T5-small-cnndm-bild-aligned / trainer_state.json
Sehoon's picture
store
680d80c
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 11.145165784341042,
"global_step": 200000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5805,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5732,
"step": 200
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5959,
"step": 300
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6017,
"step": 400
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6004,
"step": 500
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5835,
"step": 600
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5751,
"step": 700
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.611,
"step": 800
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.6164,
"step": 900
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.5925,
"step": 1000
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.6045,
"step": 1100
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 0.6015,
"step": 1200
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 0.594,
"step": 1300
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 0.594,
"step": 1400
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 0.5996,
"step": 1500
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 0.6044,
"step": 1600
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 0.6066,
"step": 1700
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 0.5974,
"step": 1800
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 0.5914,
"step": 1900
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 0.5953,
"step": 2000
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 0.5899,
"step": 2100
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 0.5944,
"step": 2200
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 0.5942,
"step": 2300
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 0.5967,
"step": 2400
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 0.583,
"step": 2500
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 0.6051,
"step": 2600
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 0.5985,
"step": 2700
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 0.5988,
"step": 2800
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 0.5909,
"step": 2900
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 0.5862,
"step": 3000
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 0.5955,
"step": 3100
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 0.6082,
"step": 3200
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 0.5945,
"step": 3300
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 0.5902,
"step": 3400
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 0.5972,
"step": 3500
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 0.6033,
"step": 3600
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 0.5833,
"step": 3700
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 0.6024,
"step": 3800
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 0.5846,
"step": 3900
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 0.608,
"step": 4000
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 0.6056,
"step": 4100
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 0.5992,
"step": 4200
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 0.5884,
"step": 4300
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 0.611,
"step": 4400
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 0.6021,
"step": 4500
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 0.6078,
"step": 4600
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 0.6079,
"step": 4700
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 0.5802,
"step": 4800
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 0.5957,
"step": 4900
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 0.5927,
"step": 5000
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 0.601,
"step": 5100
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 0.6067,
"step": 5200
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 0.6032,
"step": 5300
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 0.5967,
"step": 5400
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 0.6086,
"step": 5500
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 0.6088,
"step": 5600
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 0.6004,
"step": 5700
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 0.6081,
"step": 5800
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 0.5881,
"step": 5900
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 0.6046,
"step": 6000
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 0.5831,
"step": 6100
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 0.5986,
"step": 6200
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 0.5978,
"step": 6300
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 0.6047,
"step": 6400
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 0.6051,
"step": 6500
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 0.5896,
"step": 6600
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 0.5985,
"step": 6700
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 0.6038,
"step": 6800
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 0.6022,
"step": 6900
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 0.6061,
"step": 7000
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 0.5962,
"step": 7100
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 0.6063,
"step": 7200
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 0.5968,
"step": 7300
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 0.6073,
"step": 7400
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 0.5951,
"step": 7500
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 0.596,
"step": 7600
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 0.5992,
"step": 7700
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 0.6136,
"step": 7800
},
{
"epoch": 0.44,
"learning_rate": 0.0002,
"loss": 0.6,
"step": 7900
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 0.6036,
"step": 8000
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 0.6085,
"step": 8100
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 0.5925,
"step": 8200
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 0.6132,
"step": 8300
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 0.5988,
"step": 8400
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 0.6097,
"step": 8500
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 0.5982,
"step": 8600
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 0.6047,
"step": 8700
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 0.614,
"step": 8800
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 0.6009,
"step": 8900
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 0.6006,
"step": 9000
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 0.5976,
"step": 9100
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 0.5978,
"step": 9200
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 0.6068,
"step": 9300
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 0.6083,
"step": 9400
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 0.6061,
"step": 9500
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 0.6045,
"step": 9600
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 0.5928,
"step": 9700
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 0.5981,
"step": 9800
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 0.6171,
"step": 9900
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 0.6079,
"step": 10000
},
{
"epoch": 0.56,
"eval_gen_len": 18.999476361460204,
"eval_loss": 2.610891819000244,
"eval_rouge1": 25.2905,
"eval_rouge2": 12.3803,
"eval_rougeL": 20.8964,
"eval_rougeLsum": 23.9052,
"eval_runtime": 491.8614,
"eval_samples_per_second": 27.178,
"eval_steps_per_second": 1.7,
"step": 10000
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 0.6068,
"step": 10100
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 0.5903,
"step": 10200
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 0.6039,
"step": 10300
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 0.6014,
"step": 10400
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 0.6076,
"step": 10500
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 0.6062,
"step": 10600
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 0.6013,
"step": 10700
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 0.615,
"step": 10800
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 0.6003,
"step": 10900
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 0.6059,
"step": 11000
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 0.6144,
"step": 11100
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 0.626,
"step": 11200
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 0.5908,
"step": 11300
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 0.6052,
"step": 11400
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 0.6159,
"step": 11500
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 0.6093,
"step": 11600
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 0.6048,
"step": 11700
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 0.6134,
"step": 11800
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 0.603,
"step": 11900
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 0.5971,
"step": 12000
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 0.6122,
"step": 12100
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 0.603,
"step": 12200
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 0.6016,
"step": 12300
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 0.5888,
"step": 12400
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 0.6016,
"step": 12500
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 0.6155,
"step": 12600
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 0.6121,
"step": 12700
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 0.6147,
"step": 12800
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 0.5936,
"step": 12900
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 0.5999,
"step": 13000
},
{
"epoch": 0.73,
"learning_rate": 0.0002,
"loss": 0.6058,
"step": 13100
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 0.6123,
"step": 13200
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 0.5933,
"step": 13300
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 0.5945,
"step": 13400
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 0.6042,
"step": 13500
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 0.6169,
"step": 13600
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 0.6122,
"step": 13700
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 0.6122,
"step": 13800
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 0.6034,
"step": 13900
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 0.5984,
"step": 14000
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 0.6166,
"step": 14100
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 0.623,
"step": 14200
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 0.6052,
"step": 14300
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 0.6056,
"step": 14400
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 0.6185,
"step": 14500
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 0.6204,
"step": 14600
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 0.6194,
"step": 14700
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 0.6042,
"step": 14800
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 0.5974,
"step": 14900
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 0.6052,
"step": 15000
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 0.597,
"step": 15100
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 0.6095,
"step": 15200
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 0.6187,
"step": 15300
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 0.6066,
"step": 15400
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 0.6132,
"step": 15500
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 0.6156,
"step": 15600
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 0.6081,
"step": 15700
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 0.6079,
"step": 15800
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 0.6253,
"step": 15900
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 0.6029,
"step": 16000
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 0.6056,
"step": 16100
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 0.6165,
"step": 16200
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 0.6223,
"step": 16300
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 0.5993,
"step": 16400
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 0.6096,
"step": 16500
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 0.613,
"step": 16600
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 0.5931,
"step": 16700
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 0.6158,
"step": 16800
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 0.6129,
"step": 16900
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 0.6097,
"step": 17000
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 0.6102,
"step": 17100
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 0.6232,
"step": 17200
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 0.6099,
"step": 17300
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 0.6182,
"step": 17400
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 0.6115,
"step": 17500
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 0.6156,
"step": 17600
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 0.6217,
"step": 17700
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 0.6155,
"step": 17800
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 0.5991,
"step": 17900
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 0.5913,
"step": 18000
},
{
"epoch": 1.01,
"learning_rate": 0.0002,
"loss": 0.5782,
"step": 18100
},
{
"epoch": 1.01,
"learning_rate": 0.0002,
"loss": 0.5648,
"step": 18200
},
{
"epoch": 1.02,
"learning_rate": 0.0002,
"loss": 0.5837,
"step": 18300
},
{
"epoch": 1.03,
"learning_rate": 0.0002,
"loss": 0.582,
"step": 18400
},
{
"epoch": 1.03,
"learning_rate": 0.0002,
"loss": 0.5695,
"step": 18500
},
{
"epoch": 1.04,
"learning_rate": 0.0002,
"loss": 0.59,
"step": 18600
},
{
"epoch": 1.04,
"learning_rate": 0.0002,
"loss": 0.5753,
"step": 18700
},
{
"epoch": 1.05,
"learning_rate": 0.0002,
"loss": 0.5902,
"step": 18800
},
{
"epoch": 1.05,
"learning_rate": 0.0002,
"loss": 0.5841,
"step": 18900
},
{
"epoch": 1.06,
"learning_rate": 0.0002,
"loss": 0.579,
"step": 19000
},
{
"epoch": 1.06,
"learning_rate": 0.0002,
"loss": 0.5733,
"step": 19100
},
{
"epoch": 1.07,
"learning_rate": 0.0002,
"loss": 0.5818,
"step": 19200
},
{
"epoch": 1.08,
"learning_rate": 0.0002,
"loss": 0.5821,
"step": 19300
},
{
"epoch": 1.08,
"learning_rate": 0.0002,
"loss": 0.5814,
"step": 19400
},
{
"epoch": 1.09,
"learning_rate": 0.0002,
"loss": 0.5849,
"step": 19500
},
{
"epoch": 1.09,
"learning_rate": 0.0002,
"loss": 0.5966,
"step": 19600
},
{
"epoch": 1.1,
"learning_rate": 0.0002,
"loss": 0.5895,
"step": 19700
},
{
"epoch": 1.1,
"learning_rate": 0.0002,
"loss": 0.5865,
"step": 19800
},
{
"epoch": 1.11,
"learning_rate": 0.0002,
"loss": 0.5904,
"step": 19900
},
{
"epoch": 1.11,
"learning_rate": 0.0002,
"loss": 0.578,
"step": 20000
},
{
"epoch": 1.11,
"eval_gen_len": 18.99970077797726,
"eval_loss": 2.692544460296631,
"eval_rouge1": 25.2837,
"eval_rouge2": 12.3389,
"eval_rougeL": 20.91,
"eval_rougeLsum": 23.8923,
"eval_runtime": 488.8383,
"eval_samples_per_second": 27.346,
"eval_steps_per_second": 1.71,
"step": 20000
},
{
"epoch": 1.12,
"learning_rate": 0.0002,
"loss": 0.5816,
"step": 20100
},
{
"epoch": 1.13,
"learning_rate": 0.0002,
"loss": 0.602,
"step": 20200
},
{
"epoch": 1.13,
"learning_rate": 0.0002,
"loss": 0.594,
"step": 20300
},
{
"epoch": 1.14,
"learning_rate": 0.0002,
"loss": 0.5886,
"step": 20400
},
{
"epoch": 1.14,
"learning_rate": 0.0002,
"loss": 0.5985,
"step": 20500
},
{
"epoch": 1.15,
"learning_rate": 0.0002,
"loss": 0.5962,
"step": 20600
},
{
"epoch": 1.15,
"learning_rate": 0.0002,
"loss": 0.5733,
"step": 20700
},
{
"epoch": 1.16,
"learning_rate": 0.0002,
"loss": 0.5889,
"step": 20800
},
{
"epoch": 1.16,
"learning_rate": 0.0002,
"loss": 0.6017,
"step": 20900
},
{
"epoch": 1.17,
"learning_rate": 0.0002,
"loss": 0.5867,
"step": 21000
},
{
"epoch": 1.18,
"learning_rate": 0.0002,
"loss": 0.5847,
"step": 21100
},
{
"epoch": 1.18,
"learning_rate": 0.0002,
"loss": 0.5918,
"step": 21200
},
{
"epoch": 1.19,
"learning_rate": 0.0002,
"loss": 0.5794,
"step": 21300
},
{
"epoch": 1.19,
"learning_rate": 0.0002,
"loss": 0.5806,
"step": 21400
},
{
"epoch": 1.2,
"learning_rate": 0.0002,
"loss": 0.5855,
"step": 21500
},
{
"epoch": 1.2,
"learning_rate": 0.0002,
"loss": 0.5821,
"step": 21600
},
{
"epoch": 1.21,
"learning_rate": 0.0002,
"loss": 0.5735,
"step": 21700
},
{
"epoch": 1.21,
"learning_rate": 0.0002,
"loss": 0.5953,
"step": 21800
},
{
"epoch": 1.22,
"learning_rate": 0.0002,
"loss": 0.5904,
"step": 21900
},
{
"epoch": 1.23,
"learning_rate": 0.0002,
"loss": 0.5962,
"step": 22000
},
{
"epoch": 1.23,
"learning_rate": 0.0002,
"loss": 0.5942,
"step": 22100
},
{
"epoch": 1.24,
"learning_rate": 0.0002,
"loss": 0.5871,
"step": 22200
},
{
"epoch": 1.24,
"learning_rate": 0.0002,
"loss": 0.5851,
"step": 22300
},
{
"epoch": 1.25,
"learning_rate": 0.0002,
"loss": 0.5921,
"step": 22400
},
{
"epoch": 1.25,
"learning_rate": 0.0002,
"loss": 0.5971,
"step": 22500
},
{
"epoch": 1.26,
"learning_rate": 0.0002,
"loss": 0.5882,
"step": 22600
},
{
"epoch": 1.26,
"learning_rate": 0.0002,
"loss": 0.5813,
"step": 22700
},
{
"epoch": 1.27,
"learning_rate": 0.0002,
"loss": 0.5916,
"step": 22800
},
{
"epoch": 1.28,
"learning_rate": 0.0002,
"loss": 0.5959,
"step": 22900
},
{
"epoch": 1.28,
"learning_rate": 0.0002,
"loss": 0.5926,
"step": 23000
},
{
"epoch": 1.29,
"learning_rate": 0.0002,
"loss": 0.5883,
"step": 23100
},
{
"epoch": 1.29,
"learning_rate": 0.0002,
"loss": 0.5929,
"step": 23200
},
{
"epoch": 1.3,
"learning_rate": 0.0002,
"loss": 0.584,
"step": 23300
},
{
"epoch": 1.3,
"learning_rate": 0.0002,
"loss": 0.5957,
"step": 23400
},
{
"epoch": 1.31,
"learning_rate": 0.0002,
"loss": 0.5954,
"step": 23500
},
{
"epoch": 1.32,
"learning_rate": 0.0002,
"loss": 0.5938,
"step": 23600
},
{
"epoch": 1.32,
"learning_rate": 0.0002,
"loss": 0.5961,
"step": 23700
},
{
"epoch": 1.33,
"learning_rate": 0.0002,
"loss": 0.6012,
"step": 23800
},
{
"epoch": 1.33,
"learning_rate": 0.0002,
"loss": 0.5899,
"step": 23900
},
{
"epoch": 1.34,
"learning_rate": 0.0002,
"loss": 0.5941,
"step": 24000
},
{
"epoch": 1.34,
"learning_rate": 0.0002,
"loss": 0.5936,
"step": 24100
},
{
"epoch": 1.35,
"learning_rate": 0.0002,
"loss": 0.5912,
"step": 24200
},
{
"epoch": 1.35,
"learning_rate": 0.0002,
"loss": 0.5873,
"step": 24300
},
{
"epoch": 1.36,
"learning_rate": 0.0002,
"loss": 0.578,
"step": 24400
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 0.5942,
"step": 24500
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 0.5918,
"step": 24600
},
{
"epoch": 1.38,
"learning_rate": 0.0002,
"loss": 0.5923,
"step": 24700
},
{
"epoch": 1.38,
"learning_rate": 0.0002,
"loss": 0.5818,
"step": 24800
},
{
"epoch": 1.39,
"learning_rate": 0.0002,
"loss": 0.5904,
"step": 24900
},
{
"epoch": 1.39,
"learning_rate": 0.0002,
"loss": 0.5991,
"step": 25000
},
{
"epoch": 1.4,
"learning_rate": 0.0002,
"loss": 0.601,
"step": 25100
},
{
"epoch": 1.4,
"learning_rate": 0.0002,
"loss": 0.5919,
"step": 25200
},
{
"epoch": 1.41,
"learning_rate": 0.0002,
"loss": 0.5836,
"step": 25300
},
{
"epoch": 1.42,
"learning_rate": 0.0002,
"loss": 0.592,
"step": 25400
},
{
"epoch": 1.42,
"learning_rate": 0.0002,
"loss": 0.5917,
"step": 25500
},
{
"epoch": 1.43,
"learning_rate": 0.0002,
"loss": 0.5796,
"step": 25600
},
{
"epoch": 1.43,
"learning_rate": 0.0002,
"loss": 0.5914,
"step": 25700
},
{
"epoch": 1.44,
"learning_rate": 0.0002,
"loss": 0.5897,
"step": 25800
},
{
"epoch": 1.44,
"learning_rate": 0.0002,
"loss": 0.5851,
"step": 25900
},
{
"epoch": 1.45,
"learning_rate": 0.0002,
"loss": 0.5803,
"step": 26000
},
{
"epoch": 1.45,
"learning_rate": 0.0002,
"loss": 0.5905,
"step": 26100
},
{
"epoch": 1.46,
"learning_rate": 0.0002,
"loss": 0.598,
"step": 26200
},
{
"epoch": 1.47,
"learning_rate": 0.0002,
"loss": 0.5915,
"step": 26300
},
{
"epoch": 1.47,
"learning_rate": 0.0002,
"loss": 0.6016,
"step": 26400
},
{
"epoch": 1.48,
"learning_rate": 0.0002,
"loss": 0.593,
"step": 26500
},
{
"epoch": 1.48,
"learning_rate": 0.0002,
"loss": 0.5911,
"step": 26600
},
{
"epoch": 1.49,
"learning_rate": 0.0002,
"loss": 0.5933,
"step": 26700
},
{
"epoch": 1.49,
"learning_rate": 0.0002,
"loss": 0.613,
"step": 26800
},
{
"epoch": 1.5,
"learning_rate": 0.0002,
"loss": 0.5972,
"step": 26900
},
{
"epoch": 1.5,
"learning_rate": 0.0002,
"loss": 0.5806,
"step": 27000
},
{
"epoch": 1.51,
"learning_rate": 0.0002,
"loss": 0.5964,
"step": 27100
},
{
"epoch": 1.52,
"learning_rate": 0.0002,
"loss": 0.5815,
"step": 27200
},
{
"epoch": 1.52,
"learning_rate": 0.0002,
"loss": 0.6144,
"step": 27300
},
{
"epoch": 1.53,
"learning_rate": 0.0002,
"loss": 0.6142,
"step": 27400
},
{
"epoch": 1.53,
"learning_rate": 0.0002,
"loss": 0.583,
"step": 27500
},
{
"epoch": 1.54,
"learning_rate": 0.0002,
"loss": 0.5924,
"step": 27600
},
{
"epoch": 1.54,
"learning_rate": 0.0002,
"loss": 0.586,
"step": 27700
},
{
"epoch": 1.55,
"learning_rate": 0.0002,
"loss": 0.5985,
"step": 27800
},
{
"epoch": 1.55,
"learning_rate": 0.0002,
"loss": 0.5974,
"step": 27900
},
{
"epoch": 1.56,
"learning_rate": 0.0002,
"loss": 0.5967,
"step": 28000
},
{
"epoch": 1.57,
"learning_rate": 0.0002,
"loss": 0.5927,
"step": 28100
},
{
"epoch": 1.57,
"learning_rate": 0.0002,
"loss": 0.6018,
"step": 28200
},
{
"epoch": 1.58,
"learning_rate": 0.0002,
"loss": 0.5816,
"step": 28300
},
{
"epoch": 1.58,
"learning_rate": 0.0002,
"loss": 0.601,
"step": 28400
},
{
"epoch": 1.59,
"learning_rate": 0.0002,
"loss": 0.6021,
"step": 28500
},
{
"epoch": 1.59,
"learning_rate": 0.0002,
"loss": 0.5941,
"step": 28600
},
{
"epoch": 1.6,
"learning_rate": 0.0002,
"loss": 0.5921,
"step": 28700
},
{
"epoch": 1.6,
"learning_rate": 0.0002,
"loss": 0.6102,
"step": 28800
},
{
"epoch": 1.61,
"learning_rate": 0.0002,
"loss": 0.5957,
"step": 28900
},
{
"epoch": 1.62,
"learning_rate": 0.0002,
"loss": 0.5884,
"step": 29000
},
{
"epoch": 1.62,
"learning_rate": 0.0002,
"loss": 0.596,
"step": 29100
},
{
"epoch": 1.63,
"learning_rate": 0.0002,
"loss": 0.5879,
"step": 29200
},
{
"epoch": 1.63,
"learning_rate": 0.0002,
"loss": 0.5907,
"step": 29300
},
{
"epoch": 1.64,
"learning_rate": 0.0002,
"loss": 0.586,
"step": 29400
},
{
"epoch": 1.64,
"learning_rate": 0.0002,
"loss": 0.5921,
"step": 29500
},
{
"epoch": 1.65,
"learning_rate": 0.0002,
"loss": 0.5971,
"step": 29600
},
{
"epoch": 1.66,
"learning_rate": 0.0002,
"loss": 0.6035,
"step": 29700
},
{
"epoch": 1.66,
"learning_rate": 0.0002,
"loss": 0.6047,
"step": 29800
},
{
"epoch": 1.67,
"learning_rate": 0.0002,
"loss": 0.5819,
"step": 29900
},
{
"epoch": 1.67,
"learning_rate": 0.0002,
"loss": 0.6072,
"step": 30000
},
{
"epoch": 1.67,
"eval_gen_len": 18.99970077797726,
"eval_loss": 2.629517078399658,
"eval_rouge1": 25.3476,
"eval_rouge2": 12.4149,
"eval_rougeL": 20.9269,
"eval_rougeLsum": 23.9015,
"eval_runtime": 487.904,
"eval_samples_per_second": 27.399,
"eval_steps_per_second": 1.713,
"step": 30000
},
{
"epoch": 1.68,
"learning_rate": 0.0002,
"loss": 0.6078,
"step": 30100
},
{
"epoch": 1.68,
"learning_rate": 0.0002,
"loss": 0.5932,
"step": 30200
},
{
"epoch": 1.69,
"learning_rate": 0.0002,
"loss": 0.5958,
"step": 30300
},
{
"epoch": 1.69,
"learning_rate": 0.0002,
"loss": 0.5965,
"step": 30400
},
{
"epoch": 1.7,
"learning_rate": 0.0002,
"loss": 0.5863,
"step": 30500
},
{
"epoch": 1.71,
"learning_rate": 0.0002,
"loss": 0.5901,
"step": 30600
},
{
"epoch": 1.71,
"learning_rate": 0.0002,
"loss": 0.604,
"step": 30700
},
{
"epoch": 1.72,
"learning_rate": 0.0002,
"loss": 0.5981,
"step": 30800
},
{
"epoch": 1.72,
"learning_rate": 0.0002,
"loss": 0.5928,
"step": 30900
},
{
"epoch": 1.73,
"learning_rate": 0.0002,
"loss": 0.5911,
"step": 31000
},
{
"epoch": 1.73,
"learning_rate": 0.0002,
"loss": 0.5957,
"step": 31100
},
{
"epoch": 1.74,
"learning_rate": 0.0002,
"loss": 0.5924,
"step": 31200
},
{
"epoch": 1.74,
"learning_rate": 0.0002,
"loss": 0.5909,
"step": 31300
},
{
"epoch": 1.75,
"learning_rate": 0.0002,
"loss": 0.6015,
"step": 31400
},
{
"epoch": 1.76,
"learning_rate": 0.0002,
"loss": 0.5902,
"step": 31500
},
{
"epoch": 1.76,
"learning_rate": 0.0002,
"loss": 0.5853,
"step": 31600
},
{
"epoch": 1.77,
"learning_rate": 0.0002,
"loss": 0.5808,
"step": 31700
},
{
"epoch": 1.77,
"learning_rate": 0.0002,
"loss": 0.6019,
"step": 31800
},
{
"epoch": 1.78,
"learning_rate": 0.0002,
"loss": 0.6043,
"step": 31900
},
{
"epoch": 1.78,
"learning_rate": 0.0002,
"loss": 0.5967,
"step": 32000
},
{
"epoch": 1.79,
"learning_rate": 0.0002,
"loss": 0.6074,
"step": 32100
},
{
"epoch": 1.79,
"learning_rate": 0.0002,
"loss": 0.5957,
"step": 32200
},
{
"epoch": 1.8,
"learning_rate": 0.0002,
"loss": 0.5929,
"step": 32300
},
{
"epoch": 1.81,
"learning_rate": 0.0002,
"loss": 0.6048,
"step": 32400
},
{
"epoch": 1.81,
"learning_rate": 0.0002,
"loss": 0.5983,
"step": 32500
},
{
"epoch": 1.82,
"learning_rate": 0.0002,
"loss": 0.6049,
"step": 32600
},
{
"epoch": 1.82,
"learning_rate": 0.0002,
"loss": 0.5919,
"step": 32700
},
{
"epoch": 1.83,
"learning_rate": 0.0002,
"loss": 0.5978,
"step": 32800
},
{
"epoch": 1.83,
"learning_rate": 0.0002,
"loss": 0.6035,
"step": 32900
},
{
"epoch": 1.84,
"learning_rate": 0.0002,
"loss": 0.5923,
"step": 33000
},
{
"epoch": 1.84,
"learning_rate": 0.0002,
"loss": 0.599,
"step": 33100
},
{
"epoch": 1.85,
"learning_rate": 0.0002,
"loss": 0.6021,
"step": 33200
},
{
"epoch": 1.86,
"learning_rate": 0.0002,
"loss": 0.6071,
"step": 33300
},
{
"epoch": 1.86,
"learning_rate": 0.0002,
"loss": 0.6054,
"step": 33400
},
{
"epoch": 1.87,
"learning_rate": 0.0002,
"loss": 0.6068,
"step": 33500
},
{
"epoch": 1.87,
"learning_rate": 0.0002,
"loss": 0.6015,
"step": 33600
},
{
"epoch": 1.88,
"learning_rate": 0.0002,
"loss": 0.6029,
"step": 33700
},
{
"epoch": 1.88,
"learning_rate": 0.0002,
"loss": 0.6054,
"step": 33800
},
{
"epoch": 1.89,
"learning_rate": 0.0002,
"loss": 0.6003,
"step": 33900
},
{
"epoch": 1.89,
"learning_rate": 0.0002,
"loss": 0.6049,
"step": 34000
},
{
"epoch": 1.9,
"learning_rate": 0.0002,
"loss": 0.5992,
"step": 34100
},
{
"epoch": 1.91,
"learning_rate": 0.0002,
"loss": 0.605,
"step": 34200
},
{
"epoch": 1.91,
"learning_rate": 0.0002,
"loss": 0.604,
"step": 34300
},
{
"epoch": 1.92,
"learning_rate": 0.0002,
"loss": 0.6024,
"step": 34400
},
{
"epoch": 1.92,
"learning_rate": 0.0002,
"loss": 0.6052,
"step": 34500
},
{
"epoch": 1.93,
"learning_rate": 0.0002,
"loss": 0.6082,
"step": 34600
},
{
"epoch": 1.93,
"learning_rate": 0.0002,
"loss": 0.5998,
"step": 34700
},
{
"epoch": 1.94,
"learning_rate": 0.0002,
"loss": 0.5957,
"step": 34800
},
{
"epoch": 1.94,
"learning_rate": 0.0002,
"loss": 0.6004,
"step": 34900
},
{
"epoch": 1.95,
"learning_rate": 0.0002,
"loss": 0.6019,
"step": 35000
},
{
"epoch": 1.96,
"learning_rate": 0.0002,
"loss": 0.5966,
"step": 35100
},
{
"epoch": 1.96,
"learning_rate": 0.0002,
"loss": 0.6017,
"step": 35200
},
{
"epoch": 1.97,
"learning_rate": 0.0002,
"loss": 0.5934,
"step": 35300
},
{
"epoch": 1.97,
"learning_rate": 0.0002,
"loss": 0.6139,
"step": 35400
},
{
"epoch": 1.98,
"learning_rate": 0.0002,
"loss": 0.6122,
"step": 35500
},
{
"epoch": 1.98,
"learning_rate": 0.0002,
"loss": 0.6056,
"step": 35600
},
{
"epoch": 1.99,
"learning_rate": 0.0002,
"loss": 0.6016,
"step": 35700
},
{
"epoch": 1.99,
"learning_rate": 0.0002,
"loss": 0.5992,
"step": 35800
},
{
"epoch": 2.0,
"learning_rate": 0.0002,
"loss": 0.6011,
"step": 35900
},
{
"epoch": 2.01,
"learning_rate": 0.0002,
"loss": 0.5693,
"step": 36000
},
{
"epoch": 2.01,
"learning_rate": 0.0002,
"loss": 0.58,
"step": 36100
},
{
"epoch": 2.02,
"learning_rate": 0.0002,
"loss": 0.5761,
"step": 36200
},
{
"epoch": 2.02,
"learning_rate": 0.0002,
"loss": 0.5743,
"step": 36300
},
{
"epoch": 2.03,
"learning_rate": 0.0002,
"loss": 0.596,
"step": 36400
},
{
"epoch": 2.03,
"learning_rate": 0.0002,
"loss": 0.5819,
"step": 36500
},
{
"epoch": 2.04,
"learning_rate": 0.0002,
"loss": 0.5774,
"step": 36600
},
{
"epoch": 2.05,
"learning_rate": 0.0002,
"loss": 0.5728,
"step": 36700
},
{
"epoch": 2.05,
"learning_rate": 0.0002,
"loss": 0.5731,
"step": 36800
},
{
"epoch": 2.06,
"learning_rate": 0.0002,
"loss": 0.5581,
"step": 36900
},
{
"epoch": 2.06,
"learning_rate": 0.0002,
"loss": 0.5765,
"step": 37000
},
{
"epoch": 2.07,
"learning_rate": 0.0002,
"loss": 0.5834,
"step": 37100
},
{
"epoch": 2.07,
"learning_rate": 0.0002,
"loss": 0.5782,
"step": 37200
},
{
"epoch": 2.08,
"learning_rate": 0.0002,
"loss": 0.5666,
"step": 37300
},
{
"epoch": 2.08,
"learning_rate": 0.0002,
"loss": 0.5876,
"step": 37400
},
{
"epoch": 2.09,
"learning_rate": 0.0002,
"loss": 0.5814,
"step": 37500
},
{
"epoch": 2.1,
"learning_rate": 0.0002,
"loss": 0.5725,
"step": 37600
},
{
"epoch": 2.1,
"learning_rate": 0.0002,
"loss": 0.577,
"step": 37700
},
{
"epoch": 2.11,
"learning_rate": 0.0002,
"loss": 0.5717,
"step": 37800
},
{
"epoch": 2.11,
"learning_rate": 0.0002,
"loss": 0.5775,
"step": 37900
},
{
"epoch": 2.12,
"learning_rate": 0.0002,
"loss": 0.5777,
"step": 38000
},
{
"epoch": 2.12,
"learning_rate": 0.0002,
"loss": 0.5907,
"step": 38100
},
{
"epoch": 2.13,
"learning_rate": 0.0002,
"loss": 0.5656,
"step": 38200
},
{
"epoch": 2.13,
"learning_rate": 0.0002,
"loss": 0.574,
"step": 38300
},
{
"epoch": 2.14,
"learning_rate": 0.0002,
"loss": 0.5883,
"step": 38400
},
{
"epoch": 2.15,
"learning_rate": 0.0002,
"loss": 0.5836,
"step": 38500
},
{
"epoch": 2.15,
"learning_rate": 0.0002,
"loss": 0.5699,
"step": 38600
},
{
"epoch": 2.16,
"learning_rate": 0.0002,
"loss": 0.5808,
"step": 38700
},
{
"epoch": 2.16,
"learning_rate": 0.0002,
"loss": 0.5871,
"step": 38800
},
{
"epoch": 2.17,
"learning_rate": 0.0002,
"loss": 0.5876,
"step": 38900
},
{
"epoch": 2.17,
"learning_rate": 0.0002,
"loss": 0.5783,
"step": 39000
},
{
"epoch": 2.18,
"learning_rate": 0.0002,
"loss": 0.5787,
"step": 39100
},
{
"epoch": 2.18,
"learning_rate": 0.0002,
"loss": 0.5748,
"step": 39200
},
{
"epoch": 2.19,
"learning_rate": 0.0002,
"loss": 0.5892,
"step": 39300
},
{
"epoch": 2.2,
"learning_rate": 0.0002,
"loss": 0.574,
"step": 39400
},
{
"epoch": 2.2,
"learning_rate": 0.0002,
"loss": 0.5739,
"step": 39500
},
{
"epoch": 2.21,
"learning_rate": 0.0002,
"loss": 0.5854,
"step": 39600
},
{
"epoch": 2.21,
"learning_rate": 0.0002,
"loss": 0.5805,
"step": 39700
},
{
"epoch": 2.22,
"learning_rate": 0.0002,
"loss": 0.583,
"step": 39800
},
{
"epoch": 2.22,
"learning_rate": 0.0002,
"loss": 0.5755,
"step": 39900
},
{
"epoch": 2.23,
"learning_rate": 0.0002,
"loss": 0.5823,
"step": 40000
},
{
"epoch": 2.23,
"eval_gen_len": 18.999326750448834,
"eval_loss": 2.674076557159424,
"eval_rouge1": 25.2523,
"eval_rouge2": 12.374,
"eval_rougeL": 20.8567,
"eval_rougeLsum": 23.8483,
"eval_runtime": 489.0303,
"eval_samples_per_second": 27.336,
"eval_steps_per_second": 1.71,
"step": 40000
},
{
"epoch": 2.23,
"learning_rate": 0.0002,
"loss": 0.5809,
"step": 40100
},
{
"epoch": 2.24,
"learning_rate": 0.0002,
"loss": 0.584,
"step": 40200
},
{
"epoch": 2.25,
"learning_rate": 0.0002,
"loss": 0.5734,
"step": 40300
},
{
"epoch": 2.25,
"learning_rate": 0.0002,
"loss": 0.5707,
"step": 40400
},
{
"epoch": 2.26,
"learning_rate": 0.0002,
"loss": 0.5797,
"step": 40500
},
{
"epoch": 2.26,
"learning_rate": 0.0002,
"loss": 0.5752,
"step": 40600
},
{
"epoch": 2.27,
"learning_rate": 0.0002,
"loss": 0.5887,
"step": 40700
},
{
"epoch": 2.27,
"learning_rate": 0.0002,
"loss": 0.5814,
"step": 40800
},
{
"epoch": 2.28,
"learning_rate": 0.0002,
"loss": 0.5852,
"step": 40900
},
{
"epoch": 2.28,
"learning_rate": 0.0002,
"loss": 0.5796,
"step": 41000
},
{
"epoch": 2.29,
"learning_rate": 0.0002,
"loss": 0.5758,
"step": 41100
},
{
"epoch": 2.3,
"learning_rate": 0.0002,
"loss": 0.5844,
"step": 41200
},
{
"epoch": 2.3,
"learning_rate": 0.0002,
"loss": 0.5859,
"step": 41300
},
{
"epoch": 2.31,
"learning_rate": 0.0002,
"loss": 0.5693,
"step": 41400
},
{
"epoch": 2.31,
"learning_rate": 0.0002,
"loss": 0.5805,
"step": 41500
},
{
"epoch": 2.32,
"learning_rate": 0.0002,
"loss": 0.5677,
"step": 41600
},
{
"epoch": 2.32,
"learning_rate": 0.0002,
"loss": 0.5764,
"step": 41700
},
{
"epoch": 2.33,
"learning_rate": 0.0002,
"loss": 0.568,
"step": 41800
},
{
"epoch": 2.33,
"learning_rate": 0.0002,
"loss": 0.573,
"step": 41900
},
{
"epoch": 2.34,
"learning_rate": 0.0002,
"loss": 0.5856,
"step": 42000
},
{
"epoch": 2.35,
"learning_rate": 0.0002,
"loss": 0.5831,
"step": 42100
},
{
"epoch": 2.35,
"learning_rate": 0.0002,
"loss": 0.5815,
"step": 42200
},
{
"epoch": 2.36,
"learning_rate": 0.0002,
"loss": 0.5834,
"step": 42300
},
{
"epoch": 2.36,
"learning_rate": 0.0002,
"loss": 0.5786,
"step": 42400
},
{
"epoch": 2.37,
"learning_rate": 0.0002,
"loss": 0.5914,
"step": 42500
},
{
"epoch": 2.37,
"learning_rate": 0.0002,
"loss": 0.5717,
"step": 42600
},
{
"epoch": 2.38,
"learning_rate": 0.0002,
"loss": 0.5857,
"step": 42700
},
{
"epoch": 2.39,
"learning_rate": 0.0002,
"loss": 0.591,
"step": 42800
},
{
"epoch": 2.39,
"learning_rate": 0.0002,
"loss": 0.59,
"step": 42900
},
{
"epoch": 2.4,
"learning_rate": 0.0002,
"loss": 0.5756,
"step": 43000
},
{
"epoch": 2.4,
"learning_rate": 0.0002,
"loss": 0.5975,
"step": 43100
},
{
"epoch": 2.41,
"learning_rate": 0.0002,
"loss": 0.5751,
"step": 43200
},
{
"epoch": 2.41,
"learning_rate": 0.0002,
"loss": 0.5824,
"step": 43300
},
{
"epoch": 2.42,
"learning_rate": 0.0002,
"loss": 0.5916,
"step": 43400
},
{
"epoch": 2.42,
"learning_rate": 0.0002,
"loss": 0.575,
"step": 43500
},
{
"epoch": 2.43,
"learning_rate": 0.0002,
"loss": 0.5894,
"step": 43600
},
{
"epoch": 2.44,
"learning_rate": 0.0002,
"loss": 0.5894,
"step": 43700
},
{
"epoch": 2.44,
"learning_rate": 0.0002,
"loss": 0.5753,
"step": 43800
},
{
"epoch": 2.45,
"learning_rate": 0.0002,
"loss": 0.5857,
"step": 43900
},
{
"epoch": 2.45,
"learning_rate": 0.0002,
"loss": 0.5766,
"step": 44000
},
{
"epoch": 2.46,
"learning_rate": 0.0002,
"loss": 0.5763,
"step": 44100
},
{
"epoch": 2.46,
"learning_rate": 0.0002,
"loss": 0.576,
"step": 44200
},
{
"epoch": 2.47,
"learning_rate": 0.0002,
"loss": 0.5874,
"step": 44300
},
{
"epoch": 2.47,
"learning_rate": 0.0002,
"loss": 0.5772,
"step": 44400
},
{
"epoch": 2.48,
"learning_rate": 0.0002,
"loss": 0.5825,
"step": 44500
},
{
"epoch": 2.49,
"learning_rate": 0.0002,
"loss": 0.5925,
"step": 44600
},
{
"epoch": 2.49,
"learning_rate": 0.0002,
"loss": 0.5797,
"step": 44700
},
{
"epoch": 2.5,
"learning_rate": 0.0002,
"loss": 0.5805,
"step": 44800
},
{
"epoch": 2.5,
"learning_rate": 0.0002,
"loss": 0.5747,
"step": 44900
},
{
"epoch": 2.51,
"learning_rate": 0.0002,
"loss": 0.591,
"step": 45000
},
{
"epoch": 2.51,
"learning_rate": 0.0002,
"loss": 0.5858,
"step": 45100
},
{
"epoch": 2.52,
"learning_rate": 0.0002,
"loss": 0.5865,
"step": 45200
},
{
"epoch": 2.52,
"learning_rate": 0.0002,
"loss": 0.5849,
"step": 45300
},
{
"epoch": 2.53,
"learning_rate": 0.0002,
"loss": 0.5829,
"step": 45400
},
{
"epoch": 2.54,
"learning_rate": 0.0002,
"loss": 0.5974,
"step": 45500
},
{
"epoch": 2.54,
"learning_rate": 0.0002,
"loss": 0.5808,
"step": 45600
},
{
"epoch": 2.55,
"learning_rate": 0.0002,
"loss": 0.582,
"step": 45700
},
{
"epoch": 2.55,
"learning_rate": 0.0002,
"loss": 0.5809,
"step": 45800
},
{
"epoch": 2.56,
"learning_rate": 0.0002,
"loss": 0.5842,
"step": 45900
},
{
"epoch": 2.56,
"learning_rate": 0.0002,
"loss": 0.5924,
"step": 46000
},
{
"epoch": 2.57,
"learning_rate": 0.0002,
"loss": 0.5927,
"step": 46100
},
{
"epoch": 2.57,
"learning_rate": 0.0002,
"loss": 0.6064,
"step": 46200
},
{
"epoch": 2.58,
"learning_rate": 0.0002,
"loss": 0.5891,
"step": 46300
},
{
"epoch": 2.59,
"learning_rate": 0.0002,
"loss": 0.5968,
"step": 46400
},
{
"epoch": 2.59,
"learning_rate": 0.0002,
"loss": 0.5984,
"step": 46500
},
{
"epoch": 2.6,
"learning_rate": 0.0002,
"loss": 0.5988,
"step": 46600
},
{
"epoch": 2.6,
"learning_rate": 0.0002,
"loss": 0.5838,
"step": 46700
},
{
"epoch": 2.61,
"learning_rate": 0.0002,
"loss": 0.5851,
"step": 46800
},
{
"epoch": 2.61,
"learning_rate": 0.0002,
"loss": 0.5889,
"step": 46900
},
{
"epoch": 2.62,
"learning_rate": 0.0002,
"loss": 0.5814,
"step": 47000
},
{
"epoch": 2.62,
"learning_rate": 0.0002,
"loss": 0.5874,
"step": 47100
},
{
"epoch": 2.63,
"learning_rate": 0.0002,
"loss": 0.5747,
"step": 47200
},
{
"epoch": 2.64,
"learning_rate": 0.0002,
"loss": 0.5752,
"step": 47300
},
{
"epoch": 2.64,
"learning_rate": 0.0002,
"loss": 0.5863,
"step": 47400
},
{
"epoch": 2.65,
"learning_rate": 0.0002,
"loss": 0.5961,
"step": 47500
},
{
"epoch": 2.65,
"learning_rate": 0.0002,
"loss": 0.5942,
"step": 47600
},
{
"epoch": 2.66,
"learning_rate": 0.0002,
"loss": 0.5969,
"step": 47700
},
{
"epoch": 2.66,
"learning_rate": 0.0002,
"loss": 0.5686,
"step": 47800
},
{
"epoch": 2.67,
"learning_rate": 0.0002,
"loss": 0.5889,
"step": 47900
},
{
"epoch": 2.67,
"learning_rate": 0.0002,
"loss": 0.5823,
"step": 48000
},
{
"epoch": 2.68,
"learning_rate": 0.0002,
"loss": 0.5915,
"step": 48100
},
{
"epoch": 2.69,
"learning_rate": 0.0002,
"loss": 0.5911,
"step": 48200
},
{
"epoch": 2.69,
"learning_rate": 0.0002,
"loss": 0.5729,
"step": 48300
},
{
"epoch": 2.7,
"learning_rate": 0.0002,
"loss": 0.5869,
"step": 48400
},
{
"epoch": 2.7,
"learning_rate": 0.0002,
"loss": 0.5831,
"step": 48500
},
{
"epoch": 2.71,
"learning_rate": 0.0002,
"loss": 0.5893,
"step": 48600
},
{
"epoch": 2.71,
"learning_rate": 0.0002,
"loss": 0.5912,
"step": 48700
},
{
"epoch": 2.72,
"learning_rate": 0.0002,
"loss": 0.5927,
"step": 48800
},
{
"epoch": 2.72,
"learning_rate": 0.0002,
"loss": 0.5816,
"step": 48900
},
{
"epoch": 2.73,
"learning_rate": 0.0002,
"loss": 0.5849,
"step": 49000
},
{
"epoch": 2.74,
"learning_rate": 0.0002,
"loss": 0.5918,
"step": 49100
},
{
"epoch": 2.74,
"learning_rate": 0.0002,
"loss": 0.5974,
"step": 49200
},
{
"epoch": 2.75,
"learning_rate": 0.0002,
"loss": 0.5887,
"step": 49300
},
{
"epoch": 2.75,
"learning_rate": 0.0002,
"loss": 0.5906,
"step": 49400
},
{
"epoch": 2.76,
"learning_rate": 0.0002,
"loss": 0.5889,
"step": 49500
},
{
"epoch": 2.76,
"learning_rate": 0.0002,
"loss": 0.5868,
"step": 49600
},
{
"epoch": 2.77,
"learning_rate": 0.0002,
"loss": 0.5709,
"step": 49700
},
{
"epoch": 2.78,
"learning_rate": 0.0002,
"loss": 0.5891,
"step": 49800
},
{
"epoch": 2.78,
"learning_rate": 0.0002,
"loss": 0.6005,
"step": 49900
},
{
"epoch": 2.79,
"learning_rate": 0.0002,
"loss": 0.6005,
"step": 50000
},
{
"epoch": 2.79,
"eval_gen_len": 18.999476361460204,
"eval_loss": 2.6170895099639893,
"eval_rouge1": 25.4354,
"eval_rouge2": 12.4785,
"eval_rougeL": 20.9991,
"eval_rougeLsum": 24.0222,
"eval_runtime": 478.2398,
"eval_samples_per_second": 27.953,
"eval_steps_per_second": 1.748,
"step": 50000
},
{
"epoch": 2.79,
"learning_rate": 0.0002,
"loss": 0.5748,
"step": 50100
},
{
"epoch": 2.8,
"learning_rate": 0.0002,
"loss": 0.6024,
"step": 50200
},
{
"epoch": 2.8,
"learning_rate": 0.0002,
"loss": 0.5859,
"step": 50300
},
{
"epoch": 2.81,
"learning_rate": 0.0002,
"loss": 0.5833,
"step": 50400
},
{
"epoch": 2.81,
"learning_rate": 0.0002,
"loss": 0.5993,
"step": 50500
},
{
"epoch": 2.82,
"learning_rate": 0.0002,
"loss": 0.5915,
"step": 50600
},
{
"epoch": 2.83,
"learning_rate": 0.0002,
"loss": 0.6065,
"step": 50700
},
{
"epoch": 2.83,
"learning_rate": 0.0002,
"loss": 0.588,
"step": 50800
},
{
"epoch": 2.84,
"learning_rate": 0.0002,
"loss": 0.5919,
"step": 50900
},
{
"epoch": 2.84,
"learning_rate": 0.0002,
"loss": 0.602,
"step": 51000
},
{
"epoch": 2.85,
"learning_rate": 0.0002,
"loss": 0.5956,
"step": 51100
},
{
"epoch": 2.85,
"learning_rate": 0.0002,
"loss": 0.5902,
"step": 51200
},
{
"epoch": 2.86,
"learning_rate": 0.0002,
"loss": 0.5957,
"step": 51300
},
{
"epoch": 2.86,
"learning_rate": 0.0002,
"loss": 0.59,
"step": 51400
},
{
"epoch": 2.87,
"learning_rate": 0.0002,
"loss": 0.5979,
"step": 51500
},
{
"epoch": 2.88,
"learning_rate": 0.0002,
"loss": 0.5866,
"step": 51600
},
{
"epoch": 2.88,
"learning_rate": 0.0002,
"loss": 0.6044,
"step": 51700
},
{
"epoch": 2.89,
"learning_rate": 0.0002,
"loss": 0.6081,
"step": 51800
},
{
"epoch": 2.89,
"learning_rate": 0.0002,
"loss": 0.5913,
"step": 51900
},
{
"epoch": 2.9,
"learning_rate": 0.0002,
"loss": 0.5963,
"step": 52000
},
{
"epoch": 2.9,
"learning_rate": 0.0002,
"loss": 0.5866,
"step": 52100
},
{
"epoch": 2.91,
"learning_rate": 0.0002,
"loss": 0.5958,
"step": 52200
},
{
"epoch": 2.91,
"learning_rate": 0.0002,
"loss": 0.5928,
"step": 52300
},
{
"epoch": 2.92,
"learning_rate": 0.0002,
"loss": 0.598,
"step": 52400
},
{
"epoch": 2.93,
"learning_rate": 0.0002,
"loss": 0.5956,
"step": 52500
},
{
"epoch": 2.93,
"learning_rate": 0.0002,
"loss": 0.5936,
"step": 52600
},
{
"epoch": 2.94,
"learning_rate": 0.0002,
"loss": 0.5993,
"step": 52700
},
{
"epoch": 2.94,
"learning_rate": 0.0002,
"loss": 0.595,
"step": 52800
},
{
"epoch": 2.95,
"learning_rate": 0.0002,
"loss": 0.5832,
"step": 52900
},
{
"epoch": 2.95,
"learning_rate": 0.0002,
"loss": 0.5852,
"step": 53000
},
{
"epoch": 2.96,
"learning_rate": 0.0002,
"loss": 0.6021,
"step": 53100
},
{
"epoch": 2.96,
"learning_rate": 0.0002,
"loss": 0.5775,
"step": 53200
},
{
"epoch": 2.97,
"learning_rate": 0.0002,
"loss": 0.5884,
"step": 53300
},
{
"epoch": 2.98,
"learning_rate": 0.0002,
"loss": 0.5869,
"step": 53400
},
{
"epoch": 2.98,
"learning_rate": 0.0002,
"loss": 0.591,
"step": 53500
},
{
"epoch": 2.99,
"learning_rate": 0.0002,
"loss": 0.6016,
"step": 53600
},
{
"epoch": 2.99,
"learning_rate": 0.0002,
"loss": 0.5903,
"step": 53700
},
{
"epoch": 3.0,
"learning_rate": 0.0002,
"loss": 0.6011,
"step": 53800
},
{
"epoch": 3.0,
"learning_rate": 0.0002,
"loss": 0.5817,
"step": 53900
},
{
"epoch": 3.01,
"learning_rate": 0.0002,
"loss": 0.5661,
"step": 54000
},
{
"epoch": 3.01,
"learning_rate": 0.0002,
"loss": 0.5718,
"step": 54100
},
{
"epoch": 3.02,
"learning_rate": 0.0002,
"loss": 0.5666,
"step": 54200
},
{
"epoch": 3.03,
"learning_rate": 0.0002,
"loss": 0.5652,
"step": 54300
},
{
"epoch": 3.03,
"learning_rate": 0.0002,
"loss": 0.5642,
"step": 54400
},
{
"epoch": 3.04,
"learning_rate": 0.0002,
"loss": 0.5686,
"step": 54500
},
{
"epoch": 3.04,
"learning_rate": 0.0002,
"loss": 0.5641,
"step": 54600
},
{
"epoch": 3.05,
"learning_rate": 0.0002,
"loss": 0.5638,
"step": 54700
},
{
"epoch": 3.05,
"learning_rate": 0.0002,
"loss": 0.5696,
"step": 54800
},
{
"epoch": 3.06,
"learning_rate": 0.0002,
"loss": 0.5741,
"step": 54900
},
{
"epoch": 3.06,
"learning_rate": 0.0002,
"loss": 0.5615,
"step": 55000
},
{
"epoch": 3.07,
"learning_rate": 0.0002,
"loss": 0.5784,
"step": 55100
},
{
"epoch": 3.08,
"learning_rate": 0.0002,
"loss": 0.5653,
"step": 55200
},
{
"epoch": 3.08,
"learning_rate": 0.0002,
"loss": 0.5747,
"step": 55300
},
{
"epoch": 3.09,
"learning_rate": 0.0002,
"loss": 0.5537,
"step": 55400
},
{
"epoch": 3.09,
"learning_rate": 0.0002,
"loss": 0.5715,
"step": 55500
},
{
"epoch": 3.1,
"learning_rate": 0.0002,
"loss": 0.5653,
"step": 55600
},
{
"epoch": 3.1,
"learning_rate": 0.0002,
"loss": 0.5816,
"step": 55700
},
{
"epoch": 3.11,
"learning_rate": 0.0002,
"loss": 0.5714,
"step": 55800
},
{
"epoch": 3.12,
"learning_rate": 0.0002,
"loss": 0.5657,
"step": 55900
},
{
"epoch": 3.12,
"learning_rate": 0.0002,
"loss": 0.5628,
"step": 56000
},
{
"epoch": 3.13,
"learning_rate": 0.0002,
"loss": 0.5718,
"step": 56100
},
{
"epoch": 3.13,
"learning_rate": 0.0002,
"loss": 0.5609,
"step": 56200
},
{
"epoch": 3.14,
"learning_rate": 0.0002,
"loss": 0.567,
"step": 56300
},
{
"epoch": 3.14,
"learning_rate": 0.0002,
"loss": 0.5624,
"step": 56400
},
{
"epoch": 3.15,
"learning_rate": 0.0002,
"loss": 0.5781,
"step": 56500
},
{
"epoch": 3.15,
"learning_rate": 0.0002,
"loss": 0.5673,
"step": 56600
},
{
"epoch": 3.16,
"learning_rate": 0.0002,
"loss": 0.5561,
"step": 56700
},
{
"epoch": 3.17,
"learning_rate": 0.0002,
"loss": 0.5635,
"step": 56800
},
{
"epoch": 3.17,
"learning_rate": 0.0002,
"loss": 0.5719,
"step": 56900
},
{
"epoch": 3.18,
"learning_rate": 0.0002,
"loss": 0.5809,
"step": 57000
},
{
"epoch": 3.18,
"learning_rate": 0.0002,
"loss": 0.577,
"step": 57100
},
{
"epoch": 3.19,
"learning_rate": 0.0002,
"loss": 0.5801,
"step": 57200
},
{
"epoch": 3.19,
"learning_rate": 0.0002,
"loss": 0.5742,
"step": 57300
},
{
"epoch": 3.2,
"learning_rate": 0.0002,
"loss": 0.5615,
"step": 57400
},
{
"epoch": 3.2,
"learning_rate": 0.0002,
"loss": 0.5636,
"step": 57500
},
{
"epoch": 3.21,
"learning_rate": 0.0002,
"loss": 0.5679,
"step": 57600
},
{
"epoch": 3.22,
"learning_rate": 0.0002,
"loss": 0.5935,
"step": 57700
},
{
"epoch": 3.22,
"learning_rate": 0.0002,
"loss": 0.5807,
"step": 57800
},
{
"epoch": 3.23,
"learning_rate": 0.0002,
"loss": 0.564,
"step": 57900
},
{
"epoch": 3.23,
"learning_rate": 0.0002,
"loss": 0.5651,
"step": 58000
},
{
"epoch": 3.24,
"learning_rate": 0.0002,
"loss": 0.5757,
"step": 58100
},
{
"epoch": 3.24,
"learning_rate": 0.0002,
"loss": 0.5674,
"step": 58200
},
{
"epoch": 3.25,
"learning_rate": 0.0002,
"loss": 0.576,
"step": 58300
},
{
"epoch": 3.25,
"learning_rate": 0.0002,
"loss": 0.5661,
"step": 58400
},
{
"epoch": 3.26,
"learning_rate": 0.0002,
"loss": 0.5748,
"step": 58500
},
{
"epoch": 3.27,
"learning_rate": 0.0002,
"loss": 0.5732,
"step": 58600
},
{
"epoch": 3.27,
"learning_rate": 0.0002,
"loss": 0.5791,
"step": 58700
},
{
"epoch": 3.28,
"learning_rate": 0.0002,
"loss": 0.5658,
"step": 58800
},
{
"epoch": 3.28,
"learning_rate": 0.0002,
"loss": 0.577,
"step": 58900
},
{
"epoch": 3.29,
"learning_rate": 0.0002,
"loss": 0.5809,
"step": 59000
},
{
"epoch": 3.29,
"learning_rate": 0.0002,
"loss": 0.5807,
"step": 59100
},
{
"epoch": 3.3,
"learning_rate": 0.0002,
"loss": 0.5686,
"step": 59200
},
{
"epoch": 3.3,
"learning_rate": 0.0002,
"loss": 0.5679,
"step": 59300
},
{
"epoch": 3.31,
"learning_rate": 0.0002,
"loss": 0.5861,
"step": 59400
},
{
"epoch": 3.32,
"learning_rate": 0.0002,
"loss": 0.5753,
"step": 59500
},
{
"epoch": 3.32,
"learning_rate": 0.0002,
"loss": 0.5636,
"step": 59600
},
{
"epoch": 3.33,
"learning_rate": 0.0002,
"loss": 0.5711,
"step": 59700
},
{
"epoch": 3.33,
"learning_rate": 0.0002,
"loss": 0.5762,
"step": 59800
},
{
"epoch": 3.34,
"learning_rate": 0.0002,
"loss": 0.5712,
"step": 59900
},
{
"epoch": 3.34,
"learning_rate": 0.0002,
"loss": 0.5757,
"step": 60000
},
{
"epoch": 3.34,
"eval_gen_len": 18.999925194494313,
"eval_loss": 2.659139394760132,
"eval_rouge1": 25.3502,
"eval_rouge2": 12.4437,
"eval_rougeL": 20.9208,
"eval_rougeLsum": 23.9305,
"eval_runtime": 475.715,
"eval_samples_per_second": 28.101,
"eval_steps_per_second": 1.757,
"step": 60000
},
{
"epoch": 3.35,
"learning_rate": 0.0002,
"loss": 0.5747,
"step": 60100
},
{
"epoch": 3.35,
"learning_rate": 0.0002,
"loss": 0.5769,
"step": 60200
},
{
"epoch": 3.36,
"learning_rate": 0.0002,
"loss": 0.5794,
"step": 60300
},
{
"epoch": 3.37,
"learning_rate": 0.0002,
"loss": 0.581,
"step": 60400
},
{
"epoch": 3.37,
"learning_rate": 0.0002,
"loss": 0.5785,
"step": 60500
},
{
"epoch": 3.38,
"learning_rate": 0.0002,
"loss": 0.5871,
"step": 60600
},
{
"epoch": 3.38,
"learning_rate": 0.0002,
"loss": 0.5682,
"step": 60700
},
{
"epoch": 3.39,
"learning_rate": 0.0002,
"loss": 0.5752,
"step": 60800
},
{
"epoch": 3.39,
"learning_rate": 0.0002,
"loss": 0.5789,
"step": 60900
},
{
"epoch": 3.4,
"learning_rate": 0.0002,
"loss": 0.5722,
"step": 61000
},
{
"epoch": 3.4,
"learning_rate": 0.0002,
"loss": 0.5862,
"step": 61100
},
{
"epoch": 3.41,
"learning_rate": 0.0002,
"loss": 0.5649,
"step": 61200
},
{
"epoch": 3.42,
"learning_rate": 0.0002,
"loss": 0.5761,
"step": 61300
},
{
"epoch": 3.42,
"learning_rate": 0.0002,
"loss": 0.5655,
"step": 61400
},
{
"epoch": 3.43,
"learning_rate": 0.0002,
"loss": 0.5642,
"step": 61500
},
{
"epoch": 3.43,
"learning_rate": 0.0002,
"loss": 0.573,
"step": 61600
},
{
"epoch": 3.44,
"learning_rate": 0.0002,
"loss": 0.5891,
"step": 61700
},
{
"epoch": 3.44,
"learning_rate": 0.0002,
"loss": 0.579,
"step": 61800
},
{
"epoch": 3.45,
"learning_rate": 0.0002,
"loss": 0.5825,
"step": 61900
},
{
"epoch": 3.46,
"learning_rate": 0.0002,
"loss": 0.5834,
"step": 62000
},
{
"epoch": 3.46,
"learning_rate": 0.0002,
"loss": 0.5807,
"step": 62100
},
{
"epoch": 3.47,
"learning_rate": 0.0002,
"loss": 0.5752,
"step": 62200
},
{
"epoch": 3.47,
"learning_rate": 0.0002,
"loss": 0.5666,
"step": 62300
},
{
"epoch": 3.48,
"learning_rate": 0.0002,
"loss": 0.5886,
"step": 62400
},
{
"epoch": 3.48,
"learning_rate": 0.0002,
"loss": 0.5913,
"step": 62500
},
{
"epoch": 3.49,
"learning_rate": 0.0002,
"loss": 0.5877,
"step": 62600
},
{
"epoch": 3.49,
"learning_rate": 0.0002,
"loss": 0.5842,
"step": 62700
},
{
"epoch": 3.5,
"learning_rate": 0.0002,
"loss": 0.5786,
"step": 62800
},
{
"epoch": 3.51,
"learning_rate": 0.0002,
"loss": 0.5848,
"step": 62900
},
{
"epoch": 3.51,
"learning_rate": 0.0002,
"loss": 0.5735,
"step": 63000
},
{
"epoch": 3.52,
"learning_rate": 0.0002,
"loss": 0.5793,
"step": 63100
},
{
"epoch": 3.52,
"learning_rate": 0.0002,
"loss": 0.5799,
"step": 63200
},
{
"epoch": 3.53,
"learning_rate": 0.0002,
"loss": 0.5792,
"step": 63300
},
{
"epoch": 3.53,
"learning_rate": 0.0002,
"loss": 0.5679,
"step": 63400
},
{
"epoch": 3.54,
"learning_rate": 0.0002,
"loss": 0.579,
"step": 63500
},
{
"epoch": 3.54,
"learning_rate": 0.0002,
"loss": 0.5686,
"step": 63600
},
{
"epoch": 3.55,
"learning_rate": 0.0002,
"loss": 0.5718,
"step": 63700
},
{
"epoch": 3.56,
"learning_rate": 0.0002,
"loss": 0.5702,
"step": 63800
},
{
"epoch": 3.56,
"learning_rate": 0.0002,
"loss": 0.5801,
"step": 63900
},
{
"epoch": 3.57,
"learning_rate": 0.0002,
"loss": 0.5804,
"step": 64000
},
{
"epoch": 3.57,
"learning_rate": 0.0002,
"loss": 0.568,
"step": 64100
},
{
"epoch": 3.58,
"learning_rate": 0.0002,
"loss": 0.5687,
"step": 64200
},
{
"epoch": 3.58,
"learning_rate": 0.0002,
"loss": 0.5794,
"step": 64300
},
{
"epoch": 3.59,
"learning_rate": 0.0002,
"loss": 0.5774,
"step": 64400
},
{
"epoch": 3.59,
"learning_rate": 0.0002,
"loss": 0.5788,
"step": 64500
},
{
"epoch": 3.6,
"learning_rate": 0.0002,
"loss": 0.596,
"step": 64600
},
{
"epoch": 3.61,
"learning_rate": 0.0002,
"loss": 0.5814,
"step": 64700
},
{
"epoch": 3.61,
"learning_rate": 0.0002,
"loss": 0.5777,
"step": 64800
},
{
"epoch": 3.62,
"learning_rate": 0.0002,
"loss": 0.5811,
"step": 64900
},
{
"epoch": 3.62,
"learning_rate": 0.0002,
"loss": 0.584,
"step": 65000
},
{
"epoch": 3.63,
"learning_rate": 0.0002,
"loss": 0.5806,
"step": 65100
},
{
"epoch": 3.63,
"learning_rate": 0.0002,
"loss": 0.5709,
"step": 65200
},
{
"epoch": 3.64,
"learning_rate": 0.0002,
"loss": 0.5723,
"step": 65300
},
{
"epoch": 3.64,
"learning_rate": 0.0002,
"loss": 0.5644,
"step": 65400
},
{
"epoch": 3.65,
"learning_rate": 0.0002,
"loss": 0.579,
"step": 65500
},
{
"epoch": 3.66,
"learning_rate": 0.0002,
"loss": 0.574,
"step": 65600
},
{
"epoch": 3.66,
"learning_rate": 0.0002,
"loss": 0.5685,
"step": 65700
},
{
"epoch": 3.67,
"learning_rate": 0.0002,
"loss": 0.5842,
"step": 65800
},
{
"epoch": 3.67,
"learning_rate": 0.0002,
"loss": 0.585,
"step": 65900
},
{
"epoch": 3.68,
"learning_rate": 0.0002,
"loss": 0.5808,
"step": 66000
},
{
"epoch": 3.68,
"learning_rate": 0.0002,
"loss": 0.5851,
"step": 66100
},
{
"epoch": 3.69,
"learning_rate": 0.0002,
"loss": 0.5732,
"step": 66200
},
{
"epoch": 3.69,
"learning_rate": 0.0002,
"loss": 0.5807,
"step": 66300
},
{
"epoch": 3.7,
"learning_rate": 0.0002,
"loss": 0.5777,
"step": 66400
},
{
"epoch": 3.71,
"learning_rate": 0.0002,
"loss": 0.5786,
"step": 66500
},
{
"epoch": 3.71,
"learning_rate": 0.0002,
"loss": 0.5753,
"step": 66600
},
{
"epoch": 3.72,
"learning_rate": 0.0002,
"loss": 0.5784,
"step": 66700
},
{
"epoch": 3.72,
"learning_rate": 0.0002,
"loss": 0.5821,
"step": 66800
},
{
"epoch": 3.73,
"learning_rate": 0.0002,
"loss": 0.5891,
"step": 66900
},
{
"epoch": 3.73,
"learning_rate": 0.0002,
"loss": 0.5765,
"step": 67000
},
{
"epoch": 3.74,
"learning_rate": 0.0002,
"loss": 0.58,
"step": 67100
},
{
"epoch": 3.74,
"learning_rate": 0.0002,
"loss": 0.5853,
"step": 67200
},
{
"epoch": 3.75,
"learning_rate": 0.0002,
"loss": 0.5872,
"step": 67300
},
{
"epoch": 3.76,
"learning_rate": 0.0002,
"loss": 0.5754,
"step": 67400
},
{
"epoch": 3.76,
"learning_rate": 0.0002,
"loss": 0.5762,
"step": 67500
},
{
"epoch": 3.77,
"learning_rate": 0.0002,
"loss": 0.5862,
"step": 67600
},
{
"epoch": 3.77,
"learning_rate": 0.0002,
"loss": 0.5955,
"step": 67700
},
{
"epoch": 3.78,
"learning_rate": 0.0002,
"loss": 0.5846,
"step": 67800
},
{
"epoch": 3.78,
"learning_rate": 0.0002,
"loss": 0.5797,
"step": 67900
},
{
"epoch": 3.79,
"learning_rate": 0.0002,
"loss": 0.5913,
"step": 68000
},
{
"epoch": 3.79,
"learning_rate": 0.0002,
"loss": 0.5758,
"step": 68100
},
{
"epoch": 3.8,
"learning_rate": 0.0002,
"loss": 0.586,
"step": 68200
},
{
"epoch": 3.81,
"learning_rate": 0.0002,
"loss": 0.5766,
"step": 68300
},
{
"epoch": 3.81,
"learning_rate": 0.0002,
"loss": 0.5887,
"step": 68400
},
{
"epoch": 3.82,
"learning_rate": 0.0002,
"loss": 0.5903,
"step": 68500
},
{
"epoch": 3.82,
"learning_rate": 0.0002,
"loss": 0.5825,
"step": 68600
},
{
"epoch": 3.83,
"learning_rate": 0.0002,
"loss": 0.5884,
"step": 68700
},
{
"epoch": 3.83,
"learning_rate": 0.0002,
"loss": 0.5784,
"step": 68800
},
{
"epoch": 3.84,
"learning_rate": 0.0002,
"loss": 0.5985,
"step": 68900
},
{
"epoch": 3.85,
"learning_rate": 0.0002,
"loss": 0.6003,
"step": 69000
},
{
"epoch": 3.85,
"learning_rate": 0.0002,
"loss": 0.5723,
"step": 69100
},
{
"epoch": 3.86,
"learning_rate": 0.0002,
"loss": 0.5924,
"step": 69200
},
{
"epoch": 3.86,
"learning_rate": 0.0002,
"loss": 0.5921,
"step": 69300
},
{
"epoch": 3.87,
"learning_rate": 0.0002,
"loss": 0.5882,
"step": 69400
},
{
"epoch": 3.87,
"learning_rate": 0.0002,
"loss": 0.5845,
"step": 69500
},
{
"epoch": 3.88,
"learning_rate": 0.0002,
"loss": 0.5883,
"step": 69600
},
{
"epoch": 3.88,
"learning_rate": 0.0002,
"loss": 0.5887,
"step": 69700
},
{
"epoch": 3.89,
"learning_rate": 0.0002,
"loss": 0.5837,
"step": 69800
},
{
"epoch": 3.9,
"learning_rate": 0.0002,
"loss": 0.5772,
"step": 69900
},
{
"epoch": 3.9,
"learning_rate": 0.0002,
"loss": 0.5861,
"step": 70000
},
{
"epoch": 3.9,
"eval_gen_len": 18.99985038898863,
"eval_loss": 2.6559603214263916,
"eval_rouge1": 25.3295,
"eval_rouge2": 12.3962,
"eval_rougeL": 20.8838,
"eval_rougeLsum": 23.8838,
"eval_runtime": 478.6986,
"eval_samples_per_second": 27.926,
"eval_steps_per_second": 1.746,
"step": 70000
},
{
"epoch": 3.91,
"learning_rate": 0.0002,
"loss": 0.5741,
"step": 70100
},
{
"epoch": 3.91,
"learning_rate": 0.0002,
"loss": 0.5985,
"step": 70200
},
{
"epoch": 3.92,
"learning_rate": 0.0002,
"loss": 0.5858,
"step": 70300
},
{
"epoch": 3.92,
"learning_rate": 0.0002,
"loss": 0.5875,
"step": 70400
},
{
"epoch": 3.93,
"learning_rate": 0.0002,
"loss": 0.5933,
"step": 70500
},
{
"epoch": 3.93,
"learning_rate": 0.0002,
"loss": 0.5907,
"step": 70600
},
{
"epoch": 3.94,
"learning_rate": 0.0002,
"loss": 0.5862,
"step": 70700
},
{
"epoch": 3.95,
"learning_rate": 0.0002,
"loss": 0.581,
"step": 70800
},
{
"epoch": 3.95,
"learning_rate": 0.0002,
"loss": 0.5837,
"step": 70900
},
{
"epoch": 3.96,
"learning_rate": 0.0002,
"loss": 0.5949,
"step": 71000
},
{
"epoch": 3.96,
"learning_rate": 0.0002,
"loss": 0.5737,
"step": 71100
},
{
"epoch": 3.97,
"learning_rate": 0.0002,
"loss": 0.5864,
"step": 71200
},
{
"epoch": 3.97,
"learning_rate": 0.0002,
"loss": 0.5771,
"step": 71300
},
{
"epoch": 3.98,
"learning_rate": 0.0002,
"loss": 0.5926,
"step": 71400
},
{
"epoch": 3.98,
"learning_rate": 0.0002,
"loss": 0.572,
"step": 71500
},
{
"epoch": 3.99,
"learning_rate": 0.0002,
"loss": 0.5779,
"step": 71600
},
{
"epoch": 4.0,
"learning_rate": 0.0002,
"loss": 0.5775,
"step": 71700
},
{
"epoch": 4.0,
"learning_rate": 0.0002,
"loss": 0.5602,
"step": 71800
},
{
"epoch": 4.01,
"learning_rate": 0.0002,
"loss": 0.5671,
"step": 71900
},
{
"epoch": 4.01,
"learning_rate": 0.0002,
"loss": 0.5618,
"step": 72000
},
{
"epoch": 4.02,
"learning_rate": 0.0002,
"loss": 0.5457,
"step": 72100
},
{
"epoch": 4.02,
"learning_rate": 0.0002,
"loss": 0.5569,
"step": 72200
},
{
"epoch": 4.03,
"learning_rate": 0.0002,
"loss": 0.5486,
"step": 72300
},
{
"epoch": 4.03,
"learning_rate": 0.0002,
"loss": 0.563,
"step": 72400
},
{
"epoch": 4.04,
"learning_rate": 0.0002,
"loss": 0.562,
"step": 72500
},
{
"epoch": 4.05,
"learning_rate": 0.0002,
"loss": 0.5526,
"step": 72600
},
{
"epoch": 4.05,
"learning_rate": 0.0002,
"loss": 0.5637,
"step": 72700
},
{
"epoch": 4.06,
"learning_rate": 0.0002,
"loss": 0.5603,
"step": 72800
},
{
"epoch": 4.06,
"learning_rate": 0.0002,
"loss": 0.5511,
"step": 72900
},
{
"epoch": 4.07,
"learning_rate": 0.0002,
"loss": 0.5513,
"step": 73000
},
{
"epoch": 4.07,
"learning_rate": 0.0002,
"loss": 0.563,
"step": 73100
},
{
"epoch": 4.08,
"learning_rate": 0.0002,
"loss": 0.5532,
"step": 73200
},
{
"epoch": 4.08,
"learning_rate": 0.0002,
"loss": 0.5475,
"step": 73300
},
{
"epoch": 4.09,
"learning_rate": 0.0002,
"loss": 0.5603,
"step": 73400
},
{
"epoch": 4.1,
"learning_rate": 0.0002,
"loss": 0.5531,
"step": 73500
},
{
"epoch": 4.1,
"learning_rate": 0.0002,
"loss": 0.5607,
"step": 73600
},
{
"epoch": 4.11,
"learning_rate": 0.0002,
"loss": 0.5731,
"step": 73700
},
{
"epoch": 4.11,
"learning_rate": 0.0002,
"loss": 0.575,
"step": 73800
},
{
"epoch": 4.12,
"learning_rate": 0.0002,
"loss": 0.5583,
"step": 73900
},
{
"epoch": 4.12,
"learning_rate": 0.0002,
"loss": 0.5499,
"step": 74000
},
{
"epoch": 4.13,
"learning_rate": 0.0002,
"loss": 0.5669,
"step": 74100
},
{
"epoch": 4.13,
"learning_rate": 0.0002,
"loss": 0.5584,
"step": 74200
},
{
"epoch": 4.14,
"learning_rate": 0.0002,
"loss": 0.5679,
"step": 74300
},
{
"epoch": 4.15,
"learning_rate": 0.0002,
"loss": 0.5709,
"step": 74400
},
{
"epoch": 4.15,
"learning_rate": 0.0002,
"loss": 0.5598,
"step": 74500
},
{
"epoch": 4.16,
"learning_rate": 0.0002,
"loss": 0.5663,
"step": 74600
},
{
"epoch": 4.16,
"learning_rate": 0.0002,
"loss": 0.5663,
"step": 74700
},
{
"epoch": 4.17,
"learning_rate": 0.0002,
"loss": 0.5692,
"step": 74800
},
{
"epoch": 4.17,
"learning_rate": 0.0002,
"loss": 0.5686,
"step": 74900
},
{
"epoch": 4.18,
"learning_rate": 0.0002,
"loss": 0.5649,
"step": 75000
},
{
"epoch": 4.19,
"learning_rate": 0.0002,
"loss": 0.5628,
"step": 75100
},
{
"epoch": 4.19,
"learning_rate": 0.0002,
"loss": 0.5688,
"step": 75200
},
{
"epoch": 4.2,
"learning_rate": 0.0002,
"loss": 0.5705,
"step": 75300
},
{
"epoch": 4.2,
"learning_rate": 0.0002,
"loss": 0.549,
"step": 75400
},
{
"epoch": 4.21,
"learning_rate": 0.0002,
"loss": 0.5568,
"step": 75500
},
{
"epoch": 4.21,
"learning_rate": 0.0002,
"loss": 0.5649,
"step": 75600
},
{
"epoch": 4.22,
"learning_rate": 0.0002,
"loss": 0.5766,
"step": 75700
},
{
"epoch": 4.22,
"learning_rate": 0.0002,
"loss": 0.5709,
"step": 75800
},
{
"epoch": 4.23,
"learning_rate": 0.0002,
"loss": 0.5595,
"step": 75900
},
{
"epoch": 4.24,
"learning_rate": 0.0002,
"loss": 0.5636,
"step": 76000
},
{
"epoch": 4.24,
"learning_rate": 0.0002,
"loss": 0.5823,
"step": 76100
},
{
"epoch": 4.25,
"learning_rate": 0.0002,
"loss": 0.5677,
"step": 76200
},
{
"epoch": 4.25,
"learning_rate": 0.0002,
"loss": 0.5667,
"step": 76300
},
{
"epoch": 4.26,
"learning_rate": 0.0002,
"loss": 0.5578,
"step": 76400
},
{
"epoch": 4.26,
"learning_rate": 0.0002,
"loss": 0.5755,
"step": 76500
},
{
"epoch": 4.27,
"learning_rate": 0.0002,
"loss": 0.564,
"step": 76600
},
{
"epoch": 4.27,
"learning_rate": 0.0002,
"loss": 0.5604,
"step": 76700
},
{
"epoch": 4.28,
"learning_rate": 0.0002,
"loss": 0.5689,
"step": 76800
},
{
"epoch": 4.29,
"learning_rate": 0.0002,
"loss": 0.5689,
"step": 76900
},
{
"epoch": 4.29,
"learning_rate": 0.0002,
"loss": 0.5676,
"step": 77000
},
{
"epoch": 4.3,
"learning_rate": 0.0002,
"loss": 0.5589,
"step": 77100
},
{
"epoch": 4.3,
"learning_rate": 0.0002,
"loss": 0.5697,
"step": 77200
},
{
"epoch": 4.31,
"learning_rate": 0.0002,
"loss": 0.5785,
"step": 77300
},
{
"epoch": 4.31,
"learning_rate": 0.0002,
"loss": 0.5593,
"step": 77400
},
{
"epoch": 4.32,
"learning_rate": 0.0002,
"loss": 0.5769,
"step": 77500
},
{
"epoch": 4.32,
"learning_rate": 0.0002,
"loss": 0.5705,
"step": 77600
},
{
"epoch": 4.33,
"learning_rate": 0.0002,
"loss": 0.5497,
"step": 77700
},
{
"epoch": 4.34,
"learning_rate": 0.0002,
"loss": 0.5697,
"step": 77800
},
{
"epoch": 4.34,
"learning_rate": 0.0002,
"loss": 0.5683,
"step": 77900
},
{
"epoch": 4.35,
"learning_rate": 0.0002,
"loss": 0.5571,
"step": 78000
},
{
"epoch": 4.35,
"learning_rate": 0.0002,
"loss": 0.5651,
"step": 78100
},
{
"epoch": 4.36,
"learning_rate": 0.0002,
"loss": 0.5605,
"step": 78200
},
{
"epoch": 4.36,
"learning_rate": 0.0002,
"loss": 0.5736,
"step": 78300
},
{
"epoch": 4.37,
"learning_rate": 0.0002,
"loss": 0.5736,
"step": 78400
},
{
"epoch": 4.37,
"learning_rate": 0.0002,
"loss": 0.5658,
"step": 78500
},
{
"epoch": 4.38,
"learning_rate": 0.0002,
"loss": 0.5583,
"step": 78600
},
{
"epoch": 4.39,
"learning_rate": 0.0002,
"loss": 0.5612,
"step": 78700
},
{
"epoch": 4.39,
"learning_rate": 0.0002,
"loss": 0.5549,
"step": 78800
},
{
"epoch": 4.4,
"learning_rate": 0.0002,
"loss": 0.5716,
"step": 78900
},
{
"epoch": 4.4,
"learning_rate": 0.0002,
"loss": 0.5598,
"step": 79000
},
{
"epoch": 4.41,
"learning_rate": 0.0002,
"loss": 0.5757,
"step": 79100
},
{
"epoch": 4.41,
"learning_rate": 0.0002,
"loss": 0.5601,
"step": 79200
},
{
"epoch": 4.42,
"learning_rate": 0.0002,
"loss": 0.5804,
"step": 79300
},
{
"epoch": 4.42,
"learning_rate": 0.0002,
"loss": 0.572,
"step": 79400
},
{
"epoch": 4.43,
"learning_rate": 0.0002,
"loss": 0.588,
"step": 79500
},
{
"epoch": 4.44,
"learning_rate": 0.0002,
"loss": 0.5641,
"step": 79600
},
{
"epoch": 4.44,
"learning_rate": 0.0002,
"loss": 0.5719,
"step": 79700
},
{
"epoch": 4.45,
"learning_rate": 0.0002,
"loss": 0.5689,
"step": 79800
},
{
"epoch": 4.45,
"learning_rate": 0.0002,
"loss": 0.5786,
"step": 79900
},
{
"epoch": 4.46,
"learning_rate": 0.0002,
"loss": 0.5615,
"step": 80000
},
{
"epoch": 4.46,
"eval_gen_len": 18.99985038898863,
"eval_loss": 2.6867384910583496,
"eval_rouge1": 25.3508,
"eval_rouge2": 12.4212,
"eval_rougeL": 20.9341,
"eval_rougeLsum": 23.949,
"eval_runtime": 474.7006,
"eval_samples_per_second": 28.161,
"eval_steps_per_second": 1.761,
"step": 80000
},
{
"epoch": 4.46,
"learning_rate": 0.0002,
"loss": 0.5773,
"step": 80100
},
{
"epoch": 4.47,
"learning_rate": 0.0002,
"loss": 0.5652,
"step": 80200
},
{
"epoch": 4.47,
"learning_rate": 0.0002,
"loss": 0.575,
"step": 80300
},
{
"epoch": 4.48,
"learning_rate": 0.0002,
"loss": 0.5599,
"step": 80400
},
{
"epoch": 4.49,
"learning_rate": 0.0002,
"loss": 0.5621,
"step": 80500
},
{
"epoch": 4.49,
"learning_rate": 0.0002,
"loss": 0.5787,
"step": 80600
},
{
"epoch": 4.5,
"learning_rate": 0.0002,
"loss": 0.573,
"step": 80700
},
{
"epoch": 4.5,
"learning_rate": 0.0002,
"loss": 0.5698,
"step": 80800
},
{
"epoch": 4.51,
"learning_rate": 0.0002,
"loss": 0.5748,
"step": 80900
},
{
"epoch": 4.51,
"learning_rate": 0.0002,
"loss": 0.577,
"step": 81000
},
{
"epoch": 4.52,
"learning_rate": 0.0002,
"loss": 0.5789,
"step": 81100
},
{
"epoch": 4.52,
"learning_rate": 0.0002,
"loss": 0.5693,
"step": 81200
},
{
"epoch": 4.53,
"learning_rate": 0.0002,
"loss": 0.567,
"step": 81300
},
{
"epoch": 4.54,
"learning_rate": 0.0002,
"loss": 0.5708,
"step": 81400
},
{
"epoch": 4.54,
"learning_rate": 0.0002,
"loss": 0.566,
"step": 81500
},
{
"epoch": 4.55,
"learning_rate": 0.0002,
"loss": 0.5643,
"step": 81600
},
{
"epoch": 4.55,
"learning_rate": 0.0002,
"loss": 0.5774,
"step": 81700
},
{
"epoch": 4.56,
"learning_rate": 0.0002,
"loss": 0.5571,
"step": 81800
},
{
"epoch": 4.56,
"learning_rate": 0.0002,
"loss": 0.5739,
"step": 81900
},
{
"epoch": 4.57,
"learning_rate": 0.0002,
"loss": 0.5811,
"step": 82000
},
{
"epoch": 4.58,
"learning_rate": 0.0002,
"loss": 0.5809,
"step": 82100
},
{
"epoch": 4.58,
"learning_rate": 0.0002,
"loss": 0.5672,
"step": 82200
},
{
"epoch": 4.59,
"learning_rate": 0.0002,
"loss": 0.5883,
"step": 82300
},
{
"epoch": 4.59,
"learning_rate": 0.0002,
"loss": 0.5576,
"step": 82400
},
{
"epoch": 4.6,
"learning_rate": 0.0002,
"loss": 0.5705,
"step": 82500
},
{
"epoch": 4.6,
"learning_rate": 0.0002,
"loss": 0.5699,
"step": 82600
},
{
"epoch": 4.61,
"learning_rate": 0.0002,
"loss": 0.5786,
"step": 82700
},
{
"epoch": 4.61,
"learning_rate": 0.0002,
"loss": 0.5674,
"step": 82800
},
{
"epoch": 4.62,
"learning_rate": 0.0002,
"loss": 0.5753,
"step": 82900
},
{
"epoch": 4.63,
"learning_rate": 0.0002,
"loss": 0.5733,
"step": 83000
},
{
"epoch": 4.63,
"learning_rate": 0.0002,
"loss": 0.5706,
"step": 83100
},
{
"epoch": 4.64,
"learning_rate": 0.0002,
"loss": 0.5635,
"step": 83200
},
{
"epoch": 4.64,
"learning_rate": 0.0002,
"loss": 0.5721,
"step": 83300
},
{
"epoch": 4.65,
"learning_rate": 0.0002,
"loss": 0.5665,
"step": 83400
},
{
"epoch": 4.65,
"learning_rate": 0.0002,
"loss": 0.5839,
"step": 83500
},
{
"epoch": 4.66,
"learning_rate": 0.0002,
"loss": 0.5831,
"step": 83600
},
{
"epoch": 4.66,
"learning_rate": 0.0002,
"loss": 0.5699,
"step": 83700
},
{
"epoch": 4.67,
"learning_rate": 0.0002,
"loss": 0.5777,
"step": 83800
},
{
"epoch": 4.68,
"learning_rate": 0.0002,
"loss": 0.5809,
"step": 83900
},
{
"epoch": 4.68,
"learning_rate": 0.0002,
"loss": 0.5846,
"step": 84000
},
{
"epoch": 4.69,
"learning_rate": 0.0002,
"loss": 0.5711,
"step": 84100
},
{
"epoch": 4.69,
"learning_rate": 0.0002,
"loss": 0.5668,
"step": 84200
},
{
"epoch": 4.7,
"learning_rate": 0.0002,
"loss": 0.5747,
"step": 84300
},
{
"epoch": 4.7,
"learning_rate": 0.0002,
"loss": 0.5752,
"step": 84400
},
{
"epoch": 4.71,
"learning_rate": 0.0002,
"loss": 0.5707,
"step": 84500
},
{
"epoch": 4.71,
"learning_rate": 0.0002,
"loss": 0.5777,
"step": 84600
},
{
"epoch": 4.72,
"learning_rate": 0.0002,
"loss": 0.5725,
"step": 84700
},
{
"epoch": 4.73,
"learning_rate": 0.0002,
"loss": 0.5749,
"step": 84800
},
{
"epoch": 4.73,
"learning_rate": 0.0002,
"loss": 0.5892,
"step": 84900
},
{
"epoch": 4.74,
"learning_rate": 0.0002,
"loss": 0.5735,
"step": 85000
},
{
"epoch": 4.74,
"learning_rate": 0.0002,
"loss": 0.5753,
"step": 85100
},
{
"epoch": 4.75,
"learning_rate": 0.0002,
"loss": 0.5699,
"step": 85200
},
{
"epoch": 4.75,
"learning_rate": 0.0002,
"loss": 0.5702,
"step": 85300
},
{
"epoch": 4.76,
"learning_rate": 0.0002,
"loss": 0.576,
"step": 85400
},
{
"epoch": 4.76,
"learning_rate": 0.0002,
"loss": 0.5835,
"step": 85500
},
{
"epoch": 4.77,
"learning_rate": 0.0002,
"loss": 0.5764,
"step": 85600
},
{
"epoch": 4.78,
"learning_rate": 0.0002,
"loss": 0.5746,
"step": 85700
},
{
"epoch": 4.78,
"learning_rate": 0.0002,
"loss": 0.5814,
"step": 85800
},
{
"epoch": 4.79,
"learning_rate": 0.0002,
"loss": 0.5689,
"step": 85900
},
{
"epoch": 4.79,
"learning_rate": 0.0002,
"loss": 0.5669,
"step": 86000
},
{
"epoch": 4.8,
"learning_rate": 0.0002,
"loss": 0.5775,
"step": 86100
},
{
"epoch": 4.8,
"learning_rate": 0.0002,
"loss": 0.5753,
"step": 86200
},
{
"epoch": 4.81,
"learning_rate": 0.0002,
"loss": 0.5978,
"step": 86300
},
{
"epoch": 4.81,
"learning_rate": 0.0002,
"loss": 0.5812,
"step": 86400
},
{
"epoch": 4.82,
"learning_rate": 0.0002,
"loss": 0.5726,
"step": 86500
},
{
"epoch": 4.83,
"learning_rate": 0.0002,
"loss": 0.5865,
"step": 86600
},
{
"epoch": 4.83,
"learning_rate": 0.0002,
"loss": 0.5809,
"step": 86700
},
{
"epoch": 4.84,
"learning_rate": 0.0002,
"loss": 0.5846,
"step": 86800
},
{
"epoch": 4.84,
"learning_rate": 0.0002,
"loss": 0.5694,
"step": 86900
},
{
"epoch": 4.85,
"learning_rate": 0.0002,
"loss": 0.5694,
"step": 87000
},
{
"epoch": 4.85,
"learning_rate": 0.0002,
"loss": 0.581,
"step": 87100
},
{
"epoch": 4.86,
"learning_rate": 0.0002,
"loss": 0.5801,
"step": 87200
},
{
"epoch": 4.86,
"learning_rate": 0.0002,
"loss": 0.596,
"step": 87300
},
{
"epoch": 4.87,
"learning_rate": 0.0002,
"loss": 0.5683,
"step": 87400
},
{
"epoch": 4.88,
"learning_rate": 0.0002,
"loss": 0.5771,
"step": 87500
},
{
"epoch": 4.88,
"learning_rate": 0.0002,
"loss": 0.5772,
"step": 87600
},
{
"epoch": 4.89,
"learning_rate": 0.0002,
"loss": 0.5719,
"step": 87700
},
{
"epoch": 4.89,
"learning_rate": 0.0002,
"loss": 0.5911,
"step": 87800
},
{
"epoch": 4.9,
"learning_rate": 0.0002,
"loss": 0.5747,
"step": 87900
},
{
"epoch": 4.9,
"learning_rate": 0.0002,
"loss": 0.5804,
"step": 88000
},
{
"epoch": 4.91,
"learning_rate": 0.0002,
"loss": 0.5736,
"step": 88100
},
{
"epoch": 4.92,
"learning_rate": 0.0002,
"loss": 0.5621,
"step": 88200
},
{
"epoch": 4.92,
"learning_rate": 0.0002,
"loss": 0.5716,
"step": 88300
},
{
"epoch": 4.93,
"learning_rate": 0.0002,
"loss": 0.582,
"step": 88400
},
{
"epoch": 4.93,
"learning_rate": 0.0002,
"loss": 0.5743,
"step": 88500
},
{
"epoch": 4.94,
"learning_rate": 0.0002,
"loss": 0.5756,
"step": 88600
},
{
"epoch": 4.94,
"learning_rate": 0.0002,
"loss": 0.5729,
"step": 88700
},
{
"epoch": 4.95,
"learning_rate": 0.0002,
"loss": 0.5546,
"step": 88800
},
{
"epoch": 4.95,
"learning_rate": 0.0002,
"loss": 0.5688,
"step": 88900
},
{
"epoch": 4.96,
"learning_rate": 0.0002,
"loss": 0.5702,
"step": 89000
},
{
"epoch": 4.97,
"learning_rate": 0.0002,
"loss": 0.5811,
"step": 89100
},
{
"epoch": 4.97,
"learning_rate": 0.0002,
"loss": 0.565,
"step": 89200
},
{
"epoch": 4.98,
"learning_rate": 0.0002,
"loss": 0.5643,
"step": 89300
},
{
"epoch": 4.98,
"learning_rate": 0.0002,
"loss": 0.5915,
"step": 89400
},
{
"epoch": 4.99,
"learning_rate": 0.0002,
"loss": 0.5978,
"step": 89500
},
{
"epoch": 4.99,
"learning_rate": 0.0002,
"loss": 0.5888,
"step": 89600
},
{
"epoch": 5.0,
"learning_rate": 0.0002,
"loss": 0.5706,
"step": 89700
},
{
"epoch": 5.0,
"learning_rate": 0.0002,
"loss": 0.5537,
"step": 89800
},
{
"epoch": 5.01,
"learning_rate": 0.0002,
"loss": 0.5571,
"step": 89900
},
{
"epoch": 5.02,
"learning_rate": 0.0002,
"loss": 0.5387,
"step": 90000
},
{
"epoch": 5.02,
"eval_gen_len": 18.99955116696589,
"eval_loss": 2.7078752517700195,
"eval_rouge1": 25.2864,
"eval_rouge2": 12.3885,
"eval_rougeL": 20.9095,
"eval_rougeLsum": 23.8569,
"eval_runtime": 479.4466,
"eval_samples_per_second": 27.882,
"eval_steps_per_second": 1.744,
"step": 90000
},
{
"epoch": 5.02,
"learning_rate": 0.0002,
"loss": 0.5436,
"step": 90100
},
{
"epoch": 5.03,
"learning_rate": 0.0002,
"loss": 0.55,
"step": 90200
},
{
"epoch": 5.03,
"learning_rate": 0.0002,
"loss": 0.5454,
"step": 90300
},
{
"epoch": 5.04,
"learning_rate": 0.0002,
"loss": 0.5504,
"step": 90400
},
{
"epoch": 5.04,
"learning_rate": 0.0002,
"loss": 0.5469,
"step": 90500
},
{
"epoch": 5.05,
"learning_rate": 0.0002,
"loss": 0.5441,
"step": 90600
},
{
"epoch": 5.05,
"learning_rate": 0.0002,
"loss": 0.5517,
"step": 90700
},
{
"epoch": 5.06,
"learning_rate": 0.0002,
"loss": 0.5517,
"step": 90800
},
{
"epoch": 5.07,
"learning_rate": 0.0002,
"loss": 0.5419,
"step": 90900
},
{
"epoch": 5.07,
"learning_rate": 0.0002,
"loss": 0.5447,
"step": 91000
},
{
"epoch": 5.08,
"learning_rate": 0.0002,
"loss": 0.5425,
"step": 91100
},
{
"epoch": 5.08,
"learning_rate": 0.0002,
"loss": 0.5549,
"step": 91200
},
{
"epoch": 5.09,
"learning_rate": 0.0002,
"loss": 0.5595,
"step": 91300
},
{
"epoch": 5.09,
"learning_rate": 0.0002,
"loss": 0.5442,
"step": 91400
},
{
"epoch": 5.1,
"learning_rate": 0.0002,
"loss": 0.552,
"step": 91500
},
{
"epoch": 5.1,
"learning_rate": 0.0002,
"loss": 0.5665,
"step": 91600
},
{
"epoch": 5.11,
"learning_rate": 0.0002,
"loss": 0.5503,
"step": 91700
},
{
"epoch": 5.12,
"learning_rate": 0.0002,
"loss": 0.5589,
"step": 91800
},
{
"epoch": 5.12,
"learning_rate": 0.0002,
"loss": 0.5792,
"step": 91900
},
{
"epoch": 5.13,
"learning_rate": 0.0002,
"loss": 0.5517,
"step": 92000
},
{
"epoch": 5.13,
"learning_rate": 0.0002,
"loss": 0.5693,
"step": 92100
},
{
"epoch": 5.14,
"learning_rate": 0.0002,
"loss": 0.5496,
"step": 92200
},
{
"epoch": 5.14,
"learning_rate": 0.0002,
"loss": 0.5557,
"step": 92300
},
{
"epoch": 5.15,
"learning_rate": 0.0002,
"loss": 0.5545,
"step": 92400
},
{
"epoch": 5.15,
"learning_rate": 0.0002,
"loss": 0.5533,
"step": 92500
},
{
"epoch": 5.16,
"learning_rate": 0.0002,
"loss": 0.544,
"step": 92600
},
{
"epoch": 5.17,
"learning_rate": 0.0002,
"loss": 0.5582,
"step": 92700
},
{
"epoch": 5.17,
"learning_rate": 0.0002,
"loss": 0.5517,
"step": 92800
},
{
"epoch": 5.18,
"learning_rate": 0.0002,
"loss": 0.5585,
"step": 92900
},
{
"epoch": 5.18,
"learning_rate": 0.0002,
"loss": 0.5561,
"step": 93000
},
{
"epoch": 5.19,
"learning_rate": 0.0002,
"loss": 0.5446,
"step": 93100
},
{
"epoch": 5.19,
"learning_rate": 0.0002,
"loss": 0.5587,
"step": 93200
},
{
"epoch": 5.2,
"learning_rate": 0.0002,
"loss": 0.5644,
"step": 93300
},
{
"epoch": 5.2,
"learning_rate": 0.0002,
"loss": 0.5549,
"step": 93400
},
{
"epoch": 5.21,
"learning_rate": 0.0002,
"loss": 0.5679,
"step": 93500
},
{
"epoch": 5.22,
"learning_rate": 0.0002,
"loss": 0.5663,
"step": 93600
},
{
"epoch": 5.22,
"learning_rate": 0.0002,
"loss": 0.5499,
"step": 93700
},
{
"epoch": 5.23,
"learning_rate": 0.0002,
"loss": 0.561,
"step": 93800
},
{
"epoch": 5.23,
"learning_rate": 0.0002,
"loss": 0.5538,
"step": 93900
},
{
"epoch": 5.24,
"learning_rate": 0.0002,
"loss": 0.5563,
"step": 94000
},
{
"epoch": 5.24,
"learning_rate": 0.0002,
"loss": 0.5515,
"step": 94100
},
{
"epoch": 5.25,
"learning_rate": 0.0002,
"loss": 0.5626,
"step": 94200
},
{
"epoch": 5.25,
"learning_rate": 0.0002,
"loss": 0.5562,
"step": 94300
},
{
"epoch": 5.26,
"learning_rate": 0.0002,
"loss": 0.5474,
"step": 94400
},
{
"epoch": 5.27,
"learning_rate": 0.0002,
"loss": 0.5698,
"step": 94500
},
{
"epoch": 5.27,
"learning_rate": 0.0002,
"loss": 0.5642,
"step": 94600
},
{
"epoch": 5.28,
"learning_rate": 0.0002,
"loss": 0.5564,
"step": 94700
},
{
"epoch": 5.28,
"learning_rate": 0.0002,
"loss": 0.5562,
"step": 94800
},
{
"epoch": 5.29,
"learning_rate": 0.0002,
"loss": 0.5623,
"step": 94900
},
{
"epoch": 5.29,
"learning_rate": 0.0002,
"loss": 0.5565,
"step": 95000
},
{
"epoch": 5.3,
"learning_rate": 0.0002,
"loss": 0.565,
"step": 95100
},
{
"epoch": 5.31,
"learning_rate": 0.0002,
"loss": 0.5618,
"step": 95200
},
{
"epoch": 5.31,
"learning_rate": 0.0002,
"loss": 0.5586,
"step": 95300
},
{
"epoch": 5.32,
"learning_rate": 0.0002,
"loss": 0.5572,
"step": 95400
},
{
"epoch": 5.32,
"learning_rate": 0.0002,
"loss": 0.5605,
"step": 95500
},
{
"epoch": 5.33,
"learning_rate": 0.0002,
"loss": 0.563,
"step": 95600
},
{
"epoch": 5.33,
"learning_rate": 0.0002,
"loss": 0.5688,
"step": 95700
},
{
"epoch": 5.34,
"learning_rate": 0.0002,
"loss": 0.5562,
"step": 95800
},
{
"epoch": 5.34,
"learning_rate": 0.0002,
"loss": 0.5529,
"step": 95900
},
{
"epoch": 5.35,
"learning_rate": 0.0002,
"loss": 0.5564,
"step": 96000
},
{
"epoch": 5.36,
"learning_rate": 0.0002,
"loss": 0.5708,
"step": 96100
},
{
"epoch": 5.36,
"learning_rate": 0.0002,
"loss": 0.5667,
"step": 96200
},
{
"epoch": 5.37,
"learning_rate": 0.0002,
"loss": 0.552,
"step": 96300
},
{
"epoch": 5.37,
"learning_rate": 0.0002,
"loss": 0.5715,
"step": 96400
},
{
"epoch": 5.38,
"learning_rate": 0.0002,
"loss": 0.5697,
"step": 96500
},
{
"epoch": 5.38,
"learning_rate": 0.0002,
"loss": 0.5552,
"step": 96600
},
{
"epoch": 5.39,
"learning_rate": 0.0002,
"loss": 0.5791,
"step": 96700
},
{
"epoch": 5.39,
"learning_rate": 0.0002,
"loss": 0.5527,
"step": 96800
},
{
"epoch": 5.4,
"learning_rate": 0.0002,
"loss": 0.5761,
"step": 96900
},
{
"epoch": 5.41,
"learning_rate": 0.0002,
"loss": 0.5725,
"step": 97000
},
{
"epoch": 5.41,
"learning_rate": 0.0002,
"loss": 0.5731,
"step": 97100
},
{
"epoch": 5.42,
"learning_rate": 0.0002,
"loss": 0.5688,
"step": 97200
},
{
"epoch": 5.42,
"learning_rate": 0.0002,
"loss": 0.555,
"step": 97300
},
{
"epoch": 5.43,
"learning_rate": 0.0002,
"loss": 0.564,
"step": 97400
},
{
"epoch": 5.43,
"learning_rate": 0.0002,
"loss": 0.5729,
"step": 97500
},
{
"epoch": 5.44,
"learning_rate": 0.0002,
"loss": 0.5668,
"step": 97600
},
{
"epoch": 5.44,
"learning_rate": 0.0002,
"loss": 0.5735,
"step": 97700
},
{
"epoch": 5.45,
"learning_rate": 0.0002,
"loss": 0.566,
"step": 97800
},
{
"epoch": 5.46,
"learning_rate": 0.0002,
"loss": 0.5525,
"step": 97900
},
{
"epoch": 5.46,
"learning_rate": 0.0002,
"loss": 0.5592,
"step": 98000
},
{
"epoch": 5.47,
"learning_rate": 0.0002,
"loss": 0.5664,
"step": 98100
},
{
"epoch": 5.47,
"learning_rate": 0.0002,
"loss": 0.5622,
"step": 98200
},
{
"epoch": 5.48,
"learning_rate": 0.0002,
"loss": 0.5678,
"step": 98300
},
{
"epoch": 5.48,
"learning_rate": 0.0002,
"loss": 0.5802,
"step": 98400
},
{
"epoch": 5.49,
"learning_rate": 0.0002,
"loss": 0.5661,
"step": 98500
},
{
"epoch": 5.49,
"learning_rate": 0.0002,
"loss": 0.5603,
"step": 98600
},
{
"epoch": 5.5,
"learning_rate": 0.0002,
"loss": 0.5653,
"step": 98700
},
{
"epoch": 5.51,
"learning_rate": 0.0002,
"loss": 0.5568,
"step": 98800
},
{
"epoch": 5.51,
"learning_rate": 0.0002,
"loss": 0.5695,
"step": 98900
},
{
"epoch": 5.52,
"learning_rate": 0.0002,
"loss": 0.5688,
"step": 99000
},
{
"epoch": 5.52,
"learning_rate": 0.0002,
"loss": 0.5689,
"step": 99100
},
{
"epoch": 5.53,
"learning_rate": 0.0002,
"loss": 0.5637,
"step": 99200
},
{
"epoch": 5.53,
"learning_rate": 0.0002,
"loss": 0.5671,
"step": 99300
},
{
"epoch": 5.54,
"learning_rate": 0.0002,
"loss": 0.5667,
"step": 99400
},
{
"epoch": 5.54,
"learning_rate": 0.0002,
"loss": 0.5797,
"step": 99500
},
{
"epoch": 5.55,
"learning_rate": 0.0002,
"loss": 0.5687,
"step": 99600
},
{
"epoch": 5.56,
"learning_rate": 0.0002,
"loss": 0.5743,
"step": 99700
},
{
"epoch": 5.56,
"learning_rate": 0.0002,
"loss": 0.575,
"step": 99800
},
{
"epoch": 5.57,
"learning_rate": 0.0002,
"loss": 0.5626,
"step": 99900
},
{
"epoch": 5.57,
"learning_rate": 0.0002,
"loss": 0.5662,
"step": 100000
},
{
"epoch": 5.57,
"eval_gen_len": 18.99985038898863,
"eval_loss": 2.673166275024414,
"eval_rouge1": 25.3971,
"eval_rouge2": 12.406,
"eval_rougeL": 20.9243,
"eval_rougeLsum": 23.9681,
"eval_runtime": 474.5023,
"eval_samples_per_second": 28.173,
"eval_steps_per_second": 1.762,
"step": 100000
},
{
"epoch": 5.58,
"learning_rate": 0.0002,
"loss": 0.5734,
"step": 100100
},
{
"epoch": 5.58,
"learning_rate": 0.0002,
"loss": 0.562,
"step": 100200
},
{
"epoch": 5.59,
"learning_rate": 0.0002,
"loss": 0.5777,
"step": 100300
},
{
"epoch": 5.59,
"learning_rate": 0.0002,
"loss": 0.5653,
"step": 100400
},
{
"epoch": 5.6,
"learning_rate": 0.0002,
"loss": 0.562,
"step": 100500
},
{
"epoch": 5.61,
"learning_rate": 0.0002,
"loss": 0.5713,
"step": 100600
},
{
"epoch": 5.61,
"learning_rate": 0.0002,
"loss": 0.5686,
"step": 100700
},
{
"epoch": 5.62,
"learning_rate": 0.0002,
"loss": 0.5673,
"step": 100800
},
{
"epoch": 5.62,
"learning_rate": 0.0002,
"loss": 0.5635,
"step": 100900
},
{
"epoch": 5.63,
"learning_rate": 0.0002,
"loss": 0.5625,
"step": 101000
},
{
"epoch": 5.63,
"learning_rate": 0.0002,
"loss": 0.5609,
"step": 101100
},
{
"epoch": 5.64,
"learning_rate": 0.0002,
"loss": 0.5761,
"step": 101200
},
{
"epoch": 5.65,
"learning_rate": 0.0002,
"loss": 0.5744,
"step": 101300
},
{
"epoch": 5.65,
"learning_rate": 0.0002,
"loss": 0.5672,
"step": 101400
},
{
"epoch": 5.66,
"learning_rate": 0.0002,
"loss": 0.5728,
"step": 101500
},
{
"epoch": 5.66,
"learning_rate": 0.0002,
"loss": 0.5725,
"step": 101600
},
{
"epoch": 5.67,
"learning_rate": 0.0002,
"loss": 0.5741,
"step": 101700
},
{
"epoch": 5.67,
"learning_rate": 0.0002,
"loss": 0.5661,
"step": 101800
},
{
"epoch": 5.68,
"learning_rate": 0.0002,
"loss": 0.5594,
"step": 101900
},
{
"epoch": 5.68,
"learning_rate": 0.0002,
"loss": 0.5622,
"step": 102000
},
{
"epoch": 5.69,
"learning_rate": 0.0002,
"loss": 0.5683,
"step": 102100
},
{
"epoch": 5.7,
"learning_rate": 0.0002,
"loss": 0.5642,
"step": 102200
},
{
"epoch": 5.7,
"learning_rate": 0.0002,
"loss": 0.5788,
"step": 102300
},
{
"epoch": 5.71,
"learning_rate": 0.0002,
"loss": 0.564,
"step": 102400
},
{
"epoch": 5.71,
"learning_rate": 0.0002,
"loss": 0.5563,
"step": 102500
},
{
"epoch": 5.72,
"learning_rate": 0.0002,
"loss": 0.5587,
"step": 102600
},
{
"epoch": 5.72,
"learning_rate": 0.0002,
"loss": 0.5744,
"step": 102700
},
{
"epoch": 5.73,
"learning_rate": 0.0002,
"loss": 0.5776,
"step": 102800
},
{
"epoch": 5.73,
"learning_rate": 0.0002,
"loss": 0.5711,
"step": 102900
},
{
"epoch": 5.74,
"learning_rate": 0.0002,
"loss": 0.5646,
"step": 103000
},
{
"epoch": 5.75,
"learning_rate": 0.0002,
"loss": 0.569,
"step": 103100
},
{
"epoch": 5.75,
"learning_rate": 0.0002,
"loss": 0.5704,
"step": 103200
},
{
"epoch": 5.76,
"learning_rate": 0.0002,
"loss": 0.5439,
"step": 103300
},
{
"epoch": 5.76,
"learning_rate": 0.0002,
"loss": 0.5685,
"step": 103400
},
{
"epoch": 5.77,
"learning_rate": 0.0002,
"loss": 0.5519,
"step": 103500
},
{
"epoch": 5.77,
"learning_rate": 0.0002,
"loss": 0.5806,
"step": 103600
},
{
"epoch": 5.78,
"learning_rate": 0.0002,
"loss": 0.5666,
"step": 103700
},
{
"epoch": 5.78,
"learning_rate": 0.0002,
"loss": 0.5706,
"step": 103800
},
{
"epoch": 5.79,
"learning_rate": 0.0002,
"loss": 0.5681,
"step": 103900
},
{
"epoch": 5.8,
"learning_rate": 0.0002,
"loss": 0.5766,
"step": 104000
},
{
"epoch": 5.8,
"learning_rate": 0.0002,
"loss": 0.584,
"step": 104100
},
{
"epoch": 5.81,
"learning_rate": 0.0002,
"loss": 0.5765,
"step": 104200
},
{
"epoch": 5.81,
"learning_rate": 0.0002,
"loss": 0.5586,
"step": 104300
},
{
"epoch": 5.82,
"learning_rate": 0.0002,
"loss": 0.5694,
"step": 104400
},
{
"epoch": 5.82,
"learning_rate": 0.0002,
"loss": 0.5556,
"step": 104500
},
{
"epoch": 5.83,
"learning_rate": 0.0002,
"loss": 0.5757,
"step": 104600
},
{
"epoch": 5.83,
"learning_rate": 0.0002,
"loss": 0.5501,
"step": 104700
},
{
"epoch": 5.84,
"learning_rate": 0.0002,
"loss": 0.5656,
"step": 104800
},
{
"epoch": 5.85,
"learning_rate": 0.0002,
"loss": 0.5775,
"step": 104900
},
{
"epoch": 5.85,
"learning_rate": 0.0002,
"loss": 0.5772,
"step": 105000
},
{
"epoch": 5.86,
"learning_rate": 0.0002,
"loss": 0.5664,
"step": 105100
},
{
"epoch": 5.86,
"learning_rate": 0.0002,
"loss": 0.5648,
"step": 105200
},
{
"epoch": 5.87,
"learning_rate": 0.0002,
"loss": 0.5565,
"step": 105300
},
{
"epoch": 5.87,
"learning_rate": 0.0002,
"loss": 0.5608,
"step": 105400
},
{
"epoch": 5.88,
"learning_rate": 0.0002,
"loss": 0.5614,
"step": 105500
},
{
"epoch": 5.88,
"learning_rate": 0.0002,
"loss": 0.5664,
"step": 105600
},
{
"epoch": 5.89,
"learning_rate": 0.0002,
"loss": 0.5822,
"step": 105700
},
{
"epoch": 5.9,
"learning_rate": 0.0002,
"loss": 0.5655,
"step": 105800
},
{
"epoch": 5.9,
"learning_rate": 0.0002,
"loss": 0.5814,
"step": 105900
},
{
"epoch": 5.91,
"learning_rate": 0.0002,
"loss": 0.555,
"step": 106000
},
{
"epoch": 5.91,
"learning_rate": 0.0002,
"loss": 0.5776,
"step": 106100
},
{
"epoch": 5.92,
"learning_rate": 0.0002,
"loss": 0.5832,
"step": 106200
},
{
"epoch": 5.92,
"learning_rate": 0.0002,
"loss": 0.5637,
"step": 106300
},
{
"epoch": 5.93,
"learning_rate": 0.0002,
"loss": 0.563,
"step": 106400
},
{
"epoch": 5.93,
"learning_rate": 0.0002,
"loss": 0.5648,
"step": 106500
},
{
"epoch": 5.94,
"learning_rate": 0.0002,
"loss": 0.5727,
"step": 106600
},
{
"epoch": 5.95,
"learning_rate": 0.0002,
"loss": 0.5745,
"step": 106700
},
{
"epoch": 5.95,
"learning_rate": 0.0002,
"loss": 0.5797,
"step": 106800
},
{
"epoch": 5.96,
"learning_rate": 0.0002,
"loss": 0.5714,
"step": 106900
},
{
"epoch": 5.96,
"learning_rate": 0.0002,
"loss": 0.5603,
"step": 107000
},
{
"epoch": 5.97,
"learning_rate": 0.0002,
"loss": 0.5671,
"step": 107100
},
{
"epoch": 5.97,
"learning_rate": 0.0002,
"loss": 0.56,
"step": 107200
},
{
"epoch": 5.98,
"learning_rate": 0.0002,
"loss": 0.5676,
"step": 107300
},
{
"epoch": 5.98,
"learning_rate": 0.0002,
"loss": 0.5907,
"step": 107400
},
{
"epoch": 5.99,
"learning_rate": 0.0002,
"loss": 0.5651,
"step": 107500
},
{
"epoch": 6.0,
"learning_rate": 0.0002,
"loss": 0.5675,
"step": 107600
},
{
"epoch": 6.0,
"learning_rate": 0.0002,
"loss": 0.5716,
"step": 107700
},
{
"epoch": 6.01,
"learning_rate": 0.0002,
"loss": 0.5342,
"step": 107800
},
{
"epoch": 6.01,
"learning_rate": 0.0002,
"loss": 0.5334,
"step": 107900
},
{
"epoch": 6.02,
"learning_rate": 0.0002,
"loss": 0.5439,
"step": 108000
},
{
"epoch": 6.02,
"learning_rate": 0.0002,
"loss": 0.5571,
"step": 108100
},
{
"epoch": 6.03,
"learning_rate": 0.0002,
"loss": 0.5569,
"step": 108200
},
{
"epoch": 6.04,
"learning_rate": 0.0002,
"loss": 0.5569,
"step": 108300
},
{
"epoch": 6.04,
"learning_rate": 0.0002,
"loss": 0.5481,
"step": 108400
},
{
"epoch": 6.05,
"learning_rate": 0.0002,
"loss": 0.5507,
"step": 108500
},
{
"epoch": 6.05,
"learning_rate": 0.0002,
"loss": 0.5438,
"step": 108600
},
{
"epoch": 6.06,
"learning_rate": 0.0002,
"loss": 0.5498,
"step": 108700
},
{
"epoch": 6.06,
"learning_rate": 0.0002,
"loss": 0.55,
"step": 108800
},
{
"epoch": 6.07,
"learning_rate": 0.0002,
"loss": 0.5625,
"step": 108900
},
{
"epoch": 6.07,
"learning_rate": 0.0002,
"loss": 0.547,
"step": 109000
},
{
"epoch": 6.08,
"learning_rate": 0.0002,
"loss": 0.5498,
"step": 109100
},
{
"epoch": 6.09,
"learning_rate": 0.0002,
"loss": 0.5467,
"step": 109200
},
{
"epoch": 6.09,
"learning_rate": 0.0002,
"loss": 0.5346,
"step": 109300
},
{
"epoch": 6.1,
"learning_rate": 0.0002,
"loss": 0.5439,
"step": 109400
},
{
"epoch": 6.1,
"learning_rate": 0.0002,
"loss": 0.5395,
"step": 109500
},
{
"epoch": 6.11,
"learning_rate": 0.0002,
"loss": 0.543,
"step": 109600
},
{
"epoch": 6.11,
"learning_rate": 0.0002,
"loss": 0.5494,
"step": 109700
},
{
"epoch": 6.12,
"learning_rate": 0.0002,
"loss": 0.5471,
"step": 109800
},
{
"epoch": 6.12,
"learning_rate": 0.0002,
"loss": 0.5491,
"step": 109900
},
{
"epoch": 6.13,
"learning_rate": 0.0002,
"loss": 0.5515,
"step": 110000
},
{
"epoch": 6.13,
"eval_gen_len": 18.999925194494313,
"eval_loss": 2.722730875015259,
"eval_rouge1": 25.2536,
"eval_rouge2": 12.3269,
"eval_rougeL": 20.8448,
"eval_rougeLsum": 23.8308,
"eval_runtime": 477.19,
"eval_samples_per_second": 28.014,
"eval_steps_per_second": 1.752,
"step": 110000
},
{
"epoch": 6.14,
"learning_rate": 0.0002,
"loss": 0.5518,
"step": 110100
},
{
"epoch": 6.14,
"learning_rate": 0.0002,
"loss": 0.5394,
"step": 110200
},
{
"epoch": 6.15,
"learning_rate": 0.0002,
"loss": 0.5362,
"step": 110300
},
{
"epoch": 6.15,
"learning_rate": 0.0002,
"loss": 0.5357,
"step": 110400
},
{
"epoch": 6.16,
"learning_rate": 0.0002,
"loss": 0.5489,
"step": 110500
},
{
"epoch": 6.16,
"learning_rate": 0.0002,
"loss": 0.5506,
"step": 110600
},
{
"epoch": 6.17,
"learning_rate": 0.0002,
"loss": 0.5659,
"step": 110700
},
{
"epoch": 6.17,
"learning_rate": 0.0002,
"loss": 0.5502,
"step": 110800
},
{
"epoch": 6.18,
"learning_rate": 0.0002,
"loss": 0.5564,
"step": 110900
},
{
"epoch": 6.19,
"learning_rate": 0.0002,
"loss": 0.5411,
"step": 111000
},
{
"epoch": 6.19,
"learning_rate": 0.0002,
"loss": 0.542,
"step": 111100
},
{
"epoch": 6.2,
"learning_rate": 0.0002,
"loss": 0.5582,
"step": 111200
},
{
"epoch": 6.2,
"learning_rate": 0.0002,
"loss": 0.535,
"step": 111300
},
{
"epoch": 6.21,
"learning_rate": 0.0002,
"loss": 0.5458,
"step": 111400
},
{
"epoch": 6.21,
"learning_rate": 0.0002,
"loss": 0.5683,
"step": 111500
},
{
"epoch": 6.22,
"learning_rate": 0.0002,
"loss": 0.5659,
"step": 111600
},
{
"epoch": 6.22,
"learning_rate": 0.0002,
"loss": 0.5536,
"step": 111700
},
{
"epoch": 6.23,
"learning_rate": 0.0002,
"loss": 0.5594,
"step": 111800
},
{
"epoch": 6.24,
"learning_rate": 0.0002,
"loss": 0.5633,
"step": 111900
},
{
"epoch": 6.24,
"learning_rate": 0.0002,
"loss": 0.561,
"step": 112000
},
{
"epoch": 6.25,
"learning_rate": 0.0002,
"loss": 0.5485,
"step": 112100
},
{
"epoch": 6.25,
"learning_rate": 0.0002,
"loss": 0.5567,
"step": 112200
},
{
"epoch": 6.26,
"learning_rate": 0.0002,
"loss": 0.5568,
"step": 112300
},
{
"epoch": 6.26,
"learning_rate": 0.0002,
"loss": 0.5407,
"step": 112400
},
{
"epoch": 6.27,
"learning_rate": 0.0002,
"loss": 0.5433,
"step": 112500
},
{
"epoch": 6.27,
"learning_rate": 0.0002,
"loss": 0.5583,
"step": 112600
},
{
"epoch": 6.28,
"learning_rate": 0.0002,
"loss": 0.5516,
"step": 112700
},
{
"epoch": 6.29,
"learning_rate": 0.0002,
"loss": 0.5493,
"step": 112800
},
{
"epoch": 6.29,
"learning_rate": 0.0002,
"loss": 0.5513,
"step": 112900
},
{
"epoch": 6.3,
"learning_rate": 0.0002,
"loss": 0.5622,
"step": 113000
},
{
"epoch": 6.3,
"learning_rate": 0.0002,
"loss": 0.5431,
"step": 113100
},
{
"epoch": 6.31,
"learning_rate": 0.0002,
"loss": 0.5497,
"step": 113200
},
{
"epoch": 6.31,
"learning_rate": 0.0002,
"loss": 0.5398,
"step": 113300
},
{
"epoch": 6.32,
"learning_rate": 0.0002,
"loss": 0.5613,
"step": 113400
},
{
"epoch": 6.32,
"learning_rate": 0.0002,
"loss": 0.5565,
"step": 113500
},
{
"epoch": 6.33,
"learning_rate": 0.0002,
"loss": 0.5485,
"step": 113600
},
{
"epoch": 6.34,
"learning_rate": 0.0002,
"loss": 0.554,
"step": 113700
},
{
"epoch": 6.34,
"learning_rate": 0.0002,
"loss": 0.5594,
"step": 113800
},
{
"epoch": 6.35,
"learning_rate": 0.0002,
"loss": 0.5483,
"step": 113900
},
{
"epoch": 6.35,
"learning_rate": 0.0002,
"loss": 0.5468,
"step": 114000
},
{
"epoch": 6.36,
"learning_rate": 0.0002,
"loss": 0.5549,
"step": 114100
},
{
"epoch": 6.36,
"learning_rate": 0.0002,
"loss": 0.5605,
"step": 114200
},
{
"epoch": 6.37,
"learning_rate": 0.0002,
"loss": 0.5541,
"step": 114300
},
{
"epoch": 6.38,
"learning_rate": 0.0002,
"loss": 0.5553,
"step": 114400
},
{
"epoch": 6.38,
"learning_rate": 0.0002,
"loss": 0.5566,
"step": 114500
},
{
"epoch": 6.39,
"learning_rate": 0.0002,
"loss": 0.5599,
"step": 114600
},
{
"epoch": 6.39,
"learning_rate": 0.0002,
"loss": 0.5422,
"step": 114700
},
{
"epoch": 6.4,
"learning_rate": 0.0002,
"loss": 0.5648,
"step": 114800
},
{
"epoch": 6.4,
"learning_rate": 0.0002,
"loss": 0.5511,
"step": 114900
},
{
"epoch": 6.41,
"learning_rate": 0.0002,
"loss": 0.553,
"step": 115000
},
{
"epoch": 6.41,
"learning_rate": 0.0002,
"loss": 0.5412,
"step": 115100
},
{
"epoch": 6.42,
"learning_rate": 0.0002,
"loss": 0.5762,
"step": 115200
},
{
"epoch": 6.43,
"learning_rate": 0.0002,
"loss": 0.5528,
"step": 115300
},
{
"epoch": 6.43,
"learning_rate": 0.0002,
"loss": 0.5404,
"step": 115400
},
{
"epoch": 6.44,
"learning_rate": 0.0002,
"loss": 0.5462,
"step": 115500
},
{
"epoch": 6.44,
"learning_rate": 0.0002,
"loss": 0.5516,
"step": 115600
},
{
"epoch": 6.45,
"learning_rate": 0.0002,
"loss": 0.5538,
"step": 115700
},
{
"epoch": 6.45,
"learning_rate": 0.0002,
"loss": 0.5509,
"step": 115800
},
{
"epoch": 6.46,
"learning_rate": 0.0002,
"loss": 0.5516,
"step": 115900
},
{
"epoch": 6.46,
"learning_rate": 0.0002,
"loss": 0.5522,
"step": 116000
},
{
"epoch": 6.47,
"learning_rate": 0.0002,
"loss": 0.556,
"step": 116100
},
{
"epoch": 6.48,
"learning_rate": 0.0002,
"loss": 0.5657,
"step": 116200
},
{
"epoch": 6.48,
"learning_rate": 0.0002,
"loss": 0.5643,
"step": 116300
},
{
"epoch": 6.49,
"learning_rate": 0.0002,
"loss": 0.5467,
"step": 116400
},
{
"epoch": 6.49,
"learning_rate": 0.0002,
"loss": 0.5562,
"step": 116500
},
{
"epoch": 6.5,
"learning_rate": 0.0002,
"loss": 0.5572,
"step": 116600
},
{
"epoch": 6.5,
"learning_rate": 0.0002,
"loss": 0.5423,
"step": 116700
},
{
"epoch": 6.51,
"learning_rate": 0.0002,
"loss": 0.5541,
"step": 116800
},
{
"epoch": 6.51,
"learning_rate": 0.0002,
"loss": 0.5601,
"step": 116900
},
{
"epoch": 6.52,
"learning_rate": 0.0002,
"loss": 0.5675,
"step": 117000
},
{
"epoch": 6.53,
"learning_rate": 0.0002,
"loss": 0.5427,
"step": 117100
},
{
"epoch": 6.53,
"learning_rate": 0.0002,
"loss": 0.554,
"step": 117200
},
{
"epoch": 6.54,
"learning_rate": 0.0002,
"loss": 0.5649,
"step": 117300
},
{
"epoch": 6.54,
"learning_rate": 0.0002,
"loss": 0.556,
"step": 117400
},
{
"epoch": 6.55,
"learning_rate": 0.0002,
"loss": 0.5549,
"step": 117500
},
{
"epoch": 6.55,
"learning_rate": 0.0002,
"loss": 0.5614,
"step": 117600
},
{
"epoch": 6.56,
"learning_rate": 0.0002,
"loss": 0.5721,
"step": 117700
},
{
"epoch": 6.56,
"learning_rate": 0.0002,
"loss": 0.5596,
"step": 117800
},
{
"epoch": 6.57,
"learning_rate": 0.0002,
"loss": 0.5656,
"step": 117900
},
{
"epoch": 6.58,
"learning_rate": 0.0002,
"loss": 0.5459,
"step": 118000
},
{
"epoch": 6.58,
"learning_rate": 0.0002,
"loss": 0.552,
"step": 118100
},
{
"epoch": 6.59,
"learning_rate": 0.0002,
"loss": 0.5642,
"step": 118200
},
{
"epoch": 6.59,
"learning_rate": 0.0002,
"loss": 0.5729,
"step": 118300
},
{
"epoch": 6.6,
"learning_rate": 0.0002,
"loss": 0.5577,
"step": 118400
},
{
"epoch": 6.6,
"learning_rate": 0.0002,
"loss": 0.5576,
"step": 118500
},
{
"epoch": 6.61,
"learning_rate": 0.0002,
"loss": 0.5848,
"step": 118600
},
{
"epoch": 6.61,
"learning_rate": 0.0002,
"loss": 0.5571,
"step": 118700
},
{
"epoch": 6.62,
"learning_rate": 0.0002,
"loss": 0.5502,
"step": 118800
},
{
"epoch": 6.63,
"learning_rate": 0.0002,
"loss": 0.5676,
"step": 118900
},
{
"epoch": 6.63,
"learning_rate": 0.0002,
"loss": 0.5556,
"step": 119000
},
{
"epoch": 6.64,
"learning_rate": 0.0002,
"loss": 0.5538,
"step": 119100
},
{
"epoch": 6.64,
"learning_rate": 0.0002,
"loss": 0.5527,
"step": 119200
},
{
"epoch": 6.65,
"learning_rate": 0.0002,
"loss": 0.5675,
"step": 119300
},
{
"epoch": 6.65,
"learning_rate": 0.0002,
"loss": 0.543,
"step": 119400
},
{
"epoch": 6.66,
"learning_rate": 0.0002,
"loss": 0.5614,
"step": 119500
},
{
"epoch": 6.66,
"learning_rate": 0.0002,
"loss": 0.5577,
"step": 119600
},
{
"epoch": 6.67,
"learning_rate": 0.0002,
"loss": 0.5507,
"step": 119700
},
{
"epoch": 6.68,
"learning_rate": 0.0002,
"loss": 0.562,
"step": 119800
},
{
"epoch": 6.68,
"learning_rate": 0.0002,
"loss": 0.554,
"step": 119900
},
{
"epoch": 6.69,
"learning_rate": 0.0002,
"loss": 0.5651,
"step": 120000
},
{
"epoch": 6.69,
"eval_gen_len": 18.99955116696589,
"eval_loss": 2.6814467906951904,
"eval_rouge1": 25.3277,
"eval_rouge2": 12.4166,
"eval_rougeL": 20.9334,
"eval_rougeLsum": 23.9166,
"eval_runtime": 477.4979,
"eval_samples_per_second": 27.996,
"eval_steps_per_second": 1.751,
"step": 120000
},
{
"epoch": 6.69,
"learning_rate": 0.0002,
"loss": 0.5714,
"step": 120100
},
{
"epoch": 6.7,
"learning_rate": 0.0002,
"loss": 0.5739,
"step": 120200
},
{
"epoch": 6.7,
"learning_rate": 0.0002,
"loss": 0.552,
"step": 120300
},
{
"epoch": 6.71,
"learning_rate": 0.0002,
"loss": 0.5548,
"step": 120400
},
{
"epoch": 6.71,
"learning_rate": 0.0002,
"loss": 0.5658,
"step": 120500
},
{
"epoch": 6.72,
"learning_rate": 0.0002,
"loss": 0.5729,
"step": 120600
},
{
"epoch": 6.73,
"learning_rate": 0.0002,
"loss": 0.5614,
"step": 120700
},
{
"epoch": 6.73,
"learning_rate": 0.0002,
"loss": 0.5745,
"step": 120800
},
{
"epoch": 6.74,
"learning_rate": 0.0002,
"loss": 0.5595,
"step": 120900
},
{
"epoch": 6.74,
"learning_rate": 0.0002,
"loss": 0.5583,
"step": 121000
},
{
"epoch": 6.75,
"learning_rate": 0.0002,
"loss": 0.553,
"step": 121100
},
{
"epoch": 6.75,
"learning_rate": 0.0002,
"loss": 0.5788,
"step": 121200
},
{
"epoch": 6.76,
"learning_rate": 0.0002,
"loss": 0.5535,
"step": 121300
},
{
"epoch": 6.77,
"learning_rate": 0.0002,
"loss": 0.5666,
"step": 121400
},
{
"epoch": 6.77,
"learning_rate": 0.0002,
"loss": 0.5616,
"step": 121500
},
{
"epoch": 6.78,
"learning_rate": 0.0002,
"loss": 0.5619,
"step": 121600
},
{
"epoch": 6.78,
"learning_rate": 0.0002,
"loss": 0.559,
"step": 121700
},
{
"epoch": 6.79,
"learning_rate": 0.0002,
"loss": 0.5806,
"step": 121800
},
{
"epoch": 6.79,
"learning_rate": 0.0002,
"loss": 0.5696,
"step": 121900
},
{
"epoch": 6.8,
"learning_rate": 0.0002,
"loss": 0.5667,
"step": 122000
},
{
"epoch": 6.8,
"learning_rate": 0.0002,
"loss": 0.5452,
"step": 122100
},
{
"epoch": 6.81,
"learning_rate": 0.0002,
"loss": 0.5609,
"step": 122200
},
{
"epoch": 6.82,
"learning_rate": 0.0002,
"loss": 0.5703,
"step": 122300
},
{
"epoch": 6.82,
"learning_rate": 0.0002,
"loss": 0.5568,
"step": 122400
},
{
"epoch": 6.83,
"learning_rate": 0.0002,
"loss": 0.565,
"step": 122500
},
{
"epoch": 6.83,
"learning_rate": 0.0002,
"loss": 0.5556,
"step": 122600
},
{
"epoch": 6.84,
"learning_rate": 0.0002,
"loss": 0.5577,
"step": 122700
},
{
"epoch": 6.84,
"learning_rate": 0.0002,
"loss": 0.5625,
"step": 122800
},
{
"epoch": 6.85,
"learning_rate": 0.0002,
"loss": 0.5589,
"step": 122900
},
{
"epoch": 6.85,
"learning_rate": 0.0002,
"loss": 0.5728,
"step": 123000
},
{
"epoch": 6.86,
"learning_rate": 0.0002,
"loss": 0.5534,
"step": 123100
},
{
"epoch": 6.87,
"learning_rate": 0.0002,
"loss": 0.5592,
"step": 123200
},
{
"epoch": 6.87,
"learning_rate": 0.0002,
"loss": 0.5646,
"step": 123300
},
{
"epoch": 6.88,
"learning_rate": 0.0002,
"loss": 0.5774,
"step": 123400
},
{
"epoch": 6.88,
"learning_rate": 0.0002,
"loss": 0.5629,
"step": 123500
},
{
"epoch": 6.89,
"learning_rate": 0.0002,
"loss": 0.5676,
"step": 123600
},
{
"epoch": 6.89,
"learning_rate": 0.0002,
"loss": 0.5734,
"step": 123700
},
{
"epoch": 6.9,
"learning_rate": 0.0002,
"loss": 0.5566,
"step": 123800
},
{
"epoch": 6.9,
"learning_rate": 0.0002,
"loss": 0.5603,
"step": 123900
},
{
"epoch": 6.91,
"learning_rate": 0.0002,
"loss": 0.5758,
"step": 124000
},
{
"epoch": 6.92,
"learning_rate": 0.0002,
"loss": 0.57,
"step": 124100
},
{
"epoch": 6.92,
"learning_rate": 0.0002,
"loss": 0.5823,
"step": 124200
},
{
"epoch": 6.93,
"learning_rate": 0.0002,
"loss": 0.5699,
"step": 124300
},
{
"epoch": 6.93,
"learning_rate": 0.0002,
"loss": 0.5487,
"step": 124400
},
{
"epoch": 6.94,
"learning_rate": 0.0002,
"loss": 0.561,
"step": 124500
},
{
"epoch": 6.94,
"learning_rate": 0.0002,
"loss": 0.585,
"step": 124600
},
{
"epoch": 6.95,
"learning_rate": 0.0002,
"loss": 0.5693,
"step": 124700
},
{
"epoch": 6.95,
"learning_rate": 0.0002,
"loss": 0.5728,
"step": 124800
},
{
"epoch": 6.96,
"learning_rate": 0.0002,
"loss": 0.5794,
"step": 124900
},
{
"epoch": 6.97,
"learning_rate": 0.0002,
"loss": 0.5483,
"step": 125000
},
{
"epoch": 6.97,
"learning_rate": 0.0002,
"loss": 0.56,
"step": 125100
},
{
"epoch": 6.98,
"learning_rate": 0.0002,
"loss": 0.5635,
"step": 125200
},
{
"epoch": 6.98,
"learning_rate": 0.0002,
"loss": 0.5735,
"step": 125300
},
{
"epoch": 6.99,
"learning_rate": 0.0002,
"loss": 0.5811,
"step": 125400
},
{
"epoch": 6.99,
"learning_rate": 0.0002,
"loss": 0.5757,
"step": 125500
},
{
"epoch": 7.0,
"learning_rate": 0.0002,
"loss": 0.5567,
"step": 125600
},
{
"epoch": 7.0,
"learning_rate": 0.0002,
"loss": 0.5306,
"step": 125700
},
{
"epoch": 7.01,
"learning_rate": 0.0002,
"loss": 0.5365,
"step": 125800
},
{
"epoch": 7.02,
"learning_rate": 0.0002,
"loss": 0.5386,
"step": 125900
},
{
"epoch": 7.02,
"learning_rate": 0.0002,
"loss": 0.5402,
"step": 126000
},
{
"epoch": 7.03,
"learning_rate": 0.0002,
"loss": 0.5341,
"step": 126100
},
{
"epoch": 7.03,
"learning_rate": 0.0002,
"loss": 0.5384,
"step": 126200
},
{
"epoch": 7.04,
"learning_rate": 0.0002,
"loss": 0.5285,
"step": 126300
},
{
"epoch": 7.04,
"learning_rate": 0.0002,
"loss": 0.553,
"step": 126400
},
{
"epoch": 7.05,
"learning_rate": 0.0002,
"loss": 0.5334,
"step": 126500
},
{
"epoch": 7.05,
"learning_rate": 0.0002,
"loss": 0.5277,
"step": 126600
},
{
"epoch": 7.06,
"learning_rate": 0.0002,
"loss": 0.56,
"step": 126700
},
{
"epoch": 7.07,
"learning_rate": 0.0002,
"loss": 0.5326,
"step": 126800
},
{
"epoch": 7.07,
"learning_rate": 0.0002,
"loss": 0.5438,
"step": 126900
},
{
"epoch": 7.08,
"learning_rate": 0.0002,
"loss": 0.551,
"step": 127000
},
{
"epoch": 7.08,
"learning_rate": 0.0002,
"loss": 0.5461,
"step": 127100
},
{
"epoch": 7.09,
"learning_rate": 0.0002,
"loss": 0.5438,
"step": 127200
},
{
"epoch": 7.09,
"learning_rate": 0.0002,
"loss": 0.5459,
"step": 127300
},
{
"epoch": 7.1,
"learning_rate": 0.0002,
"loss": 0.5509,
"step": 127400
},
{
"epoch": 7.11,
"learning_rate": 0.0002,
"loss": 0.5329,
"step": 127500
},
{
"epoch": 7.11,
"learning_rate": 0.0002,
"loss": 0.5525,
"step": 127600
},
{
"epoch": 7.12,
"learning_rate": 0.0002,
"loss": 0.5337,
"step": 127700
},
{
"epoch": 7.12,
"learning_rate": 0.0002,
"loss": 0.541,
"step": 127800
},
{
"epoch": 7.13,
"learning_rate": 0.0002,
"loss": 0.5577,
"step": 127900
},
{
"epoch": 7.13,
"learning_rate": 0.0002,
"loss": 0.546,
"step": 128000
},
{
"epoch": 7.14,
"learning_rate": 0.0002,
"loss": 0.5478,
"step": 128100
},
{
"epoch": 7.14,
"learning_rate": 0.0002,
"loss": 0.5394,
"step": 128200
},
{
"epoch": 7.15,
"learning_rate": 0.0002,
"loss": 0.5302,
"step": 128300
},
{
"epoch": 7.16,
"learning_rate": 0.0002,
"loss": 0.5545,
"step": 128400
},
{
"epoch": 7.16,
"learning_rate": 0.0002,
"loss": 0.532,
"step": 128500
},
{
"epoch": 7.17,
"learning_rate": 0.0002,
"loss": 0.5468,
"step": 128600
},
{
"epoch": 7.17,
"learning_rate": 0.0002,
"loss": 0.5394,
"step": 128700
},
{
"epoch": 7.18,
"learning_rate": 0.0002,
"loss": 0.542,
"step": 128800
},
{
"epoch": 7.18,
"learning_rate": 0.0002,
"loss": 0.5319,
"step": 128900
},
{
"epoch": 7.19,
"learning_rate": 0.0002,
"loss": 0.5431,
"step": 129000
},
{
"epoch": 7.19,
"learning_rate": 0.0002,
"loss": 0.5413,
"step": 129100
},
{
"epoch": 7.2,
"learning_rate": 0.0002,
"loss": 0.5368,
"step": 129200
},
{
"epoch": 7.21,
"learning_rate": 0.0002,
"loss": 0.5458,
"step": 129300
},
{
"epoch": 7.21,
"learning_rate": 0.0002,
"loss": 0.5405,
"step": 129400
},
{
"epoch": 7.22,
"learning_rate": 0.0002,
"loss": 0.5543,
"step": 129500
},
{
"epoch": 7.22,
"learning_rate": 0.0002,
"loss": 0.5318,
"step": 129600
},
{
"epoch": 7.23,
"learning_rate": 0.0002,
"loss": 0.5489,
"step": 129700
},
{
"epoch": 7.23,
"learning_rate": 0.0002,
"loss": 0.5346,
"step": 129800
},
{
"epoch": 7.24,
"learning_rate": 0.0002,
"loss": 0.5403,
"step": 129900
},
{
"epoch": 7.24,
"learning_rate": 0.0002,
"loss": 0.5442,
"step": 130000
},
{
"epoch": 7.24,
"eval_gen_len": 18.99970077797726,
"eval_loss": 2.7132627964019775,
"eval_rouge1": 25.3009,
"eval_rouge2": 12.3948,
"eval_rougeL": 20.9085,
"eval_rougeLsum": 23.8773,
"eval_runtime": 477.2595,
"eval_samples_per_second": 28.01,
"eval_steps_per_second": 1.752,
"step": 130000
},
{
"epoch": 7.25,
"learning_rate": 0.0002,
"loss": 0.5588,
"step": 130100
},
{
"epoch": 7.26,
"learning_rate": 0.0002,
"loss": 0.5397,
"step": 130200
},
{
"epoch": 7.26,
"learning_rate": 0.0002,
"loss": 0.5392,
"step": 130300
},
{
"epoch": 7.27,
"learning_rate": 0.0002,
"loss": 0.538,
"step": 130400
},
{
"epoch": 7.27,
"learning_rate": 0.0002,
"loss": 0.5464,
"step": 130500
},
{
"epoch": 7.28,
"learning_rate": 0.0002,
"loss": 0.5475,
"step": 130600
},
{
"epoch": 7.28,
"learning_rate": 0.0002,
"loss": 0.547,
"step": 130700
},
{
"epoch": 7.29,
"learning_rate": 0.0002,
"loss": 0.5494,
"step": 130800
},
{
"epoch": 7.29,
"learning_rate": 0.0002,
"loss": 0.5357,
"step": 130900
},
{
"epoch": 7.3,
"learning_rate": 0.0002,
"loss": 0.5518,
"step": 131000
},
{
"epoch": 7.31,
"learning_rate": 0.0002,
"loss": 0.546,
"step": 131100
},
{
"epoch": 7.31,
"learning_rate": 0.0002,
"loss": 0.5416,
"step": 131200
},
{
"epoch": 7.32,
"learning_rate": 0.0002,
"loss": 0.5489,
"step": 131300
},
{
"epoch": 7.32,
"learning_rate": 0.0002,
"loss": 0.5483,
"step": 131400
},
{
"epoch": 7.33,
"learning_rate": 0.0002,
"loss": 0.5557,
"step": 131500
},
{
"epoch": 7.33,
"learning_rate": 0.0002,
"loss": 0.5605,
"step": 131600
},
{
"epoch": 7.34,
"learning_rate": 0.0002,
"loss": 0.5532,
"step": 131700
},
{
"epoch": 7.34,
"learning_rate": 0.0002,
"loss": 0.5482,
"step": 131800
},
{
"epoch": 7.35,
"learning_rate": 0.0002,
"loss": 0.5482,
"step": 131900
},
{
"epoch": 7.36,
"learning_rate": 0.0002,
"loss": 0.5458,
"step": 132000
},
{
"epoch": 7.36,
"learning_rate": 0.0002,
"loss": 0.5499,
"step": 132100
},
{
"epoch": 7.37,
"learning_rate": 0.0002,
"loss": 0.5537,
"step": 132200
},
{
"epoch": 7.37,
"learning_rate": 0.0002,
"loss": 0.5375,
"step": 132300
},
{
"epoch": 7.38,
"learning_rate": 0.0002,
"loss": 0.5515,
"step": 132400
},
{
"epoch": 7.38,
"learning_rate": 0.0002,
"loss": 0.5499,
"step": 132500
},
{
"epoch": 7.39,
"learning_rate": 0.0002,
"loss": 0.535,
"step": 132600
},
{
"epoch": 7.39,
"learning_rate": 0.0002,
"loss": 0.5537,
"step": 132700
},
{
"epoch": 7.4,
"learning_rate": 0.0002,
"loss": 0.5498,
"step": 132800
},
{
"epoch": 7.41,
"learning_rate": 0.0002,
"loss": 0.5648,
"step": 132900
},
{
"epoch": 7.41,
"learning_rate": 0.0002,
"loss": 0.5372,
"step": 133000
},
{
"epoch": 7.42,
"learning_rate": 0.0002,
"loss": 0.5622,
"step": 133100
},
{
"epoch": 7.42,
"learning_rate": 0.0002,
"loss": 0.5463,
"step": 133200
},
{
"epoch": 7.43,
"learning_rate": 0.0002,
"loss": 0.5639,
"step": 133300
},
{
"epoch": 7.43,
"learning_rate": 0.0002,
"loss": 0.5437,
"step": 133400
},
{
"epoch": 7.44,
"learning_rate": 0.0002,
"loss": 0.542,
"step": 133500
},
{
"epoch": 7.44,
"learning_rate": 0.0002,
"loss": 0.5435,
"step": 133600
},
{
"epoch": 7.45,
"learning_rate": 0.0002,
"loss": 0.5531,
"step": 133700
},
{
"epoch": 7.46,
"learning_rate": 0.0002,
"loss": 0.5522,
"step": 133800
},
{
"epoch": 7.46,
"learning_rate": 0.0002,
"loss": 0.5569,
"step": 133900
},
{
"epoch": 7.47,
"learning_rate": 0.0002,
"loss": 0.5489,
"step": 134000
},
{
"epoch": 7.47,
"learning_rate": 0.0002,
"loss": 0.5459,
"step": 134100
},
{
"epoch": 7.48,
"learning_rate": 0.0002,
"loss": 0.5584,
"step": 134200
},
{
"epoch": 7.48,
"learning_rate": 0.0002,
"loss": 0.5563,
"step": 134300
},
{
"epoch": 7.49,
"learning_rate": 0.0002,
"loss": 0.5459,
"step": 134400
},
{
"epoch": 7.5,
"learning_rate": 0.0002,
"loss": 0.5389,
"step": 134500
},
{
"epoch": 7.5,
"learning_rate": 0.0002,
"loss": 0.5451,
"step": 134600
},
{
"epoch": 7.51,
"learning_rate": 0.0002,
"loss": 0.5435,
"step": 134700
},
{
"epoch": 7.51,
"learning_rate": 0.0002,
"loss": 0.5538,
"step": 134800
},
{
"epoch": 7.52,
"learning_rate": 0.0002,
"loss": 0.5466,
"step": 134900
},
{
"epoch": 7.52,
"learning_rate": 0.0002,
"loss": 0.5522,
"step": 135000
},
{
"epoch": 7.53,
"learning_rate": 0.0002,
"loss": 0.5564,
"step": 135100
},
{
"epoch": 7.53,
"learning_rate": 0.0002,
"loss": 0.5531,
"step": 135200
},
{
"epoch": 7.54,
"learning_rate": 0.0002,
"loss": 0.5478,
"step": 135300
},
{
"epoch": 7.55,
"learning_rate": 0.0002,
"loss": 0.5715,
"step": 135400
},
{
"epoch": 7.55,
"learning_rate": 0.0002,
"loss": 0.5547,
"step": 135500
},
{
"epoch": 7.56,
"learning_rate": 0.0002,
"loss": 0.5514,
"step": 135600
},
{
"epoch": 7.56,
"learning_rate": 0.0002,
"loss": 0.5506,
"step": 135700
},
{
"epoch": 7.57,
"learning_rate": 0.0002,
"loss": 0.547,
"step": 135800
},
{
"epoch": 7.57,
"learning_rate": 0.0002,
"loss": 0.5566,
"step": 135900
},
{
"epoch": 7.58,
"learning_rate": 0.0002,
"loss": 0.5594,
"step": 136000
},
{
"epoch": 7.58,
"learning_rate": 0.0002,
"loss": 0.5524,
"step": 136100
},
{
"epoch": 7.59,
"learning_rate": 0.0002,
"loss": 0.5635,
"step": 136200
},
{
"epoch": 7.6,
"learning_rate": 0.0002,
"loss": 0.5551,
"step": 136300
},
{
"epoch": 7.6,
"learning_rate": 0.0002,
"loss": 0.553,
"step": 136400
},
{
"epoch": 7.61,
"learning_rate": 0.0002,
"loss": 0.5664,
"step": 136500
},
{
"epoch": 7.61,
"learning_rate": 0.0002,
"loss": 0.5394,
"step": 136600
},
{
"epoch": 7.62,
"learning_rate": 0.0002,
"loss": 0.5626,
"step": 136700
},
{
"epoch": 7.62,
"learning_rate": 0.0002,
"loss": 0.5541,
"step": 136800
},
{
"epoch": 7.63,
"learning_rate": 0.0002,
"loss": 0.5575,
"step": 136900
},
{
"epoch": 7.63,
"learning_rate": 0.0002,
"loss": 0.5567,
"step": 137000
},
{
"epoch": 7.64,
"learning_rate": 0.0002,
"loss": 0.5554,
"step": 137100
},
{
"epoch": 7.65,
"learning_rate": 0.0002,
"loss": 0.5423,
"step": 137200
},
{
"epoch": 7.65,
"learning_rate": 0.0002,
"loss": 0.5524,
"step": 137300
},
{
"epoch": 7.66,
"learning_rate": 0.0002,
"loss": 0.5636,
"step": 137400
},
{
"epoch": 7.66,
"learning_rate": 0.0002,
"loss": 0.5629,
"step": 137500
},
{
"epoch": 7.67,
"learning_rate": 0.0002,
"loss": 0.5536,
"step": 137600
},
{
"epoch": 7.67,
"learning_rate": 0.0002,
"loss": 0.5506,
"step": 137700
},
{
"epoch": 7.68,
"learning_rate": 0.0002,
"loss": 0.5601,
"step": 137800
},
{
"epoch": 7.68,
"learning_rate": 0.0002,
"loss": 0.5649,
"step": 137900
},
{
"epoch": 7.69,
"learning_rate": 0.0002,
"loss": 0.5438,
"step": 138000
},
{
"epoch": 7.7,
"learning_rate": 0.0002,
"loss": 0.5511,
"step": 138100
},
{
"epoch": 7.7,
"learning_rate": 0.0002,
"loss": 0.5453,
"step": 138200
},
{
"epoch": 7.71,
"learning_rate": 0.0002,
"loss": 0.5592,
"step": 138300
},
{
"epoch": 7.71,
"learning_rate": 0.0002,
"loss": 0.5518,
"step": 138400
},
{
"epoch": 7.72,
"learning_rate": 0.0002,
"loss": 0.5637,
"step": 138500
},
{
"epoch": 7.72,
"learning_rate": 0.0002,
"loss": 0.5533,
"step": 138600
},
{
"epoch": 7.73,
"learning_rate": 0.0002,
"loss": 0.5615,
"step": 138700
},
{
"epoch": 7.73,
"learning_rate": 0.0002,
"loss": 0.549,
"step": 138800
},
{
"epoch": 7.74,
"learning_rate": 0.0002,
"loss": 0.5433,
"step": 138900
},
{
"epoch": 7.75,
"learning_rate": 0.0002,
"loss": 0.5614,
"step": 139000
},
{
"epoch": 7.75,
"learning_rate": 0.0002,
"loss": 0.5621,
"step": 139100
},
{
"epoch": 7.76,
"learning_rate": 0.0002,
"loss": 0.5581,
"step": 139200
},
{
"epoch": 7.76,
"learning_rate": 0.0002,
"loss": 0.5498,
"step": 139300
},
{
"epoch": 7.77,
"learning_rate": 0.0002,
"loss": 0.5725,
"step": 139400
},
{
"epoch": 7.77,
"learning_rate": 0.0002,
"loss": 0.5553,
"step": 139500
},
{
"epoch": 7.78,
"learning_rate": 0.0002,
"loss": 0.556,
"step": 139600
},
{
"epoch": 7.78,
"learning_rate": 0.0002,
"loss": 0.5517,
"step": 139700
},
{
"epoch": 7.79,
"learning_rate": 0.0002,
"loss": 0.5554,
"step": 139800
},
{
"epoch": 7.8,
"learning_rate": 0.0002,
"loss": 0.5647,
"step": 139900
},
{
"epoch": 7.8,
"learning_rate": 0.0002,
"loss": 0.5574,
"step": 140000
},
{
"epoch": 7.8,
"eval_gen_len": 18.999027528426094,
"eval_loss": 2.6958916187286377,
"eval_rouge1": 25.3491,
"eval_rouge2": 12.3925,
"eval_rougeL": 20.911,
"eval_rougeLsum": 23.9331,
"eval_runtime": 475.0144,
"eval_samples_per_second": 28.142,
"eval_steps_per_second": 1.76,
"step": 140000
},
{
"epoch": 7.81,
"learning_rate": 0.0002,
"loss": 0.5604,
"step": 140100
},
{
"epoch": 7.81,
"learning_rate": 0.0002,
"loss": 0.5708,
"step": 140200
},
{
"epoch": 7.82,
"learning_rate": 0.0002,
"loss": 0.5585,
"step": 140300
},
{
"epoch": 7.82,
"learning_rate": 0.0002,
"loss": 0.5554,
"step": 140400
},
{
"epoch": 7.83,
"learning_rate": 0.0002,
"loss": 0.5517,
"step": 140500
},
{
"epoch": 7.84,
"learning_rate": 0.0002,
"loss": 0.5564,
"step": 140600
},
{
"epoch": 7.84,
"learning_rate": 0.0002,
"loss": 0.5588,
"step": 140700
},
{
"epoch": 7.85,
"learning_rate": 0.0002,
"loss": 0.5506,
"step": 140800
},
{
"epoch": 7.85,
"learning_rate": 0.0002,
"loss": 0.55,
"step": 140900
},
{
"epoch": 7.86,
"learning_rate": 0.0002,
"loss": 0.5656,
"step": 141000
},
{
"epoch": 7.86,
"learning_rate": 0.0002,
"loss": 0.5566,
"step": 141100
},
{
"epoch": 7.87,
"learning_rate": 0.0002,
"loss": 0.5513,
"step": 141200
},
{
"epoch": 7.87,
"learning_rate": 0.0002,
"loss": 0.5572,
"step": 141300
},
{
"epoch": 7.88,
"learning_rate": 0.0002,
"loss": 0.5448,
"step": 141400
},
{
"epoch": 7.89,
"learning_rate": 0.0002,
"loss": 0.5676,
"step": 141500
},
{
"epoch": 7.89,
"learning_rate": 0.0002,
"loss": 0.5592,
"step": 141600
},
{
"epoch": 7.9,
"learning_rate": 0.0002,
"loss": 0.5619,
"step": 141700
},
{
"epoch": 7.9,
"learning_rate": 0.0002,
"loss": 0.5511,
"step": 141800
},
{
"epoch": 7.91,
"learning_rate": 0.0002,
"loss": 0.557,
"step": 141900
},
{
"epoch": 7.91,
"learning_rate": 0.0002,
"loss": 0.5537,
"step": 142000
},
{
"epoch": 7.92,
"learning_rate": 0.0002,
"loss": 0.5544,
"step": 142100
},
{
"epoch": 7.92,
"learning_rate": 0.0002,
"loss": 0.5628,
"step": 142200
},
{
"epoch": 7.93,
"learning_rate": 0.0002,
"loss": 0.5547,
"step": 142300
},
{
"epoch": 7.94,
"learning_rate": 0.0002,
"loss": 0.5657,
"step": 142400
},
{
"epoch": 7.94,
"learning_rate": 0.0002,
"loss": 0.5575,
"step": 142500
},
{
"epoch": 7.95,
"learning_rate": 0.0002,
"loss": 0.5755,
"step": 142600
},
{
"epoch": 7.95,
"learning_rate": 0.0002,
"loss": 0.5491,
"step": 142700
},
{
"epoch": 7.96,
"learning_rate": 0.0002,
"loss": 0.5622,
"step": 142800
},
{
"epoch": 7.96,
"learning_rate": 0.0002,
"loss": 0.5463,
"step": 142900
},
{
"epoch": 7.97,
"learning_rate": 0.0002,
"loss": 0.5626,
"step": 143000
},
{
"epoch": 7.97,
"learning_rate": 0.0002,
"loss": 0.5753,
"step": 143100
},
{
"epoch": 7.98,
"learning_rate": 0.0002,
"loss": 0.5586,
"step": 143200
},
{
"epoch": 7.99,
"learning_rate": 0.0002,
"loss": 0.5518,
"step": 143300
},
{
"epoch": 7.99,
"learning_rate": 0.0002,
"loss": 0.5666,
"step": 143400
},
{
"epoch": 8.0,
"learning_rate": 0.0002,
"loss": 0.5732,
"step": 143500
},
{
"epoch": 8.0,
"learning_rate": 0.0002,
"loss": 0.5422,
"step": 143600
},
{
"epoch": 8.01,
"learning_rate": 0.0002,
"loss": 0.5353,
"step": 143700
},
{
"epoch": 8.01,
"learning_rate": 0.0002,
"loss": 0.5337,
"step": 143800
},
{
"epoch": 8.02,
"learning_rate": 0.0002,
"loss": 0.5239,
"step": 143900
},
{
"epoch": 8.02,
"learning_rate": 0.0002,
"loss": 0.526,
"step": 144000
},
{
"epoch": 8.03,
"learning_rate": 0.0002,
"loss": 0.5331,
"step": 144100
},
{
"epoch": 8.04,
"learning_rate": 0.0002,
"loss": 0.537,
"step": 144200
},
{
"epoch": 8.04,
"learning_rate": 0.0002,
"loss": 0.5256,
"step": 144300
},
{
"epoch": 8.05,
"learning_rate": 0.0002,
"loss": 0.5276,
"step": 144400
},
{
"epoch": 8.05,
"learning_rate": 0.0002,
"loss": 0.5404,
"step": 144500
},
{
"epoch": 8.06,
"learning_rate": 0.0002,
"loss": 0.53,
"step": 144600
},
{
"epoch": 8.06,
"learning_rate": 0.0002,
"loss": 0.5364,
"step": 144700
},
{
"epoch": 8.07,
"learning_rate": 0.0002,
"loss": 0.5441,
"step": 144800
},
{
"epoch": 8.07,
"learning_rate": 0.0002,
"loss": 0.5423,
"step": 144900
},
{
"epoch": 8.08,
"learning_rate": 0.0002,
"loss": 0.5399,
"step": 145000
},
{
"epoch": 8.09,
"learning_rate": 0.0002,
"loss": 0.5367,
"step": 145100
},
{
"epoch": 8.09,
"learning_rate": 0.0002,
"loss": 0.5313,
"step": 145200
},
{
"epoch": 8.1,
"learning_rate": 0.0002,
"loss": 0.5339,
"step": 145300
},
{
"epoch": 8.1,
"learning_rate": 0.0002,
"loss": 0.5247,
"step": 145400
},
{
"epoch": 8.11,
"learning_rate": 0.0002,
"loss": 0.545,
"step": 145500
},
{
"epoch": 8.11,
"learning_rate": 0.0002,
"loss": 0.53,
"step": 145600
},
{
"epoch": 8.12,
"learning_rate": 0.0002,
"loss": 0.5461,
"step": 145700
},
{
"epoch": 8.12,
"learning_rate": 0.0002,
"loss": 0.5278,
"step": 145800
},
{
"epoch": 8.13,
"learning_rate": 0.0002,
"loss": 0.5479,
"step": 145900
},
{
"epoch": 8.14,
"learning_rate": 0.0002,
"loss": 0.5442,
"step": 146000
},
{
"epoch": 8.14,
"learning_rate": 0.0002,
"loss": 0.5381,
"step": 146100
},
{
"epoch": 8.15,
"learning_rate": 0.0002,
"loss": 0.5421,
"step": 146200
},
{
"epoch": 8.15,
"learning_rate": 0.0002,
"loss": 0.5307,
"step": 146300
},
{
"epoch": 8.16,
"learning_rate": 0.0002,
"loss": 0.5392,
"step": 146400
},
{
"epoch": 8.16,
"learning_rate": 0.0002,
"loss": 0.5243,
"step": 146500
},
{
"epoch": 8.17,
"learning_rate": 0.0002,
"loss": 0.5124,
"step": 146600
},
{
"epoch": 8.17,
"learning_rate": 0.0002,
"loss": 0.5479,
"step": 146700
},
{
"epoch": 8.18,
"learning_rate": 0.0002,
"loss": 0.5614,
"step": 146800
},
{
"epoch": 8.19,
"learning_rate": 0.0002,
"loss": 0.5362,
"step": 146900
},
{
"epoch": 8.19,
"learning_rate": 0.0002,
"loss": 0.5495,
"step": 147000
},
{
"epoch": 8.2,
"learning_rate": 0.0002,
"loss": 0.5425,
"step": 147100
},
{
"epoch": 8.2,
"learning_rate": 0.0002,
"loss": 0.541,
"step": 147200
},
{
"epoch": 8.21,
"learning_rate": 0.0002,
"loss": 0.5362,
"step": 147300
},
{
"epoch": 8.21,
"learning_rate": 0.0002,
"loss": 0.542,
"step": 147400
},
{
"epoch": 8.22,
"learning_rate": 0.0002,
"loss": 0.5384,
"step": 147500
},
{
"epoch": 8.23,
"learning_rate": 0.0002,
"loss": 0.5356,
"step": 147600
},
{
"epoch": 8.23,
"learning_rate": 0.0002,
"loss": 0.5508,
"step": 147700
},
{
"epoch": 8.24,
"learning_rate": 0.0002,
"loss": 0.528,
"step": 147800
},
{
"epoch": 8.24,
"learning_rate": 0.0002,
"loss": 0.5416,
"step": 147900
},
{
"epoch": 8.25,
"learning_rate": 0.0002,
"loss": 0.5389,
"step": 148000
},
{
"epoch": 8.25,
"learning_rate": 0.0002,
"loss": 0.5429,
"step": 148100
},
{
"epoch": 8.26,
"learning_rate": 0.0002,
"loss": 0.5313,
"step": 148200
},
{
"epoch": 8.26,
"learning_rate": 0.0002,
"loss": 0.5464,
"step": 148300
},
{
"epoch": 8.27,
"learning_rate": 0.0002,
"loss": 0.5389,
"step": 148400
},
{
"epoch": 8.28,
"learning_rate": 0.0002,
"loss": 0.541,
"step": 148500
},
{
"epoch": 8.28,
"learning_rate": 0.0002,
"loss": 0.5405,
"step": 148600
},
{
"epoch": 8.29,
"learning_rate": 0.0002,
"loss": 0.5413,
"step": 148700
},
{
"epoch": 8.29,
"learning_rate": 0.0002,
"loss": 0.5379,
"step": 148800
},
{
"epoch": 8.3,
"learning_rate": 0.0002,
"loss": 0.5388,
"step": 148900
},
{
"epoch": 8.3,
"learning_rate": 0.0002,
"loss": 0.5401,
"step": 149000
},
{
"epoch": 8.31,
"learning_rate": 0.0002,
"loss": 0.5521,
"step": 149100
},
{
"epoch": 8.31,
"learning_rate": 0.0002,
"loss": 0.5362,
"step": 149200
},
{
"epoch": 8.32,
"learning_rate": 0.0002,
"loss": 0.5296,
"step": 149300
},
{
"epoch": 8.33,
"learning_rate": 0.0002,
"loss": 0.5261,
"step": 149400
},
{
"epoch": 8.33,
"learning_rate": 0.0002,
"loss": 0.5475,
"step": 149500
},
{
"epoch": 8.34,
"learning_rate": 0.0002,
"loss": 0.5374,
"step": 149600
},
{
"epoch": 8.34,
"learning_rate": 0.0002,
"loss": 0.5505,
"step": 149700
},
{
"epoch": 8.35,
"learning_rate": 0.0002,
"loss": 0.5434,
"step": 149800
},
{
"epoch": 8.35,
"learning_rate": 0.0002,
"loss": 0.5448,
"step": 149900
},
{
"epoch": 8.36,
"learning_rate": 0.0002,
"loss": 0.5518,
"step": 150000
},
{
"epoch": 8.36,
"eval_gen_len": 18.999251944943147,
"eval_loss": 2.71974515914917,
"eval_rouge1": 25.2364,
"eval_rouge2": 12.3372,
"eval_rougeL": 20.8569,
"eval_rougeLsum": 23.8285,
"eval_runtime": 474.6128,
"eval_samples_per_second": 28.166,
"eval_steps_per_second": 1.761,
"step": 150000
},
{
"epoch": 8.36,
"learning_rate": 0.0002,
"loss": 0.5358,
"step": 150100
},
{
"epoch": 8.37,
"learning_rate": 0.0002,
"loss": 0.5428,
"step": 150200
},
{
"epoch": 8.38,
"learning_rate": 0.0002,
"loss": 0.5452,
"step": 150300
},
{
"epoch": 8.38,
"learning_rate": 0.0002,
"loss": 0.5507,
"step": 150400
},
{
"epoch": 8.39,
"learning_rate": 0.0002,
"loss": 0.5443,
"step": 150500
},
{
"epoch": 8.39,
"learning_rate": 0.0002,
"loss": 0.533,
"step": 150600
},
{
"epoch": 8.4,
"learning_rate": 0.0002,
"loss": 0.5419,
"step": 150700
},
{
"epoch": 8.4,
"learning_rate": 0.0002,
"loss": 0.5339,
"step": 150800
},
{
"epoch": 8.41,
"learning_rate": 0.0002,
"loss": 0.5349,
"step": 150900
},
{
"epoch": 8.41,
"learning_rate": 0.0002,
"loss": 0.5347,
"step": 151000
},
{
"epoch": 8.42,
"learning_rate": 0.0002,
"loss": 0.5357,
"step": 151100
},
{
"epoch": 8.43,
"learning_rate": 0.0002,
"loss": 0.5466,
"step": 151200
},
{
"epoch": 8.43,
"learning_rate": 0.0002,
"loss": 0.5467,
"step": 151300
},
{
"epoch": 8.44,
"learning_rate": 0.0002,
"loss": 0.5596,
"step": 151400
},
{
"epoch": 8.44,
"learning_rate": 0.0002,
"loss": 0.552,
"step": 151500
},
{
"epoch": 8.45,
"learning_rate": 0.0002,
"loss": 0.5514,
"step": 151600
},
{
"epoch": 8.45,
"learning_rate": 0.0002,
"loss": 0.5506,
"step": 151700
},
{
"epoch": 8.46,
"learning_rate": 0.0002,
"loss": 0.5414,
"step": 151800
},
{
"epoch": 8.46,
"learning_rate": 0.0002,
"loss": 0.5394,
"step": 151900
},
{
"epoch": 8.47,
"learning_rate": 0.0002,
"loss": 0.548,
"step": 152000
},
{
"epoch": 8.48,
"learning_rate": 0.0002,
"loss": 0.5334,
"step": 152100
},
{
"epoch": 8.48,
"learning_rate": 0.0002,
"loss": 0.5516,
"step": 152200
},
{
"epoch": 8.49,
"learning_rate": 0.0002,
"loss": 0.5587,
"step": 152300
},
{
"epoch": 8.49,
"learning_rate": 0.0002,
"loss": 0.5423,
"step": 152400
},
{
"epoch": 8.5,
"learning_rate": 0.0002,
"loss": 0.5519,
"step": 152500
},
{
"epoch": 8.5,
"learning_rate": 0.0002,
"loss": 0.5395,
"step": 152600
},
{
"epoch": 8.51,
"learning_rate": 0.0002,
"loss": 0.5368,
"step": 152700
},
{
"epoch": 8.51,
"learning_rate": 0.0002,
"loss": 0.554,
"step": 152800
},
{
"epoch": 8.52,
"learning_rate": 0.0002,
"loss": 0.5437,
"step": 152900
},
{
"epoch": 8.53,
"learning_rate": 0.0002,
"loss": 0.5485,
"step": 153000
},
{
"epoch": 8.53,
"learning_rate": 0.0002,
"loss": 0.5463,
"step": 153100
},
{
"epoch": 8.54,
"learning_rate": 0.0002,
"loss": 0.5429,
"step": 153200
},
{
"epoch": 8.54,
"learning_rate": 0.0002,
"loss": 0.5436,
"step": 153300
},
{
"epoch": 8.55,
"learning_rate": 0.0002,
"loss": 0.5445,
"step": 153400
},
{
"epoch": 8.55,
"learning_rate": 0.0002,
"loss": 0.5458,
"step": 153500
},
{
"epoch": 8.56,
"learning_rate": 0.0002,
"loss": 0.5417,
"step": 153600
},
{
"epoch": 8.57,
"learning_rate": 0.0002,
"loss": 0.5412,
"step": 153700
},
{
"epoch": 8.57,
"learning_rate": 0.0002,
"loss": 0.54,
"step": 153800
},
{
"epoch": 8.58,
"learning_rate": 0.0002,
"loss": 0.5561,
"step": 153900
},
{
"epoch": 8.58,
"learning_rate": 0.0002,
"loss": 0.5431,
"step": 154000
},
{
"epoch": 8.59,
"learning_rate": 0.0002,
"loss": 0.5445,
"step": 154100
},
{
"epoch": 8.59,
"learning_rate": 0.0002,
"loss": 0.5549,
"step": 154200
},
{
"epoch": 8.6,
"learning_rate": 0.0002,
"loss": 0.5478,
"step": 154300
},
{
"epoch": 8.6,
"learning_rate": 0.0002,
"loss": 0.5493,
"step": 154400
},
{
"epoch": 8.61,
"learning_rate": 0.0002,
"loss": 0.5445,
"step": 154500
},
{
"epoch": 8.62,
"learning_rate": 0.0002,
"loss": 0.55,
"step": 154600
},
{
"epoch": 8.62,
"learning_rate": 0.0002,
"loss": 0.5478,
"step": 154700
},
{
"epoch": 8.63,
"learning_rate": 0.0002,
"loss": 0.5339,
"step": 154800
},
{
"epoch": 8.63,
"learning_rate": 0.0002,
"loss": 0.5501,
"step": 154900
},
{
"epoch": 8.64,
"learning_rate": 0.0002,
"loss": 0.5357,
"step": 155000
},
{
"epoch": 8.64,
"learning_rate": 0.0002,
"loss": 0.5444,
"step": 155100
},
{
"epoch": 8.65,
"learning_rate": 0.0002,
"loss": 0.5563,
"step": 155200
},
{
"epoch": 8.65,
"learning_rate": 0.0002,
"loss": 0.5588,
"step": 155300
},
{
"epoch": 8.66,
"learning_rate": 0.0002,
"loss": 0.5416,
"step": 155400
},
{
"epoch": 8.67,
"learning_rate": 0.0002,
"loss": 0.5581,
"step": 155500
},
{
"epoch": 8.67,
"learning_rate": 0.0002,
"loss": 0.5446,
"step": 155600
},
{
"epoch": 8.68,
"learning_rate": 0.0002,
"loss": 0.5425,
"step": 155700
},
{
"epoch": 8.68,
"learning_rate": 0.0002,
"loss": 0.551,
"step": 155800
},
{
"epoch": 8.69,
"learning_rate": 0.0002,
"loss": 0.5342,
"step": 155900
},
{
"epoch": 8.69,
"learning_rate": 0.0002,
"loss": 0.5547,
"step": 156000
},
{
"epoch": 8.7,
"learning_rate": 0.0002,
"loss": 0.555,
"step": 156100
},
{
"epoch": 8.7,
"learning_rate": 0.0002,
"loss": 0.5554,
"step": 156200
},
{
"epoch": 8.71,
"learning_rate": 0.0002,
"loss": 0.5408,
"step": 156300
},
{
"epoch": 8.72,
"learning_rate": 0.0002,
"loss": 0.5596,
"step": 156400
},
{
"epoch": 8.72,
"learning_rate": 0.0002,
"loss": 0.555,
"step": 156500
},
{
"epoch": 8.73,
"learning_rate": 0.0002,
"loss": 0.555,
"step": 156600
},
{
"epoch": 8.73,
"learning_rate": 0.0002,
"loss": 0.54,
"step": 156700
},
{
"epoch": 8.74,
"learning_rate": 0.0002,
"loss": 0.5525,
"step": 156800
},
{
"epoch": 8.74,
"learning_rate": 0.0002,
"loss": 0.548,
"step": 156900
},
{
"epoch": 8.75,
"learning_rate": 0.0002,
"loss": 0.5516,
"step": 157000
},
{
"epoch": 8.75,
"learning_rate": 0.0002,
"loss": 0.5529,
"step": 157100
},
{
"epoch": 8.76,
"learning_rate": 0.0002,
"loss": 0.5571,
"step": 157200
},
{
"epoch": 8.77,
"learning_rate": 0.0002,
"loss": 0.5417,
"step": 157300
},
{
"epoch": 8.77,
"learning_rate": 0.0002,
"loss": 0.5547,
"step": 157400
},
{
"epoch": 8.78,
"learning_rate": 0.0002,
"loss": 0.5384,
"step": 157500
},
{
"epoch": 8.78,
"learning_rate": 0.0002,
"loss": 0.5475,
"step": 157600
},
{
"epoch": 8.79,
"learning_rate": 0.0002,
"loss": 0.5433,
"step": 157700
},
{
"epoch": 8.79,
"learning_rate": 0.0002,
"loss": 0.5399,
"step": 157800
},
{
"epoch": 8.8,
"learning_rate": 0.0002,
"loss": 0.5513,
"step": 157900
},
{
"epoch": 8.8,
"learning_rate": 0.0002,
"loss": 0.5509,
"step": 158000
},
{
"epoch": 8.81,
"learning_rate": 0.0002,
"loss": 0.5535,
"step": 158100
},
{
"epoch": 8.82,
"learning_rate": 0.0002,
"loss": 0.5473,
"step": 158200
},
{
"epoch": 8.82,
"learning_rate": 0.0002,
"loss": 0.5421,
"step": 158300
},
{
"epoch": 8.83,
"learning_rate": 0.0002,
"loss": 0.5507,
"step": 158400
},
{
"epoch": 8.83,
"learning_rate": 0.0002,
"loss": 0.5534,
"step": 158500
},
{
"epoch": 8.84,
"learning_rate": 0.0002,
"loss": 0.5578,
"step": 158600
},
{
"epoch": 8.84,
"learning_rate": 0.0002,
"loss": 0.5521,
"step": 158700
},
{
"epoch": 8.85,
"learning_rate": 0.0002,
"loss": 0.5543,
"step": 158800
},
{
"epoch": 8.85,
"learning_rate": 0.0002,
"loss": 0.5527,
"step": 158900
},
{
"epoch": 8.86,
"learning_rate": 0.0002,
"loss": 0.564,
"step": 159000
},
{
"epoch": 8.87,
"learning_rate": 0.0002,
"loss": 0.5587,
"step": 159100
},
{
"epoch": 8.87,
"learning_rate": 0.0002,
"loss": 0.5576,
"step": 159200
},
{
"epoch": 8.88,
"learning_rate": 0.0002,
"loss": 0.5505,
"step": 159300
},
{
"epoch": 8.88,
"learning_rate": 0.0002,
"loss": 0.5528,
"step": 159400
},
{
"epoch": 8.89,
"learning_rate": 0.0002,
"loss": 0.5384,
"step": 159500
},
{
"epoch": 8.89,
"learning_rate": 0.0002,
"loss": 0.5531,
"step": 159600
},
{
"epoch": 8.9,
"learning_rate": 0.0002,
"loss": 0.5595,
"step": 159700
},
{
"epoch": 8.9,
"learning_rate": 0.0002,
"loss": 0.5588,
"step": 159800
},
{
"epoch": 8.91,
"learning_rate": 0.0002,
"loss": 0.5555,
"step": 159900
},
{
"epoch": 8.92,
"learning_rate": 0.0002,
"loss": 0.5573,
"step": 160000
},
{
"epoch": 8.92,
"eval_gen_len": 18.99955116696589,
"eval_loss": 2.7115721702575684,
"eval_rouge1": 25.334,
"eval_rouge2": 12.363,
"eval_rougeL": 20.8863,
"eval_rougeLsum": 23.93,
"eval_runtime": 474.6063,
"eval_samples_per_second": 28.167,
"eval_steps_per_second": 1.761,
"step": 160000
},
{
"epoch": 8.92,
"learning_rate": 0.0002,
"loss": 0.5481,
"step": 160100
},
{
"epoch": 8.93,
"learning_rate": 0.0002,
"loss": 0.5629,
"step": 160200
},
{
"epoch": 8.93,
"learning_rate": 0.0002,
"loss": 0.5519,
"step": 160300
},
{
"epoch": 8.94,
"learning_rate": 0.0002,
"loss": 0.5581,
"step": 160400
},
{
"epoch": 8.94,
"learning_rate": 0.0002,
"loss": 0.5452,
"step": 160500
},
{
"epoch": 8.95,
"learning_rate": 0.0002,
"loss": 0.55,
"step": 160600
},
{
"epoch": 8.96,
"learning_rate": 0.0002,
"loss": 0.5602,
"step": 160700
},
{
"epoch": 8.96,
"learning_rate": 0.0002,
"loss": 0.5394,
"step": 160800
},
{
"epoch": 8.97,
"learning_rate": 0.0002,
"loss": 0.5509,
"step": 160900
},
{
"epoch": 8.97,
"learning_rate": 0.0002,
"loss": 0.5535,
"step": 161000
},
{
"epoch": 8.98,
"learning_rate": 0.0002,
"loss": 0.5718,
"step": 161100
},
{
"epoch": 8.98,
"learning_rate": 0.0002,
"loss": 0.5674,
"step": 161200
},
{
"epoch": 8.99,
"learning_rate": 0.0002,
"loss": 0.547,
"step": 161300
},
{
"epoch": 8.99,
"learning_rate": 0.0002,
"loss": 0.5581,
"step": 161400
},
{
"epoch": 9.0,
"learning_rate": 0.0002,
"loss": 0.5519,
"step": 161500
},
{
"epoch": 9.01,
"learning_rate": 0.0002,
"loss": 0.5362,
"step": 161600
},
{
"epoch": 9.01,
"learning_rate": 0.0002,
"loss": 0.5365,
"step": 161700
},
{
"epoch": 9.02,
"learning_rate": 0.0002,
"loss": 0.5084,
"step": 161800
},
{
"epoch": 9.02,
"learning_rate": 0.0002,
"loss": 0.5278,
"step": 161900
},
{
"epoch": 9.03,
"learning_rate": 0.0002,
"loss": 0.5293,
"step": 162000
},
{
"epoch": 9.03,
"learning_rate": 0.0002,
"loss": 0.5331,
"step": 162100
},
{
"epoch": 9.04,
"learning_rate": 0.0002,
"loss": 0.5307,
"step": 162200
},
{
"epoch": 9.04,
"learning_rate": 0.0002,
"loss": 0.5459,
"step": 162300
},
{
"epoch": 9.05,
"learning_rate": 0.0002,
"loss": 0.5259,
"step": 162400
},
{
"epoch": 9.06,
"learning_rate": 0.0002,
"loss": 0.532,
"step": 162500
},
{
"epoch": 9.06,
"learning_rate": 0.0002,
"loss": 0.5166,
"step": 162600
},
{
"epoch": 9.07,
"learning_rate": 0.0002,
"loss": 0.5336,
"step": 162700
},
{
"epoch": 9.07,
"learning_rate": 0.0002,
"loss": 0.5253,
"step": 162800
},
{
"epoch": 9.08,
"learning_rate": 0.0002,
"loss": 0.5324,
"step": 162900
},
{
"epoch": 9.08,
"learning_rate": 0.0002,
"loss": 0.5249,
"step": 163000
},
{
"epoch": 9.09,
"learning_rate": 0.0002,
"loss": 0.5111,
"step": 163100
},
{
"epoch": 9.09,
"learning_rate": 0.0002,
"loss": 0.5426,
"step": 163200
},
{
"epoch": 9.1,
"learning_rate": 0.0002,
"loss": 0.531,
"step": 163300
},
{
"epoch": 9.11,
"learning_rate": 0.0002,
"loss": 0.5279,
"step": 163400
},
{
"epoch": 9.11,
"learning_rate": 0.0002,
"loss": 0.5135,
"step": 163500
},
{
"epoch": 9.12,
"learning_rate": 0.0002,
"loss": 0.5335,
"step": 163600
},
{
"epoch": 9.12,
"learning_rate": 0.0002,
"loss": 0.5267,
"step": 163700
},
{
"epoch": 9.13,
"learning_rate": 0.0002,
"loss": 0.5336,
"step": 163800
},
{
"epoch": 9.13,
"learning_rate": 0.0002,
"loss": 0.5383,
"step": 163900
},
{
"epoch": 9.14,
"learning_rate": 0.0002,
"loss": 0.5256,
"step": 164000
},
{
"epoch": 9.14,
"learning_rate": 0.0002,
"loss": 0.5333,
"step": 164100
},
{
"epoch": 9.15,
"learning_rate": 0.0002,
"loss": 0.5335,
"step": 164200
},
{
"epoch": 9.16,
"learning_rate": 0.0002,
"loss": 0.5282,
"step": 164300
},
{
"epoch": 9.16,
"learning_rate": 0.0002,
"loss": 0.535,
"step": 164400
},
{
"epoch": 9.17,
"learning_rate": 0.0002,
"loss": 0.5298,
"step": 164500
},
{
"epoch": 9.17,
"learning_rate": 0.0002,
"loss": 0.5353,
"step": 164600
},
{
"epoch": 9.18,
"learning_rate": 0.0002,
"loss": 0.5209,
"step": 164700
},
{
"epoch": 9.18,
"learning_rate": 0.0002,
"loss": 0.5476,
"step": 164800
},
{
"epoch": 9.19,
"learning_rate": 0.0002,
"loss": 0.5329,
"step": 164900
},
{
"epoch": 9.19,
"learning_rate": 0.0002,
"loss": 0.5145,
"step": 165000
},
{
"epoch": 9.2,
"learning_rate": 0.0002,
"loss": 0.5455,
"step": 165100
},
{
"epoch": 9.21,
"learning_rate": 0.0002,
"loss": 0.5414,
"step": 165200
},
{
"epoch": 9.21,
"learning_rate": 0.0002,
"loss": 0.5301,
"step": 165300
},
{
"epoch": 9.22,
"learning_rate": 0.0002,
"loss": 0.5325,
"step": 165400
},
{
"epoch": 9.22,
"learning_rate": 0.0002,
"loss": 0.5183,
"step": 165500
},
{
"epoch": 9.23,
"learning_rate": 0.0002,
"loss": 0.5309,
"step": 165600
},
{
"epoch": 9.23,
"learning_rate": 0.0002,
"loss": 0.5325,
"step": 165700
},
{
"epoch": 9.24,
"learning_rate": 0.0002,
"loss": 0.5233,
"step": 165800
},
{
"epoch": 9.24,
"learning_rate": 0.0002,
"loss": 0.5404,
"step": 165900
},
{
"epoch": 9.25,
"learning_rate": 0.0002,
"loss": 0.5505,
"step": 166000
},
{
"epoch": 9.26,
"learning_rate": 0.0002,
"loss": 0.5324,
"step": 166100
},
{
"epoch": 9.26,
"learning_rate": 0.0002,
"loss": 0.5407,
"step": 166200
},
{
"epoch": 9.27,
"learning_rate": 0.0002,
"loss": 0.525,
"step": 166300
},
{
"epoch": 9.27,
"learning_rate": 0.0002,
"loss": 0.5371,
"step": 166400
},
{
"epoch": 9.28,
"learning_rate": 0.0002,
"loss": 0.5302,
"step": 166500
},
{
"epoch": 9.28,
"learning_rate": 0.0002,
"loss": 0.5252,
"step": 166600
},
{
"epoch": 9.29,
"learning_rate": 0.0002,
"loss": 0.5418,
"step": 166700
},
{
"epoch": 9.3,
"learning_rate": 0.0002,
"loss": 0.5428,
"step": 166800
},
{
"epoch": 9.3,
"learning_rate": 0.0002,
"loss": 0.5319,
"step": 166900
},
{
"epoch": 9.31,
"learning_rate": 0.0002,
"loss": 0.5379,
"step": 167000
},
{
"epoch": 9.31,
"learning_rate": 0.0002,
"loss": 0.5344,
"step": 167100
},
{
"epoch": 9.32,
"learning_rate": 0.0002,
"loss": 0.5416,
"step": 167200
},
{
"epoch": 9.32,
"learning_rate": 0.0002,
"loss": 0.5404,
"step": 167300
},
{
"epoch": 9.33,
"learning_rate": 0.0002,
"loss": 0.5353,
"step": 167400
},
{
"epoch": 9.33,
"learning_rate": 0.0002,
"loss": 0.5403,
"step": 167500
},
{
"epoch": 9.34,
"learning_rate": 0.0002,
"loss": 0.5418,
"step": 167600
},
{
"epoch": 9.35,
"learning_rate": 0.0002,
"loss": 0.535,
"step": 167700
},
{
"epoch": 9.35,
"learning_rate": 0.0002,
"loss": 0.5351,
"step": 167800
},
{
"epoch": 9.36,
"learning_rate": 0.0002,
"loss": 0.5278,
"step": 167900
},
{
"epoch": 9.36,
"learning_rate": 0.0002,
"loss": 0.5318,
"step": 168000
},
{
"epoch": 9.37,
"learning_rate": 0.0002,
"loss": 0.5521,
"step": 168100
},
{
"epoch": 9.37,
"learning_rate": 0.0002,
"loss": 0.5358,
"step": 168200
},
{
"epoch": 9.38,
"learning_rate": 0.0002,
"loss": 0.5364,
"step": 168300
},
{
"epoch": 9.38,
"learning_rate": 0.0002,
"loss": 0.5399,
"step": 168400
},
{
"epoch": 9.39,
"learning_rate": 0.0002,
"loss": 0.558,
"step": 168500
},
{
"epoch": 9.4,
"learning_rate": 0.0002,
"loss": 0.5534,
"step": 168600
},
{
"epoch": 9.4,
"learning_rate": 0.0002,
"loss": 0.526,
"step": 168700
},
{
"epoch": 9.41,
"learning_rate": 0.0002,
"loss": 0.5424,
"step": 168800
},
{
"epoch": 9.41,
"learning_rate": 0.0002,
"loss": 0.5253,
"step": 168900
},
{
"epoch": 9.42,
"learning_rate": 0.0002,
"loss": 0.5365,
"step": 169000
},
{
"epoch": 9.42,
"learning_rate": 0.0002,
"loss": 0.5369,
"step": 169100
},
{
"epoch": 9.43,
"learning_rate": 0.0002,
"loss": 0.5361,
"step": 169200
},
{
"epoch": 9.43,
"learning_rate": 0.0002,
"loss": 0.5415,
"step": 169300
},
{
"epoch": 9.44,
"learning_rate": 0.0002,
"loss": 0.5368,
"step": 169400
},
{
"epoch": 9.45,
"learning_rate": 0.0002,
"loss": 0.5502,
"step": 169500
},
{
"epoch": 9.45,
"learning_rate": 0.0002,
"loss": 0.5378,
"step": 169600
},
{
"epoch": 9.46,
"learning_rate": 0.0002,
"loss": 0.524,
"step": 169700
},
{
"epoch": 9.46,
"learning_rate": 0.0002,
"loss": 0.5337,
"step": 169800
},
{
"epoch": 9.47,
"learning_rate": 0.0002,
"loss": 0.5375,
"step": 169900
},
{
"epoch": 9.47,
"learning_rate": 0.0002,
"loss": 0.5336,
"step": 170000
},
{
"epoch": 9.47,
"eval_gen_len": 18.99970077797726,
"eval_loss": 2.7171103954315186,
"eval_rouge1": 25.2508,
"eval_rouge2": 12.3825,
"eval_rougeL": 20.8692,
"eval_rougeLsum": 23.8414,
"eval_runtime": 472.9738,
"eval_samples_per_second": 28.264,
"eval_steps_per_second": 1.768,
"step": 170000
},
{
"epoch": 9.48,
"learning_rate": 0.0002,
"loss": 0.547,
"step": 170100
},
{
"epoch": 9.48,
"learning_rate": 0.0002,
"loss": 0.5296,
"step": 170200
},
{
"epoch": 9.49,
"learning_rate": 0.0002,
"loss": 0.5416,
"step": 170300
},
{
"epoch": 9.5,
"learning_rate": 0.0002,
"loss": 0.5479,
"step": 170400
},
{
"epoch": 9.5,
"learning_rate": 0.0002,
"loss": 0.5469,
"step": 170500
},
{
"epoch": 9.51,
"learning_rate": 0.0002,
"loss": 0.534,
"step": 170600
},
{
"epoch": 9.51,
"learning_rate": 0.0002,
"loss": 0.5279,
"step": 170700
},
{
"epoch": 9.52,
"learning_rate": 0.0002,
"loss": 0.5364,
"step": 170800
},
{
"epoch": 9.52,
"learning_rate": 0.0002,
"loss": 0.5243,
"step": 170900
},
{
"epoch": 9.53,
"learning_rate": 0.0002,
"loss": 0.52,
"step": 171000
},
{
"epoch": 9.53,
"learning_rate": 0.0002,
"loss": 0.5427,
"step": 171100
},
{
"epoch": 9.54,
"learning_rate": 0.0002,
"loss": 0.5384,
"step": 171200
},
{
"epoch": 9.55,
"learning_rate": 0.0002,
"loss": 0.5301,
"step": 171300
},
{
"epoch": 9.55,
"learning_rate": 0.0002,
"loss": 0.5386,
"step": 171400
},
{
"epoch": 9.56,
"learning_rate": 0.0002,
"loss": 0.5555,
"step": 171500
},
{
"epoch": 9.56,
"learning_rate": 0.0002,
"loss": 0.5462,
"step": 171600
},
{
"epoch": 9.57,
"learning_rate": 0.0002,
"loss": 0.5394,
"step": 171700
},
{
"epoch": 9.57,
"learning_rate": 0.0002,
"loss": 0.5438,
"step": 171800
},
{
"epoch": 9.58,
"learning_rate": 0.0002,
"loss": 0.5386,
"step": 171900
},
{
"epoch": 9.58,
"learning_rate": 0.0002,
"loss": 0.5469,
"step": 172000
},
{
"epoch": 9.59,
"learning_rate": 0.0002,
"loss": 0.5511,
"step": 172100
},
{
"epoch": 9.6,
"learning_rate": 0.0002,
"loss": 0.5418,
"step": 172200
},
{
"epoch": 9.6,
"learning_rate": 0.0002,
"loss": 0.5376,
"step": 172300
},
{
"epoch": 9.61,
"learning_rate": 0.0002,
"loss": 0.5583,
"step": 172400
},
{
"epoch": 9.61,
"learning_rate": 0.0002,
"loss": 0.5459,
"step": 172500
},
{
"epoch": 9.62,
"learning_rate": 0.0002,
"loss": 0.5393,
"step": 172600
},
{
"epoch": 9.62,
"learning_rate": 0.0002,
"loss": 0.5434,
"step": 172700
},
{
"epoch": 9.63,
"learning_rate": 0.0002,
"loss": 0.5472,
"step": 172800
},
{
"epoch": 9.63,
"learning_rate": 0.0002,
"loss": 0.5535,
"step": 172900
},
{
"epoch": 9.64,
"learning_rate": 0.0002,
"loss": 0.5424,
"step": 173000
},
{
"epoch": 9.65,
"learning_rate": 0.0002,
"loss": 0.5458,
"step": 173100
},
{
"epoch": 9.65,
"learning_rate": 0.0002,
"loss": 0.5552,
"step": 173200
},
{
"epoch": 9.66,
"learning_rate": 0.0002,
"loss": 0.5353,
"step": 173300
},
{
"epoch": 9.66,
"learning_rate": 0.0002,
"loss": 0.5362,
"step": 173400
},
{
"epoch": 9.67,
"learning_rate": 0.0002,
"loss": 0.5329,
"step": 173500
},
{
"epoch": 9.67,
"learning_rate": 0.0002,
"loss": 0.544,
"step": 173600
},
{
"epoch": 9.68,
"learning_rate": 0.0002,
"loss": 0.5365,
"step": 173700
},
{
"epoch": 9.69,
"learning_rate": 0.0002,
"loss": 0.5506,
"step": 173800
},
{
"epoch": 9.69,
"learning_rate": 0.0002,
"loss": 0.5403,
"step": 173900
},
{
"epoch": 9.7,
"learning_rate": 0.0002,
"loss": 0.5453,
"step": 174000
},
{
"epoch": 9.7,
"learning_rate": 0.0002,
"loss": 0.5467,
"step": 174100
},
{
"epoch": 9.71,
"learning_rate": 0.0002,
"loss": 0.5368,
"step": 174200
},
{
"epoch": 9.71,
"learning_rate": 0.0002,
"loss": 0.5376,
"step": 174300
},
{
"epoch": 9.72,
"learning_rate": 0.0002,
"loss": 0.5534,
"step": 174400
},
{
"epoch": 9.72,
"learning_rate": 0.0002,
"loss": 0.5407,
"step": 174500
},
{
"epoch": 9.73,
"learning_rate": 0.0002,
"loss": 0.5508,
"step": 174600
},
{
"epoch": 9.74,
"learning_rate": 0.0002,
"loss": 0.5367,
"step": 174700
},
{
"epoch": 9.74,
"learning_rate": 0.0002,
"loss": 0.5506,
"step": 174800
},
{
"epoch": 9.75,
"learning_rate": 0.0002,
"loss": 0.5397,
"step": 174900
},
{
"epoch": 9.75,
"learning_rate": 0.0002,
"loss": 0.5403,
"step": 175000
},
{
"epoch": 9.76,
"learning_rate": 0.0002,
"loss": 0.5395,
"step": 175100
},
{
"epoch": 9.76,
"learning_rate": 0.0002,
"loss": 0.5429,
"step": 175200
},
{
"epoch": 9.77,
"learning_rate": 0.0002,
"loss": 0.554,
"step": 175300
},
{
"epoch": 9.77,
"learning_rate": 0.0002,
"loss": 0.5445,
"step": 175400
},
{
"epoch": 9.78,
"learning_rate": 0.0002,
"loss": 0.5426,
"step": 175500
},
{
"epoch": 9.79,
"learning_rate": 0.0002,
"loss": 0.5454,
"step": 175600
},
{
"epoch": 9.79,
"learning_rate": 0.0002,
"loss": 0.5651,
"step": 175700
},
{
"epoch": 9.8,
"learning_rate": 0.0002,
"loss": 0.5494,
"step": 175800
},
{
"epoch": 9.8,
"learning_rate": 0.0002,
"loss": 0.5408,
"step": 175900
},
{
"epoch": 9.81,
"learning_rate": 0.0002,
"loss": 0.5528,
"step": 176000
},
{
"epoch": 9.81,
"learning_rate": 0.0002,
"loss": 0.5511,
"step": 176100
},
{
"epoch": 9.82,
"learning_rate": 0.0002,
"loss": 0.5406,
"step": 176200
},
{
"epoch": 9.82,
"learning_rate": 0.0002,
"loss": 0.5588,
"step": 176300
},
{
"epoch": 9.83,
"learning_rate": 0.0002,
"loss": 0.56,
"step": 176400
},
{
"epoch": 9.84,
"learning_rate": 0.0002,
"loss": 0.5472,
"step": 176500
},
{
"epoch": 9.84,
"learning_rate": 0.0002,
"loss": 0.5445,
"step": 176600
},
{
"epoch": 9.85,
"learning_rate": 0.0002,
"loss": 0.5527,
"step": 176700
},
{
"epoch": 9.85,
"learning_rate": 0.0002,
"loss": 0.5385,
"step": 176800
},
{
"epoch": 9.86,
"learning_rate": 0.0002,
"loss": 0.5327,
"step": 176900
},
{
"epoch": 9.86,
"learning_rate": 0.0002,
"loss": 0.55,
"step": 177000
},
{
"epoch": 9.87,
"learning_rate": 0.0002,
"loss": 0.5555,
"step": 177100
},
{
"epoch": 9.87,
"learning_rate": 0.0002,
"loss": 0.5413,
"step": 177200
},
{
"epoch": 9.88,
"learning_rate": 0.0002,
"loss": 0.5533,
"step": 177300
},
{
"epoch": 9.89,
"learning_rate": 0.0002,
"loss": 0.5504,
"step": 177400
},
{
"epoch": 9.89,
"learning_rate": 0.0002,
"loss": 0.559,
"step": 177500
},
{
"epoch": 9.9,
"learning_rate": 0.0002,
"loss": 0.5433,
"step": 177600
},
{
"epoch": 9.9,
"learning_rate": 0.0002,
"loss": 0.5495,
"step": 177700
},
{
"epoch": 9.91,
"learning_rate": 0.0002,
"loss": 0.5308,
"step": 177800
},
{
"epoch": 9.91,
"learning_rate": 0.0002,
"loss": 0.5479,
"step": 177900
},
{
"epoch": 9.92,
"learning_rate": 0.0002,
"loss": 0.5562,
"step": 178000
},
{
"epoch": 9.92,
"learning_rate": 0.0002,
"loss": 0.5418,
"step": 178100
},
{
"epoch": 9.93,
"learning_rate": 0.0002,
"loss": 0.5496,
"step": 178200
},
{
"epoch": 9.94,
"learning_rate": 0.0002,
"loss": 0.5532,
"step": 178300
},
{
"epoch": 9.94,
"learning_rate": 0.0002,
"loss": 0.54,
"step": 178400
},
{
"epoch": 9.95,
"learning_rate": 0.0002,
"loss": 0.549,
"step": 178500
},
{
"epoch": 9.95,
"learning_rate": 0.0002,
"loss": 0.5341,
"step": 178600
},
{
"epoch": 9.96,
"learning_rate": 0.0002,
"loss": 0.5487,
"step": 178700
},
{
"epoch": 9.96,
"learning_rate": 0.0002,
"loss": 0.5403,
"step": 178800
},
{
"epoch": 9.97,
"learning_rate": 0.0002,
"loss": 0.5369,
"step": 178900
},
{
"epoch": 9.97,
"learning_rate": 0.0002,
"loss": 0.5506,
"step": 179000
},
{
"epoch": 9.98,
"learning_rate": 0.0002,
"loss": 0.5423,
"step": 179100
},
{
"epoch": 9.99,
"learning_rate": 0.0002,
"loss": 0.5442,
"step": 179200
},
{
"epoch": 9.99,
"learning_rate": 0.0002,
"loss": 0.5455,
"step": 179300
},
{
"epoch": 10.0,
"learning_rate": 0.0002,
"loss": 0.565,
"step": 179400
},
{
"epoch": 10.0,
"learning_rate": 0.0002,
"loss": 0.5376,
"step": 179500
},
{
"epoch": 10.01,
"learning_rate": 0.0002,
"loss": 0.5155,
"step": 179600
},
{
"epoch": 10.01,
"learning_rate": 0.0002,
"loss": 0.5199,
"step": 179700
},
{
"epoch": 10.02,
"learning_rate": 0.0002,
"loss": 0.5276,
"step": 179800
},
{
"epoch": 10.03,
"learning_rate": 0.0002,
"loss": 0.5285,
"step": 179900
},
{
"epoch": 10.03,
"learning_rate": 0.0002,
"loss": 0.513,
"step": 180000
},
{
"epoch": 10.03,
"eval_gen_len": 18.99970077797726,
"eval_loss": 2.771777391433716,
"eval_rouge1": 25.3651,
"eval_rouge2": 12.4707,
"eval_rougeL": 20.9642,
"eval_rougeLsum": 23.9479,
"eval_runtime": 473.669,
"eval_samples_per_second": 28.222,
"eval_steps_per_second": 1.765,
"step": 180000
},
{
"epoch": 10.04,
"learning_rate": 0.0002,
"loss": 0.531,
"step": 180100
},
{
"epoch": 10.04,
"learning_rate": 0.0002,
"loss": 0.5042,
"step": 180200
},
{
"epoch": 10.05,
"learning_rate": 0.0002,
"loss": 0.5018,
"step": 180300
},
{
"epoch": 10.05,
"learning_rate": 0.0002,
"loss": 0.5239,
"step": 180400
},
{
"epoch": 10.06,
"learning_rate": 0.0002,
"loss": 0.5154,
"step": 180500
},
{
"epoch": 10.06,
"learning_rate": 0.0002,
"loss": 0.5311,
"step": 180600
},
{
"epoch": 10.07,
"learning_rate": 0.0002,
"loss": 0.5206,
"step": 180700
},
{
"epoch": 10.08,
"learning_rate": 0.0002,
"loss": 0.5234,
"step": 180800
},
{
"epoch": 10.08,
"learning_rate": 0.0002,
"loss": 0.5209,
"step": 180900
},
{
"epoch": 10.09,
"learning_rate": 0.0002,
"loss": 0.533,
"step": 181000
},
{
"epoch": 10.09,
"learning_rate": 0.0002,
"loss": 0.5323,
"step": 181100
},
{
"epoch": 10.1,
"learning_rate": 0.0002,
"loss": 0.5174,
"step": 181200
},
{
"epoch": 10.1,
"learning_rate": 0.0002,
"loss": 0.5279,
"step": 181300
},
{
"epoch": 10.11,
"learning_rate": 0.0002,
"loss": 0.5141,
"step": 181400
},
{
"epoch": 10.11,
"learning_rate": 0.0002,
"loss": 0.533,
"step": 181500
},
{
"epoch": 10.12,
"learning_rate": 0.0002,
"loss": 0.5359,
"step": 181600
},
{
"epoch": 10.13,
"learning_rate": 0.0002,
"loss": 0.5312,
"step": 181700
},
{
"epoch": 10.13,
"learning_rate": 0.0002,
"loss": 0.51,
"step": 181800
},
{
"epoch": 10.14,
"learning_rate": 0.0002,
"loss": 0.5172,
"step": 181900
},
{
"epoch": 10.14,
"learning_rate": 0.0002,
"loss": 0.5128,
"step": 182000
},
{
"epoch": 10.15,
"learning_rate": 0.0002,
"loss": 0.5275,
"step": 182100
},
{
"epoch": 10.15,
"learning_rate": 0.0002,
"loss": 0.5317,
"step": 182200
},
{
"epoch": 10.16,
"learning_rate": 0.0002,
"loss": 0.5378,
"step": 182300
},
{
"epoch": 10.16,
"learning_rate": 0.0002,
"loss": 0.5298,
"step": 182400
},
{
"epoch": 10.17,
"learning_rate": 0.0002,
"loss": 0.5181,
"step": 182500
},
{
"epoch": 10.18,
"learning_rate": 0.0002,
"loss": 0.5086,
"step": 182600
},
{
"epoch": 10.18,
"learning_rate": 0.0002,
"loss": 0.5257,
"step": 182700
},
{
"epoch": 10.19,
"learning_rate": 0.0002,
"loss": 0.5237,
"step": 182800
},
{
"epoch": 10.19,
"learning_rate": 0.0002,
"loss": 0.5226,
"step": 182900
},
{
"epoch": 10.2,
"learning_rate": 0.0002,
"loss": 0.526,
"step": 183000
},
{
"epoch": 10.2,
"learning_rate": 0.0002,
"loss": 0.5257,
"step": 183100
},
{
"epoch": 10.21,
"learning_rate": 0.0002,
"loss": 0.5188,
"step": 183200
},
{
"epoch": 10.21,
"learning_rate": 0.0002,
"loss": 0.5265,
"step": 183300
},
{
"epoch": 10.22,
"learning_rate": 0.0002,
"loss": 0.5292,
"step": 183400
},
{
"epoch": 10.23,
"learning_rate": 0.0002,
"loss": 0.5394,
"step": 183500
},
{
"epoch": 10.23,
"learning_rate": 0.0002,
"loss": 0.533,
"step": 183600
},
{
"epoch": 10.24,
"learning_rate": 0.0002,
"loss": 0.5327,
"step": 183700
},
{
"epoch": 10.24,
"learning_rate": 0.0002,
"loss": 0.5291,
"step": 183800
},
{
"epoch": 10.25,
"learning_rate": 0.0002,
"loss": 0.5398,
"step": 183900
},
{
"epoch": 10.25,
"learning_rate": 0.0002,
"loss": 0.5236,
"step": 184000
},
{
"epoch": 10.26,
"learning_rate": 0.0002,
"loss": 0.5248,
"step": 184100
},
{
"epoch": 10.26,
"learning_rate": 0.0002,
"loss": 0.5148,
"step": 184200
},
{
"epoch": 10.27,
"learning_rate": 0.0002,
"loss": 0.5402,
"step": 184300
},
{
"epoch": 10.28,
"learning_rate": 0.0002,
"loss": 0.5241,
"step": 184400
},
{
"epoch": 10.28,
"learning_rate": 0.0002,
"loss": 0.5356,
"step": 184500
},
{
"epoch": 10.29,
"learning_rate": 0.0002,
"loss": 0.5171,
"step": 184600
},
{
"epoch": 10.29,
"learning_rate": 0.0002,
"loss": 0.5339,
"step": 184700
},
{
"epoch": 10.3,
"learning_rate": 0.0002,
"loss": 0.5228,
"step": 184800
},
{
"epoch": 10.3,
"learning_rate": 0.0002,
"loss": 0.5405,
"step": 184900
},
{
"epoch": 10.31,
"learning_rate": 0.0002,
"loss": 0.5441,
"step": 185000
},
{
"epoch": 10.31,
"learning_rate": 0.0002,
"loss": 0.5335,
"step": 185100
},
{
"epoch": 10.32,
"learning_rate": 0.0002,
"loss": 0.5289,
"step": 185200
},
{
"epoch": 10.33,
"learning_rate": 0.0002,
"loss": 0.5374,
"step": 185300
},
{
"epoch": 10.33,
"learning_rate": 0.0002,
"loss": 0.5185,
"step": 185400
},
{
"epoch": 10.34,
"learning_rate": 0.0002,
"loss": 0.5413,
"step": 185500
},
{
"epoch": 10.34,
"learning_rate": 0.0002,
"loss": 0.5399,
"step": 185600
},
{
"epoch": 10.35,
"learning_rate": 0.0002,
"loss": 0.521,
"step": 185700
},
{
"epoch": 10.35,
"learning_rate": 0.0002,
"loss": 0.5314,
"step": 185800
},
{
"epoch": 10.36,
"learning_rate": 0.0002,
"loss": 0.5355,
"step": 185900
},
{
"epoch": 10.37,
"learning_rate": 0.0002,
"loss": 0.537,
"step": 186000
},
{
"epoch": 10.37,
"learning_rate": 0.0002,
"loss": 0.5304,
"step": 186100
},
{
"epoch": 10.38,
"learning_rate": 0.0002,
"loss": 0.532,
"step": 186200
},
{
"epoch": 10.38,
"learning_rate": 0.0002,
"loss": 0.5198,
"step": 186300
},
{
"epoch": 10.39,
"learning_rate": 0.0002,
"loss": 0.5347,
"step": 186400
},
{
"epoch": 10.39,
"learning_rate": 0.0002,
"loss": 0.5288,
"step": 186500
},
{
"epoch": 10.4,
"learning_rate": 0.0002,
"loss": 0.5347,
"step": 186600
},
{
"epoch": 10.4,
"learning_rate": 0.0002,
"loss": 0.5324,
"step": 186700
},
{
"epoch": 10.41,
"learning_rate": 0.0002,
"loss": 0.5292,
"step": 186800
},
{
"epoch": 10.42,
"learning_rate": 0.0002,
"loss": 0.5339,
"step": 186900
},
{
"epoch": 10.42,
"learning_rate": 0.0002,
"loss": 0.5327,
"step": 187000
},
{
"epoch": 10.43,
"learning_rate": 0.0002,
"loss": 0.5309,
"step": 187100
},
{
"epoch": 10.43,
"learning_rate": 0.0002,
"loss": 0.5216,
"step": 187200
},
{
"epoch": 10.44,
"learning_rate": 0.0002,
"loss": 0.5325,
"step": 187300
},
{
"epoch": 10.44,
"learning_rate": 0.0002,
"loss": 0.5251,
"step": 187400
},
{
"epoch": 10.45,
"learning_rate": 0.0002,
"loss": 0.5321,
"step": 187500
},
{
"epoch": 10.45,
"learning_rate": 0.0002,
"loss": 0.5425,
"step": 187600
},
{
"epoch": 10.46,
"learning_rate": 0.0002,
"loss": 0.5305,
"step": 187700
},
{
"epoch": 10.47,
"learning_rate": 0.0002,
"loss": 0.5306,
"step": 187800
},
{
"epoch": 10.47,
"learning_rate": 0.0002,
"loss": 0.5345,
"step": 187900
},
{
"epoch": 10.48,
"learning_rate": 0.0002,
"loss": 0.5374,
"step": 188000
},
{
"epoch": 10.48,
"learning_rate": 0.0002,
"loss": 0.5142,
"step": 188100
},
{
"epoch": 10.49,
"learning_rate": 0.0002,
"loss": 0.5354,
"step": 188200
},
{
"epoch": 10.49,
"learning_rate": 0.0002,
"loss": 0.5265,
"step": 188300
},
{
"epoch": 10.5,
"learning_rate": 0.0002,
"loss": 0.5264,
"step": 188400
},
{
"epoch": 10.5,
"learning_rate": 0.0002,
"loss": 0.5377,
"step": 188500
},
{
"epoch": 10.51,
"learning_rate": 0.0002,
"loss": 0.5393,
"step": 188600
},
{
"epoch": 10.52,
"learning_rate": 0.0002,
"loss": 0.532,
"step": 188700
},
{
"epoch": 10.52,
"learning_rate": 0.0002,
"loss": 0.5439,
"step": 188800
},
{
"epoch": 10.53,
"learning_rate": 0.0002,
"loss": 0.5392,
"step": 188900
},
{
"epoch": 10.53,
"learning_rate": 0.0002,
"loss": 0.5407,
"step": 189000
},
{
"epoch": 10.54,
"learning_rate": 0.0002,
"loss": 0.5352,
"step": 189100
},
{
"epoch": 10.54,
"learning_rate": 0.0002,
"loss": 0.5384,
"step": 189200
},
{
"epoch": 10.55,
"learning_rate": 0.0002,
"loss": 0.5453,
"step": 189300
},
{
"epoch": 10.55,
"learning_rate": 0.0002,
"loss": 0.5289,
"step": 189400
},
{
"epoch": 10.56,
"learning_rate": 0.0002,
"loss": 0.5363,
"step": 189500
},
{
"epoch": 10.57,
"learning_rate": 0.0002,
"loss": 0.5311,
"step": 189600
},
{
"epoch": 10.57,
"learning_rate": 0.0002,
"loss": 0.5483,
"step": 189700
},
{
"epoch": 10.58,
"learning_rate": 0.0002,
"loss": 0.5446,
"step": 189800
},
{
"epoch": 10.58,
"learning_rate": 0.0002,
"loss": 0.5417,
"step": 189900
},
{
"epoch": 10.59,
"learning_rate": 0.0002,
"loss": 0.5348,
"step": 190000
},
{
"epoch": 10.59,
"eval_gen_len": 18.99970077797726,
"eval_loss": 2.70188045501709,
"eval_rouge1": 25.274,
"eval_rouge2": 12.3837,
"eval_rougeL": 20.8714,
"eval_rougeLsum": 23.8766,
"eval_runtime": 474.7941,
"eval_samples_per_second": 28.155,
"eval_steps_per_second": 1.761,
"step": 190000
},
{
"epoch": 10.59,
"learning_rate": 0.0002,
"loss": 0.549,
"step": 190100
},
{
"epoch": 10.6,
"learning_rate": 0.0002,
"loss": 0.5398,
"step": 190200
},
{
"epoch": 10.6,
"learning_rate": 0.0002,
"loss": 0.5492,
"step": 190300
},
{
"epoch": 10.61,
"learning_rate": 0.0002,
"loss": 0.5443,
"step": 190400
},
{
"epoch": 10.62,
"learning_rate": 0.0002,
"loss": 0.5407,
"step": 190500
},
{
"epoch": 10.62,
"learning_rate": 0.0002,
"loss": 0.5348,
"step": 190600
},
{
"epoch": 10.63,
"learning_rate": 0.0002,
"loss": 0.5335,
"step": 190700
},
{
"epoch": 10.63,
"learning_rate": 0.0002,
"loss": 0.5479,
"step": 190800
},
{
"epoch": 10.64,
"learning_rate": 0.0002,
"loss": 0.5297,
"step": 190900
},
{
"epoch": 10.64,
"learning_rate": 0.0002,
"loss": 0.5317,
"step": 191000
},
{
"epoch": 10.65,
"learning_rate": 0.0002,
"loss": 0.5418,
"step": 191100
},
{
"epoch": 10.65,
"learning_rate": 0.0002,
"loss": 0.5397,
"step": 191200
},
{
"epoch": 10.66,
"learning_rate": 0.0002,
"loss": 0.5381,
"step": 191300
},
{
"epoch": 10.67,
"learning_rate": 0.0002,
"loss": 0.5266,
"step": 191400
},
{
"epoch": 10.67,
"learning_rate": 0.0002,
"loss": 0.5321,
"step": 191500
},
{
"epoch": 10.68,
"learning_rate": 0.0002,
"loss": 0.5549,
"step": 191600
},
{
"epoch": 10.68,
"learning_rate": 0.0002,
"loss": 0.5473,
"step": 191700
},
{
"epoch": 10.69,
"learning_rate": 0.0002,
"loss": 0.5292,
"step": 191800
},
{
"epoch": 10.69,
"learning_rate": 0.0002,
"loss": 0.5326,
"step": 191900
},
{
"epoch": 10.7,
"learning_rate": 0.0002,
"loss": 0.5344,
"step": 192000
},
{
"epoch": 10.7,
"learning_rate": 0.0002,
"loss": 0.5493,
"step": 192100
},
{
"epoch": 10.71,
"learning_rate": 0.0002,
"loss": 0.5407,
"step": 192200
},
{
"epoch": 10.72,
"learning_rate": 0.0002,
"loss": 0.5373,
"step": 192300
},
{
"epoch": 10.72,
"learning_rate": 0.0002,
"loss": 0.5357,
"step": 192400
},
{
"epoch": 10.73,
"learning_rate": 0.0002,
"loss": 0.5288,
"step": 192500
},
{
"epoch": 10.73,
"learning_rate": 0.0002,
"loss": 0.5439,
"step": 192600
},
{
"epoch": 10.74,
"learning_rate": 0.0002,
"loss": 0.5521,
"step": 192700
},
{
"epoch": 10.74,
"learning_rate": 0.0002,
"loss": 0.551,
"step": 192800
},
{
"epoch": 10.75,
"learning_rate": 0.0002,
"loss": 0.5298,
"step": 192900
},
{
"epoch": 10.76,
"learning_rate": 0.0002,
"loss": 0.5484,
"step": 193000
},
{
"epoch": 10.76,
"learning_rate": 0.0002,
"loss": 0.5351,
"step": 193100
},
{
"epoch": 10.77,
"learning_rate": 0.0002,
"loss": 0.5399,
"step": 193200
},
{
"epoch": 10.77,
"learning_rate": 0.0002,
"loss": 0.5424,
"step": 193300
},
{
"epoch": 10.78,
"learning_rate": 0.0002,
"loss": 0.5401,
"step": 193400
},
{
"epoch": 10.78,
"learning_rate": 0.0002,
"loss": 0.5417,
"step": 193500
},
{
"epoch": 10.79,
"learning_rate": 0.0002,
"loss": 0.5265,
"step": 193600
},
{
"epoch": 10.79,
"learning_rate": 0.0002,
"loss": 0.5315,
"step": 193700
},
{
"epoch": 10.8,
"learning_rate": 0.0002,
"loss": 0.5348,
"step": 193800
},
{
"epoch": 10.81,
"learning_rate": 0.0002,
"loss": 0.5475,
"step": 193900
},
{
"epoch": 10.81,
"learning_rate": 0.0002,
"loss": 0.5381,
"step": 194000
},
{
"epoch": 10.82,
"learning_rate": 0.0002,
"loss": 0.5387,
"step": 194100
},
{
"epoch": 10.82,
"learning_rate": 0.0002,
"loss": 0.5442,
"step": 194200
},
{
"epoch": 10.83,
"learning_rate": 0.0002,
"loss": 0.5332,
"step": 194300
},
{
"epoch": 10.83,
"learning_rate": 0.0002,
"loss": 0.5377,
"step": 194400
},
{
"epoch": 10.84,
"learning_rate": 0.0002,
"loss": 0.5426,
"step": 194500
},
{
"epoch": 10.84,
"learning_rate": 0.0002,
"loss": 0.5512,
"step": 194600
},
{
"epoch": 10.85,
"learning_rate": 0.0002,
"loss": 0.5364,
"step": 194700
},
{
"epoch": 10.86,
"learning_rate": 0.0002,
"loss": 0.5418,
"step": 194800
},
{
"epoch": 10.86,
"learning_rate": 0.0002,
"loss": 0.5566,
"step": 194900
},
{
"epoch": 10.87,
"learning_rate": 0.0002,
"loss": 0.5395,
"step": 195000
},
{
"epoch": 10.87,
"learning_rate": 0.0002,
"loss": 0.5356,
"step": 195100
},
{
"epoch": 10.88,
"learning_rate": 0.0002,
"loss": 0.5351,
"step": 195200
},
{
"epoch": 10.88,
"learning_rate": 0.0002,
"loss": 0.5411,
"step": 195300
},
{
"epoch": 10.89,
"learning_rate": 0.0002,
"loss": 0.5446,
"step": 195400
},
{
"epoch": 10.89,
"learning_rate": 0.0002,
"loss": 0.5496,
"step": 195500
},
{
"epoch": 10.9,
"learning_rate": 0.0002,
"loss": 0.5284,
"step": 195600
},
{
"epoch": 10.91,
"learning_rate": 0.0002,
"loss": 0.5406,
"step": 195700
},
{
"epoch": 10.91,
"learning_rate": 0.0002,
"loss": 0.5461,
"step": 195800
},
{
"epoch": 10.92,
"learning_rate": 0.0002,
"loss": 0.5376,
"step": 195900
},
{
"epoch": 10.92,
"learning_rate": 0.0002,
"loss": 0.5552,
"step": 196000
},
{
"epoch": 10.93,
"learning_rate": 0.0002,
"loss": 0.5493,
"step": 196100
},
{
"epoch": 10.93,
"learning_rate": 0.0002,
"loss": 0.5328,
"step": 196200
},
{
"epoch": 10.94,
"learning_rate": 0.0002,
"loss": 0.5427,
"step": 196300
},
{
"epoch": 10.94,
"learning_rate": 0.0002,
"loss": 0.5296,
"step": 196400
},
{
"epoch": 10.95,
"learning_rate": 0.0002,
"loss": 0.5362,
"step": 196500
},
{
"epoch": 10.96,
"learning_rate": 0.0002,
"loss": 0.5336,
"step": 196600
},
{
"epoch": 10.96,
"learning_rate": 0.0002,
"loss": 0.5329,
"step": 196700
},
{
"epoch": 10.97,
"learning_rate": 0.0002,
"loss": 0.5411,
"step": 196800
},
{
"epoch": 10.97,
"learning_rate": 0.0002,
"loss": 0.5385,
"step": 196900
},
{
"epoch": 10.98,
"learning_rate": 0.0002,
"loss": 0.5469,
"step": 197000
},
{
"epoch": 10.98,
"learning_rate": 0.0002,
"loss": 0.5579,
"step": 197100
},
{
"epoch": 10.99,
"learning_rate": 0.0002,
"loss": 0.548,
"step": 197200
},
{
"epoch": 10.99,
"learning_rate": 0.0002,
"loss": 0.5447,
"step": 197300
},
{
"epoch": 11.0,
"learning_rate": 0.0002,
"loss": 0.5431,
"step": 197400
},
{
"epoch": 11.01,
"learning_rate": 0.0002,
"loss": 0.5184,
"step": 197500
},
{
"epoch": 11.01,
"learning_rate": 0.0002,
"loss": 0.5116,
"step": 197600
},
{
"epoch": 11.02,
"learning_rate": 0.0002,
"loss": 0.5287,
"step": 197700
},
{
"epoch": 11.02,
"learning_rate": 0.0002,
"loss": 0.5241,
"step": 197800
},
{
"epoch": 11.03,
"learning_rate": 0.0002,
"loss": 0.5229,
"step": 197900
},
{
"epoch": 11.03,
"learning_rate": 0.0002,
"loss": 0.5249,
"step": 198000
},
{
"epoch": 11.04,
"learning_rate": 0.0002,
"loss": 0.5093,
"step": 198100
},
{
"epoch": 11.04,
"learning_rate": 0.0002,
"loss": 0.5304,
"step": 198200
},
{
"epoch": 11.05,
"learning_rate": 0.0002,
"loss": 0.5147,
"step": 198300
},
{
"epoch": 11.06,
"learning_rate": 0.0002,
"loss": 0.5274,
"step": 198400
},
{
"epoch": 11.06,
"learning_rate": 0.0002,
"loss": 0.5266,
"step": 198500
},
{
"epoch": 11.07,
"learning_rate": 0.0002,
"loss": 0.507,
"step": 198600
},
{
"epoch": 11.07,
"learning_rate": 0.0002,
"loss": 0.5189,
"step": 198700
},
{
"epoch": 11.08,
"learning_rate": 0.0002,
"loss": 0.5388,
"step": 198800
},
{
"epoch": 11.08,
"learning_rate": 0.0002,
"loss": 0.5069,
"step": 198900
},
{
"epoch": 11.09,
"learning_rate": 0.0002,
"loss": 0.5212,
"step": 199000
},
{
"epoch": 11.1,
"learning_rate": 0.0002,
"loss": 0.5088,
"step": 199100
},
{
"epoch": 11.1,
"learning_rate": 0.0002,
"loss": 0.5189,
"step": 199200
},
{
"epoch": 11.11,
"learning_rate": 0.0002,
"loss": 0.5218,
"step": 199300
},
{
"epoch": 11.11,
"learning_rate": 0.0002,
"loss": 0.5197,
"step": 199400
},
{
"epoch": 11.12,
"learning_rate": 0.0002,
"loss": 0.5246,
"step": 199500
},
{
"epoch": 11.12,
"learning_rate": 0.0002,
"loss": 0.5255,
"step": 199600
},
{
"epoch": 11.13,
"learning_rate": 0.0002,
"loss": 0.5164,
"step": 199700
},
{
"epoch": 11.13,
"learning_rate": 0.0002,
"loss": 0.5201,
"step": 199800
},
{
"epoch": 11.14,
"learning_rate": 0.0002,
"loss": 0.5277,
"step": 199900
},
{
"epoch": 11.15,
"learning_rate": 0.0002,
"loss": 0.5277,
"step": 200000
},
{
"epoch": 11.15,
"eval_gen_len": 18.999476361460204,
"eval_loss": 2.7242300510406494,
"eval_rouge1": 25.376,
"eval_rouge2": 12.4944,
"eval_rougeL": 20.9774,
"eval_rougeLsum": 23.985,
"eval_runtime": 476.9451,
"eval_samples_per_second": 28.028,
"eval_steps_per_second": 1.753,
"step": 200000
}
],
"max_steps": 897250,
"num_train_epochs": 50,
"total_flos": 8.661379023313306e+17,
"trial_name": null,
"trial_params": null
}