": 1.8335806131362915,
"eval_runtime": 405.093,
"eval_samples_per_second": 457.117,
"eval_steps_per_second": 3.572,
"step": 12500
},
{
"epoch": 3.61,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.906,
"step": 13000
},
{
"epoch": 3.75,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.8833,
"step": 13500
},
{
"epoch": 3.89,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.8601,
"step": 14000
},
{
"epoch": 4.02,
"learning_rate": 5.8e-05,
"loss": 1.8405,
"step": 14500
},
{
"epoch": 4.16,
"learning_rate": 6e-05,
"loss": 1.822,
"step": 15000
},
{
"epoch": 4.3,
"learning_rate": 6.2e-05,
"loss": 1.8035,
"step": 15500
},
{
"epoch": 4.44,
"learning_rate": 6.400000000000001e-05,
"loss": 1.7869,
"step": 16000
},
{
"epoch": 4.58,
"learning_rate": 6.6e-05,
"loss": 1.7719,
"step": 16500
},
{
"epoch": 4.72,
"learning_rate": 6.800000000000001e-05,
"loss": 1.7585,
"step": 17000
},
{
"epoch": 4.86,
"learning_rate": 7e-05,
"loss": 1.746,
"step": 17500
},
{
"epoch": 5.0,
"learning_rate": 7.2e-05,
"loss": 1.7321,
"step": 18000
},
{
"epoch": 5.13,
"learning_rate": 7.4e-05,
"loss": 1.7189,
"step": 18500
},
{
"epoch": 5.27,
"learning_rate": 7.6e-05,
"loss": 1.7075,
"step": 19000
},
{
"epoch": 5.41,
"learning_rate": 7.800000000000001e-05,
"loss": 1.6968,
"step": 19500
},
{
"epoch": 5.55,
"learning_rate": 8e-05,
"loss": 1.6874,
"step": 20000
},
{
"epoch": 5.69,
"learning_rate": 8.2e-05,
"loss": 1.6807,
"step": 20500
},
{
"epoch": 5.83,
"learning_rate": 8.4e-05,
"loss": 1.6724,
"step": 21000
},
{
"epoch": 5.97,
"learning_rate": 8.6e-05,
"loss": 1.6606,
"step": 21500
},
{
"epoch": 6.11,
"learning_rate": 8.800000000000001e-05,
"loss": 1.6524,
"step": 22000
},
{
"epoch": 6.24,
"learning_rate": 9e-05,
"loss": 1.6434,
"step": 22500
},
{
"epoch": 6.38,
"learning_rate": 9.200000000000001e-05,
"loss": 1.6354,
"step": 23000
},
{
"epoch": 6.52,
"learning_rate": 9.4e-05,
"loss": 1.6275,
"step": 23500
},
{
"epoch": 6.66,
"learning_rate": 9.6e-05,
"loss": 1.6204,
"step": 24000
},
{
"epoch": 6.8,
"learning_rate": 9.8e-05,
"loss": 1.6143,
"step": 24500
},
{
"epoch": 6.94,
"learning_rate": 0.0001,
"loss": 1.6099,
"step": 25000
},
{
"epoch": 6.94,
"eval_loss": 1.537390947341919,
"eval_runtime": 389.453,
"eval_samples_per_second": 475.475,
"eval_steps_per_second": 3.715,
"step": 25000
},
{
"epoch": 7.08,
"learning_rate": 9.977777777777779e-05,
"loss": 1.6084,
"step": 25500
},
{
"epoch": 7.22,
"learning_rate": 9.955555555555556e-05,
"loss": 1.596,
"step": 26000
},
{
"epoch": 7.35,
"learning_rate": 9.933333333333334e-05,
"loss": 1.5903,
"step": 26500
},
{
"epoch": 7.49,
"learning_rate": 9.911111111111112e-05,
"loss": 1.5825,
"step": 27000
},
{
"epoch": 7.63,
"learning_rate": 9.888888888888889e-05,
"loss": 1.5759,
"step": 27500
},
{
"epoch": 7.77,
"learning_rate": 9.866666666666668e-05,
"loss": 1.5692,
"step": 28000
},
{
"epoch": 7.91,
"learning_rate": 9.844444444444444e-05,
"loss": 1.5673,
"step": 28500
},
{
"epoch": 8.05,
"learning_rate": 9.822222222222223e-05,
"loss": 1.5617,
"step": 29000
},
{
"epoch": 8.19,
"learning_rate": 9.8e-05,
"loss": 1.5554,
"step": 29500
},
{
"epoch": 8.33,
"learning_rate": 9.777777777777778e-05,
"loss": 1.551,
"step": 30000
},
{
"epoch": 8.47,
"learning_rate": 9.755555555555555e-05,
"loss": 1.5474,
"step": 30500
},
{
"epoch": 8.6,
"learning_rate": 9.733333333333335e-05,
"loss": 1.543,
"step": 31000
},
{
"epoch": 8.74,
"learning_rate": 9.711111111111111e-05,
"loss": 1.538,
"step": 31500
},
{
"epoch": 8.88,
"learning_rate": 9.68888888888889e-05,
"loss": 1.5341,
"step": 32000
},
{
"epoch": 9.02,
"learning_rate": 9.666666666666667e-05,
"loss": 1.5333,
"step": 32500
},
{
"epoch": 9.16,
"learning_rate": 9.644444444444445e-05,
"loss": 1.5245,
"step": 33000
},
{
"epoch": 9.3,
"learning_rate": 9.622222222222222e-05,
"loss": 1.5229,
"step": 33500
},
{
"epoch": 9.44,
"learning_rate": 9.6e-05,
"loss": 1.5181,
"step": 34000
},
{
"epoch": 9.58,
"learning_rate": 9.577777777777777e-05,
"loss": 1.5163,
"step": 34500
},
{
"epoch": 9.71,
"learning_rate": 9.555555555555557e-05,
"loss": 1.5131,
"step": 35000
},
{
"epoch": 9.85,
"learning_rate": 9.533333333333334e-05,
"loss": 1.5106,
"step": 35500
},
{
"epoch": 9.99,
"learning_rate": 9.511111111111112e-05,
"loss": 1.5067,
"step": 36000
},
{
"epoch": 10.13,
"learning_rate": 9.488888888888889e-05,
"loss": 1.5016,
"step": 36500
},
{
"epoch": 10.27,
"learning_rate": 9.466666666666667e-05,
"loss": 1.4968,
"step": 37000
},
{
"epoch": 10.41,
"learning_rate": 9.444444444444444e-05,
"loss": 1.4956,
"step": 37500
},
{
"epoch": 10.41,
"eval_loss": 1.436057448387146,
"eval_runtime": 389.7996,
"eval_samples_per_second": 475.052,
"eval_steps_per_second": 3.712,
"step": 37500
},
{
"epoch": 10.55,
"learning_rate": 9.422222222222223e-05,
"loss": 1.4937,
"step": 38000
},
{
"epoch": 10.69,
"learning_rate": 9.4e-05,
"loss": 1.4894,
"step": 38500
},
{
"epoch": 10.82,
"learning_rate": 9.377777777777779e-05,
"loss": 1.4884,
"step": 39000
},
{
"epoch": 10.96,
"learning_rate": 9.355555555555556e-05,
"loss": 1.4848,
"step": 39500
},
{
"epoch": 11.1,
"learning_rate": 9.333333333333334e-05,
"loss": 1.4803,
"step": 40000
},
{
"epoch": 11.24,
"learning_rate": 9.311111111111111e-05,
"loss": 1.4785,
"step": 40500
},
{
"epoch": 11.38,
"learning_rate": 9.28888888888889e-05,
"loss": 1.4757,
"step": 41000
},
{
"epoch": 11.52,
"learning_rate": 9.266666666666666e-05,
"loss": 1.4761,
"step": 41500
},
{
"epoch": 11.66,
"learning_rate": 9.244444444444445e-05,
"loss": 1.4715,
"step": 42000
},
{
"epoch": 11.8,
"learning_rate": 9.222222222222223e-05,
"loss": 1.4719,
"step": 42500
},
{
"epoch": 11.93,
"learning_rate": 9.200000000000001e-05,
"loss": 1.4686,
"step": 43000
},
{
"epoch": 12.07,
"learning_rate": 9.177777777777778e-05,
"loss": 1.4649,
"step": 43500
},
{
"epoch": 12.21,
"learning_rate": 9.155555555555557e-05,
"loss": 1.4614,
"step": 44000
},
{
"epoch": 12.35,
"learning_rate": 9.133333333333334e-05,
"loss": 1.4597,
"step": 44500
},
{
"epoch": 12.49,
"learning_rate": 9.111111111111112e-05,
"loss": 1.4596,
"step": 45000
},
{
"epoch": 12.63,
"learning_rate": 9.088888888888889e-05,
"loss": 1.4563,
"step": 45500
},
{
"epoch": 12.77,
"learning_rate": 9.066666666666667e-05,
"loss": 1.4544,
"step": 46000
},
{
"epoch": 12.91,
"learning_rate": 9.044444444444445e-05,
"loss": 1.4542,
"step": 46500
},
{
"epoch": 13.04,
"learning_rate": 9.022222222222224e-05,
"loss": 1.4527,
"step": 47000
},
{
"epoch": 13.18,
"learning_rate": 9e-05,
"loss": 1.4485,
"step": 47500
},
{
"epoch": 13.32,
"learning_rate": 8.977777777777779e-05,
"loss": 1.4472,
"step": 48000
},
{
"epoch": 13.46,
"learning_rate": 8.955555555555556e-05,
"loss": 1.4451,
"step": 48500
},
{
"epoch": 13.6,
"learning_rate": 8.933333333333334e-05,
"loss": 1.4423,
"step": 49000
},
{
"epoch": 13.74,
"learning_rate": 8.911111111111111e-05,
"loss": 1.4434,
"step": 49500
},
{
"epoch": 13.88,
"learning_rate": 8.888888888888889e-05,
"loss": 1.4436,
"step": 50000
},
{
"epoch": 13.88,
"eval_loss": 1.388383150100708,
"eval_runtime": 389.6407,
"eval_samples_per_second": 475.245,
"eval_steps_per_second": 3.714,
"step": 50000
},
{
"epoch": 14.02,
"learning_rate": 8.866666666666668e-05,
"loss": 1.4407,
"step": 50500
},
{
"epoch": 14.15,
"learning_rate": 8.844444444444445e-05,
"loss": 1.4361,
"step": 51000
},
{
"epoch": 14.29,
"learning_rate": 8.822222222222223e-05,
"loss": 1.435,
"step": 51500
},
{
"epoch": 14.43,
"learning_rate": 8.800000000000001e-05,
"loss": 1.4321,
"step": 52000
},
{
"epoch": 14.57,
"learning_rate": 8.777777777777778e-05,
"loss": 1.4341,
"step": 52500
},
{
"epoch": 14.71,
"learning_rate": 8.755555555555556e-05,
"loss": 1.432,
"step": 53000
},
{
"epoch": 14.85,
"learning_rate": 8.733333333333333e-05,
"loss": 1.4303,
"step": 53500
},
{
"epoch": 14.99,
"learning_rate": 8.711111111111112e-05,
"loss": 1.4267,
"step": 54000
},
{
"epoch": 15.13,
"learning_rate": 8.68888888888889e-05,
"loss": 1.4254,
"step": 54500
},
{
"epoch": 15.27,
"learning_rate": 8.666666666666667e-05,
"loss": 1.4246,
"step": 55000
},
{
"epoch": 15.4,
"learning_rate": 8.644444444444445e-05,
"loss": 1.4249,
"step": 55500
},
{
"epoch": 15.54,
"learning_rate": 8.622222222222222e-05,
"loss": 1.4246,
"step": 56000
},
{
"epoch": 15.68,
"learning_rate": 8.6e-05,
"loss": 1.4218,
"step": 56500
},
{
"epoch": 15.82,
"learning_rate": 8.577777777777777e-05,
"loss": 1.4183,
"step": 57000
},
{
"epoch": 15.96,
"learning_rate": 8.555555555555556e-05,
"loss": 1.4215,
"step": 57500
},
{
"epoch": 16.1,
"learning_rate": 8.533333333333334e-05,
"loss": 1.4148,
"step": 58000
},
{
"epoch": 16.24,
"learning_rate": 8.511111111111112e-05,
"loss": 1.4134,
"step": 58500
},
{
"epoch": 16.38,
"learning_rate": 8.488888888888889e-05,
"loss": 1.4138,
"step": 59000
},
{
"epoch": 16.51,
"learning_rate": 8.466666666666667e-05,
"loss": 1.414,
"step": 59500
},
{
"epoch": 16.65,
"learning_rate": 8.444444444444444e-05,
"loss": 1.4126,
"step": 60000
},
{
"epoch": 16.79,
"learning_rate": 8.422222222222223e-05,
"loss": 1.4101,
"step": 60500
},
{
"epoch": 16.93,
"learning_rate": 8.4e-05,
"loss": 1.4109,
"step": 61000
},
{
"epoch": 17.07,
"learning_rate": 8.377777777777778e-05,
"loss": 1.4063,
"step": 61500
},
{
"epoch": 17.21,
"learning_rate": 8.355555555555556e-05,
"loss": 1.4065,
"step": 62000
},
{
"epoch": 17.35,
"learning_rate": 8.333333333333334e-05,
"loss": 1.4048,
"step": 62500
},
{
"epoch": 17.35,
"eval_loss": 1.3567780256271362,
"eval_runtime": 389.8272,
"eval_samples_per_second": 475.018,
"eval_steps_per_second": 3.712,
"step": 62500
},
{
"epoch": 17.49,
"learning_rate": 8.311111111111111e-05,
"loss": 1.404,
"step": 63000
},
{
"epoch": 17.62,
"learning_rate": 8.28888888888889e-05,
"loss": 1.4021,
"step": 63500
},
{
"epoch": 17.76,
"learning_rate": 8.266666666666667e-05,
"loss": 1.4007,
"step": 64000
},
{
"epoch": 17.9,
"learning_rate": 8.244444444444445e-05,
"loss": 1.4021,
"step": 64500
},
{
"epoch": 18.04,
"learning_rate": 8.222222222222222e-05,
"loss": 1.4005,
"step": 65000
},
{
"epoch": 18.18,
"learning_rate": 8.2e-05,
"loss": 1.3965,
"step": 65500
},
{
"epoch": 18.32,
"learning_rate": 8.177777777777778e-05,
"loss": 1.3971,
"step": 66000
},
{
"epoch": 18.46,
"learning_rate": 8.155555555555557e-05,
"loss": 1.3976,
"step": 66500
},
{
"epoch": 18.6,
"learning_rate": 8.133333333333334e-05,
"loss": 1.3968,
"step": 67000
},
{
"epoch": 18.73,
"learning_rate": 8.111111111111112e-05,
"loss": 1.395,
"step": 67500
},
{
"epoch": 18.87,
"learning_rate": 8.088888888888889e-05,
"loss": 1.3936,
"step": 68000
},
{
"epoch": 19.01,
"learning_rate": 8.066666666666667e-05,
"loss": 1.3941,
"step": 68500
},
{
"epoch": 19.15,
"learning_rate": 8.044444444444444e-05,
"loss": 1.3874,
"step": 69000
},
{
"epoch": 19.29,
"learning_rate": 8.022222222222222e-05,
"loss": 1.3901,
"step": 69500
},
{
"epoch": 19.43,
"learning_rate": 8e-05,
"loss": 1.3888,
"step": 70000
},
{
"epoch": 19.57,
"learning_rate": 7.977777777777779e-05,
"loss": 1.3905,
"step": 70500
},
{
"epoch": 19.71,
"learning_rate": 7.955555555555556e-05,
"loss": 1.3899,
"step": 71000
},
{
"epoch": 19.84,
"learning_rate": 7.933333333333334e-05,
"loss": 1.3872,
"step": 71500
},
{
"epoch": 19.98,
"learning_rate": 7.911111111111111e-05,
"loss": 1.3857,
"step": 72000
},
{
"epoch": 20.12,
"learning_rate": 7.88888888888889e-05,
"loss": 1.3831,
"step": 72500
},
{
"epoch": 20.26,
"learning_rate": 7.866666666666666e-05,
"loss": 1.3827,
"step": 73000
},
{
"epoch": 20.4,
"learning_rate": 7.844444444444446e-05,
"loss": 1.3824,
"step": 73500
},
{
"epoch": 20.54,
"learning_rate": 7.822222222222223e-05,
"loss": 1.3832,
"step": 74000
},
{
"epoch": 20.68,
"learning_rate": 7.800000000000001e-05,
"loss": 1.3837,
"step": 74500
},
{
"epoch": 20.82,
"learning_rate": 7.777777777777778e-05,
"loss": 1.3789,
"step": 75000
},
{
"epoch": 20.82,
"eval_loss": 1.3401681184768677,
"eval_runtime": 389.9204,
"eval_samples_per_second": 474.905,
"eval_steps_per_second": 3.711,
"step": 75000
},
{
"epoch": 20.95,
"learning_rate": 7.755555555555556e-05,
"loss": 1.3813,
"step": 75500
},
{
"epoch": 21.09,
"learning_rate": 7.733333333333333e-05,
"loss": 1.3808,
"step": 76000
},
{
"epoch": 21.23,
"learning_rate": 7.711111111111112e-05,
"loss": 1.3783,
"step": 76500
},
{
"epoch": 21.37,
"learning_rate": 7.688888888888889e-05,
"loss": 1.3778,
"step": 77000
},
{
"epoch": 21.51,
"learning_rate": 7.666666666666667e-05,
"loss": 1.3785,
"step": 77500
},
{
"epoch": 21.65,
"learning_rate": 7.644444444444445e-05,
"loss": 1.3773,
"step": 78000
},
{
"epoch": 21.79,
"learning_rate": 7.622222222222223e-05,
"loss": 1.3774,
"step": 78500
},
{
"epoch": 21.93,
"learning_rate": 7.6e-05,
"loss": 1.3774,
"step": 79000
},
{
"epoch": 22.06,
"learning_rate": 7.577777777777779e-05,
"loss": 1.3757,
"step": 79500
},
{
"epoch": 22.2,
"learning_rate": 7.555555555555556e-05,
"loss": 1.3721,
"step": 80000
},
{
"epoch": 22.34,
"learning_rate": 7.533333333333334e-05,
"loss": 1.371,
"step": 80500
},
{
"epoch": 22.48,
"learning_rate": 7.511111111111111e-05,
"loss": 1.3718,
"step": 81000
},
{
"epoch": 22.62,
"learning_rate": 7.488888888888889e-05,
"loss": 1.3706,
"step": 81500
},
{
"epoch": 22.76,
"learning_rate": 7.466666666666667e-05,
"loss": 1.3726,
"step": 82000
},
{
"epoch": 22.9,
"learning_rate": 7.444444444444444e-05,
"loss": 1.3759,
"step": 82500
},
{
"epoch": 23.04,
"learning_rate": 7.422222222222223e-05,
"loss": 1.3727,
"step": 83000
},
{
"epoch": 23.18,
"learning_rate": 7.4e-05,
"loss": 1.3689,
"step": 83500
},
{
"epoch": 23.31,
"learning_rate": 7.377777777777778e-05,
"loss": 1.3677,
"step": 84000
},
{
"epoch": 23.45,
"learning_rate": 7.355555555555556e-05,
"loss": 1.3688,
"step": 84500
},
{
"epoch": 23.59,
"learning_rate": 7.333333333333333e-05,
"loss": 1.3663,
"step": 85000
},
{
"epoch": 23.73,
"learning_rate": 7.311111111111111e-05,
"loss": 1.3662,
"step": 85500
},
{
"epoch": 23.87,
"learning_rate": 7.28888888888889e-05,
"loss": 1.3647,
"step": 86000
},
{
"epoch": 24.01,
"learning_rate": 7.266666666666667e-05,
"loss": 1.3661,
"step": 86500
},
{
"epoch": 24.15,
"learning_rate": 7.244444444444445e-05,
"loss": 1.3619,
"step": 87000
},
{
"epoch": 24.29,
"learning_rate": 7.222222222222222e-05,
"loss": 1.363,
"step": 87500
},
{
"epoch": 24.29,
"eval_loss": 1.3217395544052124,
"eval_runtime": 389.4524,
"eval_samples_per_second": 475.475,
"eval_steps_per_second": 3.715,
"step": 87500
},
{
"epoch": 24.42,
"learning_rate": 7.2e-05,
"loss": 1.362,
"step": 88000
},
{
"epoch": 24.56,
"learning_rate": 7.177777777777777e-05,
"loss": 1.3594,
"step": 88500
},
{
"epoch": 24.7,
"learning_rate": 7.155555555555555e-05,
"loss": 1.3598,
"step": 89000
},
{
"epoch": 24.84,
"learning_rate": 7.133333333333334e-05,
"loss": 1.3605,
"step": 89500
},
{
"epoch": 24.98,
"learning_rate": 7.111111111111112e-05,
"loss": 1.3589,
"step": 90000
},
{
"epoch": 25.12,
"learning_rate": 7.088888888888889e-05,
"loss": 1.3574,
"step": 90500
},
{
"epoch": 25.26,
"learning_rate": 7.066666666666667e-05,
"loss": 1.3562,
"step": 91000
},
{
"epoch": 25.4,
"learning_rate": 7.044444444444444e-05,
"loss": 1.3569,
"step": 91500
},
{
"epoch": 25.53,
"learning_rate": 7.022222222222222e-05,
"loss": 1.3568,
"step": 92000
},
{
"epoch": 25.67,
"learning_rate": 7e-05,
"loss": 1.3556,
"step": 92500
},
{
"epoch": 25.81,
"learning_rate": 6.977777777777779e-05,
"loss": 1.3581,
"step": 93000
},
{
"epoch": 25.95,
"learning_rate": 6.955555555555556e-05,
"loss": 1.3583,
"step": 93500
},
{
"epoch": 26.09,
"learning_rate": 6.933333333333334e-05,
"loss": 1.3546,
"step": 94000
},
{
"epoch": 26.23,
"learning_rate": 6.911111111111111e-05,
"loss": 1.3535,
"step": 94500
},
{
"epoch": 26.37,
"learning_rate": 6.88888888888889e-05,
"loss": 1.3526,
"step": 95000
},
{
"epoch": 26.51,
"learning_rate": 6.866666666666666e-05,
"loss": 1.3531,
"step": 95500
},
{
"epoch": 26.64,
"learning_rate": 6.844444444444445e-05,
"loss": 1.351,
"step": 96000
},
{
"epoch": 26.78,
"learning_rate": 6.822222222222222e-05,
"loss": 1.3525,
"step": 96500
},
{
"epoch": 26.92,
"learning_rate": 6.800000000000001e-05,
"loss": 1.3529,
"step": 97000
},
{
"epoch": 27.06,
"learning_rate": 6.777777777777778e-05,
"loss": 1.3519,
"step": 97500
},
{
"epoch": 27.2,
"learning_rate": 6.755555555555557e-05,
"loss": 1.3482,
"step": 98000
},
{
"epoch": 27.34,
"learning_rate": 6.733333333333333e-05,
"loss": 1.349,
"step": 98500
},
{
"epoch": 27.48,
"learning_rate": 6.711111111111112e-05,
"loss": 1.3478,
"step": 99000
},
{
"epoch": 27.62,
"learning_rate": 6.688888888888889e-05,
"loss": 1.3488,
"step": 99500
},
{
"epoch": 27.75,
"learning_rate": 6.666666666666667e-05,
"loss": 1.3481,
"step": 100000
},
{
"epoch": 27.75,
"eval_loss": 1.3101322650909424,
"eval_runtime": 389.668,
"eval_samples_per_second": 475.212,
"eval_steps_per_second": 3.713,
"step": 100000
},
{
"epoch": 27.89,
"learning_rate": 6.644444444444444e-05,
"loss": 1.347,
"step": 100500
},
{
"epoch": 28.03,
"learning_rate": 6.622222222222224e-05,
"loss": 1.3488,
"step": 101000
},
{
"epoch": 28.17,
"learning_rate": 6.6e-05,
"loss": 1.3447,
"step": 101500
},
{
"epoch": 28.31,
"learning_rate": 6.577777777777779e-05,
"loss": 1.3465,
"step": 102000
},
{
"epoch": 28.45,
"learning_rate": 6.555555555555556e-05,
"loss": 1.3428,
"step": 102500
},
{
"epoch": 28.59,
"learning_rate": 6.533333333333334e-05,
"loss": 1.3442,
"step": 103000
},
{
"epoch": 28.73,
"learning_rate": 6.511111111111111e-05,
"loss": 1.3478,
"step": 103500
},
{
"epoch": 28.86,
"learning_rate": 6.488888888888889e-05,
"loss": 1.3437,
"step": 104000
},
{
"epoch": 29.0,
"learning_rate": 6.466666666666666e-05,
"loss": 1.346,
"step": 104500
},
{
"epoch": 29.14,
"learning_rate": 6.444444444444446e-05,
"loss": 1.3398,
"step": 105000
},
{
"epoch": 29.28,
"learning_rate": 6.422222222222223e-05,
"loss": 1.3419,
"step": 105500
},
{
"epoch": 29.42,
"learning_rate": 6.400000000000001e-05,
"loss": 1.3422,
"step": 106000
},
{
"epoch": 29.56,
"learning_rate": 6.377777777777778e-05,
"loss": 1.3419,
"step": 106500
},
{
"epoch": 29.7,
"learning_rate": 6.355555555555556e-05,
"loss": 1.3432,
"step": 107000
},
{
"epoch": 29.84,
"learning_rate": 6.333333333333333e-05,
"loss": 1.3386,
"step": 107500
},
{
"epoch": 29.97,
"learning_rate": 6.311111111111112e-05,
"loss": 1.3415,
"step": 108000
},
{
"epoch": 30.11,
"learning_rate": 6.28888888888889e-05,
"loss": 1.3408,
"step": 108500
},
{
"epoch": 30.25,
"learning_rate": 6.266666666666667e-05,
"loss": 1.3376,
"step": 109000
},
{
"epoch": 30.39,
"learning_rate": 6.244444444444445e-05,
"loss": 1.3383,
"step": 109500
},
{
"epoch": 30.53,
"learning_rate": 6.222222222222222e-05,
"loss": 1.3389,
"step": 110000
},
{
"epoch": 30.67,
"learning_rate": 6.2e-05,
"loss": 1.3393,
"step": 110500
},
{
"epoch": 30.81,
"learning_rate": 6.177777777777779e-05,
"loss": 1.3379,
"step": 111000
},
{
"epoch": 30.95,
"learning_rate": 6.155555555555555e-05,
"loss": 1.3352,
"step": 111500
},
{
"epoch": 31.09,
"learning_rate": 6.133333333333334e-05,
"loss": 1.3364,
"step": 112000
},
{
"epoch": 31.22,
"learning_rate": 6.111111111111112e-05,
"loss": 1.3361,
"step": 112500
},
{
"epoch": 31.22,
"eval_loss": 1.2985332012176514,
"eval_runtime": 389.5056,
"eval_samples_per_second": 475.41,
"eval_steps_per_second": 3.715,
"step": 112500
},
{
"epoch": 31.36,
"learning_rate": 6.08888888888889e-05,
"loss": 1.3346,
"step": 113000
},
{
"epoch": 31.5,
"learning_rate": 6.066666666666667e-05,
"loss": 1.334,
"step": 113500
},
{
"epoch": 31.64,
"learning_rate": 6.044444444444445e-05,
"loss": 1.3318,
"step": 114000
},
{
"epoch": 31.78,
"learning_rate": 6.0222222222222225e-05,
"loss": 1.3338,
"step": 114500
},
{
"epoch": 31.92,
"learning_rate": 6e-05,
"loss": 1.3335,
"step": 115000
},
{
"epoch": 32.06,
"learning_rate": 5.977777777777778e-05,
"loss": 1.3335,
"step": 115500
},
{
"epoch": 32.2,
"learning_rate": 5.9555555555555554e-05,
"loss": 1.3305,
"step": 116000
},
{
"epoch": 32.33,
"learning_rate": 5.9333333333333343e-05,
"loss": 1.3643,
"step": 116500
},
{
"epoch": 32.47,
"learning_rate": 5.911111111111112e-05,
"loss": 1.411,
"step": 117000
},
{
"epoch": 32.61,
"learning_rate": 5.8888888888888896e-05,
"loss": 1.3549,
"step": 117500
},
{
"epoch": 32.75,
"learning_rate": 5.866666666666667e-05,
"loss": 1.3419,
"step": 118000
},
{
"epoch": 32.89,
"learning_rate": 5.844444444444445e-05,
"loss": 1.3362,
"step": 118500
},
{
"epoch": 33.03,
"learning_rate": 5.8222222222222224e-05,
"loss": 1.3355,
"step": 119000
},
{
"epoch": 33.17,
"learning_rate": 5.8e-05,
"loss": 1.3308,
"step": 119500
},
{
"epoch": 33.31,
"learning_rate": 5.7777777777777776e-05,
"loss": 1.33,
"step": 120000
},
{
"epoch": 33.44,
"learning_rate": 5.755555555555556e-05,
"loss": 1.3318,
"step": 120500
},
{
"epoch": 33.58,
"learning_rate": 5.7333333333333336e-05,
"loss": 1.3311,
"step": 121000
},
{
"epoch": 33.72,
"learning_rate": 5.711111111111112e-05,
"loss": 1.3266,
"step": 121500
},
{
"epoch": 33.86,
"learning_rate": 5.6888888888888895e-05,
"loss": 1.3258,
"step": 122000
},
{
"epoch": 34.0,
"learning_rate": 5.666666666666667e-05,
"loss": 1.3266,
"step": 122500
},
{
"epoch": 34.14,
"learning_rate": 5.644444444444445e-05,
"loss": 1.3279,
"step": 123000
},
{
"epoch": 34.28,
"learning_rate": 5.622222222222222e-05,
"loss": 1.3238,
"step": 123500
},
{
"epoch": 34.42,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.3252,
"step": 124000
},
{
"epoch": 34.55,
"learning_rate": 5.577777777777778e-05,
"loss": 1.3222,
"step": 124500
},
{
"epoch": 34.69,
"learning_rate": 5.555555555555556e-05,
"loss": 1.3239,
"step": 125000
},
{
"epoch": 34.69,
"eval_loss": 1.2895334959030151,
"eval_runtime": 389.8228,
"eval_samples_per_second": 475.023,
"eval_steps_per_second": 3.712,
"step": 125000
},
{
"epoch": 34.83,
"learning_rate": 5.5333333333333334e-05,
"loss": 1.3251,
"step": 125500
},
{
"epoch": 34.97,
"learning_rate": 5.511111111111111e-05,
"loss": 1.3228,
"step": 126000
},
{
"epoch": 35.11,
"learning_rate": 5.488888888888889e-05,
"loss": 1.3226,
"step": 126500
},
{
"epoch": 35.25,
"learning_rate": 5.466666666666666e-05,
"loss": 1.3197,
"step": 127000
},
{
"epoch": 35.39,
"learning_rate": 5.4444444444444446e-05,
"loss": 1.3211,
"step": 127500
},
{
"epoch": 35.53,
"learning_rate": 5.422222222222223e-05,
"loss": 1.3199,
"step": 128000
},
{
"epoch": 35.66,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.3192,
"step": 128500
},
{
"epoch": 35.8,
"learning_rate": 5.377777777777778e-05,
"loss": 1.3211,
"step": 129000
},
{
"epoch": 35.94,
"learning_rate": 5.355555555555556e-05,
"loss": 1.3209,
"step": 129500
},
{
"epoch": 36.08,
"learning_rate": 5.333333333333333e-05,
"loss": 1.3198,
"step": 130000
},
{
"epoch": 36.22,
"learning_rate": 5.311111111111111e-05,
"loss": 1.3151,
"step": 130500
},
{
"epoch": 36.36,
"learning_rate": 5.2888888888888885e-05,
"loss": 1.3166,
"step": 131000
},
{
"epoch": 36.5,
"learning_rate": 5.266666666666666e-05,
"loss": 1.315,
"step": 131500
},
{
"epoch": 36.64,
"learning_rate": 5.244444444444445e-05,
"loss": 1.318,
"step": 132000
},
{
"epoch": 36.77,
"learning_rate": 5.222222222222223e-05,
"loss": 1.3169,
"step": 132500
},
{
"epoch": 36.91,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.3195,
"step": 133000
},
{
"epoch": 37.05,
"learning_rate": 5.177777777777778e-05,
"loss": 1.3146,
"step": 133500
},
{
"epoch": 37.19,
"learning_rate": 5.1555555555555556e-05,
"loss": 1.3143,
"step": 134000
},
{
"epoch": 37.33,
"learning_rate": 5.133333333333333e-05,
"loss": 1.3128,
"step": 134500
},
{
"epoch": 37.47,
"learning_rate": 5.111111111111111e-05,
"loss": 1.3145,
"step": 135000
},
{
"epoch": 37.61,
"learning_rate": 5.0888888888888884e-05,
"loss": 1.3125,
"step": 135500
},
{
"epoch": 37.75,
"learning_rate": 5.0666666666666674e-05,
"loss": 1.3133,
"step": 136000
},
{
"epoch": 37.89,
"learning_rate": 5.044444444444445e-05,
"loss": 1.3138,
"step": 136500
},
{
"epoch": 38.02,
"learning_rate": 5.0222222222222226e-05,
"loss": 1.3132,
"step": 137000
},
{
"epoch": 38.16,
"learning_rate": 5e-05,
"loss": 1.311,
"step": 137500
},
{
"epoch": 38.16,
"eval_loss": 1.2769075632095337,
"eval_runtime": 389.676,
"eval_samples_per_second": 475.202,
"eval_steps_per_second": 3.713,
"step": 137500
},
{
"epoch": 38.3,
"learning_rate": 4.977777777777778e-05,
"loss": 1.3099,
"step": 138000
},
{
"epoch": 38.44,
"learning_rate": 4.955555555555556e-05,
"loss": 1.3104,
"step": 138500
},
{
"epoch": 38.58,
"learning_rate": 4.933333333333334e-05,
"loss": 1.3105,
"step": 139000
},
{
"epoch": 38.72,
"learning_rate": 4.9111111111111114e-05,
"loss": 1.3094,
"step": 139500
},
{
"epoch": 38.86,
"learning_rate": 4.888888888888889e-05,
"loss": 1.3105,
"step": 140000
},
{
"epoch": 39.0,
"learning_rate": 4.866666666666667e-05,
"loss": 1.312,
"step": 140500
},
{
"epoch": 39.13,
"learning_rate": 4.844444444444445e-05,
"loss": 1.307,
"step": 141000
},
{
"epoch": 39.27,
"learning_rate": 4.8222222222222225e-05,
"loss": 1.3071,
"step": 141500
},
{
"epoch": 39.41,
"learning_rate": 4.8e-05,
"loss": 1.3073,
"step": 142000
},
{
"epoch": 39.55,
"learning_rate": 4.7777777777777784e-05,
"loss": 1.309,
"step": 142500
},
{
"epoch": 39.69,
"learning_rate": 4.755555555555556e-05,
"loss": 1.3068,
"step": 143000
},
{
"epoch": 39.83,
"learning_rate": 4.7333333333333336e-05,
"loss": 1.3094,
"step": 143500
},
{
"epoch": 39.97,
"learning_rate": 4.711111111111111e-05,
"loss": 1.3096,
"step": 144000
},
{
"epoch": 40.11,
"learning_rate": 4.6888888888888895e-05,
"loss": 1.3067,
"step": 144500
},
{
"epoch": 40.24,
"learning_rate": 4.666666666666667e-05,
"loss": 1.3065,
"step": 145000
},
{
"epoch": 40.38,
"learning_rate": 4.644444444444445e-05,
"loss": 1.3088,
"step": 145500
},
{
"epoch": 40.52,
"learning_rate": 4.6222222222222224e-05,
"loss": 1.3087,
"step": 146000
},
{
"epoch": 40.66,
"learning_rate": 4.600000000000001e-05,
"loss": 1.3036,
"step": 146500
},
{
"epoch": 40.8,
"learning_rate": 4.577777777777778e-05,
"loss": 1.3062,
"step": 147000
},
{
"epoch": 40.94,
"learning_rate": 4.555555555555556e-05,
"loss": 1.3038,
"step": 147500
},
{
"epoch": 41.08,
"learning_rate": 4.5333333333333335e-05,
"loss": 1.3024,
"step": 148000
},
{
"epoch": 41.22,
"learning_rate": 4.511111111111112e-05,
"loss": 1.3034,
"step": 148500
},
{
"epoch": 41.35,
"learning_rate": 4.4888888888888894e-05,
"loss": 1.3009,
"step": 149000
},
{
"epoch": 41.49,
"learning_rate": 4.466666666666667e-05,
"loss": 1.3055,
"step": 149500
},
{
"epoch": 41.63,
"learning_rate": 4.4444444444444447e-05,
"loss": 1.3053,
"step": 150000
},
{
"epoch": 41.63,
"eval_loss": 1.2693954706192017,
"eval_runtime": 389.9924,
"eval_samples_per_second": 474.817,
"eval_steps_per_second": 3.71,
"step": 150000
},
{
"epoch": 41.77,
"learning_rate": 4.422222222222222e-05,
"loss": 1.3025,
"step": 150500
},
{
"epoch": 41.91,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.3022,
"step": 151000
},
{
"epoch": 42.05,
"learning_rate": 4.377777777777778e-05,
"loss": 1.301,
"step": 151500
},
{
"epoch": 42.19,
"learning_rate": 4.355555555555556e-05,
"loss": 1.3016,
"step": 152000
},
{
"epoch": 42.33,
"learning_rate": 4.3333333333333334e-05,
"loss": 1.3006,
"step": 152500
},
{
"epoch": 42.46,
"learning_rate": 4.311111111111111e-05,
"loss": 1.3004,
"step": 153000
},
{
"epoch": 42.6,
"learning_rate": 4.2888888888888886e-05,
"loss": 1.3038,
"step": 153500
},
{
"epoch": 42.74,
"learning_rate": 4.266666666666667e-05,
"loss": 1.3015,
"step": 154000
},
{
"epoch": 42.88,
"learning_rate": 4.2444444444444445e-05,
"loss": 1.3019,
"step": 154500
},
{
"epoch": 43.02,
"learning_rate": 4.222222222222222e-05,
"loss": 1.2987,
"step": 155000
},
{
"epoch": 43.16,
"learning_rate": 4.2e-05,
"loss": 1.2987,
"step": 155500
},
{
"epoch": 43.3,
"learning_rate": 4.177777777777778e-05,
"loss": 1.2986,
"step": 156000
},
{
"epoch": 43.44,
"learning_rate": 4.155555555555556e-05,
"loss": 1.2987,
"step": 156500
},
{
"epoch": 43.57,
"learning_rate": 4.133333333333333e-05,
"loss": 1.2983,
"step": 157000
},
{
"epoch": 43.71,
"learning_rate": 4.111111111111111e-05,
"loss": 1.2973,
"step": 157500
},
{
"epoch": 43.85,
"learning_rate": 4.088888888888889e-05,
"loss": 1.2981,
"step": 158000
},
{
"epoch": 43.99,
"learning_rate": 4.066666666666667e-05,
"loss": 1.299,
"step": 158500
},
{
"epoch": 44.13,
"learning_rate": 4.0444444444444444e-05,
"loss": 1.2954,
"step": 159000
},
{
"epoch": 44.27,
"learning_rate": 4.022222222222222e-05,
"loss": 1.2956,
"step": 159500
},
{
"epoch": 44.41,
"learning_rate": 4e-05,
"loss": 1.297,
"step": 160000
},
{
"epoch": 44.55,
"learning_rate": 3.977777777777778e-05,
"loss": 1.296,
"step": 160500
},
{
"epoch": 44.68,
"learning_rate": 3.9555555555555556e-05,
"loss": 1.2948,
"step": 161000
},
{
"epoch": 44.82,
"learning_rate": 3.933333333333333e-05,
"loss": 1.2971,
"step": 161500
},
{
"epoch": 44.96,
"learning_rate": 3.9111111111111115e-05,
"loss": 1.2961,
"step": 162000
},
{
"epoch": 45.1,
"learning_rate": 3.888888888888889e-05,
"loss": 1.2938,
"step": 162500
},
{
"epoch": 45.1,
"eval_loss": 1.2620575428009033,
"eval_runtime": 389.8387,
"eval_samples_per_second": 475.004,
"eval_steps_per_second": 3.712,
"step": 162500
},
{
"epoch": 45.24,
"learning_rate": 3.866666666666667e-05,
"loss": 1.2942,
"step": 163000
},
{
"epoch": 45.38,
"learning_rate": 3.844444444444444e-05,
"loss": 1.2935,
"step": 163500
},
{
"epoch": 45.52,
"learning_rate": 3.8222222222222226e-05,
"loss": 1.2943,
"step": 164000
},
{
"epoch": 45.66,
"learning_rate": 3.8e-05,
"loss": 1.2943,
"step": 164500
},
{
"epoch": 45.8,
"learning_rate": 3.777777777777778e-05,
"loss": 1.295,
"step": 165000
},
{
"epoch": 45.93,
"learning_rate": 3.7555555555555554e-05,
"loss": 1.2935,
"step": 165500
},
{
"epoch": 46.07,
"learning_rate": 3.733333333333334e-05,
"loss": 1.2928,
"step": 166000
},
{
"epoch": 46.21,
"learning_rate": 3.7111111111111113e-05,
"loss": 1.2914,
"step": 166500
},
{
"epoch": 46.35,
"learning_rate": 3.688888888888889e-05,
"loss": 1.2915,
"step": 167000
},
{
"epoch": 46.49,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.2893,
"step": 167500
},
{
"epoch": 46.63,
"learning_rate": 3.644444444444445e-05,
"loss": 1.2918,
"step": 168000
},
{
"epoch": 46.77,
"learning_rate": 3.6222222222222225e-05,
"loss": 1.2902,
"step": 168500
},
{
"epoch": 46.91,
"learning_rate": 3.6e-05,
"loss": 1.2912,
"step": 169000
},
{
"epoch": 47.04,
"learning_rate": 3.577777777777778e-05,
"loss": 1.2905,
"step": 169500
},
{
"epoch": 47.18,
"learning_rate": 3.555555555555556e-05,
"loss": 1.2895,
"step": 170000
},
{
"epoch": 47.32,
"learning_rate": 3.5333333333333336e-05,
"loss": 1.2896,
"step": 170500
},
{
"epoch": 47.46,
"learning_rate": 3.511111111111111e-05,
"loss": 1.2887,
"step": 171000
},
{
"epoch": 47.6,
"learning_rate": 3.4888888888888895e-05,
"loss": 1.2902,
"step": 171500
},
{
"epoch": 47.74,
"learning_rate": 3.466666666666667e-05,
"loss": 1.2887,
"step": 172000
},
{
"epoch": 47.88,
"learning_rate": 3.444444444444445e-05,
"loss": 1.2896,
"step": 172500
},
{
"epoch": 48.02,
"learning_rate": 3.4222222222222224e-05,
"loss": 1.2886,
"step": 173000
},
{
"epoch": 48.15,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.288,
"step": 173500
},
{
"epoch": 48.29,
"learning_rate": 3.377777777777778e-05,
"loss": 1.2859,
"step": 174000
},
{
"epoch": 48.43,
"learning_rate": 3.355555555555556e-05,
"loss": 1.2868,
"step": 174500
},
{
"epoch": 48.57,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.2881,
"step": 175000
},
{
"epoch": 48.57,
"eval_loss": 1.256798505783081,
"eval_runtime": 389.7693,
"eval_samples_per_second": 475.089,
"eval_steps_per_second": 3.712,
"step": 175000
},
{
"epoch": 48.71,
"learning_rate": 3.311111111111112e-05,
"loss": 1.2844,
"step": 175500
},
{
"epoch": 48.85,
"learning_rate": 3.2888888888888894e-05,
"loss": 1.2895,
"step": 176000
},
{
"epoch": 48.99,
"learning_rate": 3.266666666666667e-05,
"loss": 1.2865,
"step": 176500
},
{
"epoch": 49.13,
"learning_rate": 3.2444444444444446e-05,
"loss": 1.2867,
"step": 177000
},
{
"epoch": 49.26,
"learning_rate": 3.222222222222223e-05,
"loss": 1.2841,
"step": 177500
},
{
"epoch": 49.4,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.2861,
"step": 178000
},
{
"epoch": 49.54,
"learning_rate": 3.177777777777778e-05,
"loss": 1.2844,
"step": 178500
},
{
"epoch": 49.68,
"learning_rate": 3.155555555555556e-05,
"loss": 1.285,
"step": 179000
},
{
"epoch": 49.82,
"learning_rate": 3.1333333333333334e-05,
"loss": 1.2813,
"step": 179500
},
{
"epoch": 49.96,
"learning_rate": 3.111111111111111e-05,
"loss": 1.2845,
"step": 180000
},
{
"epoch": 50.1,
"learning_rate": 3.088888888888889e-05,
"loss": 1.2847,
"step": 180500
},
{
"epoch": 50.24,
"learning_rate": 3.066666666666667e-05,
"loss": 1.2833,
"step": 181000
},
{
"epoch": 50.37,
"learning_rate": 3.044444444444445e-05,
"loss": 1.2814,
"step": 181500
},
{
"epoch": 50.51,
"learning_rate": 3.0222222222222225e-05,
"loss": 1.2822,
"step": 182000
},
{
"epoch": 50.65,
"learning_rate": 3e-05,
"loss": 1.2817,
"step": 182500
},
{
"epoch": 50.79,
"learning_rate": 2.9777777777777777e-05,
"loss": 1.2839,
"step": 183000
},
{
"epoch": 50.93,
"learning_rate": 2.955555555555556e-05,
"loss": 1.2827,
"step": 183500
},
{
"epoch": 51.07,
"learning_rate": 2.9333333333333336e-05,
"loss": 1.2821,
"step": 184000
},
{
"epoch": 51.21,
"learning_rate": 2.9111111111111112e-05,
"loss": 1.2804,
"step": 184500
},
{
"epoch": 51.35,
"learning_rate": 2.8888888888888888e-05,
"loss": 1.2796,
"step": 185000
},
{
"epoch": 51.48,
"learning_rate": 2.8666666666666668e-05,
"loss": 1.2791,
"step": 185500
},
{
"epoch": 51.62,
"learning_rate": 2.8444444444444447e-05,
"loss": 1.2813,
"step": 186000
},
{
"epoch": 51.76,
"learning_rate": 2.8222222222222223e-05,
"loss": 1.2825,
"step": 186500
},
{
"epoch": 51.9,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.2804,
"step": 187000
},
{
"epoch": 52.04,
"learning_rate": 2.777777777777778e-05,
"loss": 1.2805,
"step": 187500
},
{
"epoch": 52.04,
"eval_loss": 1.2479686737060547,
"eval_runtime": 389.4325,
"eval_samples_per_second": 475.5,
"eval_steps_per_second": 3.716,
"step": 187500
},
{
"epoch": 52.18,
"learning_rate": 2.7555555555555555e-05,
"loss": 1.2787,
"step": 188000
},
{
"epoch": 52.32,
"learning_rate": 2.733333333333333e-05,
"loss": 1.279,
"step": 188500
},
{
"epoch": 52.46,
"learning_rate": 2.7111111111111114e-05,
"loss": 1.2779,
"step": 189000
},
{
"epoch": 52.6,
"learning_rate": 2.688888888888889e-05,
"loss": 1.2805,
"step": 189500
},
{
"epoch": 52.73,
"learning_rate": 2.6666666666666667e-05,
"loss": 1.2775,
"step": 190000
},
{
"epoch": 52.87,
"learning_rate": 2.6444444444444443e-05,
"loss": 1.2778,
"step": 190500
},
{
"epoch": 53.01,
"learning_rate": 2.6222222222222226e-05,
"loss": 1.2809,
"step": 191000
},
{
"epoch": 53.15,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.2754,
"step": 191500
},
{
"epoch": 53.29,
"learning_rate": 2.5777777777777778e-05,
"loss": 1.2774,
"step": 192000
},
{
"epoch": 53.43,
"learning_rate": 2.5555555555555554e-05,
"loss": 1.2753,
"step": 192500
},
{
"epoch": 53.57,
"learning_rate": 2.5333333333333337e-05,
"loss": 1.2766,
"step": 193000
},
{
"epoch": 53.71,
"learning_rate": 2.5111111111111113e-05,
"loss": 1.2777,
"step": 193500
},
{
"epoch": 53.84,
"learning_rate": 2.488888888888889e-05,
"loss": 1.2758,
"step": 194000
},
{
"epoch": 53.98,
"learning_rate": 2.466666666666667e-05,
"loss": 1.2771,
"step": 194500
},
{
"epoch": 54.12,
"learning_rate": 2.4444444444444445e-05,
"loss": 1.2758,
"step": 195000
},
{
"epoch": 54.26,
"learning_rate": 2.4222222222222224e-05,
"loss": 1.2764,
"step": 195500
},
{
"epoch": 54.4,
"learning_rate": 2.4e-05,
"loss": 1.2743,
"step": 196000
},
{
"epoch": 54.54,
"learning_rate": 2.377777777777778e-05,
"loss": 1.2718,
"step": 196500
},
{
"epoch": 54.68,
"learning_rate": 2.3555555555555556e-05,
"loss": 1.2748,
"step": 197000
},
{
"epoch": 54.82,
"learning_rate": 2.3333333333333336e-05,
"loss": 1.2754,
"step": 197500
},
{
"epoch": 54.95,
"learning_rate": 2.3111111111111112e-05,
"loss": 1.2737,
"step": 198000
},
{
"epoch": 55.09,
"learning_rate": 2.288888888888889e-05,
"loss": 1.2753,
"step": 198500
},
{
"epoch": 55.23,
"learning_rate": 2.2666666666666668e-05,
"loss": 1.2731,
"step": 199000
},
{
"epoch": 55.37,
"learning_rate": 2.2444444444444447e-05,
"loss": 1.2736,
"step": 199500
},
{
"epoch": 55.51,
"learning_rate": 2.2222222222222223e-05,
"loss": 1.2741,
"step": 200000
},
{
"epoch": 55.51,
"eval_loss": 1.2437978982925415,
"eval_runtime": 390.05,
"eval_samples_per_second": 474.747,
"eval_steps_per_second": 3.71,
"step": 200000
},
{
"epoch": 55.65,
"learning_rate": 2.2000000000000003e-05,
"loss": 1.2728,
"step": 200500
},
{
"epoch": 55.79,
"learning_rate": 2.177777777777778e-05,
"loss": 1.2728,
"step": 201000
},
{
"epoch": 55.93,
"learning_rate": 2.1555555555555555e-05,
"loss": 1.2725,
"step": 201500
},
{
"epoch": 56.06,
"learning_rate": 2.1333333333333335e-05,
"loss": 1.2728,
"step": 202000
},
{
"epoch": 56.2,
"learning_rate": 2.111111111111111e-05,
"loss": 1.2701,
"step": 202500
},
{
"epoch": 56.34,
"learning_rate": 2.088888888888889e-05,
"loss": 1.2703,
"step": 203000
},
{
"epoch": 56.48,
"learning_rate": 2.0666666666666666e-05,
"loss": 1.2709,
"step": 203500
},
{
"epoch": 56.62,
"learning_rate": 2.0444444444444446e-05,
"loss": 1.2699,
"step": 204000
},
{
"epoch": 56.76,
"learning_rate": 2.0222222222222222e-05,
"loss": 1.2702,
"step": 204500
},
{
"epoch": 56.9,
"learning_rate": 2e-05,
"loss": 1.273,
"step": 205000
},
{
"epoch": 57.04,
"learning_rate": 1.9777777777777778e-05,
"loss": 1.2715,
"step": 205500
},
{
"epoch": 57.17,
"learning_rate": 1.9555555555555557e-05,
"loss": 1.2683,
"step": 206000
},
{
"epoch": 57.31,
"learning_rate": 1.9333333333333333e-05,
"loss": 1.2681,
"step": 206500
},
{
"epoch": 57.45,
"learning_rate": 1.9111111111111113e-05,
"loss": 1.2697,
"step": 207000
},
{
"epoch": 57.59,
"learning_rate": 1.888888888888889e-05,
"loss": 1.2682,
"step": 207500
},
{
"epoch": 57.73,
"learning_rate": 1.866666666666667e-05,
"loss": 1.2686,
"step": 208000
},
{
"epoch": 57.87,
"learning_rate": 1.8444444444444445e-05,
"loss": 1.2701,
"step": 208500
},
{
"epoch": 58.01,
"learning_rate": 1.8222222222222224e-05,
"loss": 1.2676,
"step": 209000
},
{
"epoch": 58.15,
"learning_rate": 1.8e-05,
"loss": 1.2668,
"step": 209500
},
{
"epoch": 58.28,
"learning_rate": 1.777777777777778e-05,
"loss": 1.2681,
"step": 210000
},
{
"epoch": 58.42,
"learning_rate": 1.7555555555555556e-05,
"loss": 1.2676,
"step": 210500
},
{
"epoch": 58.56,
"learning_rate": 1.7333333333333336e-05,
"loss": 1.2676,
"step": 211000
},
{
"epoch": 58.7,
"learning_rate": 1.7111111111111112e-05,
"loss": 1.2697,
"step": 211500
},
{
"epoch": 58.84,
"learning_rate": 1.688888888888889e-05,
"loss": 1.2666,
"step": 212000
},
{
"epoch": 58.98,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.2664,
"step": 212500
},
{
"epoch": 58.98,
"eval_loss": 1.239187240600586,
"eval_runtime": 389.678,
"eval_samples_per_second": 475.2,
"eval_steps_per_second": 3.713,
"step": 212500
},
{
"epoch": 59.12,
"learning_rate": 1.6444444444444447e-05,
"loss": 1.2661,
"step": 213000
},
{
"epoch": 59.26,
"learning_rate": 1.6222222222222223e-05,
"loss": 1.2643,
"step": 213500
},
{
"epoch": 59.39,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.2661,
"step": 214000
},
{
"epoch": 59.53,
"learning_rate": 1.577777777777778e-05,
"loss": 1.2664,
"step": 214500
},
{
"epoch": 59.67,
"learning_rate": 1.5555555555555555e-05,
"loss": 1.2662,
"step": 215000
},
{
"epoch": 59.81,
"learning_rate": 1.5333333333333334e-05,
"loss": 1.2672,
"step": 215500
},
{
"epoch": 59.95,
"learning_rate": 1.5111111111111112e-05,
"loss": 1.264,
"step": 216000
},
{
"epoch": 60.09,
"learning_rate": 1.4888888888888888e-05,
"loss": 1.2655,
"step": 216500
},
{
"epoch": 60.23,
"learning_rate": 1.4666666666666668e-05,
"loss": 1.2644,
"step": 217000
},
{
"epoch": 60.37,
"learning_rate": 1.4444444444444444e-05,
"loss": 1.2661,
"step": 217500
},
{
"epoch": 60.51,
"learning_rate": 1.4222222222222224e-05,
"loss": 1.2652,
"step": 218000
},
{
"epoch": 60.64,
"learning_rate": 1.4000000000000001e-05,
"loss": 1.2637,
"step": 218500
},
{
"epoch": 60.78,
"learning_rate": 1.3777777777777778e-05,
"loss": 1.2657,
"step": 219000
},
{
"epoch": 60.92,
"learning_rate": 1.3555555555555557e-05,
"loss": 1.2656,
"step": 219500
},
{
"epoch": 61.06,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.2626,
"step": 220000
},
{
"epoch": 61.2,
"learning_rate": 1.3111111111111113e-05,
"loss": 1.2646,
"step": 220500
},
{
"epoch": 61.34,
"learning_rate": 1.2888888888888889e-05,
"loss": 1.2627,
"step": 221000
},
{
"epoch": 61.48,
"learning_rate": 1.2666666666666668e-05,
"loss": 1.2633,
"step": 221500
},
{
"epoch": 61.62,
"learning_rate": 1.2444444444444445e-05,
"loss": 1.2641,
"step": 222000
},
{
"epoch": 61.75,
"learning_rate": 1.2222222222222222e-05,
"loss": 1.2616,
"step": 222500
},
{
"epoch": 61.89,
"learning_rate": 1.2e-05,
"loss": 1.2614,
"step": 223000
},
{
"epoch": 62.03,
"learning_rate": 1.1777777777777778e-05,
"loss": 1.2615,
"step": 223500
},
{
"epoch": 62.17,
"learning_rate": 1.1555555555555556e-05,
"loss": 1.2621,
"step": 224000
},
{
"epoch": 62.31,
"learning_rate": 1.1333333333333334e-05,
"loss": 1.2613,
"step": 224500
},
{
"epoch": 62.45,
"learning_rate": 1.1111111111111112e-05,
"loss": 1.261,
"step": 225000
},
{
"epoch": 62.45,
"eval_loss": 1.2334364652633667,
"eval_runtime": 389.7373,
"eval_samples_per_second": 475.128,
"eval_steps_per_second": 3.713,
"step": 225000
},
{
"epoch": 62.59,
"learning_rate": 1.088888888888889e-05,
"loss": 1.2617,
"step": 225500
},
{
"epoch": 62.73,
"learning_rate": 1.0666666666666667e-05,
"loss": 1.2586,
"step": 226000
},
{
"epoch": 62.86,
"learning_rate": 1.0444444444444445e-05,
"loss": 1.2615,
"step": 226500
},
{
"epoch": 63.0,
"learning_rate": 1.0222222222222223e-05,
"loss": 1.2628,
"step": 227000
},
{
"epoch": 63.14,
"learning_rate": 1e-05,
"loss": 1.2611,
"step": 227500
},
{
"epoch": 63.28,
"learning_rate": 9.777777777777779e-06,
"loss": 1.2602,
"step": 228000
},
{
"epoch": 63.42,
"learning_rate": 9.555555555555556e-06,
"loss": 1.2596,
"step": 228500
},
{
"epoch": 63.56,
"learning_rate": 9.333333333333334e-06,
"loss": 1.2619,
"step": 229000
},
{
"epoch": 63.7,
"learning_rate": 9.111111111111112e-06,
"loss": 1.2614,
"step": 229500
},
{
"epoch": 63.84,
"learning_rate": 8.88888888888889e-06,
"loss": 1.2612,
"step": 230000
},
{
"epoch": 63.97,
"learning_rate": 8.666666666666668e-06,
"loss": 1.2606,
"step": 230500
},
{
"epoch": 64.11,
"learning_rate": 8.444444444444446e-06,
"loss": 1.2582,
"step": 231000
},
{
"epoch": 64.25,
"learning_rate": 8.222222222222223e-06,
"loss": 1.2594,
"step": 231500
},
{
"epoch": 64.39,
"learning_rate": 8.000000000000001e-06,
"loss": 1.2587,
"step": 232000
},
{
"epoch": 64.53,
"learning_rate": 7.777777777777777e-06,
"loss": 1.2576,
"step": 232500
},
{
"epoch": 64.67,
"learning_rate": 7.555555555555556e-06,
"loss": 1.2588,
"step": 233000
},
{
"epoch": 64.81,
"learning_rate": 7.333333333333334e-06,
"loss": 1.2588,
"step": 233500
},
{
"epoch": 64.95,
"learning_rate": 7.111111111111112e-06,
"loss": 1.2573,
"step": 234000
},
{
"epoch": 65.08,
"learning_rate": 6.888888888888889e-06,
"loss": 1.2585,
"step": 234500
},
{
"epoch": 65.22,
"learning_rate": 6.666666666666667e-06,
"loss": 1.2576,
"step": 235000
},
{
"epoch": 65.36,
"learning_rate": 6.4444444444444445e-06,
"loss": 1.2566,
"step": 235500
},
{
"epoch": 65.5,
"learning_rate": 6.222222222222222e-06,
"loss": 1.2569,
"step": 236000
},
{
"epoch": 65.64,
"learning_rate": 6e-06,
"loss": 1.258,
"step": 236500
},
{
"epoch": 65.78,
"learning_rate": 5.777777777777778e-06,
"loss": 1.2567,
"step": 237000
},
{
"epoch": 65.92,
"learning_rate": 5.555555555555556e-06,
"loss": 1.2568,
"step": 237500
},
{
"epoch": 65.92,
"eval_loss": 1.2293188571929932,
"eval_runtime": 389.8442,
"eval_samples_per_second": 474.997,
"eval_steps_per_second": 3.712,
"step": 237500
},
{
"epoch": 66.06,
"learning_rate": 5.333333333333334e-06,
"loss": 1.2559,
"step": 238000
},
{
"epoch": 66.19,
"learning_rate": 5.1111111111111115e-06,
"loss": 1.2555,
"step": 238500
},
{
"epoch": 66.33,
"learning_rate": 4.888888888888889e-06,
"loss": 1.2585,
"step": 239000
},
{
"epoch": 66.47,
"learning_rate": 4.666666666666667e-06,
"loss": 1.257,
"step": 239500
},
{
"epoch": 66.61,
"learning_rate": 4.444444444444445e-06,
"loss": 1.255,
"step": 240000
},
{
"epoch": 66.75,
"learning_rate": 4.222222222222223e-06,
"loss": 1.256,
"step": 240500
},
{
"epoch": 66.89,
"learning_rate": 4.000000000000001e-06,
"loss": 1.2555,
"step": 241000
},
{
"epoch": 67.03,
"learning_rate": 3.777777777777778e-06,
"loss": 1.2563,
"step": 241500
},
{
"epoch": 67.17,
"learning_rate": 3.555555555555556e-06,
"loss": 1.2528,
"step": 242000
},
{
"epoch": 67.31,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.2566,
"step": 242500
},
{
"epoch": 67.44,
"learning_rate": 3.111111111111111e-06,
"loss": 1.2557,
"step": 243000
},
{
"epoch": 67.58,
"learning_rate": 2.888888888888889e-06,
"loss": 1.2521,
"step": 243500
},
{
"epoch": 67.72,
"learning_rate": 2.666666666666667e-06,
"loss": 1.2535,
"step": 244000
},
{
"epoch": 67.86,
"learning_rate": 2.4444444444444447e-06,
"loss": 1.2559,
"step": 244500
},
{
"epoch": 68.0,
"learning_rate": 2.2222222222222225e-06,
"loss": 1.2534,
"step": 245000
},
{
"epoch": 68.14,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.2562,
"step": 245500
},
{
"epoch": 68.28,
"learning_rate": 1.777777777777778e-06,
"loss": 1.2532,
"step": 246000
},
{
"epoch": 68.42,
"learning_rate": 1.5555555555555556e-06,
"loss": 1.2523,
"step": 246500
},
{
"epoch": 68.55,
"learning_rate": 1.3333333333333334e-06,
"loss": 1.2564,
"step": 247000
},
{
"epoch": 68.69,
"learning_rate": 1.1111111111111112e-06,
"loss": 1.2539,
"step": 247500
},
{
"epoch": 68.83,
"learning_rate": 8.88888888888889e-07,
"loss": 1.2529,
"step": 248000
},
{
"epoch": 68.97,
"learning_rate": 6.666666666666667e-07,
"loss": 1.2523,
"step": 248500
},
{
"epoch": 69.11,
"learning_rate": 4.444444444444445e-07,
"loss": 1.2537,
"step": 249000
},
{
"epoch": 69.25,
"learning_rate": 2.2222222222222224e-07,
"loss": 1.2548,
"step": 249500
},
{
"epoch": 69.39,
"learning_rate": 0.0,
"loss": 1.2535,
"step": 250000
},
{
"epoch": 69.39,
"eval_loss": 1.226332664489746,
"eval_runtime": 389.7782,
"eval_samples_per_second": 475.078,
"eval_steps_per_second": 3.712,
"step": 250000
}
],
"max_steps": 250000,
"num_train_epochs": 70,
"total_flos": 4.212538057807479e+18,
"trial_name": null,
"trial_params": null
}