3677 lines
90 KiB
JSON
3677 lines
90 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 94.44650108603267,
|
|
"global_step": 250000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.19,
|
|
"learning_rate": 1e-05,
|
|
"learning_rate_embeddings": 1e-05,
|
|
"loss": 8.8684,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"learning_rate": 2e-05,
|
|
"learning_rate_embeddings": 2e-05,
|
|
"loss": 7.569,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.57,
|
|
"learning_rate": 3e-05,
|
|
"learning_rate_embeddings": 3e-05,
|
|
"loss": 7.0924,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 0.76,
|
|
"learning_rate": 4e-05,
|
|
"learning_rate_embeddings": 4e-05,
|
|
"loss": 6.6867,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"learning_rate": 5e-05,
|
|
"learning_rate_embeddings": 5e-05,
|
|
"loss": 6.3504,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"epoch": 1.13,
|
|
"learning_rate": 6e-05,
|
|
"learning_rate_embeddings": 6e-05,
|
|
"loss": 6.0791,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 1.32,
|
|
"learning_rate": 7.000000000000001e-05,
|
|
"learning_rate_embeddings": 7.000000000000001e-05,
|
|
"loss": 5.862,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"epoch": 1.51,
|
|
"learning_rate": 8e-05,
|
|
"learning_rate_embeddings": 8e-05,
|
|
"loss": 5.6899,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"epoch": 1.7,
|
|
"learning_rate": 8.999999999999999e-05,
|
|
"learning_rate_embeddings": 8.999999999999999e-05,
|
|
"loss": 5.5584,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"epoch": 1.89,
|
|
"learning_rate": 0.0001,
|
|
"learning_rate_embeddings": 0.0001,
|
|
"loss": 5.4206,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"epoch": 2.08,
|
|
"learning_rate": 0.00011,
|
|
"learning_rate_embeddings": 0.00011,
|
|
"loss": 5.312,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"epoch": 2.27,
|
|
"learning_rate": 0.00012,
|
|
"learning_rate_embeddings": 0.00012,
|
|
"loss": 5.2111,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 2.46,
|
|
"learning_rate": 0.00013000000000000002,
|
|
"learning_rate_embeddings": 0.00013000000000000002,
|
|
"loss": 5.13,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"epoch": 2.64,
|
|
"learning_rate": 0.00014000000000000001,
|
|
"learning_rate_embeddings": 0.00014000000000000001,
|
|
"loss": 5.0645,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"epoch": 2.83,
|
|
"learning_rate": 0.00015,
|
|
"learning_rate_embeddings": 0.00015,
|
|
"loss": 4.9965,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"epoch": 3.02,
|
|
"learning_rate": 0.00016,
|
|
"learning_rate_embeddings": 0.00016,
|
|
"loss": 4.9517,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"epoch": 3.21,
|
|
"learning_rate": 0.00017,
|
|
"learning_rate_embeddings": 0.00017,
|
|
"loss": 4.8957,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"epoch": 3.4,
|
|
"learning_rate": 0.00017999999999999998,
|
|
"learning_rate_embeddings": 0.00017999999999999998,
|
|
"loss": 4.844,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 3.59,
|
|
"learning_rate": 0.00019,
|
|
"learning_rate_embeddings": 0.00019,
|
|
"loss": 4.8118,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"epoch": 3.78,
|
|
"learning_rate": 0.0002,
|
|
"learning_rate_embeddings": 0.0002,
|
|
"loss": 4.7787,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"epoch": 3.97,
|
|
"learning_rate": 0.00021,
|
|
"learning_rate_embeddings": 0.00021,
|
|
"loss": 4.7402,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"epoch": 4.16,
|
|
"learning_rate": 0.00022,
|
|
"learning_rate_embeddings": 0.00022,
|
|
"loss": 4.71,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"epoch": 4.34,
|
|
"learning_rate": 0.00023,
|
|
"learning_rate_embeddings": 0.00023,
|
|
"loss": 4.6801,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"epoch": 4.53,
|
|
"learning_rate": 0.00024,
|
|
"learning_rate_embeddings": 0.00024,
|
|
"loss": 4.6492,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 4.72,
|
|
"learning_rate": 0.00025,
|
|
"learning_rate_embeddings": 0.00025,
|
|
"loss": 4.6378,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"epoch": 4.72,
|
|
"eval_loss": 4.523731231689453,
|
|
"eval_runtime": 283.1562,
|
|
"eval_samples_per_second": 485.979,
|
|
"eval_steps_per_second": 3.8,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"epoch": 4.91,
|
|
"learning_rate": 0.00026000000000000003,
|
|
"learning_rate_embeddings": 0.00026000000000000003,
|
|
"loss": 4.6224,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"epoch": 5.1,
|
|
"learning_rate": 0.00027,
|
|
"learning_rate_embeddings": 0.00027,
|
|
"loss": 4.588,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"epoch": 5.29,
|
|
"learning_rate": 0.00028000000000000003,
|
|
"learning_rate_embeddings": 0.00028000000000000003,
|
|
"loss": 4.5662,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"epoch": 5.48,
|
|
"learning_rate": 0.00029,
|
|
"learning_rate_embeddings": 0.00029,
|
|
"loss": 4.5555,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"epoch": 5.67,
|
|
"learning_rate": 0.0003,
|
|
"learning_rate_embeddings": 0.0003,
|
|
"loss": 4.5393,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 5.86,
|
|
"learning_rate": 0.00031,
|
|
"learning_rate_embeddings": 0.00031,
|
|
"loss": 4.5218,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"epoch": 6.04,
|
|
"learning_rate": 0.00032,
|
|
"learning_rate_embeddings": 0.00032,
|
|
"loss": 4.5077,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"epoch": 6.23,
|
|
"learning_rate": 0.00033,
|
|
"learning_rate_embeddings": 0.00033,
|
|
"loss": 4.4752,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"epoch": 6.42,
|
|
"learning_rate": 0.00034,
|
|
"learning_rate_embeddings": 0.00034,
|
|
"loss": 4.4821,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"epoch": 6.61,
|
|
"learning_rate": 0.00035,
|
|
"learning_rate_embeddings": 0.00035,
|
|
"loss": 4.4562,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"epoch": 6.8,
|
|
"learning_rate": 0.00035999999999999997,
|
|
"learning_rate_embeddings": 0.00035999999999999997,
|
|
"loss": 4.4515,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 6.99,
|
|
"learning_rate": 0.00037,
|
|
"learning_rate_embeddings": 0.00037,
|
|
"loss": 4.4461,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"epoch": 7.18,
|
|
"learning_rate": 0.00038,
|
|
"learning_rate_embeddings": 0.00038,
|
|
"loss": 4.423,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"epoch": 7.37,
|
|
"learning_rate": 0.00039000000000000005,
|
|
"learning_rate_embeddings": 0.00039000000000000005,
|
|
"loss": 4.417,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"epoch": 7.56,
|
|
"learning_rate": 0.0004,
|
|
"learning_rate_embeddings": 0.0004,
|
|
"loss": 4.4125,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"epoch": 7.74,
|
|
"learning_rate": 0.00041,
|
|
"learning_rate_embeddings": 0.00041,
|
|
"loss": 4.4049,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"epoch": 7.93,
|
|
"learning_rate": 0.00042,
|
|
"learning_rate_embeddings": 0.00042,
|
|
"loss": 4.3919,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 8.12,
|
|
"learning_rate": 0.00043,
|
|
"learning_rate_embeddings": 0.00043,
|
|
"loss": 4.3798,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"epoch": 8.31,
|
|
"learning_rate": 0.00044,
|
|
"learning_rate_embeddings": 0.00044,
|
|
"loss": 4.3745,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"epoch": 8.5,
|
|
"learning_rate": 0.00045000000000000004,
|
|
"learning_rate_embeddings": 0.00045000000000000004,
|
|
"loss": 4.3583,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"epoch": 8.69,
|
|
"learning_rate": 0.00046,
|
|
"learning_rate_embeddings": 0.00046,
|
|
"loss": 4.3649,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"epoch": 8.88,
|
|
"learning_rate": 0.00047,
|
|
"learning_rate_embeddings": 0.00047,
|
|
"loss": 4.3559,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"epoch": 9.07,
|
|
"learning_rate": 0.00048,
|
|
"learning_rate_embeddings": 0.00048,
|
|
"loss": 4.3377,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 9.26,
|
|
"learning_rate": 0.00049,
|
|
"learning_rate_embeddings": 0.00049,
|
|
"loss": 4.3307,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"epoch": 9.44,
|
|
"learning_rate": 0.0005,
|
|
"learning_rate_embeddings": 0.0005,
|
|
"loss": 4.3347,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"epoch": 9.44,
|
|
"eval_loss": 4.262948513031006,
|
|
"eval_runtime": 269.7202,
|
|
"eval_samples_per_second": 510.188,
|
|
"eval_steps_per_second": 3.989,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"epoch": 9.63,
|
|
"learning_rate": 0.0004988888888888889,
|
|
"learning_rate_embeddings": 0.0004988888888888889,
|
|
"loss": 4.3208,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"epoch": 9.82,
|
|
"learning_rate": 0.0004977777777777778,
|
|
"learning_rate_embeddings": 0.0004977777777777778,
|
|
"loss": 4.3159,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"epoch": 10.01,
|
|
"learning_rate": 0.0004966666666666666,
|
|
"learning_rate_embeddings": 0.0004966666666666666,
|
|
"loss": 4.316,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"epoch": 10.2,
|
|
"learning_rate": 0.0004955555555555556,
|
|
"learning_rate_embeddings": 0.0004955555555555556,
|
|
"loss": 4.296,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 10.39,
|
|
"learning_rate": 0.0004944444444444445,
|
|
"learning_rate_embeddings": 0.0004944444444444445,
|
|
"loss": 4.2888,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"epoch": 10.58,
|
|
"learning_rate": 0.0004933333333333334,
|
|
"learning_rate_embeddings": 0.0004933333333333334,
|
|
"loss": 4.288,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"epoch": 10.77,
|
|
"learning_rate": 0.0004922222222222222,
|
|
"learning_rate_embeddings": 0.0004922222222222222,
|
|
"loss": 4.2951,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"epoch": 10.96,
|
|
"learning_rate": 0.0004911111111111111,
|
|
"learning_rate_embeddings": 0.0004911111111111111,
|
|
"loss": 4.2864,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"epoch": 11.14,
|
|
"learning_rate": 0.00049,
|
|
"learning_rate_embeddings": 0.00049,
|
|
"loss": 4.28,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"epoch": 11.33,
|
|
"learning_rate": 0.0004888888888888889,
|
|
"learning_rate_embeddings": 0.0004888888888888889,
|
|
"loss": 4.2704,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 11.52,
|
|
"learning_rate": 0.0004877777777777778,
|
|
"learning_rate_embeddings": 0.0004877777777777778,
|
|
"loss": 4.2725,
|
|
"step": 30500
|
|
},
|
|
{
|
|
"epoch": 11.71,
|
|
"learning_rate": 0.0004866666666666667,
|
|
"learning_rate_embeddings": 0.0004866666666666667,
|
|
"loss": 4.2626,
|
|
"step": 31000
|
|
},
|
|
{
|
|
"epoch": 11.9,
|
|
"learning_rate": 0.0004855555555555556,
|
|
"learning_rate_embeddings": 0.0004855555555555556,
|
|
"loss": 4.2503,
|
|
"step": 31500
|
|
},
|
|
{
|
|
"epoch": 12.09,
|
|
"learning_rate": 0.00048444444444444446,
|
|
"learning_rate_embeddings": 0.00048444444444444446,
|
|
"loss": 4.256,
|
|
"step": 32000
|
|
},
|
|
{
|
|
"epoch": 12.28,
|
|
"learning_rate": 0.00048333333333333334,
|
|
"learning_rate_embeddings": 0.00048333333333333334,
|
|
"loss": 4.2288,
|
|
"step": 32500
|
|
},
|
|
{
|
|
"epoch": 12.47,
|
|
"learning_rate": 0.0004822222222222222,
|
|
"learning_rate_embeddings": 0.0004822222222222222,
|
|
"loss": 4.2428,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"epoch": 12.66,
|
|
"learning_rate": 0.0004811111111111111,
|
|
"learning_rate_embeddings": 0.0004811111111111111,
|
|
"loss": 4.242,
|
|
"step": 33500
|
|
},
|
|
{
|
|
"epoch": 12.84,
|
|
"learning_rate": 0.00048,
|
|
"learning_rate_embeddings": 0.00048,
|
|
"loss": 4.2381,
|
|
"step": 34000
|
|
},
|
|
{
|
|
"epoch": 13.03,
|
|
"learning_rate": 0.0004788888888888889,
|
|
"learning_rate_embeddings": 0.0004788888888888889,
|
|
"loss": 4.2503,
|
|
"step": 34500
|
|
},
|
|
{
|
|
"epoch": 13.22,
|
|
"learning_rate": 0.0004777777777777778,
|
|
"learning_rate_embeddings": 0.0004777777777777778,
|
|
"loss": 4.2072,
|
|
"step": 35000
|
|
},
|
|
{
|
|
"epoch": 13.41,
|
|
"learning_rate": 0.0004766666666666667,
|
|
"learning_rate_embeddings": 0.0004766666666666667,
|
|
"loss": 4.2165,
|
|
"step": 35500
|
|
},
|
|
{
|
|
"epoch": 13.6,
|
|
"learning_rate": 0.00047555555555555556,
|
|
"learning_rate_embeddings": 0.00047555555555555556,
|
|
"loss": 4.2298,
|
|
"step": 36000
|
|
},
|
|
{
|
|
"epoch": 13.79,
|
|
"learning_rate": 0.00047444444444444444,
|
|
"learning_rate_embeddings": 0.00047444444444444444,
|
|
"loss": 4.2139,
|
|
"step": 36500
|
|
},
|
|
{
|
|
"epoch": 13.98,
|
|
"learning_rate": 0.00047333333333333336,
|
|
"learning_rate_embeddings": 0.00047333333333333336,
|
|
"loss": 4.2225,
|
|
"step": 37000
|
|
},
|
|
{
|
|
"epoch": 14.17,
|
|
"learning_rate": 0.00047222222222222224,
|
|
"learning_rate_embeddings": 0.00047222222222222224,
|
|
"loss": 4.2218,
|
|
"step": 37500
|
|
},
|
|
{
|
|
"epoch": 14.17,
|
|
"eval_loss": 4.170310020446777,
|
|
"eval_runtime": 269.4713,
|
|
"eval_samples_per_second": 510.659,
|
|
"eval_steps_per_second": 3.993,
|
|
"step": 37500
|
|
},
|
|
{
|
|
"epoch": 14.36,
|
|
"learning_rate": 0.0004711111111111111,
|
|
"learning_rate_embeddings": 0.0004711111111111111,
|
|
"loss": 4.2104,
|
|
"step": 38000
|
|
},
|
|
{
|
|
"epoch": 14.54,
|
|
"learning_rate": 0.00047,
|
|
"learning_rate_embeddings": 0.00047,
|
|
"loss": 4.206,
|
|
"step": 38500
|
|
},
|
|
{
|
|
"epoch": 14.73,
|
|
"learning_rate": 0.0004688888888888889,
|
|
"learning_rate_embeddings": 0.0004688888888888889,
|
|
"loss": 4.2052,
|
|
"step": 39000
|
|
},
|
|
{
|
|
"epoch": 14.92,
|
|
"learning_rate": 0.0004677777777777778,
|
|
"learning_rate_embeddings": 0.0004677777777777778,
|
|
"loss": 4.2098,
|
|
"step": 39500
|
|
},
|
|
{
|
|
"epoch": 15.11,
|
|
"learning_rate": 0.00046666666666666666,
|
|
"learning_rate_embeddings": 0.00046666666666666666,
|
|
"loss": 4.1923,
|
|
"step": 40000
|
|
},
|
|
{
|
|
"epoch": 15.3,
|
|
"learning_rate": 0.0004655555555555556,
|
|
"learning_rate_embeddings": 0.0004655555555555556,
|
|
"loss": 4.1874,
|
|
"step": 40500
|
|
},
|
|
{
|
|
"epoch": 15.49,
|
|
"learning_rate": 0.00046444444444444446,
|
|
"learning_rate_embeddings": 0.00046444444444444446,
|
|
"loss": 4.1931,
|
|
"step": 41000
|
|
},
|
|
{
|
|
"epoch": 15.68,
|
|
"learning_rate": 0.00046333333333333334,
|
|
"learning_rate_embeddings": 0.00046333333333333334,
|
|
"loss": 4.1967,
|
|
"step": 41500
|
|
},
|
|
{
|
|
"epoch": 15.87,
|
|
"learning_rate": 0.0004622222222222222,
|
|
"learning_rate_embeddings": 0.0004622222222222222,
|
|
"loss": 4.1975,
|
|
"step": 42000
|
|
},
|
|
{
|
|
"epoch": 16.06,
|
|
"learning_rate": 0.00046111111111111114,
|
|
"learning_rate_embeddings": 0.00046111111111111114,
|
|
"loss": 4.189,
|
|
"step": 42500
|
|
},
|
|
{
|
|
"epoch": 16.24,
|
|
"learning_rate": 0.00046,
|
|
"learning_rate_embeddings": 0.00046,
|
|
"loss": 4.1806,
|
|
"step": 43000
|
|
},
|
|
{
|
|
"epoch": 16.43,
|
|
"learning_rate": 0.0004588888888888889,
|
|
"learning_rate_embeddings": 0.0004588888888888889,
|
|
"loss": 4.1915,
|
|
"step": 43500
|
|
},
|
|
{
|
|
"epoch": 16.62,
|
|
"learning_rate": 0.0004577777777777778,
|
|
"learning_rate_embeddings": 0.0004577777777777778,
|
|
"loss": 4.1883,
|
|
"step": 44000
|
|
},
|
|
{
|
|
"epoch": 16.81,
|
|
"learning_rate": 0.0004566666666666667,
|
|
"learning_rate_embeddings": 0.0004566666666666667,
|
|
"loss": 4.1849,
|
|
"step": 44500
|
|
},
|
|
{
|
|
"epoch": 17.0,
|
|
"learning_rate": 0.00045555555555555556,
|
|
"learning_rate_embeddings": 0.00045555555555555556,
|
|
"loss": 4.1879,
|
|
"step": 45000
|
|
},
|
|
{
|
|
"epoch": 17.19,
|
|
"learning_rate": 0.00045444444444444444,
|
|
"learning_rate_embeddings": 0.00045444444444444444,
|
|
"loss": 4.1694,
|
|
"step": 45500
|
|
},
|
|
{
|
|
"epoch": 17.38,
|
|
"learning_rate": 0.0004533333333333333,
|
|
"learning_rate_embeddings": 0.0004533333333333333,
|
|
"loss": 4.172,
|
|
"step": 46000
|
|
},
|
|
{
|
|
"epoch": 17.57,
|
|
"learning_rate": 0.00045222222222222224,
|
|
"learning_rate_embeddings": 0.00045222222222222224,
|
|
"loss": 4.1788,
|
|
"step": 46500
|
|
},
|
|
{
|
|
"epoch": 17.76,
|
|
"learning_rate": 0.0004511111111111111,
|
|
"learning_rate_embeddings": 0.0004511111111111111,
|
|
"loss": 4.1735,
|
|
"step": 47000
|
|
},
|
|
{
|
|
"epoch": 17.94,
|
|
"learning_rate": 0.00045000000000000004,
|
|
"learning_rate_embeddings": 0.00045000000000000004,
|
|
"loss": 4.1713,
|
|
"step": 47500
|
|
},
|
|
{
|
|
"epoch": 18.13,
|
|
"learning_rate": 0.0004488888888888889,
|
|
"learning_rate_embeddings": 0.0004488888888888889,
|
|
"loss": 4.1484,
|
|
"step": 48000
|
|
},
|
|
{
|
|
"epoch": 18.32,
|
|
"learning_rate": 0.0004477777777777778,
|
|
"learning_rate_embeddings": 0.0004477777777777778,
|
|
"loss": 4.1537,
|
|
"step": 48500
|
|
},
|
|
{
|
|
"epoch": 18.51,
|
|
"learning_rate": 0.00044666666666666666,
|
|
"learning_rate_embeddings": 0.00044666666666666666,
|
|
"loss": 4.1638,
|
|
"step": 49000
|
|
},
|
|
{
|
|
"epoch": 18.7,
|
|
"learning_rate": 0.00044555555555555554,
|
|
"learning_rate_embeddings": 0.00044555555555555554,
|
|
"loss": 4.1696,
|
|
"step": 49500
|
|
},
|
|
{
|
|
"epoch": 18.89,
|
|
"learning_rate": 0.0004444444444444444,
|
|
"learning_rate_embeddings": 0.0004444444444444444,
|
|
"loss": 4.1679,
|
|
"step": 50000
|
|
},
|
|
{
|
|
"epoch": 18.89,
|
|
"eval_loss": 4.123815059661865,
|
|
"eval_runtime": 269.7323,
|
|
"eval_samples_per_second": 510.165,
|
|
"eval_steps_per_second": 3.989,
|
|
"step": 50000
|
|
},
|
|
{
|
|
"epoch": 19.08,
|
|
"learning_rate": 0.00044333333333333334,
|
|
"learning_rate_embeddings": 0.00044333333333333334,
|
|
"loss": 4.1653,
|
|
"step": 50500
|
|
},
|
|
{
|
|
"epoch": 19.27,
|
|
"learning_rate": 0.00044222222222222227,
|
|
"learning_rate_embeddings": 0.00044222222222222227,
|
|
"loss": 4.1662,
|
|
"step": 51000
|
|
},
|
|
{
|
|
"epoch": 19.46,
|
|
"learning_rate": 0.00044111111111111114,
|
|
"learning_rate_embeddings": 0.00044111111111111114,
|
|
"loss": 4.152,
|
|
"step": 51500
|
|
},
|
|
{
|
|
"epoch": 19.64,
|
|
"learning_rate": 0.00044,
|
|
"learning_rate_embeddings": 0.00044,
|
|
"loss": 4.1604,
|
|
"step": 52000
|
|
},
|
|
{
|
|
"epoch": 19.83,
|
|
"learning_rate": 0.0004388888888888889,
|
|
"learning_rate_embeddings": 0.0004388888888888889,
|
|
"loss": 4.1551,
|
|
"step": 52500
|
|
},
|
|
{
|
|
"epoch": 20.02,
|
|
"learning_rate": 0.00043777777777777776,
|
|
"learning_rate_embeddings": 0.00043777777777777776,
|
|
"loss": 4.1599,
|
|
"step": 53000
|
|
},
|
|
{
|
|
"epoch": 20.21,
|
|
"learning_rate": 0.00043666666666666664,
|
|
"learning_rate_embeddings": 0.00043666666666666664,
|
|
"loss": 4.1343,
|
|
"step": 53500
|
|
},
|
|
{
|
|
"epoch": 20.4,
|
|
"learning_rate": 0.0004355555555555555,
|
|
"learning_rate_embeddings": 0.0004355555555555555,
|
|
"loss": 4.1463,
|
|
"step": 54000
|
|
},
|
|
{
|
|
"epoch": 20.59,
|
|
"learning_rate": 0.0004344444444444445,
|
|
"learning_rate_embeddings": 0.0004344444444444445,
|
|
"loss": 4.1551,
|
|
"step": 54500
|
|
},
|
|
{
|
|
"epoch": 20.78,
|
|
"learning_rate": 0.00043333333333333337,
|
|
"learning_rate_embeddings": 0.00043333333333333337,
|
|
"loss": 4.1414,
|
|
"step": 55000
|
|
},
|
|
{
|
|
"epoch": 20.97,
|
|
"learning_rate": 0.00043222222222222224,
|
|
"learning_rate_embeddings": 0.00043222222222222224,
|
|
"loss": 4.1407,
|
|
"step": 55500
|
|
},
|
|
{
|
|
"epoch": 21.16,
|
|
"learning_rate": 0.0004311111111111111,
|
|
"learning_rate_embeddings": 0.0004311111111111111,
|
|
"loss": 4.1426,
|
|
"step": 56000
|
|
},
|
|
{
|
|
"epoch": 21.34,
|
|
"learning_rate": 0.00043,
|
|
"learning_rate_embeddings": 0.00043,
|
|
"loss": 4.1451,
|
|
"step": 56500
|
|
},
|
|
{
|
|
"epoch": 21.53,
|
|
"learning_rate": 0.00042888888888888886,
|
|
"learning_rate_embeddings": 0.00042888888888888886,
|
|
"loss": 4.1482,
|
|
"step": 57000
|
|
},
|
|
{
|
|
"epoch": 21.72,
|
|
"learning_rate": 0.0004277777777777778,
|
|
"learning_rate_embeddings": 0.0004277777777777778,
|
|
"loss": 4.1434,
|
|
"step": 57500
|
|
},
|
|
{
|
|
"epoch": 21.91,
|
|
"learning_rate": 0.0004266666666666667,
|
|
"learning_rate_embeddings": 0.0004266666666666667,
|
|
"loss": 4.1362,
|
|
"step": 58000
|
|
},
|
|
{
|
|
"epoch": 22.1,
|
|
"learning_rate": 0.0004255555555555556,
|
|
"learning_rate_embeddings": 0.0004255555555555556,
|
|
"loss": 4.1522,
|
|
"step": 58500
|
|
},
|
|
{
|
|
"epoch": 22.29,
|
|
"learning_rate": 0.00042444444444444447,
|
|
"learning_rate_embeddings": 0.00042444444444444447,
|
|
"loss": 4.1418,
|
|
"step": 59000
|
|
},
|
|
{
|
|
"epoch": 22.48,
|
|
"learning_rate": 0.00042333333333333334,
|
|
"learning_rate_embeddings": 0.00042333333333333334,
|
|
"loss": 4.1232,
|
|
"step": 59500
|
|
},
|
|
{
|
|
"epoch": 22.67,
|
|
"learning_rate": 0.0004222222222222222,
|
|
"learning_rate_embeddings": 0.0004222222222222222,
|
|
"loss": 4.1345,
|
|
"step": 60000
|
|
},
|
|
{
|
|
"epoch": 22.86,
|
|
"learning_rate": 0.0004211111111111111,
|
|
"learning_rate_embeddings": 0.0004211111111111111,
|
|
"loss": 4.1434,
|
|
"step": 60500
|
|
},
|
|
{
|
|
"epoch": 23.04,
|
|
"learning_rate": 0.00042,
|
|
"learning_rate_embeddings": 0.00042,
|
|
"loss": 4.1371,
|
|
"step": 61000
|
|
},
|
|
{
|
|
"epoch": 23.23,
|
|
"learning_rate": 0.0004188888888888889,
|
|
"learning_rate_embeddings": 0.0004188888888888889,
|
|
"loss": 4.126,
|
|
"step": 61500
|
|
},
|
|
{
|
|
"epoch": 23.42,
|
|
"learning_rate": 0.0004177777777777778,
|
|
"learning_rate_embeddings": 0.0004177777777777778,
|
|
"loss": 4.1253,
|
|
"step": 62000
|
|
},
|
|
{
|
|
"epoch": 23.61,
|
|
"learning_rate": 0.0004166666666666667,
|
|
"learning_rate_embeddings": 0.0004166666666666667,
|
|
"loss": 4.1326,
|
|
"step": 62500
|
|
},
|
|
{
|
|
"epoch": 23.61,
|
|
"eval_loss": 4.110262393951416,
|
|
"eval_runtime": 269.4713,
|
|
"eval_samples_per_second": 510.659,
|
|
"eval_steps_per_second": 3.993,
|
|
"step": 62500
|
|
},
|
|
{
|
|
"epoch": 23.8,
|
|
"learning_rate": 0.00041555555555555557,
|
|
"learning_rate_embeddings": 0.00041555555555555557,
|
|
"loss": 4.1239,
|
|
"step": 63000
|
|
},
|
|
{
|
|
"epoch": 23.99,
|
|
"learning_rate": 0.00041444444444444444,
|
|
"learning_rate_embeddings": 0.00041444444444444444,
|
|
"loss": 4.1229,
|
|
"step": 63500
|
|
},
|
|
{
|
|
"epoch": 24.18,
|
|
"learning_rate": 0.0004133333333333333,
|
|
"learning_rate_embeddings": 0.0004133333333333333,
|
|
"loss": 4.1185,
|
|
"step": 64000
|
|
},
|
|
{
|
|
"epoch": 24.37,
|
|
"learning_rate": 0.00041222222222222224,
|
|
"learning_rate_embeddings": 0.00041222222222222224,
|
|
"loss": 4.1177,
|
|
"step": 64500
|
|
},
|
|
{
|
|
"epoch": 24.56,
|
|
"learning_rate": 0.0004111111111111111,
|
|
"learning_rate_embeddings": 0.0004111111111111111,
|
|
"loss": 4.1244,
|
|
"step": 65000
|
|
},
|
|
{
|
|
"epoch": 24.74,
|
|
"learning_rate": 0.00041,
|
|
"learning_rate_embeddings": 0.00041,
|
|
"loss": 4.1273,
|
|
"step": 65500
|
|
},
|
|
{
|
|
"epoch": 24.93,
|
|
"learning_rate": 0.0004088888888888889,
|
|
"learning_rate_embeddings": 0.0004088888888888889,
|
|
"loss": 4.1333,
|
|
"step": 66000
|
|
},
|
|
{
|
|
"epoch": 25.12,
|
|
"learning_rate": 0.0004077777777777778,
|
|
"learning_rate_embeddings": 0.0004077777777777778,
|
|
"loss": 4.119,
|
|
"step": 66500
|
|
},
|
|
{
|
|
"epoch": 25.31,
|
|
"learning_rate": 0.00040666666666666667,
|
|
"learning_rate_embeddings": 0.00040666666666666667,
|
|
"loss": 4.1156,
|
|
"step": 67000
|
|
},
|
|
{
|
|
"epoch": 25.5,
|
|
"learning_rate": 0.00040555555555555554,
|
|
"learning_rate_embeddings": 0.00040555555555555554,
|
|
"loss": 4.1066,
|
|
"step": 67500
|
|
},
|
|
{
|
|
"epoch": 25.69,
|
|
"learning_rate": 0.00040444444444444447,
|
|
"learning_rate_embeddings": 0.00040444444444444447,
|
|
"loss": 4.1294,
|
|
"step": 68000
|
|
},
|
|
{
|
|
"epoch": 25.88,
|
|
"learning_rate": 0.00040333333333333334,
|
|
"learning_rate_embeddings": 0.00040333333333333334,
|
|
"loss": 4.1313,
|
|
"step": 68500
|
|
},
|
|
{
|
|
"epoch": 26.07,
|
|
"learning_rate": 0.0004022222222222222,
|
|
"learning_rate_embeddings": 0.0004022222222222222,
|
|
"loss": 4.122,
|
|
"step": 69000
|
|
},
|
|
{
|
|
"epoch": 26.26,
|
|
"learning_rate": 0.0004011111111111111,
|
|
"learning_rate_embeddings": 0.0004011111111111111,
|
|
"loss": 4.1129,
|
|
"step": 69500
|
|
},
|
|
{
|
|
"epoch": 26.44,
|
|
"learning_rate": 0.0004,
|
|
"learning_rate_embeddings": 0.0004,
|
|
"loss": 4.1211,
|
|
"step": 70000
|
|
},
|
|
{
|
|
"epoch": 26.63,
|
|
"learning_rate": 0.0003988888888888889,
|
|
"learning_rate_embeddings": 0.0003988888888888889,
|
|
"loss": 4.1235,
|
|
"step": 70500
|
|
},
|
|
{
|
|
"epoch": 26.82,
|
|
"learning_rate": 0.00039777777777777777,
|
|
"learning_rate_embeddings": 0.00039777777777777777,
|
|
"loss": 4.11,
|
|
"step": 71000
|
|
},
|
|
{
|
|
"epoch": 27.01,
|
|
"learning_rate": 0.0003966666666666667,
|
|
"learning_rate_embeddings": 0.0003966666666666667,
|
|
"loss": 4.1252,
|
|
"step": 71500
|
|
},
|
|
{
|
|
"epoch": 27.2,
|
|
"learning_rate": 0.00039555555555555557,
|
|
"learning_rate_embeddings": 0.00039555555555555557,
|
|
"loss": 4.1106,
|
|
"step": 72000
|
|
},
|
|
{
|
|
"epoch": 27.39,
|
|
"learning_rate": 0.00039444444444444444,
|
|
"learning_rate_embeddings": 0.00039444444444444444,
|
|
"loss": 4.1184,
|
|
"step": 72500
|
|
},
|
|
{
|
|
"epoch": 27.58,
|
|
"learning_rate": 0.0003933333333333333,
|
|
"learning_rate_embeddings": 0.0003933333333333333,
|
|
"loss": 4.1112,
|
|
"step": 73000
|
|
},
|
|
{
|
|
"epoch": 27.77,
|
|
"learning_rate": 0.00039222222222222225,
|
|
"learning_rate_embeddings": 0.00039222222222222225,
|
|
"loss": 4.1207,
|
|
"step": 73500
|
|
},
|
|
{
|
|
"epoch": 27.96,
|
|
"learning_rate": 0.0003911111111111111,
|
|
"learning_rate_embeddings": 0.0003911111111111111,
|
|
"loss": 4.1165,
|
|
"step": 74000
|
|
},
|
|
{
|
|
"epoch": 28.15,
|
|
"learning_rate": 0.00039000000000000005,
|
|
"learning_rate_embeddings": 0.00039000000000000005,
|
|
"loss": 4.1055,
|
|
"step": 74500
|
|
},
|
|
{
|
|
"epoch": 28.33,
|
|
"learning_rate": 0.0003888888888888889,
|
|
"learning_rate_embeddings": 0.0003888888888888889,
|
|
"loss": 4.1109,
|
|
"step": 75000
|
|
},
|
|
{
|
|
"epoch": 28.33,
|
|
"eval_loss": 4.083001136779785,
|
|
"eval_runtime": 269.5786,
|
|
"eval_samples_per_second": 510.456,
|
|
"eval_steps_per_second": 3.991,
|
|
"step": 75000
|
|
},
|
|
{
|
|
"epoch": 28.52,
|
|
"learning_rate": 0.0003877777777777778,
|
|
"learning_rate_embeddings": 0.0003877777777777778,
|
|
"loss": 4.1215,
|
|
"step": 75500
|
|
},
|
|
{
|
|
"epoch": 28.71,
|
|
"learning_rate": 0.00038666666666666667,
|
|
"learning_rate_embeddings": 0.00038666666666666667,
|
|
"loss": 4.1167,
|
|
"step": 76000
|
|
},
|
|
{
|
|
"epoch": 28.9,
|
|
"learning_rate": 0.00038555555555555554,
|
|
"learning_rate_embeddings": 0.00038555555555555554,
|
|
"loss": 4.1168,
|
|
"step": 76500
|
|
},
|
|
{
|
|
"epoch": 29.09,
|
|
"learning_rate": 0.0003844444444444444,
|
|
"learning_rate_embeddings": 0.0003844444444444444,
|
|
"loss": 4.1234,
|
|
"step": 77000
|
|
},
|
|
{
|
|
"epoch": 29.28,
|
|
"learning_rate": 0.00038333333333333334,
|
|
"learning_rate_embeddings": 0.00038333333333333334,
|
|
"loss": 4.1025,
|
|
"step": 77500
|
|
},
|
|
{
|
|
"epoch": 29.47,
|
|
"learning_rate": 0.0003822222222222223,
|
|
"learning_rate_embeddings": 0.0003822222222222223,
|
|
"loss": 4.0966,
|
|
"step": 78000
|
|
},
|
|
{
|
|
"epoch": 29.66,
|
|
"learning_rate": 0.00038111111111111115,
|
|
"learning_rate_embeddings": 0.00038111111111111115,
|
|
"loss": 4.1019,
|
|
"step": 78500
|
|
},
|
|
{
|
|
"epoch": 29.85,
|
|
"learning_rate": 0.00038,
|
|
"learning_rate_embeddings": 0.00038,
|
|
"loss": 4.0909,
|
|
"step": 79000
|
|
},
|
|
{
|
|
"epoch": 30.03,
|
|
"learning_rate": 0.0003788888888888889,
|
|
"learning_rate_embeddings": 0.0003788888888888889,
|
|
"loss": 4.0976,
|
|
"step": 79500
|
|
},
|
|
{
|
|
"epoch": 30.22,
|
|
"learning_rate": 0.00037777777777777777,
|
|
"learning_rate_embeddings": 0.00037777777777777777,
|
|
"loss": 4.0868,
|
|
"step": 80000
|
|
},
|
|
{
|
|
"epoch": 30.41,
|
|
"learning_rate": 0.00037666666666666664,
|
|
"learning_rate_embeddings": 0.00037666666666666664,
|
|
"loss": 4.088,
|
|
"step": 80500
|
|
},
|
|
{
|
|
"epoch": 30.6,
|
|
"learning_rate": 0.0003755555555555555,
|
|
"learning_rate_embeddings": 0.0003755555555555555,
|
|
"loss": 4.111,
|
|
"step": 81000
|
|
},
|
|
{
|
|
"epoch": 30.79,
|
|
"learning_rate": 0.0003744444444444445,
|
|
"learning_rate_embeddings": 0.0003744444444444445,
|
|
"loss": 4.0978,
|
|
"step": 81500
|
|
},
|
|
{
|
|
"epoch": 30.98,
|
|
"learning_rate": 0.0003733333333333334,
|
|
"learning_rate_embeddings": 0.0003733333333333334,
|
|
"loss": 4.1147,
|
|
"step": 82000
|
|
},
|
|
{
|
|
"epoch": 31.17,
|
|
"learning_rate": 0.00037222222222222225,
|
|
"learning_rate_embeddings": 0.00037222222222222225,
|
|
"loss": 4.0859,
|
|
"step": 82500
|
|
},
|
|
{
|
|
"epoch": 31.36,
|
|
"learning_rate": 0.0003711111111111111,
|
|
"learning_rate_embeddings": 0.0003711111111111111,
|
|
"loss": 4.0895,
|
|
"step": 83000
|
|
},
|
|
{
|
|
"epoch": 31.55,
|
|
"learning_rate": 0.00037,
|
|
"learning_rate_embeddings": 0.00037,
|
|
"loss": 4.0937,
|
|
"step": 83500
|
|
},
|
|
{
|
|
"epoch": 31.73,
|
|
"learning_rate": 0.00036888888888888887,
|
|
"learning_rate_embeddings": 0.00036888888888888887,
|
|
"loss": 4.1026,
|
|
"step": 84000
|
|
},
|
|
{
|
|
"epoch": 31.92,
|
|
"learning_rate": 0.00036777777777777774,
|
|
"learning_rate_embeddings": 0.00036777777777777774,
|
|
"loss": 4.1185,
|
|
"step": 84500
|
|
},
|
|
{
|
|
"epoch": 32.11,
|
|
"learning_rate": 0.00036666666666666667,
|
|
"learning_rate_embeddings": 0.00036666666666666667,
|
|
"loss": 4.0918,
|
|
"step": 85000
|
|
},
|
|
{
|
|
"epoch": 32.3,
|
|
"learning_rate": 0.0003655555555555556,
|
|
"learning_rate_embeddings": 0.0003655555555555556,
|
|
"loss": 4.0929,
|
|
"step": 85500
|
|
},
|
|
{
|
|
"epoch": 32.49,
|
|
"learning_rate": 0.00036444444444444447,
|
|
"learning_rate_embeddings": 0.00036444444444444447,
|
|
"loss": 4.0929,
|
|
"step": 86000
|
|
},
|
|
{
|
|
"epoch": 32.68,
|
|
"learning_rate": 0.00036333333333333335,
|
|
"learning_rate_embeddings": 0.00036333333333333335,
|
|
"loss": 4.0983,
|
|
"step": 86500
|
|
},
|
|
{
|
|
"epoch": 32.87,
|
|
"learning_rate": 0.0003622222222222222,
|
|
"learning_rate_embeddings": 0.0003622222222222222,
|
|
"loss": 4.0934,
|
|
"step": 87000
|
|
},
|
|
{
|
|
"epoch": 33.06,
|
|
"learning_rate": 0.0003611111111111111,
|
|
"learning_rate_embeddings": 0.0003611111111111111,
|
|
"loss": 4.0945,
|
|
"step": 87500
|
|
},
|
|
{
|
|
"epoch": 33.06,
|
|
"eval_loss": 4.083254814147949,
|
|
"eval_runtime": 269.7774,
|
|
"eval_samples_per_second": 510.08,
|
|
"eval_steps_per_second": 3.988,
|
|
"step": 87500
|
|
},
|
|
{
|
|
"epoch": 33.25,
|
|
"learning_rate": 0.00035999999999999997,
|
|
"learning_rate_embeddings": 0.00035999999999999997,
|
|
"loss": 4.0869,
|
|
"step": 88000
|
|
},
|
|
{
|
|
"epoch": 33.43,
|
|
"learning_rate": 0.0003588888888888889,
|
|
"learning_rate_embeddings": 0.0003588888888888889,
|
|
"loss": 4.0954,
|
|
"step": 88500
|
|
},
|
|
{
|
|
"epoch": 33.62,
|
|
"learning_rate": 0.00035777777777777777,
|
|
"learning_rate_embeddings": 0.00035777777777777777,
|
|
"loss": 4.0952,
|
|
"step": 89000
|
|
},
|
|
{
|
|
"epoch": 33.81,
|
|
"learning_rate": 0.0003566666666666667,
|
|
"learning_rate_embeddings": 0.0003566666666666667,
|
|
"loss": 4.0994,
|
|
"step": 89500
|
|
},
|
|
{
|
|
"epoch": 34.0,
|
|
"learning_rate": 0.00035555555555555557,
|
|
"learning_rate_embeddings": 0.00035555555555555557,
|
|
"loss": 4.1098,
|
|
"step": 90000
|
|
},
|
|
{
|
|
"epoch": 34.19,
|
|
"learning_rate": 0.00035444444444444445,
|
|
"learning_rate_embeddings": 0.00035444444444444445,
|
|
"loss": 4.074,
|
|
"step": 90500
|
|
},
|
|
{
|
|
"epoch": 34.38,
|
|
"learning_rate": 0.0003533333333333333,
|
|
"learning_rate_embeddings": 0.0003533333333333333,
|
|
"loss": 4.0965,
|
|
"step": 91000
|
|
},
|
|
{
|
|
"epoch": 34.57,
|
|
"learning_rate": 0.00035222222222222225,
|
|
"learning_rate_embeddings": 0.00035222222222222225,
|
|
"loss": 4.0917,
|
|
"step": 91500
|
|
},
|
|
{
|
|
"epoch": 34.76,
|
|
"learning_rate": 0.0003511111111111111,
|
|
"learning_rate_embeddings": 0.0003511111111111111,
|
|
"loss": 4.0914,
|
|
"step": 92000
|
|
},
|
|
{
|
|
"epoch": 34.95,
|
|
"learning_rate": 0.00035,
|
|
"learning_rate_embeddings": 0.00035,
|
|
"loss": 4.1001,
|
|
"step": 92500
|
|
},
|
|
{
|
|
"epoch": 35.13,
|
|
"learning_rate": 0.0003488888888888889,
|
|
"learning_rate_embeddings": 0.0003488888888888889,
|
|
"loss": 4.0968,
|
|
"step": 93000
|
|
},
|
|
{
|
|
"epoch": 35.32,
|
|
"learning_rate": 0.0003477777777777778,
|
|
"learning_rate_embeddings": 0.0003477777777777778,
|
|
"loss": 4.0806,
|
|
"step": 93500
|
|
},
|
|
{
|
|
"epoch": 35.51,
|
|
"learning_rate": 0.00034666666666666667,
|
|
"learning_rate_embeddings": 0.00034666666666666667,
|
|
"loss": 4.093,
|
|
"step": 94000
|
|
},
|
|
{
|
|
"epoch": 35.7,
|
|
"learning_rate": 0.00034555555555555555,
|
|
"learning_rate_embeddings": 0.00034555555555555555,
|
|
"loss": 4.0944,
|
|
"step": 94500
|
|
},
|
|
{
|
|
"epoch": 35.89,
|
|
"learning_rate": 0.0003444444444444445,
|
|
"learning_rate_embeddings": 0.0003444444444444445,
|
|
"loss": 4.0823,
|
|
"step": 95000
|
|
},
|
|
{
|
|
"epoch": 36.08,
|
|
"learning_rate": 0.00034333333333333335,
|
|
"learning_rate_embeddings": 0.00034333333333333335,
|
|
"loss": 4.0839,
|
|
"step": 95500
|
|
},
|
|
{
|
|
"epoch": 36.27,
|
|
"learning_rate": 0.0003422222222222222,
|
|
"learning_rate_embeddings": 0.0003422222222222222,
|
|
"loss": 4.0774,
|
|
"step": 96000
|
|
},
|
|
{
|
|
"epoch": 36.46,
|
|
"learning_rate": 0.0003411111111111111,
|
|
"learning_rate_embeddings": 0.0003411111111111111,
|
|
"loss": 4.0812,
|
|
"step": 96500
|
|
},
|
|
{
|
|
"epoch": 36.65,
|
|
"learning_rate": 0.00034,
|
|
"learning_rate_embeddings": 0.00034,
|
|
"loss": 4.088,
|
|
"step": 97000
|
|
},
|
|
{
|
|
"epoch": 36.83,
|
|
"learning_rate": 0.0003388888888888889,
|
|
"learning_rate_embeddings": 0.0003388888888888889,
|
|
"loss": 4.105,
|
|
"step": 97500
|
|
},
|
|
{
|
|
"epoch": 37.02,
|
|
"learning_rate": 0.00033777777777777777,
|
|
"learning_rate_embeddings": 0.00033777777777777777,
|
|
"loss": 4.0893,
|
|
"step": 98000
|
|
},
|
|
{
|
|
"epoch": 37.21,
|
|
"learning_rate": 0.0003366666666666667,
|
|
"learning_rate_embeddings": 0.0003366666666666667,
|
|
"loss": 4.0639,
|
|
"step": 98500
|
|
},
|
|
{
|
|
"epoch": 37.4,
|
|
"learning_rate": 0.0003355555555555556,
|
|
"learning_rate_embeddings": 0.0003355555555555556,
|
|
"loss": 4.0856,
|
|
"step": 99000
|
|
},
|
|
{
|
|
"epoch": 37.59,
|
|
"learning_rate": 0.00033444444444444445,
|
|
"learning_rate_embeddings": 0.00033444444444444445,
|
|
"loss": 4.0875,
|
|
"step": 99500
|
|
},
|
|
{
|
|
"epoch": 37.78,
|
|
"learning_rate": 0.0003333333333333333,
|
|
"learning_rate_embeddings": 0.0003333333333333333,
|
|
"loss": 4.0914,
|
|
"step": 100000
|
|
},
|
|
{
|
|
"epoch": 37.78,
|
|
"eval_loss": 4.074242115020752,
|
|
"eval_runtime": 269.8475,
|
|
"eval_samples_per_second": 509.947,
|
|
"eval_steps_per_second": 3.987,
|
|
"step": 100000
|
|
},
|
|
{
|
|
"epoch": 37.97,
|
|
"learning_rate": 0.0003322222222222222,
|
|
"learning_rate_embeddings": 0.0003322222222222222,
|
|
"loss": 4.0834,
|
|
"step": 100500
|
|
},
|
|
{
|
|
"epoch": 38.16,
|
|
"learning_rate": 0.0003311111111111111,
|
|
"learning_rate_embeddings": 0.0003311111111111111,
|
|
"loss": 4.0721,
|
|
"step": 101000
|
|
},
|
|
{
|
|
"epoch": 38.35,
|
|
"learning_rate": 0.00033,
|
|
"learning_rate_embeddings": 0.00033,
|
|
"loss": 4.0755,
|
|
"step": 101500
|
|
},
|
|
{
|
|
"epoch": 38.53,
|
|
"learning_rate": 0.0003288888888888889,
|
|
"learning_rate_embeddings": 0.0003288888888888889,
|
|
"loss": 4.0792,
|
|
"step": 102000
|
|
},
|
|
{
|
|
"epoch": 38.72,
|
|
"learning_rate": 0.0003277777777777778,
|
|
"learning_rate_embeddings": 0.0003277777777777778,
|
|
"loss": 4.0702,
|
|
"step": 102500
|
|
},
|
|
{
|
|
"epoch": 38.91,
|
|
"learning_rate": 0.0003266666666666667,
|
|
"learning_rate_embeddings": 0.0003266666666666667,
|
|
"loss": 4.0813,
|
|
"step": 103000
|
|
},
|
|
{
|
|
"epoch": 39.1,
|
|
"learning_rate": 0.00032555555555555555,
|
|
"learning_rate_embeddings": 0.00032555555555555555,
|
|
"loss": 4.0793,
|
|
"step": 103500
|
|
},
|
|
{
|
|
"epoch": 39.29,
|
|
"learning_rate": 0.0003244444444444444,
|
|
"learning_rate_embeddings": 0.0003244444444444444,
|
|
"loss": 4.0726,
|
|
"step": 104000
|
|
},
|
|
{
|
|
"epoch": 39.48,
|
|
"learning_rate": 0.0003233333333333333,
|
|
"learning_rate_embeddings": 0.0003233333333333333,
|
|
"loss": 4.0669,
|
|
"step": 104500
|
|
},
|
|
{
|
|
"epoch": 39.67,
|
|
"learning_rate": 0.0003222222222222222,
|
|
"learning_rate_embeddings": 0.0003222222222222222,
|
|
"loss": 4.0913,
|
|
"step": 105000
|
|
},
|
|
{
|
|
"epoch": 39.86,
|
|
"learning_rate": 0.00032111111111111115,
|
|
"learning_rate_embeddings": 0.00032111111111111115,
|
|
"loss": 4.0671,
|
|
"step": 105500
|
|
},
|
|
{
|
|
"epoch": 40.05,
|
|
"learning_rate": 0.00032,
|
|
"learning_rate_embeddings": 0.00032,
|
|
"loss": 4.0875,
|
|
"step": 106000
|
|
},
|
|
{
|
|
"epoch": 40.23,
|
|
"learning_rate": 0.0003188888888888889,
|
|
"learning_rate_embeddings": 0.0003188888888888889,
|
|
"loss": 4.0771,
|
|
"step": 106500
|
|
},
|
|
{
|
|
"epoch": 40.42,
|
|
"learning_rate": 0.0003177777777777778,
|
|
"learning_rate_embeddings": 0.0003177777777777778,
|
|
"loss": 4.0778,
|
|
"step": 107000
|
|
},
|
|
{
|
|
"epoch": 40.61,
|
|
"learning_rate": 0.00031666666666666665,
|
|
"learning_rate_embeddings": 0.00031666666666666665,
|
|
"loss": 4.0785,
|
|
"step": 107500
|
|
},
|
|
{
|
|
"epoch": 40.8,
|
|
"learning_rate": 0.0003155555555555555,
|
|
"learning_rate_embeddings": 0.0003155555555555555,
|
|
"loss": 4.0861,
|
|
"step": 108000
|
|
},
|
|
{
|
|
"epoch": 40.99,
|
|
"learning_rate": 0.0003144444444444445,
|
|
"learning_rate_embeddings": 0.0003144444444444445,
|
|
"loss": 4.0875,
|
|
"step": 108500
|
|
},
|
|
{
|
|
"epoch": 41.18,
|
|
"learning_rate": 0.0003133333333333334,
|
|
"learning_rate_embeddings": 0.0003133333333333334,
|
|
"loss": 4.0672,
|
|
"step": 109000
|
|
},
|
|
{
|
|
"epoch": 41.37,
|
|
"learning_rate": 0.00031222222222222225,
|
|
"learning_rate_embeddings": 0.00031222222222222225,
|
|
"loss": 4.0736,
|
|
"step": 109500
|
|
},
|
|
{
|
|
"epoch": 41.56,
|
|
"learning_rate": 0.0003111111111111111,
|
|
"learning_rate_embeddings": 0.0003111111111111111,
|
|
"loss": 4.0775,
|
|
"step": 110000
|
|
},
|
|
{
|
|
"epoch": 41.75,
|
|
"learning_rate": 0.00031,
|
|
"learning_rate_embeddings": 0.00031,
|
|
"loss": 4.0778,
|
|
"step": 110500
|
|
},
|
|
{
|
|
"epoch": 41.93,
|
|
"learning_rate": 0.0003088888888888889,
|
|
"learning_rate_embeddings": 0.0003088888888888889,
|
|
"loss": 4.0626,
|
|
"step": 111000
|
|
},
|
|
{
|
|
"epoch": 42.12,
|
|
"learning_rate": 0.00030777777777777775,
|
|
"learning_rate_embeddings": 0.00030777777777777775,
|
|
"loss": 4.0588,
|
|
"step": 111500
|
|
},
|
|
{
|
|
"epoch": 42.31,
|
|
"learning_rate": 0.0003066666666666667,
|
|
"learning_rate_embeddings": 0.0003066666666666667,
|
|
"loss": 4.0797,
|
|
"step": 112000
|
|
},
|
|
{
|
|
"epoch": 42.5,
|
|
"learning_rate": 0.0003055555555555556,
|
|
"learning_rate_embeddings": 0.0003055555555555556,
|
|
"loss": 4.0635,
|
|
"step": 112500
|
|
},
|
|
{
|
|
"epoch": 42.5,
|
|
"eval_loss": 4.073777675628662,
|
|
"eval_runtime": 269.6318,
|
|
"eval_samples_per_second": 510.355,
|
|
"eval_steps_per_second": 3.991,
|
|
"step": 112500
|
|
},
|
|
{
|
|
"epoch": 42.69,
|
|
"learning_rate": 0.0003044444444444445,
|
|
"learning_rate_embeddings": 0.0003044444444444445,
|
|
"loss": 4.0732,
|
|
"step": 113000
|
|
},
|
|
{
|
|
"epoch": 42.88,
|
|
"learning_rate": 0.00030333333333333335,
|
|
"learning_rate_embeddings": 0.00030333333333333335,
|
|
"loss": 4.0635,
|
|
"step": 113500
|
|
},
|
|
{
|
|
"epoch": 43.07,
|
|
"learning_rate": 0.0003022222222222222,
|
|
"learning_rate_embeddings": 0.0003022222222222222,
|
|
"loss": 4.0681,
|
|
"step": 114000
|
|
},
|
|
{
|
|
"epoch": 43.26,
|
|
"learning_rate": 0.0003011111111111111,
|
|
"learning_rate_embeddings": 0.0003011111111111111,
|
|
"loss": 4.0617,
|
|
"step": 114500
|
|
},
|
|
{
|
|
"epoch": 43.45,
|
|
"learning_rate": 0.0003,
|
|
"learning_rate_embeddings": 0.0003,
|
|
"loss": 4.075,
|
|
"step": 115000
|
|
},
|
|
{
|
|
"epoch": 43.63,
|
|
"learning_rate": 0.0002988888888888889,
|
|
"learning_rate_embeddings": 0.0002988888888888889,
|
|
"loss": 4.0482,
|
|
"step": 115500
|
|
},
|
|
{
|
|
"epoch": 43.82,
|
|
"learning_rate": 0.0002977777777777778,
|
|
"learning_rate_embeddings": 0.0002977777777777778,
|
|
"loss": 4.0659,
|
|
"step": 116000
|
|
},
|
|
{
|
|
"epoch": 44.01,
|
|
"learning_rate": 0.0002966666666666667,
|
|
"learning_rate_embeddings": 0.0002966666666666667,
|
|
"loss": 4.0719,
|
|
"step": 116500
|
|
},
|
|
{
|
|
"epoch": 44.2,
|
|
"learning_rate": 0.0002955555555555556,
|
|
"learning_rate_embeddings": 0.0002955555555555556,
|
|
"loss": 4.0533,
|
|
"step": 117000
|
|
},
|
|
{
|
|
"epoch": 44.39,
|
|
"learning_rate": 0.00029444444444444445,
|
|
"learning_rate_embeddings": 0.00029444444444444445,
|
|
"loss": 4.0544,
|
|
"step": 117500
|
|
},
|
|
{
|
|
"epoch": 44.58,
|
|
"learning_rate": 0.0002933333333333333,
|
|
"learning_rate_embeddings": 0.0002933333333333333,
|
|
"loss": 4.0798,
|
|
"step": 118000
|
|
},
|
|
{
|
|
"epoch": 44.77,
|
|
"learning_rate": 0.0002922222222222222,
|
|
"learning_rate_embeddings": 0.0002922222222222222,
|
|
"loss": 4.0689,
|
|
"step": 118500
|
|
},
|
|
{
|
|
"epoch": 44.96,
|
|
"learning_rate": 0.00029111111111111113,
|
|
"learning_rate_embeddings": 0.00029111111111111113,
|
|
"loss": 4.0669,
|
|
"step": 119000
|
|
},
|
|
{
|
|
"epoch": 45.15,
|
|
"learning_rate": 0.00029,
|
|
"learning_rate_embeddings": 0.00029,
|
|
"loss": 4.0727,
|
|
"step": 119500
|
|
},
|
|
{
|
|
"epoch": 45.33,
|
|
"learning_rate": 0.0002888888888888889,
|
|
"learning_rate_embeddings": 0.0002888888888888889,
|
|
"loss": 4.0706,
|
|
"step": 120000
|
|
},
|
|
{
|
|
"epoch": 45.52,
|
|
"learning_rate": 0.0002877777777777778,
|
|
"learning_rate_embeddings": 0.0002877777777777778,
|
|
"loss": 4.0592,
|
|
"step": 120500
|
|
},
|
|
{
|
|
"epoch": 45.71,
|
|
"learning_rate": 0.0002866666666666667,
|
|
"learning_rate_embeddings": 0.0002866666666666667,
|
|
"loss": 4.0559,
|
|
"step": 121000
|
|
},
|
|
{
|
|
"epoch": 45.9,
|
|
"learning_rate": 0.00028555555555555555,
|
|
"learning_rate_embeddings": 0.00028555555555555555,
|
|
"loss": 4.0661,
|
|
"step": 121500
|
|
},
|
|
{
|
|
"epoch": 46.09,
|
|
"learning_rate": 0.0002844444444444444,
|
|
"learning_rate_embeddings": 0.0002844444444444444,
|
|
"loss": 4.0658,
|
|
"step": 122000
|
|
},
|
|
{
|
|
"epoch": 46.28,
|
|
"learning_rate": 0.00028333333333333335,
|
|
"learning_rate_embeddings": 0.00028333333333333335,
|
|
"loss": 4.059,
|
|
"step": 122500
|
|
},
|
|
{
|
|
"epoch": 46.47,
|
|
"learning_rate": 0.00028222222222222223,
|
|
"learning_rate_embeddings": 0.00028222222222222223,
|
|
"loss": 4.0729,
|
|
"step": 123000
|
|
},
|
|
{
|
|
"epoch": 46.66,
|
|
"learning_rate": 0.0002811111111111111,
|
|
"learning_rate_embeddings": 0.0002811111111111111,
|
|
"loss": 4.0742,
|
|
"step": 123500
|
|
},
|
|
{
|
|
"epoch": 46.85,
|
|
"learning_rate": 0.00028000000000000003,
|
|
"learning_rate_embeddings": 0.00028000000000000003,
|
|
"loss": 4.0656,
|
|
"step": 124000
|
|
},
|
|
{
|
|
"epoch": 47.03,
|
|
"learning_rate": 0.0002788888888888889,
|
|
"learning_rate_embeddings": 0.0002788888888888889,
|
|
"loss": 4.0715,
|
|
"step": 124500
|
|
},
|
|
{
|
|
"epoch": 47.22,
|
|
"learning_rate": 0.0002777777777777778,
|
|
"learning_rate_embeddings": 0.0002777777777777778,
|
|
"loss": 4.0537,
|
|
"step": 125000
|
|
},
|
|
{
|
|
"epoch": 47.22,
|
|
"eval_loss": 4.063324451446533,
|
|
"eval_runtime": 269.7975,
|
|
"eval_samples_per_second": 510.042,
|
|
"eval_steps_per_second": 3.988,
|
|
"step": 125000
|
|
},
|
|
{
|
|
"epoch": 47.41,
|
|
"learning_rate": 0.00027666666666666665,
|
|
"learning_rate_embeddings": 0.00027666666666666665,
|
|
"loss": 4.0472,
|
|
"step": 125500
|
|
},
|
|
{
|
|
"epoch": 47.6,
|
|
"learning_rate": 0.0002755555555555556,
|
|
"learning_rate_embeddings": 0.0002755555555555556,
|
|
"loss": 4.0547,
|
|
"step": 126000
|
|
},
|
|
{
|
|
"epoch": 47.79,
|
|
"learning_rate": 0.00027444444444444445,
|
|
"learning_rate_embeddings": 0.00027444444444444445,
|
|
"loss": 4.0718,
|
|
"step": 126500
|
|
},
|
|
{
|
|
"epoch": 47.98,
|
|
"learning_rate": 0.00027333333333333333,
|
|
"learning_rate_embeddings": 0.00027333333333333333,
|
|
"loss": 4.059,
|
|
"step": 127000
|
|
},
|
|
{
|
|
"epoch": 48.17,
|
|
"learning_rate": 0.0002722222222222222,
|
|
"learning_rate_embeddings": 0.0002722222222222222,
|
|
"loss": 4.0521,
|
|
"step": 127500
|
|
},
|
|
{
|
|
"epoch": 48.36,
|
|
"learning_rate": 0.00027111111111111113,
|
|
"learning_rate_embeddings": 0.00027111111111111113,
|
|
"loss": 4.06,
|
|
"step": 128000
|
|
},
|
|
{
|
|
"epoch": 48.55,
|
|
"learning_rate": 0.00027,
|
|
"learning_rate_embeddings": 0.00027,
|
|
"loss": 4.0507,
|
|
"step": 128500
|
|
},
|
|
{
|
|
"epoch": 48.73,
|
|
"learning_rate": 0.00026888888888888893,
|
|
"learning_rate_embeddings": 0.00026888888888888893,
|
|
"loss": 4.0718,
|
|
"step": 129000
|
|
},
|
|
{
|
|
"epoch": 48.92,
|
|
"learning_rate": 0.0002677777777777778,
|
|
"learning_rate_embeddings": 0.0002677777777777778,
|
|
"loss": 4.0568,
|
|
"step": 129500
|
|
},
|
|
{
|
|
"epoch": 49.11,
|
|
"learning_rate": 0.0002666666666666667,
|
|
"learning_rate_embeddings": 0.0002666666666666667,
|
|
"loss": 4.0508,
|
|
"step": 130000
|
|
},
|
|
{
|
|
"epoch": 49.3,
|
|
"learning_rate": 0.00026555555555555555,
|
|
"learning_rate_embeddings": 0.00026555555555555555,
|
|
"loss": 4.0524,
|
|
"step": 130500
|
|
},
|
|
{
|
|
"epoch": 49.49,
|
|
"learning_rate": 0.00026444444444444443,
|
|
"learning_rate_embeddings": 0.00026444444444444443,
|
|
"loss": 4.0545,
|
|
"step": 131000
|
|
},
|
|
{
|
|
"epoch": 49.68,
|
|
"learning_rate": 0.0002633333333333333,
|
|
"learning_rate_embeddings": 0.0002633333333333333,
|
|
"loss": 4.0554,
|
|
"step": 131500
|
|
},
|
|
{
|
|
"epoch": 49.87,
|
|
"learning_rate": 0.00026222222222222223,
|
|
"learning_rate_embeddings": 0.00026222222222222223,
|
|
"loss": 4.0683,
|
|
"step": 132000
|
|
},
|
|
{
|
|
"epoch": 50.06,
|
|
"learning_rate": 0.00026111111111111116,
|
|
"learning_rate_embeddings": 0.00026111111111111116,
|
|
"loss": 4.0632,
|
|
"step": 132500
|
|
},
|
|
{
|
|
"epoch": 50.25,
|
|
"learning_rate": 0.00026000000000000003,
|
|
"learning_rate_embeddings": 0.00026000000000000003,
|
|
"loss": 4.048,
|
|
"step": 133000
|
|
},
|
|
{
|
|
"epoch": 50.43,
|
|
"learning_rate": 0.0002588888888888889,
|
|
"learning_rate_embeddings": 0.0002588888888888889,
|
|
"loss": 4.0552,
|
|
"step": 133500
|
|
},
|
|
{
|
|
"epoch": 50.62,
|
|
"learning_rate": 0.0002577777777777778,
|
|
"learning_rate_embeddings": 0.0002577777777777778,
|
|
"loss": 4.0522,
|
|
"step": 134000
|
|
},
|
|
{
|
|
"epoch": 50.81,
|
|
"learning_rate": 0.00025666666666666665,
|
|
"learning_rate_embeddings": 0.00025666666666666665,
|
|
"loss": 4.0476,
|
|
"step": 134500
|
|
},
|
|
{
|
|
"epoch": 51.0,
|
|
"learning_rate": 0.00025555555555555553,
|
|
"learning_rate_embeddings": 0.00025555555555555553,
|
|
"loss": 4.0654,
|
|
"step": 135000
|
|
},
|
|
{
|
|
"epoch": 51.19,
|
|
"learning_rate": 0.0002544444444444444,
|
|
"learning_rate_embeddings": 0.0002544444444444444,
|
|
"loss": 4.0507,
|
|
"step": 135500
|
|
},
|
|
{
|
|
"epoch": 51.38,
|
|
"learning_rate": 0.0002533333333333334,
|
|
"learning_rate_embeddings": 0.0002533333333333334,
|
|
"loss": 4.066,
|
|
"step": 136000
|
|
},
|
|
{
|
|
"epoch": 51.57,
|
|
"learning_rate": 0.00025222222222222226,
|
|
"learning_rate_embeddings": 0.00025222222222222226,
|
|
"loss": 4.0501,
|
|
"step": 136500
|
|
},
|
|
{
|
|
"epoch": 51.76,
|
|
"learning_rate": 0.00025111111111111113,
|
|
"learning_rate_embeddings": 0.00025111111111111113,
|
|
"loss": 4.0564,
|
|
"step": 137000
|
|
},
|
|
{
|
|
"epoch": 51.95,
|
|
"learning_rate": 0.00025,
|
|
"learning_rate_embeddings": 0.00025,
|
|
"loss": 4.0563,
|
|
"step": 137500
|
|
},
|
|
{
|
|
"epoch": 51.95,
|
|
"eval_loss": 4.050502300262451,
|
|
"eval_runtime": 269.5617,
|
|
"eval_samples_per_second": 510.488,
|
|
"eval_steps_per_second": 3.992,
|
|
"step": 137500
|
|
},
|
|
{
|
|
"epoch": 52.13,
|
|
"learning_rate": 0.0002488888888888889,
|
|
"learning_rate_embeddings": 0.0002488888888888889,
|
|
"loss": 4.0633,
|
|
"step": 138000
|
|
},
|
|
{
|
|
"epoch": 52.32,
|
|
"learning_rate": 0.0002477777777777778,
|
|
"learning_rate_embeddings": 0.0002477777777777778,
|
|
"loss": 4.0484,
|
|
"step": 138500
|
|
},
|
|
{
|
|
"epoch": 52.51,
|
|
"learning_rate": 0.0002466666666666667,
|
|
"learning_rate_embeddings": 0.0002466666666666667,
|
|
"loss": 4.0382,
|
|
"step": 139000
|
|
},
|
|
{
|
|
"epoch": 52.7,
|
|
"learning_rate": 0.00024555555555555556,
|
|
"learning_rate_embeddings": 0.00024555555555555556,
|
|
"loss": 4.0595,
|
|
"step": 139500
|
|
},
|
|
{
|
|
"epoch": 52.89,
|
|
"learning_rate": 0.00024444444444444443,
|
|
"learning_rate_embeddings": 0.00024444444444444443,
|
|
"loss": 4.0507,
|
|
"step": 140000
|
|
},
|
|
{
|
|
"epoch": 53.08,
|
|
"learning_rate": 0.00024333333333333336,
|
|
"learning_rate_embeddings": 0.00024333333333333336,
|
|
"loss": 4.0526,
|
|
"step": 140500
|
|
},
|
|
{
|
|
"epoch": 53.27,
|
|
"learning_rate": 0.00024222222222222223,
|
|
"learning_rate_embeddings": 0.00024222222222222223,
|
|
"loss": 4.0424,
|
|
"step": 141000
|
|
},
|
|
{
|
|
"epoch": 53.46,
|
|
"learning_rate": 0.0002411111111111111,
|
|
"learning_rate_embeddings": 0.0002411111111111111,
|
|
"loss": 4.0573,
|
|
"step": 141500
|
|
},
|
|
{
|
|
"epoch": 53.65,
|
|
"learning_rate": 0.00024,
|
|
"learning_rate_embeddings": 0.00024,
|
|
"loss": 4.0437,
|
|
"step": 142000
|
|
},
|
|
{
|
|
"epoch": 53.83,
|
|
"learning_rate": 0.0002388888888888889,
|
|
"learning_rate_embeddings": 0.0002388888888888889,
|
|
"loss": 4.0511,
|
|
"step": 142500
|
|
},
|
|
{
|
|
"epoch": 54.02,
|
|
"learning_rate": 0.00023777777777777778,
|
|
"learning_rate_embeddings": 0.00023777777777777778,
|
|
"loss": 4.0741,
|
|
"step": 143000
|
|
},
|
|
{
|
|
"epoch": 54.21,
|
|
"learning_rate": 0.00023666666666666668,
|
|
"learning_rate_embeddings": 0.00023666666666666668,
|
|
"loss": 4.0365,
|
|
"step": 143500
|
|
},
|
|
{
|
|
"epoch": 54.4,
|
|
"learning_rate": 0.00023555555555555556,
|
|
"learning_rate_embeddings": 0.00023555555555555556,
|
|
"loss": 4.0556,
|
|
"step": 144000
|
|
},
|
|
{
|
|
"epoch": 54.59,
|
|
"learning_rate": 0.00023444444444444446,
|
|
"learning_rate_embeddings": 0.00023444444444444446,
|
|
"loss": 4.049,
|
|
"step": 144500
|
|
},
|
|
{
|
|
"epoch": 54.78,
|
|
"learning_rate": 0.00023333333333333333,
|
|
"learning_rate_embeddings": 0.00023333333333333333,
|
|
"loss": 4.0608,
|
|
"step": 145000
|
|
},
|
|
{
|
|
"epoch": 54.97,
|
|
"learning_rate": 0.00023222222222222223,
|
|
"learning_rate_embeddings": 0.00023222222222222223,
|
|
"loss": 4.0481,
|
|
"step": 145500
|
|
},
|
|
{
|
|
"epoch": 55.16,
|
|
"learning_rate": 0.0002311111111111111,
|
|
"learning_rate_embeddings": 0.0002311111111111111,
|
|
"loss": 4.043,
|
|
"step": 146000
|
|
},
|
|
{
|
|
"epoch": 55.35,
|
|
"learning_rate": 0.00023,
|
|
"learning_rate_embeddings": 0.00023,
|
|
"loss": 4.0517,
|
|
"step": 146500
|
|
},
|
|
{
|
|
"epoch": 55.53,
|
|
"learning_rate": 0.0002288888888888889,
|
|
"learning_rate_embeddings": 0.0002288888888888889,
|
|
"loss": 4.0379,
|
|
"step": 147000
|
|
},
|
|
{
|
|
"epoch": 55.72,
|
|
"learning_rate": 0.00022777777777777778,
|
|
"learning_rate_embeddings": 0.00022777777777777778,
|
|
"loss": 4.0539,
|
|
"step": 147500
|
|
},
|
|
{
|
|
"epoch": 55.91,
|
|
"learning_rate": 0.00022666666666666666,
|
|
"learning_rate_embeddings": 0.00022666666666666666,
|
|
"loss": 4.0455,
|
|
"step": 148000
|
|
},
|
|
{
|
|
"epoch": 56.1,
|
|
"learning_rate": 0.00022555555555555556,
|
|
"learning_rate_embeddings": 0.00022555555555555556,
|
|
"loss": 4.0398,
|
|
"step": 148500
|
|
},
|
|
{
|
|
"epoch": 56.29,
|
|
"learning_rate": 0.00022444444444444446,
|
|
"learning_rate_embeddings": 0.00022444444444444446,
|
|
"loss": 4.0351,
|
|
"step": 149000
|
|
},
|
|
{
|
|
"epoch": 56.48,
|
|
"learning_rate": 0.00022333333333333333,
|
|
"learning_rate_embeddings": 0.00022333333333333333,
|
|
"loss": 4.0416,
|
|
"step": 149500
|
|
},
|
|
{
|
|
"epoch": 56.67,
|
|
"learning_rate": 0.0002222222222222222,
|
|
"learning_rate_embeddings": 0.0002222222222222222,
|
|
"loss": 4.0389,
|
|
"step": 150000
|
|
},
|
|
{
|
|
"epoch": 56.67,
|
|
"eval_loss": 4.0507025718688965,
|
|
"eval_runtime": 269.9078,
|
|
"eval_samples_per_second": 509.833,
|
|
"eval_steps_per_second": 3.987,
|
|
"step": 150000
|
|
},
|
|
{
|
|
"epoch": 56.86,
|
|
"learning_rate": 0.00022111111111111113,
|
|
"learning_rate_embeddings": 0.00022111111111111113,
|
|
"loss": 4.0423,
|
|
"step": 150500
|
|
},
|
|
{
|
|
"epoch": 57.05,
|
|
"learning_rate": 0.00022,
|
|
"learning_rate_embeddings": 0.00022,
|
|
"loss": 4.0604,
|
|
"step": 151000
|
|
},
|
|
{
|
|
"epoch": 57.23,
|
|
"learning_rate": 0.00021888888888888888,
|
|
"learning_rate_embeddings": 0.00021888888888888888,
|
|
"loss": 4.0387,
|
|
"step": 151500
|
|
},
|
|
{
|
|
"epoch": 57.42,
|
|
"learning_rate": 0.00021777777777777776,
|
|
"learning_rate_embeddings": 0.00021777777777777776,
|
|
"loss": 4.0399,
|
|
"step": 152000
|
|
},
|
|
{
|
|
"epoch": 57.61,
|
|
"learning_rate": 0.00021666666666666668,
|
|
"learning_rate_embeddings": 0.00021666666666666668,
|
|
"loss": 4.0408,
|
|
"step": 152500
|
|
},
|
|
{
|
|
"epoch": 57.8,
|
|
"learning_rate": 0.00021555555555555556,
|
|
"learning_rate_embeddings": 0.00021555555555555556,
|
|
"loss": 4.0584,
|
|
"step": 153000
|
|
},
|
|
{
|
|
"epoch": 57.99,
|
|
"learning_rate": 0.00021444444444444443,
|
|
"learning_rate_embeddings": 0.00021444444444444443,
|
|
"loss": 4.0396,
|
|
"step": 153500
|
|
},
|
|
{
|
|
"epoch": 58.18,
|
|
"learning_rate": 0.00021333333333333336,
|
|
"learning_rate_embeddings": 0.00021333333333333336,
|
|
"loss": 4.0255,
|
|
"step": 154000
|
|
},
|
|
{
|
|
"epoch": 58.37,
|
|
"learning_rate": 0.00021222222222222223,
|
|
"learning_rate_embeddings": 0.00021222222222222223,
|
|
"loss": 4.0194,
|
|
"step": 154500
|
|
},
|
|
{
|
|
"epoch": 58.56,
|
|
"learning_rate": 0.0002111111111111111,
|
|
"learning_rate_embeddings": 0.0002111111111111111,
|
|
"loss": 4.0365,
|
|
"step": 155000
|
|
},
|
|
{
|
|
"epoch": 58.75,
|
|
"learning_rate": 0.00021,
|
|
"learning_rate_embeddings": 0.00021,
|
|
"loss": 4.0507,
|
|
"step": 155500
|
|
},
|
|
{
|
|
"epoch": 58.93,
|
|
"learning_rate": 0.0002088888888888889,
|
|
"learning_rate_embeddings": 0.0002088888888888889,
|
|
"loss": 4.0364,
|
|
"step": 156000
|
|
},
|
|
{
|
|
"epoch": 59.12,
|
|
"learning_rate": 0.00020777777777777778,
|
|
"learning_rate_embeddings": 0.00020777777777777778,
|
|
"loss": 4.0323,
|
|
"step": 156500
|
|
},
|
|
{
|
|
"epoch": 59.31,
|
|
"learning_rate": 0.00020666666666666666,
|
|
"learning_rate_embeddings": 0.00020666666666666666,
|
|
"loss": 4.0479,
|
|
"step": 157000
|
|
},
|
|
{
|
|
"epoch": 59.5,
|
|
"learning_rate": 0.00020555555555555556,
|
|
"learning_rate_embeddings": 0.00020555555555555556,
|
|
"loss": 4.0357,
|
|
"step": 157500
|
|
},
|
|
{
|
|
"epoch": 59.69,
|
|
"learning_rate": 0.00020444444444444446,
|
|
"learning_rate_embeddings": 0.00020444444444444446,
|
|
"loss": 4.0317,
|
|
"step": 158000
|
|
},
|
|
{
|
|
"epoch": 59.88,
|
|
"learning_rate": 0.00020333333333333333,
|
|
"learning_rate_embeddings": 0.00020333333333333333,
|
|
"loss": 4.0436,
|
|
"step": 158500
|
|
},
|
|
{
|
|
"epoch": 60.07,
|
|
"learning_rate": 0.00020222222222222223,
|
|
"learning_rate_embeddings": 0.00020222222222222223,
|
|
"loss": 4.0551,
|
|
"step": 159000
|
|
},
|
|
{
|
|
"epoch": 60.26,
|
|
"learning_rate": 0.0002011111111111111,
|
|
"learning_rate_embeddings": 0.0002011111111111111,
|
|
"loss": 4.0356,
|
|
"step": 159500
|
|
},
|
|
{
|
|
"epoch": 60.45,
|
|
"learning_rate": 0.0002,
|
|
"learning_rate_embeddings": 0.0002,
|
|
"loss": 4.0266,
|
|
"step": 160000
|
|
},
|
|
{
|
|
"epoch": 60.63,
|
|
"learning_rate": 0.00019888888888888888,
|
|
"learning_rate_embeddings": 0.00019888888888888888,
|
|
"loss": 4.0471,
|
|
"step": 160500
|
|
},
|
|
{
|
|
"epoch": 60.82,
|
|
"learning_rate": 0.00019777777777777778,
|
|
"learning_rate_embeddings": 0.00019777777777777778,
|
|
"loss": 4.0369,
|
|
"step": 161000
|
|
},
|
|
{
|
|
"epoch": 61.01,
|
|
"learning_rate": 0.00019666666666666666,
|
|
"learning_rate_embeddings": 0.00019666666666666666,
|
|
"loss": 4.024,
|
|
"step": 161500
|
|
},
|
|
{
|
|
"epoch": 61.2,
|
|
"learning_rate": 0.00019555555555555556,
|
|
"learning_rate_embeddings": 0.00019555555555555556,
|
|
"loss": 4.013,
|
|
"step": 162000
|
|
},
|
|
{
|
|
"epoch": 61.39,
|
|
"learning_rate": 0.00019444444444444446,
|
|
"learning_rate_embeddings": 0.00019444444444444446,
|
|
"loss": 4.0339,
|
|
"step": 162500
|
|
},
|
|
{
|
|
"epoch": 61.39,
|
|
"eval_loss": 4.042232036590576,
|
|
"eval_runtime": 269.5303,
|
|
"eval_samples_per_second": 510.547,
|
|
"eval_steps_per_second": 3.992,
|
|
"step": 162500
|
|
},
|
|
{
|
|
"epoch": 61.58,
|
|
"learning_rate": 0.00019333333333333333,
|
|
"learning_rate_embeddings": 0.00019333333333333333,
|
|
"loss": 4.0214,
|
|
"step": 163000
|
|
},
|
|
{
|
|
"epoch": 61.77,
|
|
"learning_rate": 0.0001922222222222222,
|
|
"learning_rate_embeddings": 0.0001922222222222222,
|
|
"loss": 4.0539,
|
|
"step": 163500
|
|
},
|
|
{
|
|
"epoch": 61.96,
|
|
"learning_rate": 0.00019111111111111114,
|
|
"learning_rate_embeddings": 0.00019111111111111114,
|
|
"loss": 4.0385,
|
|
"step": 164000
|
|
},
|
|
{
|
|
"epoch": 62.15,
|
|
"learning_rate": 0.00019,
|
|
"learning_rate_embeddings": 0.00019,
|
|
"loss": 4.0264,
|
|
"step": 164500
|
|
},
|
|
{
|
|
"epoch": 62.33,
|
|
"learning_rate": 0.00018888888888888888,
|
|
"learning_rate_embeddings": 0.00018888888888888888,
|
|
"loss": 4.0302,
|
|
"step": 165000
|
|
},
|
|
{
|
|
"epoch": 62.52,
|
|
"learning_rate": 0.00018777777777777776,
|
|
"learning_rate_embeddings": 0.00018777777777777776,
|
|
"loss": 4.0257,
|
|
"step": 165500
|
|
},
|
|
{
|
|
"epoch": 62.71,
|
|
"learning_rate": 0.0001866666666666667,
|
|
"learning_rate_embeddings": 0.0001866666666666667,
|
|
"loss": 4.0356,
|
|
"step": 166000
|
|
},
|
|
{
|
|
"epoch": 62.9,
|
|
"learning_rate": 0.00018555555555555556,
|
|
"learning_rate_embeddings": 0.00018555555555555556,
|
|
"loss": 4.0381,
|
|
"step": 166500
|
|
},
|
|
{
|
|
"epoch": 63.09,
|
|
"learning_rate": 0.00018444444444444443,
|
|
"learning_rate_embeddings": 0.00018444444444444443,
|
|
"loss": 4.0286,
|
|
"step": 167000
|
|
},
|
|
{
|
|
"epoch": 63.28,
|
|
"learning_rate": 0.00018333333333333334,
|
|
"learning_rate_embeddings": 0.00018333333333333334,
|
|
"loss": 4.022,
|
|
"step": 167500
|
|
},
|
|
{
|
|
"epoch": 63.47,
|
|
"learning_rate": 0.00018222222222222224,
|
|
"learning_rate_embeddings": 0.00018222222222222224,
|
|
"loss": 4.0298,
|
|
"step": 168000
|
|
},
|
|
{
|
|
"epoch": 63.66,
|
|
"learning_rate": 0.0001811111111111111,
|
|
"learning_rate_embeddings": 0.0001811111111111111,
|
|
"loss": 4.0216,
|
|
"step": 168500
|
|
},
|
|
{
|
|
"epoch": 63.85,
|
|
"learning_rate": 0.00017999999999999998,
|
|
"learning_rate_embeddings": 0.00017999999999999998,
|
|
"loss": 4.0245,
|
|
"step": 169000
|
|
},
|
|
{
|
|
"epoch": 64.03,
|
|
"learning_rate": 0.00017888888888888889,
|
|
"learning_rate_embeddings": 0.00017888888888888889,
|
|
"loss": 4.0289,
|
|
"step": 169500
|
|
},
|
|
{
|
|
"epoch": 64.22,
|
|
"learning_rate": 0.00017777777777777779,
|
|
"learning_rate_embeddings": 0.00017777777777777779,
|
|
"loss": 4.0136,
|
|
"step": 170000
|
|
},
|
|
{
|
|
"epoch": 64.41,
|
|
"learning_rate": 0.00017666666666666666,
|
|
"learning_rate_embeddings": 0.00017666666666666666,
|
|
"loss": 4.0294,
|
|
"step": 170500
|
|
},
|
|
{
|
|
"epoch": 64.6,
|
|
"learning_rate": 0.00017555555555555556,
|
|
"learning_rate_embeddings": 0.00017555555555555556,
|
|
"loss": 4.0346,
|
|
"step": 171000
|
|
},
|
|
{
|
|
"epoch": 64.79,
|
|
"learning_rate": 0.00017444444444444446,
|
|
"learning_rate_embeddings": 0.00017444444444444446,
|
|
"loss": 4.0293,
|
|
"step": 171500
|
|
},
|
|
{
|
|
"epoch": 64.98,
|
|
"learning_rate": 0.00017333333333333334,
|
|
"learning_rate_embeddings": 0.00017333333333333334,
|
|
"loss": 4.0304,
|
|
"step": 172000
|
|
},
|
|
{
|
|
"epoch": 65.17,
|
|
"learning_rate": 0.00017222222222222224,
|
|
"learning_rate_embeddings": 0.00017222222222222224,
|
|
"loss": 4.0282,
|
|
"step": 172500
|
|
},
|
|
{
|
|
"epoch": 65.36,
|
|
"learning_rate": 0.0001711111111111111,
|
|
"learning_rate_embeddings": 0.0001711111111111111,
|
|
"loss": 4.0101,
|
|
"step": 173000
|
|
},
|
|
{
|
|
"epoch": 65.55,
|
|
"learning_rate": 0.00017,
|
|
"learning_rate_embeddings": 0.00017,
|
|
"loss": 4.0292,
|
|
"step": 173500
|
|
},
|
|
{
|
|
"epoch": 65.73,
|
|
"learning_rate": 0.00016888888888888889,
|
|
"learning_rate_embeddings": 0.00016888888888888889,
|
|
"loss": 4.0291,
|
|
"step": 174000
|
|
},
|
|
{
|
|
"epoch": 65.92,
|
|
"learning_rate": 0.0001677777777777778,
|
|
"learning_rate_embeddings": 0.0001677777777777778,
|
|
"loss": 4.0259,
|
|
"step": 174500
|
|
},
|
|
{
|
|
"epoch": 66.11,
|
|
"learning_rate": 0.00016666666666666666,
|
|
"learning_rate_embeddings": 0.00016666666666666666,
|
|
"loss": 4.0247,
|
|
"step": 175000
|
|
},
|
|
{
|
|
"epoch": 66.11,
|
|
"eval_loss": 4.03872013092041,
|
|
"eval_runtime": 269.6426,
|
|
"eval_samples_per_second": 510.335,
|
|
"eval_steps_per_second": 3.99,
|
|
"step": 175000
|
|
},
|
|
{
|
|
"epoch": 66.3,
|
|
"learning_rate": 0.00016555555555555556,
|
|
"learning_rate_embeddings": 0.00016555555555555556,
|
|
"loss": 4.0198,
|
|
"step": 175500
|
|
},
|
|
{
|
|
"epoch": 66.49,
|
|
"learning_rate": 0.00016444444444444446,
|
|
"learning_rate_embeddings": 0.00016444444444444446,
|
|
"loss": 4.0141,
|
|
"step": 176000
|
|
},
|
|
{
|
|
"epoch": 66.68,
|
|
"learning_rate": 0.00016333333333333334,
|
|
"learning_rate_embeddings": 0.00016333333333333334,
|
|
"loss": 4.0245,
|
|
"step": 176500
|
|
},
|
|
{
|
|
"epoch": 66.87,
|
|
"learning_rate": 0.0001622222222222222,
|
|
"learning_rate_embeddings": 0.0001622222222222222,
|
|
"loss": 4.027,
|
|
"step": 177000
|
|
},
|
|
{
|
|
"epoch": 67.06,
|
|
"learning_rate": 0.0001611111111111111,
|
|
"learning_rate_embeddings": 0.0001611111111111111,
|
|
"loss": 4.0268,
|
|
"step": 177500
|
|
},
|
|
{
|
|
"epoch": 67.25,
|
|
"learning_rate": 0.00016,
|
|
"learning_rate_embeddings": 0.00016,
|
|
"loss": 4.0055,
|
|
"step": 178000
|
|
},
|
|
{
|
|
"epoch": 67.43,
|
|
"learning_rate": 0.0001588888888888889,
|
|
"learning_rate_embeddings": 0.0001588888888888889,
|
|
"loss": 4.0282,
|
|
"step": 178500
|
|
},
|
|
{
|
|
"epoch": 67.62,
|
|
"learning_rate": 0.00015777777777777776,
|
|
"learning_rate_embeddings": 0.00015777777777777776,
|
|
"loss": 4.0292,
|
|
"step": 179000
|
|
},
|
|
{
|
|
"epoch": 67.81,
|
|
"learning_rate": 0.0001566666666666667,
|
|
"learning_rate_embeddings": 0.0001566666666666667,
|
|
"loss": 4.0215,
|
|
"step": 179500
|
|
},
|
|
{
|
|
"epoch": 68.0,
|
|
"learning_rate": 0.00015555555555555556,
|
|
"learning_rate_embeddings": 0.00015555555555555556,
|
|
"loss": 4.0364,
|
|
"step": 180000
|
|
},
|
|
{
|
|
"epoch": 68.19,
|
|
"learning_rate": 0.00015444444444444444,
|
|
"learning_rate_embeddings": 0.00015444444444444444,
|
|
"loss": 4.0157,
|
|
"step": 180500
|
|
},
|
|
{
|
|
"epoch": 68.38,
|
|
"learning_rate": 0.00015333333333333334,
|
|
"learning_rate_embeddings": 0.00015333333333333334,
|
|
"loss": 4.0205,
|
|
"step": 181000
|
|
},
|
|
{
|
|
"epoch": 68.57,
|
|
"learning_rate": 0.00015222222222222224,
|
|
"learning_rate_embeddings": 0.00015222222222222224,
|
|
"loss": 4.0136,
|
|
"step": 181500
|
|
},
|
|
{
|
|
"epoch": 68.76,
|
|
"learning_rate": 0.0001511111111111111,
|
|
"learning_rate_embeddings": 0.0001511111111111111,
|
|
"loss": 4.0226,
|
|
"step": 182000
|
|
},
|
|
{
|
|
"epoch": 68.95,
|
|
"learning_rate": 0.00015,
|
|
"learning_rate_embeddings": 0.00015,
|
|
"loss": 4.0217,
|
|
"step": 182500
|
|
},
|
|
{
|
|
"epoch": 69.13,
|
|
"learning_rate": 0.0001488888888888889,
|
|
"learning_rate_embeddings": 0.0001488888888888889,
|
|
"loss": 4.0101,
|
|
"step": 183000
|
|
},
|
|
{
|
|
"epoch": 69.32,
|
|
"learning_rate": 0.0001477777777777778,
|
|
"learning_rate_embeddings": 0.0001477777777777778,
|
|
"loss": 4.0054,
|
|
"step": 183500
|
|
},
|
|
{
|
|
"epoch": 69.51,
|
|
"learning_rate": 0.00014666666666666666,
|
|
"learning_rate_embeddings": 0.00014666666666666666,
|
|
"loss": 4.0075,
|
|
"step": 184000
|
|
},
|
|
{
|
|
"epoch": 69.7,
|
|
"learning_rate": 0.00014555555555555556,
|
|
"learning_rate_embeddings": 0.00014555555555555556,
|
|
"loss": 4.0137,
|
|
"step": 184500
|
|
},
|
|
{
|
|
"epoch": 69.89,
|
|
"learning_rate": 0.00014444444444444444,
|
|
"learning_rate_embeddings": 0.00014444444444444444,
|
|
"loss": 4.0247,
|
|
"step": 185000
|
|
},
|
|
{
|
|
"epoch": 70.08,
|
|
"learning_rate": 0.00014333333333333334,
|
|
"learning_rate_embeddings": 0.00014333333333333334,
|
|
"loss": 4.0115,
|
|
"step": 185500
|
|
},
|
|
{
|
|
"epoch": 70.27,
|
|
"learning_rate": 0.0001422222222222222,
|
|
"learning_rate_embeddings": 0.0001422222222222222,
|
|
"loss": 4.0153,
|
|
"step": 186000
|
|
},
|
|
{
|
|
"epoch": 70.46,
|
|
"learning_rate": 0.00014111111111111111,
|
|
"learning_rate_embeddings": 0.00014111111111111111,
|
|
"loss": 4.0207,
|
|
"step": 186500
|
|
},
|
|
{
|
|
"epoch": 70.65,
|
|
"learning_rate": 0.00014000000000000001,
|
|
"learning_rate_embeddings": 0.00014000000000000001,
|
|
"loss": 4.0009,
|
|
"step": 187000
|
|
},
|
|
{
|
|
"epoch": 70.83,
|
|
"learning_rate": 0.0001388888888888889,
|
|
"learning_rate_embeddings": 0.0001388888888888889,
|
|
"loss": 4.0133,
|
|
"step": 187500
|
|
},
|
|
{
|
|
"epoch": 70.83,
|
|
"eval_loss": 4.023904800415039,
|
|
"eval_runtime": 269.722,
|
|
"eval_samples_per_second": 510.184,
|
|
"eval_steps_per_second": 3.989,
|
|
"step": 187500
|
|
},
|
|
{
|
|
"epoch": 71.02,
|
|
"learning_rate": 0.0001377777777777778,
|
|
"learning_rate_embeddings": 0.0001377777777777778,
|
|
"loss": 4.0278,
|
|
"step": 188000
|
|
},
|
|
{
|
|
"epoch": 71.21,
|
|
"learning_rate": 0.00013666666666666666,
|
|
"learning_rate_embeddings": 0.00013666666666666666,
|
|
"loss": 3.9994,
|
|
"step": 188500
|
|
},
|
|
{
|
|
"epoch": 71.4,
|
|
"learning_rate": 0.00013555555555555556,
|
|
"learning_rate_embeddings": 0.00013555555555555556,
|
|
"loss": 4.0092,
|
|
"step": 189000
|
|
},
|
|
{
|
|
"epoch": 71.59,
|
|
"learning_rate": 0.00013444444444444447,
|
|
"learning_rate_embeddings": 0.00013444444444444447,
|
|
"loss": 4.0133,
|
|
"step": 189500
|
|
},
|
|
{
|
|
"epoch": 71.78,
|
|
"learning_rate": 0.00013333333333333334,
|
|
"learning_rate_embeddings": 0.00013333333333333334,
|
|
"loss": 4.0082,
|
|
"step": 190000
|
|
},
|
|
{
|
|
"epoch": 71.97,
|
|
"learning_rate": 0.00013222222222222221,
|
|
"learning_rate_embeddings": 0.00013222222222222221,
|
|
"loss": 4.0107,
|
|
"step": 190500
|
|
},
|
|
{
|
|
"epoch": 72.16,
|
|
"learning_rate": 0.00013111111111111111,
|
|
"learning_rate_embeddings": 0.00013111111111111111,
|
|
"loss": 4.0158,
|
|
"step": 191000
|
|
},
|
|
{
|
|
"epoch": 72.35,
|
|
"learning_rate": 0.00013000000000000002,
|
|
"learning_rate_embeddings": 0.00013000000000000002,
|
|
"loss": 3.9984,
|
|
"step": 191500
|
|
},
|
|
{
|
|
"epoch": 72.53,
|
|
"learning_rate": 0.0001288888888888889,
|
|
"learning_rate_embeddings": 0.0001288888888888889,
|
|
"loss": 3.9959,
|
|
"step": 192000
|
|
},
|
|
{
|
|
"epoch": 72.72,
|
|
"learning_rate": 0.00012777777777777776,
|
|
"learning_rate_embeddings": 0.00012777777777777776,
|
|
"loss": 4.0023,
|
|
"step": 192500
|
|
},
|
|
{
|
|
"epoch": 72.91,
|
|
"learning_rate": 0.0001266666666666667,
|
|
"learning_rate_embeddings": 0.0001266666666666667,
|
|
"loss": 4.0095,
|
|
"step": 193000
|
|
},
|
|
{
|
|
"epoch": 73.1,
|
|
"learning_rate": 0.00012555555555555557,
|
|
"learning_rate_embeddings": 0.00012555555555555557,
|
|
"loss": 4.008,
|
|
"step": 193500
|
|
},
|
|
{
|
|
"epoch": 73.29,
|
|
"learning_rate": 0.00012444444444444444,
|
|
"learning_rate_embeddings": 0.00012444444444444444,
|
|
"loss": 4.0049,
|
|
"step": 194000
|
|
},
|
|
{
|
|
"epoch": 73.48,
|
|
"learning_rate": 0.00012333333333333334,
|
|
"learning_rate_embeddings": 0.00012333333333333334,
|
|
"loss": 4.0155,
|
|
"step": 194500
|
|
},
|
|
{
|
|
"epoch": 73.67,
|
|
"learning_rate": 0.00012222222222222221,
|
|
"learning_rate_embeddings": 0.00012222222222222221,
|
|
"loss": 4.0208,
|
|
"step": 195000
|
|
},
|
|
{
|
|
"epoch": 73.86,
|
|
"learning_rate": 0.00012111111111111112,
|
|
"learning_rate_embeddings": 0.00012111111111111112,
|
|
"loss": 4.0103,
|
|
"step": 195500
|
|
},
|
|
{
|
|
"epoch": 74.05,
|
|
"learning_rate": 0.00012,
|
|
"learning_rate_embeddings": 0.00012,
|
|
"loss": 4.0042,
|
|
"step": 196000
|
|
},
|
|
{
|
|
"epoch": 74.23,
|
|
"learning_rate": 0.00011888888888888889,
|
|
"learning_rate_embeddings": 0.00011888888888888889,
|
|
"loss": 3.9992,
|
|
"step": 196500
|
|
},
|
|
{
|
|
"epoch": 74.42,
|
|
"learning_rate": 0.00011777777777777778,
|
|
"learning_rate_embeddings": 0.00011777777777777778,
|
|
"loss": 4.0015,
|
|
"step": 197000
|
|
},
|
|
{
|
|
"epoch": 74.61,
|
|
"learning_rate": 0.00011666666666666667,
|
|
"learning_rate_embeddings": 0.00011666666666666667,
|
|
"loss": 3.9968,
|
|
"step": 197500
|
|
},
|
|
{
|
|
"epoch": 74.8,
|
|
"learning_rate": 0.00011555555555555555,
|
|
"learning_rate_embeddings": 0.00011555555555555555,
|
|
"loss": 4.0005,
|
|
"step": 198000
|
|
},
|
|
{
|
|
"epoch": 74.99,
|
|
"learning_rate": 0.00011444444444444445,
|
|
"learning_rate_embeddings": 0.00011444444444444445,
|
|
"loss": 4.0039,
|
|
"step": 198500
|
|
},
|
|
{
|
|
"epoch": 75.18,
|
|
"learning_rate": 0.00011333333333333333,
|
|
"learning_rate_embeddings": 0.00011333333333333333,
|
|
"loss": 4.0087,
|
|
"step": 199000
|
|
},
|
|
{
|
|
"epoch": 75.37,
|
|
"learning_rate": 0.00011222222222222223,
|
|
"learning_rate_embeddings": 0.00011222222222222223,
|
|
"loss": 3.9911,
|
|
"step": 199500
|
|
},
|
|
{
|
|
"epoch": 75.56,
|
|
"learning_rate": 0.0001111111111111111,
|
|
"learning_rate_embeddings": 0.0001111111111111111,
|
|
"loss": 3.985,
|
|
"step": 200000
|
|
},
|
|
{
|
|
"epoch": 75.56,
|
|
"eval_loss": 4.020562171936035,
|
|
"eval_runtime": 269.5776,
|
|
"eval_samples_per_second": 510.458,
|
|
"eval_steps_per_second": 3.991,
|
|
"step": 200000
|
|
},
|
|
{
|
|
"epoch": 75.75,
|
|
"learning_rate": 0.00011,
|
|
"learning_rate_embeddings": 0.00011,
|
|
"loss": 4.0027,
|
|
"step": 200500
|
|
},
|
|
{
|
|
"epoch": 75.93,
|
|
"learning_rate": 0.00010888888888888888,
|
|
"learning_rate_embeddings": 0.00010888888888888888,
|
|
"loss": 4.0072,
|
|
"step": 201000
|
|
},
|
|
{
|
|
"epoch": 76.12,
|
|
"learning_rate": 0.00010777777777777778,
|
|
"learning_rate_embeddings": 0.00010777777777777778,
|
|
"loss": 4.0027,
|
|
"step": 201500
|
|
},
|
|
{
|
|
"epoch": 76.31,
|
|
"learning_rate": 0.00010666666666666668,
|
|
"learning_rate_embeddings": 0.00010666666666666668,
|
|
"loss": 3.9902,
|
|
"step": 202000
|
|
},
|
|
{
|
|
"epoch": 76.5,
|
|
"learning_rate": 0.00010555555555555555,
|
|
"learning_rate_embeddings": 0.00010555555555555555,
|
|
"loss": 4.0075,
|
|
"step": 202500
|
|
},
|
|
{
|
|
"epoch": 76.69,
|
|
"learning_rate": 0.00010444444444444445,
|
|
"learning_rate_embeddings": 0.00010444444444444445,
|
|
"loss": 4.0011,
|
|
"step": 203000
|
|
},
|
|
{
|
|
"epoch": 76.88,
|
|
"learning_rate": 0.00010333333333333333,
|
|
"learning_rate_embeddings": 0.00010333333333333333,
|
|
"loss": 4.0036,
|
|
"step": 203500
|
|
},
|
|
{
|
|
"epoch": 77.07,
|
|
"learning_rate": 0.00010222222222222223,
|
|
"learning_rate_embeddings": 0.00010222222222222223,
|
|
"loss": 3.9961,
|
|
"step": 204000
|
|
},
|
|
{
|
|
"epoch": 77.26,
|
|
"learning_rate": 0.00010111111111111112,
|
|
"learning_rate_embeddings": 0.00010111111111111112,
|
|
"loss": 4.0024,
|
|
"step": 204500
|
|
},
|
|
{
|
|
"epoch": 77.45,
|
|
"learning_rate": 0.0001,
|
|
"learning_rate_embeddings": 0.0001,
|
|
"loss": 4.001,
|
|
"step": 205000
|
|
},
|
|
{
|
|
"epoch": 77.63,
|
|
"learning_rate": 9.888888888888889e-05,
|
|
"learning_rate_embeddings": 9.888888888888889e-05,
|
|
"loss": 3.993,
|
|
"step": 205500
|
|
},
|
|
{
|
|
"epoch": 77.82,
|
|
"learning_rate": 9.777777777777778e-05,
|
|
"learning_rate_embeddings": 9.777777777777778e-05,
|
|
"loss": 3.9979,
|
|
"step": 206000
|
|
},
|
|
{
|
|
"epoch": 78.01,
|
|
"learning_rate": 9.666666666666667e-05,
|
|
"learning_rate_embeddings": 9.666666666666667e-05,
|
|
"loss": 3.9951,
|
|
"step": 206500
|
|
},
|
|
{
|
|
"epoch": 78.2,
|
|
"learning_rate": 9.555555555555557e-05,
|
|
"learning_rate_embeddings": 9.555555555555557e-05,
|
|
"loss": 3.9878,
|
|
"step": 207000
|
|
},
|
|
{
|
|
"epoch": 78.39,
|
|
"learning_rate": 9.444444444444444e-05,
|
|
"learning_rate_embeddings": 9.444444444444444e-05,
|
|
"loss": 3.9914,
|
|
"step": 207500
|
|
},
|
|
{
|
|
"epoch": 78.58,
|
|
"learning_rate": 9.333333333333334e-05,
|
|
"learning_rate_embeddings": 9.333333333333334e-05,
|
|
"loss": 3.9925,
|
|
"step": 208000
|
|
},
|
|
{
|
|
"epoch": 78.77,
|
|
"learning_rate": 9.222222222222222e-05,
|
|
"learning_rate_embeddings": 9.222222222222222e-05,
|
|
"loss": 3.9918,
|
|
"step": 208500
|
|
},
|
|
{
|
|
"epoch": 78.96,
|
|
"learning_rate": 9.111111111111112e-05,
|
|
"learning_rate_embeddings": 9.111111111111112e-05,
|
|
"loss": 3.9941,
|
|
"step": 209000
|
|
},
|
|
{
|
|
"epoch": 79.15,
|
|
"learning_rate": 8.999999999999999e-05,
|
|
"learning_rate_embeddings": 8.999999999999999e-05,
|
|
"loss": 3.9963,
|
|
"step": 209500
|
|
},
|
|
{
|
|
"epoch": 79.34,
|
|
"learning_rate": 8.888888888888889e-05,
|
|
"learning_rate_embeddings": 8.888888888888889e-05,
|
|
"loss": 3.9953,
|
|
"step": 210000
|
|
},
|
|
{
|
|
"epoch": 79.52,
|
|
"learning_rate": 8.777777777777778e-05,
|
|
"learning_rate_embeddings": 8.777777777777778e-05,
|
|
"loss": 3.9942,
|
|
"step": 210500
|
|
},
|
|
{
|
|
"epoch": 79.71,
|
|
"learning_rate": 8.666666666666667e-05,
|
|
"learning_rate_embeddings": 8.666666666666667e-05,
|
|
"loss": 3.9881,
|
|
"step": 211000
|
|
},
|
|
{
|
|
"epoch": 79.9,
|
|
"learning_rate": 8.555555555555556e-05,
|
|
"learning_rate_embeddings": 8.555555555555556e-05,
|
|
"loss": 3.9949,
|
|
"step": 211500
|
|
},
|
|
{
|
|
"epoch": 80.09,
|
|
"learning_rate": 8.444444444444444e-05,
|
|
"learning_rate_embeddings": 8.444444444444444e-05,
|
|
"loss": 3.988,
|
|
"step": 212000
|
|
},
|
|
{
|
|
"epoch": 80.28,
|
|
"learning_rate": 8.333333333333333e-05,
|
|
"learning_rate_embeddings": 8.333333333333333e-05,
|
|
"loss": 3.9783,
|
|
"step": 212500
|
|
},
|
|
{
|
|
"epoch": 80.28,
|
|
"eval_loss": 4.009425640106201,
|
|
"eval_runtime": 269.8554,
|
|
"eval_samples_per_second": 509.932,
|
|
"eval_steps_per_second": 3.987,
|
|
"step": 212500
|
|
},
|
|
{
|
|
"epoch": 80.47,
|
|
"learning_rate": 8.222222222222223e-05,
|
|
"learning_rate_embeddings": 8.222222222222223e-05,
|
|
"loss": 3.9753,
|
|
"step": 213000
|
|
},
|
|
{
|
|
"epoch": 80.66,
|
|
"learning_rate": 8.11111111111111e-05,
|
|
"learning_rate_embeddings": 8.11111111111111e-05,
|
|
"loss": 3.9889,
|
|
"step": 213500
|
|
},
|
|
{
|
|
"epoch": 80.85,
|
|
"learning_rate": 8e-05,
|
|
"learning_rate_embeddings": 8e-05,
|
|
"loss": 3.9899,
|
|
"step": 214000
|
|
},
|
|
{
|
|
"epoch": 81.04,
|
|
"learning_rate": 7.888888888888888e-05,
|
|
"learning_rate_embeddings": 7.888888888888888e-05,
|
|
"loss": 3.9901,
|
|
"step": 214500
|
|
},
|
|
{
|
|
"epoch": 81.22,
|
|
"learning_rate": 7.777777777777778e-05,
|
|
"learning_rate_embeddings": 7.777777777777778e-05,
|
|
"loss": 3.9874,
|
|
"step": 215000
|
|
},
|
|
{
|
|
"epoch": 81.41,
|
|
"learning_rate": 7.666666666666667e-05,
|
|
"learning_rate_embeddings": 7.666666666666667e-05,
|
|
"loss": 3.9937,
|
|
"step": 215500
|
|
},
|
|
{
|
|
"epoch": 81.6,
|
|
"learning_rate": 7.555555555555556e-05,
|
|
"learning_rate_embeddings": 7.555555555555556e-05,
|
|
"loss": 3.9805,
|
|
"step": 216000
|
|
},
|
|
{
|
|
"epoch": 81.79,
|
|
"learning_rate": 7.444444444444444e-05,
|
|
"learning_rate_embeddings": 7.444444444444444e-05,
|
|
"loss": 3.9901,
|
|
"step": 216500
|
|
},
|
|
{
|
|
"epoch": 81.98,
|
|
"learning_rate": 7.333333333333333e-05,
|
|
"learning_rate_embeddings": 7.333333333333333e-05,
|
|
"loss": 3.9913,
|
|
"step": 217000
|
|
},
|
|
{
|
|
"epoch": 82.17,
|
|
"learning_rate": 7.222222222222222e-05,
|
|
"learning_rate_embeddings": 7.222222222222222e-05,
|
|
"loss": 3.9876,
|
|
"step": 217500
|
|
},
|
|
{
|
|
"epoch": 82.36,
|
|
"learning_rate": 7.11111111111111e-05,
|
|
"learning_rate_embeddings": 7.11111111111111e-05,
|
|
"loss": 3.983,
|
|
"step": 218000
|
|
},
|
|
{
|
|
"epoch": 82.55,
|
|
"learning_rate": 7.000000000000001e-05,
|
|
"learning_rate_embeddings": 7.000000000000001e-05,
|
|
"loss": 3.9833,
|
|
"step": 218500
|
|
},
|
|
{
|
|
"epoch": 82.74,
|
|
"learning_rate": 6.88888888888889e-05,
|
|
"learning_rate_embeddings": 6.88888888888889e-05,
|
|
"loss": 3.9803,
|
|
"step": 219000
|
|
},
|
|
{
|
|
"epoch": 82.92,
|
|
"learning_rate": 6.777777777777778e-05,
|
|
"learning_rate_embeddings": 6.777777777777778e-05,
|
|
"loss": 3.9848,
|
|
"step": 219500
|
|
},
|
|
{
|
|
"epoch": 83.11,
|
|
"learning_rate": 6.666666666666667e-05,
|
|
"learning_rate_embeddings": 6.666666666666667e-05,
|
|
"loss": 3.9867,
|
|
"step": 220000
|
|
},
|
|
{
|
|
"epoch": 83.3,
|
|
"learning_rate": 6.555555555555556e-05,
|
|
"learning_rate_embeddings": 6.555555555555556e-05,
|
|
"loss": 3.9835,
|
|
"step": 220500
|
|
},
|
|
{
|
|
"epoch": 83.49,
|
|
"learning_rate": 6.444444444444444e-05,
|
|
"learning_rate_embeddings": 6.444444444444444e-05,
|
|
"loss": 3.9799,
|
|
"step": 221000
|
|
},
|
|
{
|
|
"epoch": 83.68,
|
|
"learning_rate": 6.333333333333335e-05,
|
|
"learning_rate_embeddings": 6.333333333333335e-05,
|
|
"loss": 3.9823,
|
|
"step": 221500
|
|
},
|
|
{
|
|
"epoch": 83.87,
|
|
"learning_rate": 6.222222222222222e-05,
|
|
"learning_rate_embeddings": 6.222222222222222e-05,
|
|
"loss": 3.9774,
|
|
"step": 222000
|
|
},
|
|
{
|
|
"epoch": 84.06,
|
|
"learning_rate": 6.111111111111111e-05,
|
|
"learning_rate_embeddings": 6.111111111111111e-05,
|
|
"loss": 3.9797,
|
|
"step": 222500
|
|
},
|
|
{
|
|
"epoch": 84.25,
|
|
"learning_rate": 6e-05,
|
|
"learning_rate_embeddings": 6e-05,
|
|
"loss": 3.9872,
|
|
"step": 223000
|
|
},
|
|
{
|
|
"epoch": 84.44,
|
|
"learning_rate": 5.888888888888889e-05,
|
|
"learning_rate_embeddings": 5.888888888888889e-05,
|
|
"loss": 3.9776,
|
|
"step": 223500
|
|
},
|
|
{
|
|
"epoch": 84.62,
|
|
"learning_rate": 5.7777777777777776e-05,
|
|
"learning_rate_embeddings": 5.7777777777777776e-05,
|
|
"loss": 3.993,
|
|
"step": 224000
|
|
},
|
|
{
|
|
"epoch": 84.81,
|
|
"learning_rate": 5.6666666666666664e-05,
|
|
"learning_rate_embeddings": 5.6666666666666664e-05,
|
|
"loss": 3.9897,
|
|
"step": 224500
|
|
},
|
|
{
|
|
"epoch": 85.0,
|
|
"learning_rate": 5.555555555555555e-05,
|
|
"learning_rate_embeddings": 5.555555555555555e-05,
|
|
"loss": 3.9688,
|
|
"step": 225000
|
|
},
|
|
{
|
|
"epoch": 85.0,
|
|
"eval_loss": 3.9982454776763916,
|
|
"eval_runtime": 269.3813,
|
|
"eval_samples_per_second": 510.83,
|
|
"eval_steps_per_second": 3.994,
|
|
"step": 225000
|
|
},
|
|
{
|
|
"epoch": 85.19,
|
|
"learning_rate": 5.444444444444444e-05,
|
|
"learning_rate_embeddings": 5.444444444444444e-05,
|
|
"loss": 3.9712,
|
|
"step": 225500
|
|
},
|
|
{
|
|
"epoch": 85.38,
|
|
"learning_rate": 5.333333333333334e-05,
|
|
"learning_rate_embeddings": 5.333333333333334e-05,
|
|
"loss": 3.9887,
|
|
"step": 226000
|
|
},
|
|
{
|
|
"epoch": 85.57,
|
|
"learning_rate": 5.222222222222223e-05,
|
|
"learning_rate_embeddings": 5.222222222222223e-05,
|
|
"loss": 3.9656,
|
|
"step": 226500
|
|
},
|
|
{
|
|
"epoch": 85.76,
|
|
"learning_rate": 5.1111111111111115e-05,
|
|
"learning_rate_embeddings": 5.1111111111111115e-05,
|
|
"loss": 3.9659,
|
|
"step": 227000
|
|
},
|
|
{
|
|
"epoch": 85.95,
|
|
"learning_rate": 5e-05,
|
|
"learning_rate_embeddings": 5e-05,
|
|
"loss": 3.9664,
|
|
"step": 227500
|
|
},
|
|
{
|
|
"epoch": 86.14,
|
|
"learning_rate": 4.888888888888889e-05,
|
|
"learning_rate_embeddings": 4.888888888888889e-05,
|
|
"loss": 3.971,
|
|
"step": 228000
|
|
},
|
|
{
|
|
"epoch": 86.32,
|
|
"learning_rate": 4.7777777777777784e-05,
|
|
"learning_rate_embeddings": 4.7777777777777784e-05,
|
|
"loss": 3.972,
|
|
"step": 228500
|
|
},
|
|
{
|
|
"epoch": 86.51,
|
|
"learning_rate": 4.666666666666667e-05,
|
|
"learning_rate_embeddings": 4.666666666666667e-05,
|
|
"loss": 3.98,
|
|
"step": 229000
|
|
},
|
|
{
|
|
"epoch": 86.7,
|
|
"learning_rate": 4.555555555555556e-05,
|
|
"learning_rate_embeddings": 4.555555555555556e-05,
|
|
"loss": 3.9787,
|
|
"step": 229500
|
|
},
|
|
{
|
|
"epoch": 86.89,
|
|
"learning_rate": 4.4444444444444447e-05,
|
|
"learning_rate_embeddings": 4.4444444444444447e-05,
|
|
"loss": 3.9816,
|
|
"step": 230000
|
|
},
|
|
{
|
|
"epoch": 87.08,
|
|
"learning_rate": 4.3333333333333334e-05,
|
|
"learning_rate_embeddings": 4.3333333333333334e-05,
|
|
"loss": 3.9713,
|
|
"step": 230500
|
|
},
|
|
{
|
|
"epoch": 87.27,
|
|
"learning_rate": 4.222222222222222e-05,
|
|
"learning_rate_embeddings": 4.222222222222222e-05,
|
|
"loss": 3.9682,
|
|
"step": 231000
|
|
},
|
|
{
|
|
"epoch": 87.46,
|
|
"learning_rate": 4.1111111111111116e-05,
|
|
"learning_rate_embeddings": 4.1111111111111116e-05,
|
|
"loss": 3.9696,
|
|
"step": 231500
|
|
},
|
|
{
|
|
"epoch": 87.65,
|
|
"learning_rate": 4e-05,
|
|
"learning_rate_embeddings": 4e-05,
|
|
"loss": 3.985,
|
|
"step": 232000
|
|
},
|
|
{
|
|
"epoch": 87.84,
|
|
"learning_rate": 3.888888888888889e-05,
|
|
"learning_rate_embeddings": 3.888888888888889e-05,
|
|
"loss": 3.9641,
|
|
"step": 232500
|
|
},
|
|
{
|
|
"epoch": 88.02,
|
|
"learning_rate": 3.777777777777778e-05,
|
|
"learning_rate_embeddings": 3.777777777777778e-05,
|
|
"loss": 3.9604,
|
|
"step": 233000
|
|
},
|
|
{
|
|
"epoch": 88.21,
|
|
"learning_rate": 3.6666666666666666e-05,
|
|
"learning_rate_embeddings": 3.6666666666666666e-05,
|
|
"loss": 3.9676,
|
|
"step": 233500
|
|
},
|
|
{
|
|
"epoch": 88.4,
|
|
"learning_rate": 3.555555555555555e-05,
|
|
"learning_rate_embeddings": 3.555555555555555e-05,
|
|
"loss": 3.983,
|
|
"step": 234000
|
|
},
|
|
{
|
|
"epoch": 88.59,
|
|
"learning_rate": 3.444444444444445e-05,
|
|
"learning_rate_embeddings": 3.444444444444445e-05,
|
|
"loss": 3.9862,
|
|
"step": 234500
|
|
},
|
|
{
|
|
"epoch": 88.78,
|
|
"learning_rate": 3.3333333333333335e-05,
|
|
"learning_rate_embeddings": 3.3333333333333335e-05,
|
|
"loss": 3.9581,
|
|
"step": 235000
|
|
},
|
|
{
|
|
"epoch": 88.97,
|
|
"learning_rate": 3.222222222222222e-05,
|
|
"learning_rate_embeddings": 3.222222222222222e-05,
|
|
"loss": 3.9727,
|
|
"step": 235500
|
|
},
|
|
{
|
|
"epoch": 89.16,
|
|
"learning_rate": 3.111111111111111e-05,
|
|
"learning_rate_embeddings": 3.111111111111111e-05,
|
|
"loss": 3.9656,
|
|
"step": 236000
|
|
},
|
|
{
|
|
"epoch": 89.35,
|
|
"learning_rate": 3e-05,
|
|
"learning_rate_embeddings": 3e-05,
|
|
"loss": 3.9659,
|
|
"step": 236500
|
|
},
|
|
{
|
|
"epoch": 89.54,
|
|
"learning_rate": 2.8888888888888888e-05,
|
|
"learning_rate_embeddings": 2.8888888888888888e-05,
|
|
"loss": 3.9732,
|
|
"step": 237000
|
|
},
|
|
{
|
|
"epoch": 89.72,
|
|
"learning_rate": 2.7777777777777776e-05,
|
|
"learning_rate_embeddings": 2.7777777777777776e-05,
|
|
"loss": 3.9729,
|
|
"step": 237500
|
|
},
|
|
{
|
|
"epoch": 89.72,
|
|
"eval_loss": 3.9874038696289062,
|
|
"eval_runtime": 269.5131,
|
|
"eval_samples_per_second": 510.58,
|
|
"eval_steps_per_second": 3.992,
|
|
"step": 237500
|
|
},
|
|
{
|
|
"epoch": 89.91,
|
|
"learning_rate": 2.666666666666667e-05,
|
|
"learning_rate_embeddings": 2.666666666666667e-05,
|
|
"loss": 3.9524,
|
|
"step": 238000
|
|
},
|
|
{
|
|
"epoch": 90.1,
|
|
"learning_rate": 2.5555555555555557e-05,
|
|
"learning_rate_embeddings": 2.5555555555555557e-05,
|
|
"loss": 3.9707,
|
|
"step": 238500
|
|
},
|
|
{
|
|
"epoch": 90.29,
|
|
"learning_rate": 2.4444444444444445e-05,
|
|
"learning_rate_embeddings": 2.4444444444444445e-05,
|
|
"loss": 3.9599,
|
|
"step": 239000
|
|
},
|
|
{
|
|
"epoch": 90.48,
|
|
"learning_rate": 2.3333333333333336e-05,
|
|
"learning_rate_embeddings": 2.3333333333333336e-05,
|
|
"loss": 3.9685,
|
|
"step": 239500
|
|
},
|
|
{
|
|
"epoch": 90.67,
|
|
"learning_rate": 2.2222222222222223e-05,
|
|
"learning_rate_embeddings": 2.2222222222222223e-05,
|
|
"loss": 3.9627,
|
|
"step": 240000
|
|
},
|
|
{
|
|
"epoch": 90.86,
|
|
"learning_rate": 2.111111111111111e-05,
|
|
"learning_rate_embeddings": 2.111111111111111e-05,
|
|
"loss": 3.959,
|
|
"step": 240500
|
|
},
|
|
{
|
|
"epoch": 91.05,
|
|
"learning_rate": 2e-05,
|
|
"learning_rate_embeddings": 2e-05,
|
|
"loss": 3.9487,
|
|
"step": 241000
|
|
},
|
|
{
|
|
"epoch": 91.24,
|
|
"learning_rate": 1.888888888888889e-05,
|
|
"learning_rate_embeddings": 1.888888888888889e-05,
|
|
"loss": 3.9651,
|
|
"step": 241500
|
|
},
|
|
{
|
|
"epoch": 91.42,
|
|
"learning_rate": 1.7777777777777777e-05,
|
|
"learning_rate_embeddings": 1.7777777777777777e-05,
|
|
"loss": 3.9577,
|
|
"step": 242000
|
|
},
|
|
{
|
|
"epoch": 91.61,
|
|
"learning_rate": 1.6666666666666667e-05,
|
|
"learning_rate_embeddings": 1.6666666666666667e-05,
|
|
"loss": 3.9586,
|
|
"step": 242500
|
|
},
|
|
{
|
|
"epoch": 91.8,
|
|
"learning_rate": 1.5555555555555555e-05,
|
|
"learning_rate_embeddings": 1.5555555555555555e-05,
|
|
"loss": 3.9687,
|
|
"step": 243000
|
|
},
|
|
{
|
|
"epoch": 91.99,
|
|
"learning_rate": 1.4444444444444444e-05,
|
|
"learning_rate_embeddings": 1.4444444444444444e-05,
|
|
"loss": 3.947,
|
|
"step": 243500
|
|
},
|
|
{
|
|
"epoch": 92.18,
|
|
"learning_rate": 1.3333333333333335e-05,
|
|
"learning_rate_embeddings": 1.3333333333333335e-05,
|
|
"loss": 3.9582,
|
|
"step": 244000
|
|
},
|
|
{
|
|
"epoch": 92.37,
|
|
"learning_rate": 1.2222222222222222e-05,
|
|
"learning_rate_embeddings": 1.2222222222222222e-05,
|
|
"loss": 3.965,
|
|
"step": 244500
|
|
},
|
|
{
|
|
"epoch": 92.56,
|
|
"learning_rate": 1.1111111111111112e-05,
|
|
"learning_rate_embeddings": 1.1111111111111112e-05,
|
|
"loss": 3.9425,
|
|
"step": 245000
|
|
},
|
|
{
|
|
"epoch": 92.75,
|
|
"learning_rate": 1e-05,
|
|
"learning_rate_embeddings": 1e-05,
|
|
"loss": 3.9466,
|
|
"step": 245500
|
|
},
|
|
{
|
|
"epoch": 92.94,
|
|
"learning_rate": 8.888888888888888e-06,
|
|
"learning_rate_embeddings": 8.888888888888888e-06,
|
|
"loss": 3.961,
|
|
"step": 246000
|
|
},
|
|
{
|
|
"epoch": 93.12,
|
|
"learning_rate": 7.777777777777777e-06,
|
|
"learning_rate_embeddings": 7.777777777777777e-06,
|
|
"loss": 3.9507,
|
|
"step": 246500
|
|
},
|
|
{
|
|
"epoch": 93.31,
|
|
"learning_rate": 6.6666666666666675e-06,
|
|
"learning_rate_embeddings": 6.6666666666666675e-06,
|
|
"loss": 3.9486,
|
|
"step": 247000
|
|
},
|
|
{
|
|
"epoch": 93.5,
|
|
"learning_rate": 5.555555555555556e-06,
|
|
"learning_rate_embeddings": 5.555555555555556e-06,
|
|
"loss": 3.9606,
|
|
"step": 247500
|
|
},
|
|
{
|
|
"epoch": 93.69,
|
|
"learning_rate": 4.444444444444444e-06,
|
|
"learning_rate_embeddings": 4.444444444444444e-06,
|
|
"loss": 3.9506,
|
|
"step": 248000
|
|
},
|
|
{
|
|
"epoch": 93.88,
|
|
"learning_rate": 3.3333333333333337e-06,
|
|
"learning_rate_embeddings": 3.3333333333333337e-06,
|
|
"loss": 3.9578,
|
|
"step": 248500
|
|
},
|
|
{
|
|
"epoch": 94.07,
|
|
"learning_rate": 2.222222222222222e-06,
|
|
"learning_rate_embeddings": 2.222222222222222e-06,
|
|
"loss": 3.9359,
|
|
"step": 249000
|
|
},
|
|
{
|
|
"epoch": 94.26,
|
|
"learning_rate": 1.111111111111111e-06,
|
|
"learning_rate_embeddings": 1.111111111111111e-06,
|
|
"loss": 3.9358,
|
|
"step": 249500
|
|
},
|
|
{
|
|
"epoch": 94.45,
|
|
"learning_rate": 0.0,
|
|
"learning_rate_embeddings": 0.0,
|
|
"loss": 3.9444,
|
|
"step": 250000
|
|
},
|
|
{
|
|
"epoch": 94.45,
|
|
"eval_loss": 3.950594663619995,
|
|
"eval_runtime": 269.5994,
|
|
"eval_samples_per_second": 510.417,
|
|
"eval_steps_per_second": 3.991,
|
|
"step": 250000
|
|
}
|
|
],
|
|
"max_steps": 250000,
|
|
"num_train_epochs": 95,
|
|
"total_flos": 4.181065495216128e+18,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|