plt5-base-msmarco / trainer_state.json
Konrad Wojtasik
Update model
09e9229
raw
history blame
23 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 20000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 9.95e-05,
"loss": 7.5958,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 9.900000000000001e-05,
"loss": 0.3186,
"step": 200
},
{
"epoch": 0.01,
"learning_rate": 9.850000000000001e-05,
"loss": 0.2868,
"step": 300
},
{
"epoch": 0.02,
"learning_rate": 9.8e-05,
"loss": 0.2434,
"step": 400
},
{
"epoch": 0.03,
"learning_rate": 9.75e-05,
"loss": 0.1965,
"step": 500
},
{
"epoch": 0.03,
"learning_rate": 9.7e-05,
"loss": 0.1758,
"step": 600
},
{
"epoch": 0.04,
"learning_rate": 9.65e-05,
"loss": 0.1722,
"step": 700
},
{
"epoch": 0.04,
"learning_rate": 9.6e-05,
"loss": 0.1605,
"step": 800
},
{
"epoch": 0.04,
"learning_rate": 9.55e-05,
"loss": 0.1588,
"step": 900
},
{
"epoch": 0.05,
"learning_rate": 9.5e-05,
"loss": 0.1493,
"step": 1000
},
{
"epoch": 0.06,
"learning_rate": 9.449999999999999e-05,
"loss": 0.1429,
"step": 1100
},
{
"epoch": 0.06,
"learning_rate": 9.4e-05,
"loss": 0.1375,
"step": 1200
},
{
"epoch": 0.07,
"learning_rate": 9.350000000000001e-05,
"loss": 0.1378,
"step": 1300
},
{
"epoch": 0.07,
"learning_rate": 9.300000000000001e-05,
"loss": 0.1372,
"step": 1400
},
{
"epoch": 0.07,
"learning_rate": 9.250000000000001e-05,
"loss": 0.1291,
"step": 1500
},
{
"epoch": 0.08,
"learning_rate": 9.200000000000001e-05,
"loss": 0.129,
"step": 1600
},
{
"epoch": 0.09,
"learning_rate": 9.15e-05,
"loss": 0.1302,
"step": 1700
},
{
"epoch": 0.09,
"learning_rate": 9.1e-05,
"loss": 0.1255,
"step": 1800
},
{
"epoch": 0.1,
"learning_rate": 9.05e-05,
"loss": 0.1256,
"step": 1900
},
{
"epoch": 0.1,
"learning_rate": 9e-05,
"loss": 0.1214,
"step": 2000
},
{
"epoch": 0.1,
"learning_rate": 8.950000000000001e-05,
"loss": 0.1199,
"step": 2100
},
{
"epoch": 0.11,
"learning_rate": 8.900000000000001e-05,
"loss": 0.1193,
"step": 2200
},
{
"epoch": 0.12,
"learning_rate": 8.850000000000001e-05,
"loss": 0.1208,
"step": 2300
},
{
"epoch": 0.12,
"learning_rate": 8.800000000000001e-05,
"loss": 0.118,
"step": 2400
},
{
"epoch": 0.12,
"learning_rate": 8.75e-05,
"loss": 0.1167,
"step": 2500
},
{
"epoch": 0.13,
"learning_rate": 8.7e-05,
"loss": 0.1136,
"step": 2600
},
{
"epoch": 0.14,
"learning_rate": 8.65e-05,
"loss": 0.1164,
"step": 2700
},
{
"epoch": 0.14,
"learning_rate": 8.6e-05,
"loss": 0.1124,
"step": 2800
},
{
"epoch": 0.14,
"learning_rate": 8.55e-05,
"loss": 0.1138,
"step": 2900
},
{
"epoch": 0.15,
"learning_rate": 8.5e-05,
"loss": 0.114,
"step": 3000
},
{
"epoch": 0.15,
"learning_rate": 8.450000000000001e-05,
"loss": 0.1137,
"step": 3100
},
{
"epoch": 0.16,
"learning_rate": 8.4e-05,
"loss": 0.1096,
"step": 3200
},
{
"epoch": 0.17,
"learning_rate": 8.35e-05,
"loss": 0.1087,
"step": 3300
},
{
"epoch": 0.17,
"learning_rate": 8.3e-05,
"loss": 0.1079,
"step": 3400
},
{
"epoch": 0.17,
"learning_rate": 8.25e-05,
"loss": 0.1085,
"step": 3500
},
{
"epoch": 0.18,
"learning_rate": 8.2e-05,
"loss": 0.112,
"step": 3600
},
{
"epoch": 0.18,
"learning_rate": 8.15e-05,
"loss": 0.1071,
"step": 3700
},
{
"epoch": 0.19,
"learning_rate": 8.1e-05,
"loss": 0.1077,
"step": 3800
},
{
"epoch": 0.2,
"learning_rate": 8.05e-05,
"loss": 0.1059,
"step": 3900
},
{
"epoch": 0.2,
"learning_rate": 8e-05,
"loss": 0.1105,
"step": 4000
},
{
"epoch": 0.2,
"learning_rate": 7.950000000000001e-05,
"loss": 0.107,
"step": 4100
},
{
"epoch": 0.21,
"learning_rate": 7.900000000000001e-05,
"loss": 0.1064,
"step": 4200
},
{
"epoch": 0.21,
"learning_rate": 7.850000000000001e-05,
"loss": 0.1049,
"step": 4300
},
{
"epoch": 0.22,
"learning_rate": 7.800000000000001e-05,
"loss": 0.1043,
"step": 4400
},
{
"epoch": 0.23,
"learning_rate": 7.75e-05,
"loss": 0.1033,
"step": 4500
},
{
"epoch": 0.23,
"learning_rate": 7.7e-05,
"loss": 0.103,
"step": 4600
},
{
"epoch": 0.23,
"learning_rate": 7.65e-05,
"loss": 0.1033,
"step": 4700
},
{
"epoch": 0.24,
"learning_rate": 7.6e-05,
"loss": 0.1014,
"step": 4800
},
{
"epoch": 0.24,
"learning_rate": 7.55e-05,
"loss": 0.1038,
"step": 4900
},
{
"epoch": 0.25,
"learning_rate": 7.500000000000001e-05,
"loss": 0.1011,
"step": 5000
},
{
"epoch": 0.26,
"learning_rate": 7.450000000000001e-05,
"loss": 0.1011,
"step": 5100
},
{
"epoch": 0.26,
"learning_rate": 7.4e-05,
"loss": 0.1006,
"step": 5200
},
{
"epoch": 0.27,
"learning_rate": 7.35e-05,
"loss": 0.1024,
"step": 5300
},
{
"epoch": 0.27,
"learning_rate": 7.3e-05,
"loss": 0.1003,
"step": 5400
},
{
"epoch": 0.28,
"learning_rate": 7.25e-05,
"loss": 0.0997,
"step": 5500
},
{
"epoch": 0.28,
"learning_rate": 7.2e-05,
"loss": 0.1019,
"step": 5600
},
{
"epoch": 0.28,
"learning_rate": 7.15e-05,
"loss": 0.1025,
"step": 5700
},
{
"epoch": 0.29,
"learning_rate": 7.1e-05,
"loss": 0.0994,
"step": 5800
},
{
"epoch": 0.29,
"learning_rate": 7.05e-05,
"loss": 0.0982,
"step": 5900
},
{
"epoch": 0.3,
"learning_rate": 7e-05,
"loss": 0.0998,
"step": 6000
},
{
"epoch": 0.3,
"learning_rate": 6.95e-05,
"loss": 0.0966,
"step": 6100
},
{
"epoch": 0.31,
"learning_rate": 6.9e-05,
"loss": 0.096,
"step": 6200
},
{
"epoch": 0.32,
"learning_rate": 6.850000000000001e-05,
"loss": 0.0972,
"step": 6300
},
{
"epoch": 0.32,
"learning_rate": 6.800000000000001e-05,
"loss": 0.0973,
"step": 6400
},
{
"epoch": 0.33,
"learning_rate": 6.750000000000001e-05,
"loss": 0.0996,
"step": 6500
},
{
"epoch": 0.33,
"learning_rate": 6.7e-05,
"loss": 0.0961,
"step": 6600
},
{
"epoch": 0.34,
"learning_rate": 6.65e-05,
"loss": 0.0964,
"step": 6700
},
{
"epoch": 0.34,
"learning_rate": 6.6e-05,
"loss": 0.0966,
"step": 6800
},
{
"epoch": 0.34,
"learning_rate": 6.55e-05,
"loss": 0.0959,
"step": 6900
},
{
"epoch": 0.35,
"learning_rate": 6.500000000000001e-05,
"loss": 0.0975,
"step": 7000
},
{
"epoch": 0.35,
"learning_rate": 6.450000000000001e-05,
"loss": 0.0983,
"step": 7100
},
{
"epoch": 0.36,
"learning_rate": 6.400000000000001e-05,
"loss": 0.0989,
"step": 7200
},
{
"epoch": 0.36,
"learning_rate": 6.35e-05,
"loss": 0.095,
"step": 7300
},
{
"epoch": 0.37,
"learning_rate": 6.3e-05,
"loss": 0.0943,
"step": 7400
},
{
"epoch": 0.38,
"learning_rate": 6.25e-05,
"loss": 0.097,
"step": 7500
},
{
"epoch": 0.38,
"learning_rate": 6.2e-05,
"loss": 0.094,
"step": 7600
},
{
"epoch": 0.39,
"learning_rate": 6.15e-05,
"loss": 0.0942,
"step": 7700
},
{
"epoch": 0.39,
"learning_rate": 6.1e-05,
"loss": 0.0966,
"step": 7800
},
{
"epoch": 0.4,
"learning_rate": 6.05e-05,
"loss": 0.0934,
"step": 7900
},
{
"epoch": 0.4,
"learning_rate": 6e-05,
"loss": 0.0941,
"step": 8000
},
{
"epoch": 0.41,
"learning_rate": 5.95e-05,
"loss": 0.0947,
"step": 8100
},
{
"epoch": 0.41,
"learning_rate": 5.9e-05,
"loss": 0.0929,
"step": 8200
},
{
"epoch": 0.41,
"learning_rate": 5.85e-05,
"loss": 0.0911,
"step": 8300
},
{
"epoch": 0.42,
"learning_rate": 5.8e-05,
"loss": 0.0962,
"step": 8400
},
{
"epoch": 0.42,
"learning_rate": 5.7499999999999995e-05,
"loss": 0.0953,
"step": 8500
},
{
"epoch": 0.43,
"learning_rate": 5.6999999999999996e-05,
"loss": 0.0926,
"step": 8600
},
{
"epoch": 0.43,
"learning_rate": 5.65e-05,
"loss": 0.0957,
"step": 8700
},
{
"epoch": 0.44,
"learning_rate": 5.6000000000000006e-05,
"loss": 0.0935,
"step": 8800
},
{
"epoch": 0.45,
"learning_rate": 5.550000000000001e-05,
"loss": 0.0931,
"step": 8900
},
{
"epoch": 0.45,
"learning_rate": 5.500000000000001e-05,
"loss": 0.0937,
"step": 9000
},
{
"epoch": 0.46,
"learning_rate": 5.45e-05,
"loss": 0.0937,
"step": 9100
},
{
"epoch": 0.46,
"learning_rate": 5.4000000000000005e-05,
"loss": 0.0929,
"step": 9200
},
{
"epoch": 0.47,
"learning_rate": 5.3500000000000006e-05,
"loss": 0.0913,
"step": 9300
},
{
"epoch": 0.47,
"learning_rate": 5.300000000000001e-05,
"loss": 0.0929,
"step": 9400
},
{
"epoch": 0.47,
"learning_rate": 5.25e-05,
"loss": 0.0896,
"step": 9500
},
{
"epoch": 0.48,
"learning_rate": 5.2000000000000004e-05,
"loss": 0.0923,
"step": 9600
},
{
"epoch": 0.48,
"learning_rate": 5.1500000000000005e-05,
"loss": 0.0909,
"step": 9700
},
{
"epoch": 0.49,
"learning_rate": 5.1000000000000006e-05,
"loss": 0.0925,
"step": 9800
},
{
"epoch": 0.49,
"learning_rate": 5.05e-05,
"loss": 0.0934,
"step": 9900
},
{
"epoch": 0.5,
"learning_rate": 5e-05,
"loss": 0.0915,
"step": 10000
},
{
"epoch": 0.51,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.0891,
"step": 10100
},
{
"epoch": 0.51,
"learning_rate": 4.9e-05,
"loss": 0.0898,
"step": 10200
},
{
"epoch": 0.52,
"learning_rate": 4.85e-05,
"loss": 0.0931,
"step": 10300
},
{
"epoch": 0.52,
"learning_rate": 4.8e-05,
"loss": 0.0905,
"step": 10400
},
{
"epoch": 0.53,
"learning_rate": 4.75e-05,
"loss": 0.0886,
"step": 10500
},
{
"epoch": 0.53,
"learning_rate": 4.7e-05,
"loss": 0.0872,
"step": 10600
},
{
"epoch": 0.54,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.09,
"step": 10700
},
{
"epoch": 0.54,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0894,
"step": 10800
},
{
"epoch": 0.55,
"learning_rate": 4.55e-05,
"loss": 0.0878,
"step": 10900
},
{
"epoch": 0.55,
"learning_rate": 4.5e-05,
"loss": 0.0903,
"step": 11000
},
{
"epoch": 0.56,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.0904,
"step": 11100
},
{
"epoch": 0.56,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0905,
"step": 11200
},
{
"epoch": 0.56,
"learning_rate": 4.35e-05,
"loss": 0.0877,
"step": 11300
},
{
"epoch": 0.57,
"learning_rate": 4.3e-05,
"loss": 0.0888,
"step": 11400
},
{
"epoch": 0.57,
"learning_rate": 4.25e-05,
"loss": 0.0904,
"step": 11500
},
{
"epoch": 0.58,
"learning_rate": 4.2e-05,
"loss": 0.0903,
"step": 11600
},
{
"epoch": 0.58,
"learning_rate": 4.15e-05,
"loss": 0.0865,
"step": 11700
},
{
"epoch": 0.59,
"learning_rate": 4.1e-05,
"loss": 0.0895,
"step": 11800
},
{
"epoch": 0.59,
"learning_rate": 4.05e-05,
"loss": 0.0888,
"step": 11900
},
{
"epoch": 0.6,
"learning_rate": 4e-05,
"loss": 0.0884,
"step": 12000
},
{
"epoch": 0.6,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0897,
"step": 12100
},
{
"epoch": 0.61,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0891,
"step": 12200
},
{
"epoch": 0.61,
"learning_rate": 3.85e-05,
"loss": 0.0904,
"step": 12300
},
{
"epoch": 0.62,
"learning_rate": 3.8e-05,
"loss": 0.0864,
"step": 12400
},
{
"epoch": 0.62,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0871,
"step": 12500
},
{
"epoch": 0.63,
"learning_rate": 3.7e-05,
"loss": 0.0859,
"step": 12600
},
{
"epoch": 0.64,
"learning_rate": 3.65e-05,
"loss": 0.0878,
"step": 12700
},
{
"epoch": 0.64,
"learning_rate": 3.6e-05,
"loss": 0.0862,
"step": 12800
},
{
"epoch": 0.65,
"learning_rate": 3.55e-05,
"loss": 0.085,
"step": 12900
},
{
"epoch": 0.65,
"learning_rate": 3.5e-05,
"loss": 0.0885,
"step": 13000
},
{
"epoch": 0.66,
"learning_rate": 3.45e-05,
"loss": 0.0889,
"step": 13100
},
{
"epoch": 0.66,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0876,
"step": 13200
},
{
"epoch": 0.67,
"learning_rate": 3.35e-05,
"loss": 0.0882,
"step": 13300
},
{
"epoch": 0.67,
"learning_rate": 3.3e-05,
"loss": 0.0884,
"step": 13400
},
{
"epoch": 0.68,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0848,
"step": 13500
},
{
"epoch": 0.68,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0859,
"step": 13600
},
{
"epoch": 0.69,
"learning_rate": 3.15e-05,
"loss": 0.0895,
"step": 13700
},
{
"epoch": 0.69,
"learning_rate": 3.1e-05,
"loss": 0.0898,
"step": 13800
},
{
"epoch": 0.69,
"learning_rate": 3.05e-05,
"loss": 0.0849,
"step": 13900
},
{
"epoch": 0.7,
"learning_rate": 3e-05,
"loss": 0.0866,
"step": 14000
},
{
"epoch": 0.7,
"learning_rate": 2.95e-05,
"loss": 0.0839,
"step": 14100
},
{
"epoch": 0.71,
"learning_rate": 2.9e-05,
"loss": 0.0855,
"step": 14200
},
{
"epoch": 0.71,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.0848,
"step": 14300
},
{
"epoch": 0.72,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0889,
"step": 14400
},
{
"epoch": 0.72,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0861,
"step": 14500
},
{
"epoch": 0.73,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0838,
"step": 14600
},
{
"epoch": 0.73,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.0878,
"step": 14700
},
{
"epoch": 0.74,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0866,
"step": 14800
},
{
"epoch": 0.74,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.086,
"step": 14900
},
{
"epoch": 0.75,
"learning_rate": 2.5e-05,
"loss": 0.0841,
"step": 15000
},
{
"epoch": 0.76,
"learning_rate": 2.45e-05,
"loss": 0.0864,
"step": 15100
},
{
"epoch": 0.76,
"learning_rate": 2.4e-05,
"loss": 0.0855,
"step": 15200
},
{
"epoch": 0.77,
"learning_rate": 2.35e-05,
"loss": 0.0861,
"step": 15300
},
{
"epoch": 0.77,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0856,
"step": 15400
},
{
"epoch": 0.78,
"learning_rate": 2.25e-05,
"loss": 0.0872,
"step": 15500
},
{
"epoch": 0.78,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0838,
"step": 15600
},
{
"epoch": 0.79,
"learning_rate": 2.15e-05,
"loss": 0.0851,
"step": 15700
},
{
"epoch": 0.79,
"learning_rate": 2.1e-05,
"loss": 0.0865,
"step": 15800
},
{
"epoch": 0.8,
"learning_rate": 2.05e-05,
"loss": 0.0866,
"step": 15900
},
{
"epoch": 0.8,
"learning_rate": 2e-05,
"loss": 0.0868,
"step": 16000
},
{
"epoch": 0.81,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.087,
"step": 16100
},
{
"epoch": 0.81,
"learning_rate": 1.9e-05,
"loss": 0.0844,
"step": 16200
},
{
"epoch": 0.81,
"learning_rate": 1.85e-05,
"loss": 0.0835,
"step": 16300
},
{
"epoch": 0.82,
"learning_rate": 1.8e-05,
"loss": 0.0863,
"step": 16400
},
{
"epoch": 0.82,
"learning_rate": 1.75e-05,
"loss": 0.0854,
"step": 16500
},
{
"epoch": 0.83,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0857,
"step": 16600
},
{
"epoch": 0.83,
"learning_rate": 1.65e-05,
"loss": 0.0844,
"step": 16700
},
{
"epoch": 0.84,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0864,
"step": 16800
},
{
"epoch": 0.84,
"learning_rate": 1.55e-05,
"loss": 0.0867,
"step": 16900
},
{
"epoch": 0.85,
"learning_rate": 1.5e-05,
"loss": 0.0849,
"step": 17000
},
{
"epoch": 0.85,
"learning_rate": 1.45e-05,
"loss": 0.0815,
"step": 17100
},
{
"epoch": 0.86,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0823,
"step": 17200
},
{
"epoch": 0.86,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0872,
"step": 17300
},
{
"epoch": 0.87,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.084,
"step": 17400
},
{
"epoch": 0.88,
"learning_rate": 1.25e-05,
"loss": 0.0812,
"step": 17500
},
{
"epoch": 0.88,
"learning_rate": 1.2e-05,
"loss": 0.0842,
"step": 17600
},
{
"epoch": 0.89,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.087,
"step": 17700
},
{
"epoch": 0.89,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0843,
"step": 17800
},
{
"epoch": 0.9,
"learning_rate": 1.05e-05,
"loss": 0.0833,
"step": 17900
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 0.0836,
"step": 18000
},
{
"epoch": 0.91,
"learning_rate": 9.5e-06,
"loss": 0.0864,
"step": 18100
},
{
"epoch": 0.91,
"learning_rate": 9e-06,
"loss": 0.0847,
"step": 18200
},
{
"epoch": 0.92,
"learning_rate": 8.500000000000002e-06,
"loss": 0.084,
"step": 18300
},
{
"epoch": 0.92,
"learning_rate": 8.000000000000001e-06,
"loss": 0.085,
"step": 18400
},
{
"epoch": 0.93,
"learning_rate": 7.5e-06,
"loss": 0.0847,
"step": 18500
},
{
"epoch": 0.93,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0847,
"step": 18600
},
{
"epoch": 0.94,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.085,
"step": 18700
},
{
"epoch": 0.94,
"learning_rate": 6e-06,
"loss": 0.0836,
"step": 18800
},
{
"epoch": 0.94,
"learning_rate": 5.500000000000001e-06,
"loss": 0.0838,
"step": 18900
},
{
"epoch": 0.95,
"learning_rate": 5e-06,
"loss": 0.0822,
"step": 19000
},
{
"epoch": 0.95,
"learning_rate": 4.5e-06,
"loss": 0.0821,
"step": 19100
},
{
"epoch": 0.96,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0852,
"step": 19200
},
{
"epoch": 0.96,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0829,
"step": 19300
},
{
"epoch": 0.97,
"learning_rate": 3e-06,
"loss": 0.085,
"step": 19400
},
{
"epoch": 0.97,
"learning_rate": 2.5e-06,
"loss": 0.0839,
"step": 19500
},
{
"epoch": 0.98,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0829,
"step": 19600
},
{
"epoch": 0.98,
"learning_rate": 1.5e-06,
"loss": 0.0849,
"step": 19700
},
{
"epoch": 0.99,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0842,
"step": 19800
},
{
"epoch": 0.99,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0837,
"step": 19900
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.0797,
"step": 20000
},
{
"epoch": 1.0,
"step": 20000,
"total_flos": 0,
"train_runtime": 84238.4398,
"train_samples_per_second": 0.237
}
],
"max_steps": 20000,
"num_train_epochs": 1,
"total_flos": 0,
"trial_name": null,
"trial_params": null
}