T5-small-cnndm / trainer_state.json
Sehoon's picture
store
73529f7
raw
history blame
111 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 26.0,
"global_step": 466570,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.9186,
"step": 500
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.9055,
"step": 1000
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.8958,
"step": 1500
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.8887,
"step": 2000
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 1.8921,
"step": 2500
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 1.8743,
"step": 3000
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 1.8678,
"step": 3500
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 1.8695,
"step": 4000
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 1.8759,
"step": 4500
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 1.8489,
"step": 5000
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 1.8643,
"step": 5500
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 1.8591,
"step": 6000
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 1.859,
"step": 6500
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 1.8667,
"step": 7000
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 1.8646,
"step": 7500
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 1.8515,
"step": 8000
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 1.8617,
"step": 8500
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 1.8569,
"step": 9000
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 1.8536,
"step": 9500
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 1.8531,
"step": 10000
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 1.8589,
"step": 10500
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 1.8462,
"step": 11000
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 1.8491,
"step": 11500
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 1.8535,
"step": 12000
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 1.8458,
"step": 12500
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 1.8425,
"step": 13000
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 1.8577,
"step": 13500
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 1.8212,
"step": 14000
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 1.8243,
"step": 14500
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 1.8373,
"step": 15000
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 1.8447,
"step": 15500
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 1.8508,
"step": 16000
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 1.8333,
"step": 16500
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 1.8298,
"step": 17000
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 1.8308,
"step": 17500
},
{
"epoch": 1.0,
"eval_gen_len": 19.0,
"eval_loss": 1.6631494760513306,
"eval_rouge1": 24.5532,
"eval_rouge2": 11.7093,
"eval_rougeL": 20.2667,
"eval_rougeLsum": 23.1638,
"eval_runtime": 448.1964,
"eval_samples_per_second": 29.826,
"eval_steps_per_second": 1.865,
"step": 17945
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 1.8428,
"step": 18000
},
{
"epoch": 1.03,
"learning_rate": 0.0002,
"loss": 1.8006,
"step": 18500
},
{
"epoch": 1.06,
"learning_rate": 0.0002,
"loss": 1.8007,
"step": 19000
},
{
"epoch": 1.09,
"learning_rate": 0.0002,
"loss": 1.8053,
"step": 19500
},
{
"epoch": 1.11,
"learning_rate": 0.0002,
"loss": 1.7934,
"step": 20000
},
{
"epoch": 1.14,
"learning_rate": 0.0002,
"loss": 1.7965,
"step": 20500
},
{
"epoch": 1.17,
"learning_rate": 0.0002,
"loss": 1.7913,
"step": 21000
},
{
"epoch": 1.2,
"learning_rate": 0.0002,
"loss": 1.8153,
"step": 21500
},
{
"epoch": 1.23,
"learning_rate": 0.0002,
"loss": 1.8004,
"step": 22000
},
{
"epoch": 1.25,
"learning_rate": 0.0002,
"loss": 1.806,
"step": 22500
},
{
"epoch": 1.28,
"learning_rate": 0.0002,
"loss": 1.7913,
"step": 23000
},
{
"epoch": 1.31,
"learning_rate": 0.0002,
"loss": 1.7987,
"step": 23500
},
{
"epoch": 1.34,
"learning_rate": 0.0002,
"loss": 1.7973,
"step": 24000
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 1.7966,
"step": 24500
},
{
"epoch": 1.39,
"learning_rate": 0.0002,
"loss": 1.7897,
"step": 25000
},
{
"epoch": 1.42,
"learning_rate": 0.0002,
"loss": 1.8089,
"step": 25500
},
{
"epoch": 1.45,
"learning_rate": 0.0002,
"loss": 1.7966,
"step": 26000
},
{
"epoch": 1.48,
"learning_rate": 0.0002,
"loss": 1.8035,
"step": 26500
},
{
"epoch": 1.5,
"learning_rate": 0.0002,
"loss": 1.803,
"step": 27000
},
{
"epoch": 1.53,
"learning_rate": 0.0002,
"loss": 1.7965,
"step": 27500
},
{
"epoch": 1.56,
"learning_rate": 0.0002,
"loss": 1.789,
"step": 28000
},
{
"epoch": 1.59,
"learning_rate": 0.0002,
"loss": 1.7869,
"step": 28500
},
{
"epoch": 1.62,
"learning_rate": 0.0002,
"loss": 1.7915,
"step": 29000
},
{
"epoch": 1.64,
"learning_rate": 0.0002,
"loss": 1.8024,
"step": 29500
},
{
"epoch": 1.67,
"learning_rate": 0.0002,
"loss": 1.8004,
"step": 30000
},
{
"epoch": 1.7,
"learning_rate": 0.0002,
"loss": 1.7968,
"step": 30500
},
{
"epoch": 1.73,
"learning_rate": 0.0002,
"loss": 1.7932,
"step": 31000
},
{
"epoch": 1.76,
"learning_rate": 0.0002,
"loss": 1.7937,
"step": 31500
},
{
"epoch": 1.78,
"learning_rate": 0.0002,
"loss": 1.8043,
"step": 32000
},
{
"epoch": 1.81,
"learning_rate": 0.0002,
"loss": 1.7975,
"step": 32500
},
{
"epoch": 1.84,
"learning_rate": 0.0002,
"loss": 1.7991,
"step": 33000
},
{
"epoch": 1.87,
"learning_rate": 0.0002,
"loss": 1.7823,
"step": 33500
},
{
"epoch": 1.89,
"learning_rate": 0.0002,
"loss": 1.7987,
"step": 34000
},
{
"epoch": 1.92,
"learning_rate": 0.0002,
"loss": 1.7788,
"step": 34500
},
{
"epoch": 1.95,
"learning_rate": 0.0002,
"loss": 1.8048,
"step": 35000
},
{
"epoch": 1.98,
"learning_rate": 0.0002,
"loss": 1.7898,
"step": 35500
},
{
"epoch": 2.0,
"eval_gen_len": 18.999925194494313,
"eval_loss": 1.6393862962722778,
"eval_rouge1": 24.5891,
"eval_rouge2": 11.7919,
"eval_rougeL": 20.3168,
"eval_rougeLsum": 23.1912,
"eval_runtime": 447.7546,
"eval_samples_per_second": 29.856,
"eval_steps_per_second": 1.867,
"step": 35890
},
{
"epoch": 2.01,
"learning_rate": 0.0002,
"loss": 1.7765,
"step": 36000
},
{
"epoch": 2.03,
"learning_rate": 0.0002,
"loss": 1.7595,
"step": 36500
},
{
"epoch": 2.06,
"learning_rate": 0.0002,
"loss": 1.7526,
"step": 37000
},
{
"epoch": 2.09,
"learning_rate": 0.0002,
"loss": 1.7677,
"step": 37500
},
{
"epoch": 2.12,
"learning_rate": 0.0002,
"loss": 1.7633,
"step": 38000
},
{
"epoch": 2.15,
"learning_rate": 0.0002,
"loss": 1.759,
"step": 38500
},
{
"epoch": 2.17,
"learning_rate": 0.0002,
"loss": 1.7633,
"step": 39000
},
{
"epoch": 2.2,
"learning_rate": 0.0002,
"loss": 1.7675,
"step": 39500
},
{
"epoch": 2.23,
"learning_rate": 0.0002,
"loss": 1.7694,
"step": 40000
},
{
"epoch": 2.26,
"learning_rate": 0.0002,
"loss": 1.7643,
"step": 40500
},
{
"epoch": 2.28,
"learning_rate": 0.0002,
"loss": 1.7591,
"step": 41000
},
{
"epoch": 2.31,
"learning_rate": 0.0002,
"loss": 1.7758,
"step": 41500
},
{
"epoch": 2.34,
"learning_rate": 0.0002,
"loss": 1.7547,
"step": 42000
},
{
"epoch": 2.37,
"learning_rate": 0.0002,
"loss": 1.755,
"step": 42500
},
{
"epoch": 2.4,
"learning_rate": 0.0002,
"loss": 1.7681,
"step": 43000
},
{
"epoch": 2.42,
"learning_rate": 0.0002,
"loss": 1.7541,
"step": 43500
},
{
"epoch": 2.45,
"learning_rate": 0.0002,
"loss": 1.754,
"step": 44000
},
{
"epoch": 2.48,
"learning_rate": 0.0002,
"loss": 1.7534,
"step": 44500
},
{
"epoch": 2.51,
"learning_rate": 0.0002,
"loss": 1.7644,
"step": 45000
},
{
"epoch": 2.54,
"learning_rate": 0.0002,
"loss": 1.7696,
"step": 45500
},
{
"epoch": 2.56,
"learning_rate": 0.0002,
"loss": 1.7675,
"step": 46000
},
{
"epoch": 2.59,
"learning_rate": 0.0002,
"loss": 1.77,
"step": 46500
},
{
"epoch": 2.62,
"learning_rate": 0.0002,
"loss": 1.7576,
"step": 47000
},
{
"epoch": 2.65,
"learning_rate": 0.0002,
"loss": 1.7618,
"step": 47500
},
{
"epoch": 2.67,
"learning_rate": 0.0002,
"loss": 1.7645,
"step": 48000
},
{
"epoch": 2.7,
"learning_rate": 0.0002,
"loss": 1.7699,
"step": 48500
},
{
"epoch": 2.73,
"learning_rate": 0.0002,
"loss": 1.7867,
"step": 49000
},
{
"epoch": 2.76,
"learning_rate": 0.0002,
"loss": 1.7632,
"step": 49500
},
{
"epoch": 2.79,
"learning_rate": 0.0002,
"loss": 1.7629,
"step": 50000
},
{
"epoch": 2.81,
"learning_rate": 0.0002,
"loss": 1.7626,
"step": 50500
},
{
"epoch": 2.84,
"learning_rate": 0.0002,
"loss": 1.7615,
"step": 51000
},
{
"epoch": 2.87,
"learning_rate": 0.0002,
"loss": 1.7611,
"step": 51500
},
{
"epoch": 2.9,
"learning_rate": 0.0002,
"loss": 1.7751,
"step": 52000
},
{
"epoch": 2.93,
"learning_rate": 0.0002,
"loss": 1.7626,
"step": 52500
},
{
"epoch": 2.95,
"learning_rate": 0.0002,
"loss": 1.7534,
"step": 53000
},
{
"epoch": 2.98,
"learning_rate": 0.0002,
"loss": 1.7617,
"step": 53500
},
{
"epoch": 3.0,
"eval_gen_len": 18.999401555954517,
"eval_loss": 1.6363353729248047,
"eval_rouge1": 24.6169,
"eval_rouge2": 11.9038,
"eval_rougeL": 20.3703,
"eval_rougeLsum": 23.2215,
"eval_runtime": 448.243,
"eval_samples_per_second": 29.823,
"eval_steps_per_second": 1.865,
"step": 53835
},
{
"epoch": 3.01,
"learning_rate": 0.0002,
"loss": 1.7507,
"step": 54000
},
{
"epoch": 3.04,
"learning_rate": 0.0002,
"loss": 1.7254,
"step": 54500
},
{
"epoch": 3.06,
"learning_rate": 0.0002,
"loss": 1.7303,
"step": 55000
},
{
"epoch": 3.09,
"learning_rate": 0.0002,
"loss": 1.7273,
"step": 55500
},
{
"epoch": 3.12,
"learning_rate": 0.0002,
"loss": 1.7415,
"step": 56000
},
{
"epoch": 3.15,
"learning_rate": 0.0002,
"loss": 1.7314,
"step": 56500
},
{
"epoch": 3.18,
"learning_rate": 0.0002,
"loss": 1.7194,
"step": 57000
},
{
"epoch": 3.2,
"learning_rate": 0.0002,
"loss": 1.7288,
"step": 57500
},
{
"epoch": 3.23,
"learning_rate": 0.0002,
"loss": 1.7415,
"step": 58000
},
{
"epoch": 3.26,
"learning_rate": 0.0002,
"loss": 1.7261,
"step": 58500
},
{
"epoch": 3.29,
"learning_rate": 0.0002,
"loss": 1.74,
"step": 59000
},
{
"epoch": 3.32,
"learning_rate": 0.0002,
"loss": 1.7383,
"step": 59500
},
{
"epoch": 3.34,
"learning_rate": 0.0002,
"loss": 1.7389,
"step": 60000
},
{
"epoch": 3.37,
"learning_rate": 0.0002,
"loss": 1.7392,
"step": 60500
},
{
"epoch": 3.4,
"learning_rate": 0.0002,
"loss": 1.7489,
"step": 61000
},
{
"epoch": 3.43,
"learning_rate": 0.0002,
"loss": 1.7284,
"step": 61500
},
{
"epoch": 3.46,
"learning_rate": 0.0002,
"loss": 1.7494,
"step": 62000
},
{
"epoch": 3.48,
"learning_rate": 0.0002,
"loss": 1.7273,
"step": 62500
},
{
"epoch": 3.51,
"learning_rate": 0.0002,
"loss": 1.7478,
"step": 63000
},
{
"epoch": 3.54,
"learning_rate": 0.0002,
"loss": 1.7296,
"step": 63500
},
{
"epoch": 3.57,
"learning_rate": 0.0002,
"loss": 1.741,
"step": 64000
},
{
"epoch": 3.59,
"learning_rate": 0.0002,
"loss": 1.7361,
"step": 64500
},
{
"epoch": 3.62,
"learning_rate": 0.0002,
"loss": 1.7422,
"step": 65000
},
{
"epoch": 3.65,
"learning_rate": 0.0002,
"loss": 1.7392,
"step": 65500
},
{
"epoch": 3.68,
"learning_rate": 0.0002,
"loss": 1.7414,
"step": 66000
},
{
"epoch": 3.71,
"learning_rate": 0.0002,
"loss": 1.7298,
"step": 66500
},
{
"epoch": 3.73,
"learning_rate": 0.0002,
"loss": 1.7358,
"step": 67000
},
{
"epoch": 3.76,
"learning_rate": 0.0002,
"loss": 1.736,
"step": 67500
},
{
"epoch": 3.79,
"learning_rate": 0.0002,
"loss": 1.7235,
"step": 68000
},
{
"epoch": 3.82,
"learning_rate": 0.0002,
"loss": 1.7511,
"step": 68500
},
{
"epoch": 3.85,
"learning_rate": 0.0002,
"loss": 1.7362,
"step": 69000
},
{
"epoch": 3.87,
"learning_rate": 0.0002,
"loss": 1.7433,
"step": 69500
},
{
"epoch": 3.9,
"learning_rate": 0.0002,
"loss": 1.7546,
"step": 70000
},
{
"epoch": 3.93,
"learning_rate": 0.0002,
"loss": 1.7399,
"step": 70500
},
{
"epoch": 3.96,
"learning_rate": 0.0002,
"loss": 1.7406,
"step": 71000
},
{
"epoch": 3.98,
"learning_rate": 0.0002,
"loss": 1.7439,
"step": 71500
},
{
"epoch": 4.0,
"eval_gen_len": 18.999925194494313,
"eval_loss": 1.618168830871582,
"eval_rouge1": 24.7438,
"eval_rouge2": 11.9392,
"eval_rougeL": 20.4669,
"eval_rougeLsum": 23.3646,
"eval_runtime": 447.3678,
"eval_samples_per_second": 29.881,
"eval_steps_per_second": 1.869,
"step": 71780
},
{
"epoch": 4.01,
"learning_rate": 0.0002,
"loss": 1.7353,
"step": 72000
},
{
"epoch": 4.04,
"learning_rate": 0.0002,
"loss": 1.6958,
"step": 72500
},
{
"epoch": 4.07,
"learning_rate": 0.0002,
"loss": 1.7017,
"step": 73000
},
{
"epoch": 4.1,
"learning_rate": 0.0002,
"loss": 1.7149,
"step": 73500
},
{
"epoch": 4.12,
"learning_rate": 0.0002,
"loss": 1.7166,
"step": 74000
},
{
"epoch": 4.15,
"learning_rate": 0.0002,
"loss": 1.701,
"step": 74500
},
{
"epoch": 4.18,
"learning_rate": 0.0002,
"loss": 1.7011,
"step": 75000
},
{
"epoch": 4.21,
"learning_rate": 0.0002,
"loss": 1.7097,
"step": 75500
},
{
"epoch": 4.24,
"learning_rate": 0.0002,
"loss": 1.7122,
"step": 76000
},
{
"epoch": 4.26,
"learning_rate": 0.0002,
"loss": 1.7165,
"step": 76500
},
{
"epoch": 4.29,
"learning_rate": 0.0002,
"loss": 1.7143,
"step": 77000
},
{
"epoch": 4.32,
"learning_rate": 0.0002,
"loss": 1.7104,
"step": 77500
},
{
"epoch": 4.35,
"learning_rate": 0.0002,
"loss": 1.7282,
"step": 78000
},
{
"epoch": 4.37,
"learning_rate": 0.0002,
"loss": 1.7172,
"step": 78500
},
{
"epoch": 4.4,
"learning_rate": 0.0002,
"loss": 1.7097,
"step": 79000
},
{
"epoch": 4.43,
"learning_rate": 0.0002,
"loss": 1.7077,
"step": 79500
},
{
"epoch": 4.46,
"learning_rate": 0.0002,
"loss": 1.7164,
"step": 80000
},
{
"epoch": 4.49,
"learning_rate": 0.0002,
"loss": 1.7131,
"step": 80500
},
{
"epoch": 4.51,
"learning_rate": 0.0002,
"loss": 1.7125,
"step": 81000
},
{
"epoch": 4.54,
"learning_rate": 0.0002,
"loss": 1.7187,
"step": 81500
},
{
"epoch": 4.57,
"learning_rate": 0.0002,
"loss": 1.722,
"step": 82000
},
{
"epoch": 4.6,
"learning_rate": 0.0002,
"loss": 1.7183,
"step": 82500
},
{
"epoch": 4.63,
"learning_rate": 0.0002,
"loss": 1.7236,
"step": 83000
},
{
"epoch": 4.65,
"learning_rate": 0.0002,
"loss": 1.7126,
"step": 83500
},
{
"epoch": 4.68,
"learning_rate": 0.0002,
"loss": 1.7109,
"step": 84000
},
{
"epoch": 4.71,
"learning_rate": 0.0002,
"loss": 1.7166,
"step": 84500
},
{
"epoch": 4.74,
"learning_rate": 0.0002,
"loss": 1.7125,
"step": 85000
},
{
"epoch": 4.76,
"learning_rate": 0.0002,
"loss": 1.7405,
"step": 85500
},
{
"epoch": 4.79,
"learning_rate": 0.0002,
"loss": 1.7195,
"step": 86000
},
{
"epoch": 4.82,
"learning_rate": 0.0002,
"loss": 1.7101,
"step": 86500
},
{
"epoch": 4.85,
"learning_rate": 0.0002,
"loss": 1.721,
"step": 87000
},
{
"epoch": 4.88,
"learning_rate": 0.0002,
"loss": 1.7238,
"step": 87500
},
{
"epoch": 4.9,
"learning_rate": 0.0002,
"loss": 1.7318,
"step": 88000
},
{
"epoch": 4.93,
"learning_rate": 0.0002,
"loss": 1.7156,
"step": 88500
},
{
"epoch": 4.96,
"learning_rate": 0.0002,
"loss": 1.7298,
"step": 89000
},
{
"epoch": 4.99,
"learning_rate": 0.0002,
"loss": 1.7278,
"step": 89500
},
{
"epoch": 5.0,
"eval_gen_len": 18.999925194494313,
"eval_loss": 1.6149933338165283,
"eval_rouge1": 24.8219,
"eval_rouge2": 12.0279,
"eval_rougeL": 20.5184,
"eval_rougeLsum": 23.4296,
"eval_runtime": 448.4677,
"eval_samples_per_second": 29.808,
"eval_steps_per_second": 1.864,
"step": 89725
},
{
"epoch": 5.02,
"learning_rate": 0.0002,
"loss": 1.7079,
"step": 90000
},
{
"epoch": 5.04,
"learning_rate": 0.0002,
"loss": 1.6885,
"step": 90500
},
{
"epoch": 5.07,
"learning_rate": 0.0002,
"loss": 1.6936,
"step": 91000
},
{
"epoch": 5.1,
"learning_rate": 0.0002,
"loss": 1.6827,
"step": 91500
},
{
"epoch": 5.13,
"learning_rate": 0.0002,
"loss": 1.695,
"step": 92000
},
{
"epoch": 5.15,
"learning_rate": 0.0002,
"loss": 1.6886,
"step": 92500
},
{
"epoch": 5.18,
"learning_rate": 0.0002,
"loss": 1.6831,
"step": 93000
},
{
"epoch": 5.21,
"learning_rate": 0.0002,
"loss": 1.6954,
"step": 93500
},
{
"epoch": 5.24,
"learning_rate": 0.0002,
"loss": 1.7029,
"step": 94000
},
{
"epoch": 5.27,
"learning_rate": 0.0002,
"loss": 1.6941,
"step": 94500
},
{
"epoch": 5.29,
"learning_rate": 0.0002,
"loss": 1.6915,
"step": 95000
},
{
"epoch": 5.32,
"learning_rate": 0.0002,
"loss": 1.7156,
"step": 95500
},
{
"epoch": 5.35,
"learning_rate": 0.0002,
"loss": 1.6947,
"step": 96000
},
{
"epoch": 5.38,
"learning_rate": 0.0002,
"loss": 1.6842,
"step": 96500
},
{
"epoch": 5.41,
"learning_rate": 0.0002,
"loss": 1.7045,
"step": 97000
},
{
"epoch": 5.43,
"learning_rate": 0.0002,
"loss": 1.7061,
"step": 97500
},
{
"epoch": 5.46,
"learning_rate": 0.0002,
"loss": 1.7024,
"step": 98000
},
{
"epoch": 5.49,
"learning_rate": 0.0002,
"loss": 1.7083,
"step": 98500
},
{
"epoch": 5.52,
"learning_rate": 0.0002,
"loss": 1.6952,
"step": 99000
},
{
"epoch": 5.54,
"learning_rate": 0.0002,
"loss": 1.697,
"step": 99500
},
{
"epoch": 5.57,
"learning_rate": 0.0002,
"loss": 1.6924,
"step": 100000
},
{
"epoch": 5.6,
"learning_rate": 0.0002,
"loss": 1.6975,
"step": 100500
},
{
"epoch": 5.63,
"learning_rate": 0.0002,
"loss": 1.7028,
"step": 101000
},
{
"epoch": 5.66,
"learning_rate": 0.0002,
"loss": 1.7037,
"step": 101500
},
{
"epoch": 5.68,
"learning_rate": 0.0002,
"loss": 1.7058,
"step": 102000
},
{
"epoch": 5.71,
"learning_rate": 0.0002,
"loss": 1.6953,
"step": 102500
},
{
"epoch": 5.74,
"learning_rate": 0.0002,
"loss": 1.7029,
"step": 103000
},
{
"epoch": 5.77,
"learning_rate": 0.0002,
"loss": 1.702,
"step": 103500
},
{
"epoch": 5.8,
"learning_rate": 0.0002,
"loss": 1.702,
"step": 104000
},
{
"epoch": 5.82,
"learning_rate": 0.0002,
"loss": 1.686,
"step": 104500
},
{
"epoch": 5.85,
"learning_rate": 0.0002,
"loss": 1.6959,
"step": 105000
},
{
"epoch": 5.88,
"learning_rate": 0.0002,
"loss": 1.7055,
"step": 105500
},
{
"epoch": 5.91,
"learning_rate": 0.0002,
"loss": 1.6958,
"step": 106000
},
{
"epoch": 5.93,
"learning_rate": 0.0002,
"loss": 1.6956,
"step": 106500
},
{
"epoch": 5.96,
"learning_rate": 0.0002,
"loss": 1.7109,
"step": 107000
},
{
"epoch": 5.99,
"learning_rate": 0.0002,
"loss": 1.697,
"step": 107500
},
{
"epoch": 6.0,
"eval_gen_len": 18.999476361460204,
"eval_loss": 1.6058918237686157,
"eval_rouge1": 24.805,
"eval_rouge2": 11.8889,
"eval_rougeL": 20.4365,
"eval_rougeLsum": 23.3773,
"eval_runtime": 447.2273,
"eval_samples_per_second": 29.891,
"eval_steps_per_second": 1.869,
"step": 107670
},
{
"epoch": 6.02,
"learning_rate": 0.0002,
"loss": 1.6862,
"step": 108000
},
{
"epoch": 6.05,
"learning_rate": 0.0002,
"loss": 1.676,
"step": 108500
},
{
"epoch": 6.07,
"learning_rate": 0.0002,
"loss": 1.6714,
"step": 109000
},
{
"epoch": 6.1,
"learning_rate": 0.0002,
"loss": 1.656,
"step": 109500
},
{
"epoch": 6.13,
"learning_rate": 0.0002,
"loss": 1.6745,
"step": 110000
},
{
"epoch": 6.16,
"learning_rate": 0.0002,
"loss": 1.6902,
"step": 110500
},
{
"epoch": 6.19,
"learning_rate": 0.0002,
"loss": 1.6914,
"step": 111000
},
{
"epoch": 6.21,
"learning_rate": 0.0002,
"loss": 1.6644,
"step": 111500
},
{
"epoch": 6.24,
"learning_rate": 0.0002,
"loss": 1.6677,
"step": 112000
},
{
"epoch": 6.27,
"learning_rate": 0.0002,
"loss": 1.6827,
"step": 112500
},
{
"epoch": 6.3,
"learning_rate": 0.0002,
"loss": 1.662,
"step": 113000
},
{
"epoch": 6.32,
"learning_rate": 0.0002,
"loss": 1.6887,
"step": 113500
},
{
"epoch": 6.35,
"learning_rate": 0.0002,
"loss": 1.6824,
"step": 114000
},
{
"epoch": 6.38,
"learning_rate": 0.0002,
"loss": 1.6793,
"step": 114500
},
{
"epoch": 6.41,
"learning_rate": 0.0002,
"loss": 1.6769,
"step": 115000
},
{
"epoch": 6.44,
"learning_rate": 0.0002,
"loss": 1.6878,
"step": 115500
},
{
"epoch": 6.46,
"learning_rate": 0.0002,
"loss": 1.6842,
"step": 116000
},
{
"epoch": 6.49,
"learning_rate": 0.0002,
"loss": 1.6721,
"step": 116500
},
{
"epoch": 6.52,
"learning_rate": 0.0002,
"loss": 1.6733,
"step": 117000
},
{
"epoch": 6.55,
"learning_rate": 0.0002,
"loss": 1.6801,
"step": 117500
},
{
"epoch": 6.58,
"learning_rate": 0.0002,
"loss": 1.6846,
"step": 118000
},
{
"epoch": 6.6,
"learning_rate": 0.0002,
"loss": 1.6888,
"step": 118500
},
{
"epoch": 6.63,
"learning_rate": 0.0002,
"loss": 1.7039,
"step": 119000
},
{
"epoch": 6.66,
"learning_rate": 0.0002,
"loss": 1.6778,
"step": 119500
},
{
"epoch": 6.69,
"learning_rate": 0.0002,
"loss": 1.692,
"step": 120000
},
{
"epoch": 6.71,
"learning_rate": 0.0002,
"loss": 1.6817,
"step": 120500
},
{
"epoch": 6.74,
"learning_rate": 0.0002,
"loss": 1.6754,
"step": 121000
},
{
"epoch": 6.77,
"learning_rate": 0.0002,
"loss": 1.6711,
"step": 121500
},
{
"epoch": 6.8,
"learning_rate": 0.0002,
"loss": 1.6907,
"step": 122000
},
{
"epoch": 6.83,
"learning_rate": 0.0002,
"loss": 1.6883,
"step": 122500
},
{
"epoch": 6.85,
"learning_rate": 0.0002,
"loss": 1.6898,
"step": 123000
},
{
"epoch": 6.88,
"learning_rate": 0.0002,
"loss": 1.6816,
"step": 123500
},
{
"epoch": 6.91,
"learning_rate": 0.0002,
"loss": 1.6961,
"step": 124000
},
{
"epoch": 6.94,
"learning_rate": 0.0002,
"loss": 1.6935,
"step": 124500
},
{
"epoch": 6.97,
"learning_rate": 0.0002,
"loss": 1.7032,
"step": 125000
},
{
"epoch": 6.99,
"learning_rate": 0.0002,
"loss": 1.6958,
"step": 125500
},
{
"epoch": 7.0,
"eval_gen_len": 19.0,
"eval_loss": 1.6058346033096313,
"eval_rouge1": 24.681,
"eval_rouge2": 11.9144,
"eval_rougeL": 20.3968,
"eval_rougeLsum": 23.2841,
"eval_runtime": 449.9498,
"eval_samples_per_second": 29.71,
"eval_steps_per_second": 1.858,
"step": 125615
},
{
"epoch": 7.02,
"learning_rate": 0.0002,
"loss": 1.6566,
"step": 126000
},
{
"epoch": 7.05,
"learning_rate": 0.0002,
"loss": 1.6548,
"step": 126500
},
{
"epoch": 7.08,
"learning_rate": 0.0002,
"loss": 1.6567,
"step": 127000
},
{
"epoch": 7.11,
"learning_rate": 0.0002,
"loss": 1.6535,
"step": 127500
},
{
"epoch": 7.13,
"learning_rate": 0.0002,
"loss": 1.6547,
"step": 128000
},
{
"epoch": 7.16,
"learning_rate": 0.0002,
"loss": 1.662,
"step": 128500
},
{
"epoch": 7.19,
"learning_rate": 0.0002,
"loss": 1.655,
"step": 129000
},
{
"epoch": 7.22,
"learning_rate": 0.0002,
"loss": 1.6619,
"step": 129500
},
{
"epoch": 7.24,
"learning_rate": 0.0002,
"loss": 1.6679,
"step": 130000
},
{
"epoch": 7.27,
"learning_rate": 0.0002,
"loss": 1.6651,
"step": 130500
},
{
"epoch": 7.3,
"learning_rate": 0.0002,
"loss": 1.6544,
"step": 131000
},
{
"epoch": 7.33,
"learning_rate": 0.0002,
"loss": 1.6578,
"step": 131500
},
{
"epoch": 7.36,
"learning_rate": 0.0002,
"loss": 1.6588,
"step": 132000
},
{
"epoch": 7.38,
"learning_rate": 0.0002,
"loss": 1.66,
"step": 132500
},
{
"epoch": 7.41,
"learning_rate": 0.0002,
"loss": 1.6612,
"step": 133000
},
{
"epoch": 7.44,
"learning_rate": 0.0002,
"loss": 1.6628,
"step": 133500
},
{
"epoch": 7.47,
"learning_rate": 0.0002,
"loss": 1.6812,
"step": 134000
},
{
"epoch": 7.5,
"learning_rate": 0.0002,
"loss": 1.672,
"step": 134500
},
{
"epoch": 7.52,
"learning_rate": 0.0002,
"loss": 1.6726,
"step": 135000
},
{
"epoch": 7.55,
"learning_rate": 0.0002,
"loss": 1.6617,
"step": 135500
},
{
"epoch": 7.58,
"learning_rate": 0.0002,
"loss": 1.6611,
"step": 136000
},
{
"epoch": 7.61,
"learning_rate": 0.0002,
"loss": 1.6718,
"step": 136500
},
{
"epoch": 7.63,
"learning_rate": 0.0002,
"loss": 1.6741,
"step": 137000
},
{
"epoch": 7.66,
"learning_rate": 0.0002,
"loss": 1.6793,
"step": 137500
},
{
"epoch": 7.69,
"learning_rate": 0.0002,
"loss": 1.6813,
"step": 138000
},
{
"epoch": 7.72,
"learning_rate": 0.0002,
"loss": 1.6803,
"step": 138500
},
{
"epoch": 7.75,
"learning_rate": 0.0002,
"loss": 1.6739,
"step": 139000
},
{
"epoch": 7.77,
"learning_rate": 0.0002,
"loss": 1.6812,
"step": 139500
},
{
"epoch": 7.8,
"learning_rate": 0.0002,
"loss": 1.6691,
"step": 140000
},
{
"epoch": 7.83,
"learning_rate": 0.0002,
"loss": 1.6739,
"step": 140500
},
{
"epoch": 7.86,
"learning_rate": 0.0002,
"loss": 1.6766,
"step": 141000
},
{
"epoch": 7.89,
"learning_rate": 0.0002,
"loss": 1.6738,
"step": 141500
},
{
"epoch": 7.91,
"learning_rate": 0.0002,
"loss": 1.6701,
"step": 142000
},
{
"epoch": 7.94,
"learning_rate": 0.0002,
"loss": 1.695,
"step": 142500
},
{
"epoch": 7.97,
"learning_rate": 0.0002,
"loss": 1.6695,
"step": 143000
},
{
"epoch": 8.0,
"learning_rate": 0.0002,
"loss": 1.6775,
"step": 143500
},
{
"epoch": 8.0,
"eval_gen_len": 19.0,
"eval_loss": 1.6005198955535889,
"eval_rouge1": 24.7596,
"eval_rouge2": 11.9899,
"eval_rougeL": 20.4974,
"eval_rougeLsum": 23.348,
"eval_runtime": 449.6575,
"eval_samples_per_second": 29.729,
"eval_steps_per_second": 1.859,
"step": 143560
},
{
"epoch": 8.02,
"learning_rate": 0.0002,
"loss": 1.6455,
"step": 144000
},
{
"epoch": 8.05,
"learning_rate": 0.0002,
"loss": 1.6342,
"step": 144500
},
{
"epoch": 8.08,
"learning_rate": 0.0002,
"loss": 1.6436,
"step": 145000
},
{
"epoch": 8.11,
"learning_rate": 0.0002,
"loss": 1.6526,
"step": 145500
},
{
"epoch": 8.14,
"learning_rate": 0.0002,
"loss": 1.6589,
"step": 146000
},
{
"epoch": 8.16,
"learning_rate": 0.0002,
"loss": 1.6313,
"step": 146500
},
{
"epoch": 8.19,
"learning_rate": 0.0002,
"loss": 1.6459,
"step": 147000
},
{
"epoch": 8.22,
"learning_rate": 0.0002,
"loss": 1.6303,
"step": 147500
},
{
"epoch": 8.25,
"learning_rate": 0.0002,
"loss": 1.6508,
"step": 148000
},
{
"epoch": 8.28,
"learning_rate": 0.0002,
"loss": 1.6477,
"step": 148500
},
{
"epoch": 8.3,
"learning_rate": 0.0002,
"loss": 1.6498,
"step": 149000
},
{
"epoch": 8.33,
"learning_rate": 0.0002,
"loss": 1.6499,
"step": 149500
},
{
"epoch": 8.36,
"learning_rate": 0.0002,
"loss": 1.6563,
"step": 150000
},
{
"epoch": 8.39,
"learning_rate": 0.0002,
"loss": 1.6585,
"step": 150500
},
{
"epoch": 8.41,
"learning_rate": 0.0002,
"loss": 1.6575,
"step": 151000
},
{
"epoch": 8.44,
"learning_rate": 0.0002,
"loss": 1.6509,
"step": 151500
},
{
"epoch": 8.47,
"learning_rate": 0.0002,
"loss": 1.652,
"step": 152000
},
{
"epoch": 8.5,
"learning_rate": 0.0002,
"loss": 1.6571,
"step": 152500
},
{
"epoch": 8.53,
"learning_rate": 0.0002,
"loss": 1.6618,
"step": 153000
},
{
"epoch": 8.55,
"learning_rate": 0.0002,
"loss": 1.6592,
"step": 153500
},
{
"epoch": 8.58,
"learning_rate": 0.0002,
"loss": 1.6706,
"step": 154000
},
{
"epoch": 8.61,
"learning_rate": 0.0002,
"loss": 1.6716,
"step": 154500
},
{
"epoch": 8.64,
"learning_rate": 0.0002,
"loss": 1.663,
"step": 155000
},
{
"epoch": 8.67,
"learning_rate": 0.0002,
"loss": 1.6682,
"step": 155500
},
{
"epoch": 8.69,
"learning_rate": 0.0002,
"loss": 1.659,
"step": 156000
},
{
"epoch": 8.72,
"learning_rate": 0.0002,
"loss": 1.6524,
"step": 156500
},
{
"epoch": 8.75,
"learning_rate": 0.0002,
"loss": 1.658,
"step": 157000
},
{
"epoch": 8.78,
"learning_rate": 0.0002,
"loss": 1.6466,
"step": 157500
},
{
"epoch": 8.8,
"learning_rate": 0.0002,
"loss": 1.6558,
"step": 158000
},
{
"epoch": 8.83,
"learning_rate": 0.0002,
"loss": 1.6529,
"step": 158500
},
{
"epoch": 8.86,
"learning_rate": 0.0002,
"loss": 1.6567,
"step": 159000
},
{
"epoch": 8.89,
"learning_rate": 0.0002,
"loss": 1.6732,
"step": 159500
},
{
"epoch": 8.92,
"learning_rate": 0.0002,
"loss": 1.6501,
"step": 160000
},
{
"epoch": 8.94,
"learning_rate": 0.0002,
"loss": 1.6712,
"step": 160500
},
{
"epoch": 8.97,
"learning_rate": 0.0002,
"loss": 1.6611,
"step": 161000
},
{
"epoch": 9.0,
"learning_rate": 0.0002,
"loss": 1.6645,
"step": 161500
},
{
"epoch": 9.0,
"eval_gen_len": 18.99970077797726,
"eval_loss": 1.6074172258377075,
"eval_rouge1": 24.6775,
"eval_rouge2": 11.9459,
"eval_rougeL": 20.399,
"eval_rougeLsum": 23.2846,
"eval_runtime": 456.3741,
"eval_samples_per_second": 29.292,
"eval_steps_per_second": 1.832,
"step": 161505
},
{
"epoch": 9.03,
"learning_rate": 0.0002,
"loss": 1.6265,
"step": 162000
},
{
"epoch": 9.06,
"learning_rate": 0.0002,
"loss": 1.6223,
"step": 162500
},
{
"epoch": 9.08,
"learning_rate": 0.0002,
"loss": 1.6367,
"step": 163000
},
{
"epoch": 9.11,
"learning_rate": 0.0002,
"loss": 1.6434,
"step": 163500
},
{
"epoch": 9.14,
"learning_rate": 0.0002,
"loss": 1.6397,
"step": 164000
},
{
"epoch": 9.17,
"learning_rate": 0.0002,
"loss": 1.6336,
"step": 164500
},
{
"epoch": 9.19,
"learning_rate": 0.0002,
"loss": 1.6323,
"step": 165000
},
{
"epoch": 9.22,
"learning_rate": 0.0002,
"loss": 1.6275,
"step": 165500
},
{
"epoch": 9.25,
"learning_rate": 0.0002,
"loss": 1.6443,
"step": 166000
},
{
"epoch": 9.28,
"learning_rate": 0.0002,
"loss": 1.6409,
"step": 166500
},
{
"epoch": 9.31,
"learning_rate": 0.0002,
"loss": 1.627,
"step": 167000
},
{
"epoch": 9.33,
"learning_rate": 0.0002,
"loss": 1.6412,
"step": 167500
},
{
"epoch": 9.36,
"learning_rate": 0.0002,
"loss": 1.6458,
"step": 168000
},
{
"epoch": 9.39,
"learning_rate": 0.0002,
"loss": 1.6435,
"step": 168500
},
{
"epoch": 9.42,
"learning_rate": 0.0002,
"loss": 1.6358,
"step": 169000
},
{
"epoch": 9.45,
"learning_rate": 0.0002,
"loss": 1.6399,
"step": 169500
},
{
"epoch": 9.47,
"learning_rate": 0.0002,
"loss": 1.6505,
"step": 170000
},
{
"epoch": 9.5,
"learning_rate": 0.0002,
"loss": 1.6379,
"step": 170500
},
{
"epoch": 9.53,
"learning_rate": 0.0002,
"loss": 1.6499,
"step": 171000
},
{
"epoch": 9.56,
"learning_rate": 0.0002,
"loss": 1.6483,
"step": 171500
},
{
"epoch": 9.58,
"learning_rate": 0.0002,
"loss": 1.6383,
"step": 172000
},
{
"epoch": 9.61,
"learning_rate": 0.0002,
"loss": 1.6454,
"step": 172500
},
{
"epoch": 9.64,
"learning_rate": 0.0002,
"loss": 1.6448,
"step": 173000
},
{
"epoch": 9.67,
"learning_rate": 0.0002,
"loss": 1.6514,
"step": 173500
},
{
"epoch": 9.7,
"learning_rate": 0.0002,
"loss": 1.6443,
"step": 174000
},
{
"epoch": 9.72,
"learning_rate": 0.0002,
"loss": 1.638,
"step": 174500
},
{
"epoch": 9.75,
"learning_rate": 0.0002,
"loss": 1.6498,
"step": 175000
},
{
"epoch": 9.78,
"learning_rate": 0.0002,
"loss": 1.6509,
"step": 175500
},
{
"epoch": 9.81,
"learning_rate": 0.0002,
"loss": 1.6547,
"step": 176000
},
{
"epoch": 9.84,
"learning_rate": 0.0002,
"loss": 1.6608,
"step": 176500
},
{
"epoch": 9.86,
"learning_rate": 0.0002,
"loss": 1.6463,
"step": 177000
},
{
"epoch": 9.89,
"learning_rate": 0.0002,
"loss": 1.6448,
"step": 177500
},
{
"epoch": 9.92,
"learning_rate": 0.0002,
"loss": 1.6561,
"step": 178000
},
{
"epoch": 9.95,
"learning_rate": 0.0002,
"loss": 1.6552,
"step": 178500
},
{
"epoch": 9.97,
"learning_rate": 0.0002,
"loss": 1.6407,
"step": 179000
},
{
"epoch": 10.0,
"eval_gen_len": 18.999476361460204,
"eval_loss": 1.5967729091644287,
"eval_rouge1": 24.656,
"eval_rouge2": 11.8517,
"eval_rougeL": 20.3594,
"eval_rougeLsum": 23.2389,
"eval_runtime": 456.5734,
"eval_samples_per_second": 29.279,
"eval_steps_per_second": 1.831,
"step": 179450
},
{
"epoch": 10.0,
"learning_rate": 0.0002,
"loss": 1.6494,
"step": 179500
},
{
"epoch": 10.03,
"learning_rate": 0.0002,
"loss": 1.6164,
"step": 180000
},
{
"epoch": 10.06,
"learning_rate": 0.0002,
"loss": 1.6252,
"step": 180500
},
{
"epoch": 10.09,
"learning_rate": 0.0002,
"loss": 1.6265,
"step": 181000
},
{
"epoch": 10.11,
"learning_rate": 0.0002,
"loss": 1.6183,
"step": 181500
},
{
"epoch": 10.14,
"learning_rate": 0.0002,
"loss": 1.6226,
"step": 182000
},
{
"epoch": 10.17,
"learning_rate": 0.0002,
"loss": 1.6254,
"step": 182500
},
{
"epoch": 10.2,
"learning_rate": 0.0002,
"loss": 1.6194,
"step": 183000
},
{
"epoch": 10.23,
"learning_rate": 0.0002,
"loss": 1.6412,
"step": 183500
},
{
"epoch": 10.25,
"learning_rate": 0.0002,
"loss": 1.6343,
"step": 184000
},
{
"epoch": 10.28,
"learning_rate": 0.0002,
"loss": 1.6196,
"step": 184500
},
{
"epoch": 10.31,
"learning_rate": 0.0002,
"loss": 1.633,
"step": 185000
},
{
"epoch": 10.34,
"learning_rate": 0.0002,
"loss": 1.6364,
"step": 185500
},
{
"epoch": 10.37,
"learning_rate": 0.0002,
"loss": 1.6292,
"step": 186000
},
{
"epoch": 10.39,
"learning_rate": 0.0002,
"loss": 1.6323,
"step": 186500
},
{
"epoch": 10.42,
"learning_rate": 0.0002,
"loss": 1.6277,
"step": 187000
},
{
"epoch": 10.45,
"learning_rate": 0.0002,
"loss": 1.6355,
"step": 187500
},
{
"epoch": 10.48,
"learning_rate": 0.0002,
"loss": 1.638,
"step": 188000
},
{
"epoch": 10.5,
"learning_rate": 0.0002,
"loss": 1.6201,
"step": 188500
},
{
"epoch": 10.53,
"learning_rate": 0.0002,
"loss": 1.631,
"step": 189000
},
{
"epoch": 10.56,
"learning_rate": 0.0002,
"loss": 1.6277,
"step": 189500
},
{
"epoch": 10.59,
"learning_rate": 0.0002,
"loss": 1.6298,
"step": 190000
},
{
"epoch": 10.62,
"learning_rate": 0.0002,
"loss": 1.6296,
"step": 190500
},
{
"epoch": 10.64,
"learning_rate": 0.0002,
"loss": 1.6416,
"step": 191000
},
{
"epoch": 10.67,
"learning_rate": 0.0002,
"loss": 1.6289,
"step": 191500
},
{
"epoch": 10.7,
"learning_rate": 0.0002,
"loss": 1.6367,
"step": 192000
},
{
"epoch": 10.73,
"learning_rate": 0.0002,
"loss": 1.6303,
"step": 192500
},
{
"epoch": 10.76,
"learning_rate": 0.0002,
"loss": 1.6393,
"step": 193000
},
{
"epoch": 10.78,
"learning_rate": 0.0002,
"loss": 1.6386,
"step": 193500
},
{
"epoch": 10.81,
"learning_rate": 0.0002,
"loss": 1.6316,
"step": 194000
},
{
"epoch": 10.84,
"learning_rate": 0.0002,
"loss": 1.6289,
"step": 194500
},
{
"epoch": 10.87,
"learning_rate": 0.0002,
"loss": 1.6388,
"step": 195000
},
{
"epoch": 10.89,
"learning_rate": 0.0002,
"loss": 1.6427,
"step": 195500
},
{
"epoch": 10.92,
"learning_rate": 0.0002,
"loss": 1.6369,
"step": 196000
},
{
"epoch": 10.95,
"learning_rate": 0.0002,
"loss": 1.6496,
"step": 196500
},
{
"epoch": 10.98,
"learning_rate": 0.0002,
"loss": 1.6374,
"step": 197000
},
{
"epoch": 11.0,
"eval_gen_len": 19.0,
"eval_loss": 1.5931986570358276,
"eval_rouge1": 24.7416,
"eval_rouge2": 11.9481,
"eval_rougeL": 20.4574,
"eval_rougeLsum": 23.3066,
"eval_runtime": 457.3631,
"eval_samples_per_second": 29.228,
"eval_steps_per_second": 1.828,
"step": 197395
},
{
"epoch": 11.01,
"learning_rate": 0.0002,
"loss": 1.6378,
"step": 197500
},
{
"epoch": 11.03,
"learning_rate": 0.0002,
"loss": 1.5992,
"step": 198000
},
{
"epoch": 11.06,
"learning_rate": 0.0002,
"loss": 1.6045,
"step": 198500
},
{
"epoch": 11.09,
"learning_rate": 0.0002,
"loss": 1.62,
"step": 199000
},
{
"epoch": 11.12,
"learning_rate": 0.0002,
"loss": 1.6175,
"step": 199500
},
{
"epoch": 11.15,
"learning_rate": 0.0002,
"loss": 1.6088,
"step": 200000
},
{
"epoch": 11.17,
"learning_rate": 0.0002,
"loss": 1.621,
"step": 200500
},
{
"epoch": 11.2,
"learning_rate": 0.0002,
"loss": 1.6141,
"step": 201000
},
{
"epoch": 11.23,
"learning_rate": 0.0002,
"loss": 1.6128,
"step": 201500
},
{
"epoch": 11.26,
"learning_rate": 0.0002,
"loss": 1.6225,
"step": 202000
},
{
"epoch": 11.28,
"learning_rate": 0.0002,
"loss": 1.6256,
"step": 202500
},
{
"epoch": 11.31,
"learning_rate": 0.0002,
"loss": 1.6125,
"step": 203000
},
{
"epoch": 11.34,
"learning_rate": 0.0002,
"loss": 1.6072,
"step": 203500
},
{
"epoch": 11.37,
"learning_rate": 0.0002,
"loss": 1.6201,
"step": 204000
},
{
"epoch": 11.4,
"learning_rate": 0.0002,
"loss": 1.6249,
"step": 204500
},
{
"epoch": 11.42,
"learning_rate": 0.0002,
"loss": 1.6256,
"step": 205000
},
{
"epoch": 11.45,
"learning_rate": 0.0002,
"loss": 1.6206,
"step": 205500
},
{
"epoch": 11.48,
"learning_rate": 0.0002,
"loss": 1.6225,
"step": 206000
},
{
"epoch": 11.51,
"learning_rate": 0.0002,
"loss": 1.6235,
"step": 206500
},
{
"epoch": 11.54,
"learning_rate": 0.0002,
"loss": 1.6141,
"step": 207000
},
{
"epoch": 11.56,
"learning_rate": 0.0002,
"loss": 1.6187,
"step": 207500
},
{
"epoch": 11.59,
"learning_rate": 0.0002,
"loss": 1.6153,
"step": 208000
},
{
"epoch": 11.62,
"learning_rate": 0.0002,
"loss": 1.6199,
"step": 208500
},
{
"epoch": 11.65,
"learning_rate": 0.0002,
"loss": 1.6241,
"step": 209000
},
{
"epoch": 11.67,
"learning_rate": 0.0002,
"loss": 1.6261,
"step": 209500
},
{
"epoch": 11.7,
"learning_rate": 0.0002,
"loss": 1.6362,
"step": 210000
},
{
"epoch": 11.73,
"learning_rate": 0.0002,
"loss": 1.6244,
"step": 210500
},
{
"epoch": 11.76,
"learning_rate": 0.0002,
"loss": 1.629,
"step": 211000
},
{
"epoch": 11.79,
"learning_rate": 0.0002,
"loss": 1.6307,
"step": 211500
},
{
"epoch": 11.81,
"learning_rate": 0.0002,
"loss": 1.628,
"step": 212000
},
{
"epoch": 11.84,
"learning_rate": 0.0002,
"loss": 1.6357,
"step": 212500
},
{
"epoch": 11.87,
"learning_rate": 0.0002,
"loss": 1.6163,
"step": 213000
},
{
"epoch": 11.9,
"learning_rate": 0.0002,
"loss": 1.6386,
"step": 213500
},
{
"epoch": 11.93,
"learning_rate": 0.0002,
"loss": 1.6352,
"step": 214000
},
{
"epoch": 11.95,
"learning_rate": 0.0002,
"loss": 1.6115,
"step": 214500
},
{
"epoch": 11.98,
"learning_rate": 0.0002,
"loss": 1.6271,
"step": 215000
},
{
"epoch": 12.0,
"eval_gen_len": 18.99985038898863,
"eval_loss": 1.5888069868087769,
"eval_rouge1": 24.8074,
"eval_rouge2": 11.9491,
"eval_rougeL": 20.4824,
"eval_rougeLsum": 23.3506,
"eval_runtime": 456.7914,
"eval_samples_per_second": 29.265,
"eval_steps_per_second": 1.83,
"step": 215340
},
{
"epoch": 12.01,
"learning_rate": 0.0002,
"loss": 1.6147,
"step": 215500
},
{
"epoch": 12.04,
"learning_rate": 0.0002,
"loss": 1.5915,
"step": 216000
},
{
"epoch": 12.06,
"learning_rate": 0.0002,
"loss": 1.5979,
"step": 216500
},
{
"epoch": 12.09,
"learning_rate": 0.0002,
"loss": 1.6021,
"step": 217000
},
{
"epoch": 12.12,
"learning_rate": 0.0002,
"loss": 1.5977,
"step": 217500
},
{
"epoch": 12.15,
"learning_rate": 0.0002,
"loss": 1.5964,
"step": 218000
},
{
"epoch": 12.18,
"learning_rate": 0.0002,
"loss": 1.6177,
"step": 218500
},
{
"epoch": 12.2,
"learning_rate": 0.0002,
"loss": 1.6073,
"step": 219000
},
{
"epoch": 12.23,
"learning_rate": 0.0002,
"loss": 1.6066,
"step": 219500
},
{
"epoch": 12.26,
"learning_rate": 0.0002,
"loss": 1.6143,
"step": 220000
},
{
"epoch": 12.29,
"learning_rate": 0.0002,
"loss": 1.6164,
"step": 220500
},
{
"epoch": 12.32,
"learning_rate": 0.0002,
"loss": 1.6209,
"step": 221000
},
{
"epoch": 12.34,
"learning_rate": 0.0002,
"loss": 1.6087,
"step": 221500
},
{
"epoch": 12.37,
"learning_rate": 0.0002,
"loss": 1.6054,
"step": 222000
},
{
"epoch": 12.4,
"learning_rate": 0.0002,
"loss": 1.6027,
"step": 222500
},
{
"epoch": 12.43,
"learning_rate": 0.0002,
"loss": 1.6046,
"step": 223000
},
{
"epoch": 12.45,
"learning_rate": 0.0002,
"loss": 1.6215,
"step": 223500
},
{
"epoch": 12.48,
"learning_rate": 0.0002,
"loss": 1.6248,
"step": 224000
},
{
"epoch": 12.51,
"learning_rate": 0.0002,
"loss": 1.6108,
"step": 224500
},
{
"epoch": 12.54,
"learning_rate": 0.0002,
"loss": 1.6,
"step": 225000
},
{
"epoch": 12.57,
"learning_rate": 0.0002,
"loss": 1.6064,
"step": 225500
},
{
"epoch": 12.59,
"learning_rate": 0.0002,
"loss": 1.6167,
"step": 226000
},
{
"epoch": 12.62,
"learning_rate": 0.0002,
"loss": 1.6142,
"step": 226500
},
{
"epoch": 12.65,
"learning_rate": 0.0002,
"loss": 1.607,
"step": 227000
},
{
"epoch": 12.68,
"learning_rate": 0.0002,
"loss": 1.6158,
"step": 227500
},
{
"epoch": 12.71,
"learning_rate": 0.0002,
"loss": 1.6143,
"step": 228000
},
{
"epoch": 12.73,
"learning_rate": 0.0002,
"loss": 1.6205,
"step": 228500
},
{
"epoch": 12.76,
"learning_rate": 0.0002,
"loss": 1.6165,
"step": 229000
},
{
"epoch": 12.79,
"learning_rate": 0.0002,
"loss": 1.6225,
"step": 229500
},
{
"epoch": 12.82,
"learning_rate": 0.0002,
"loss": 1.6285,
"step": 230000
},
{
"epoch": 12.84,
"learning_rate": 0.0002,
"loss": 1.6028,
"step": 230500
},
{
"epoch": 12.87,
"learning_rate": 0.0002,
"loss": 1.6147,
"step": 231000
},
{
"epoch": 12.9,
"learning_rate": 0.0002,
"loss": 1.608,
"step": 231500
},
{
"epoch": 12.93,
"learning_rate": 0.0002,
"loss": 1.6281,
"step": 232000
},
{
"epoch": 12.96,
"learning_rate": 0.0002,
"loss": 1.6259,
"step": 232500
},
{
"epoch": 12.98,
"learning_rate": 0.0002,
"loss": 1.6069,
"step": 233000
},
{
"epoch": 13.0,
"eval_gen_len": 18.999925194494313,
"eval_loss": 1.5894633531570435,
"eval_rouge1": 24.7893,
"eval_rouge2": 11.8992,
"eval_rougeL": 20.4586,
"eval_rougeLsum": 23.3777,
"eval_runtime": 454.974,
"eval_samples_per_second": 29.382,
"eval_steps_per_second": 1.837,
"step": 233285
},
{
"epoch": 13.01,
"learning_rate": 0.0002,
"loss": 1.6016,
"step": 233500
},
{
"epoch": 13.04,
"learning_rate": 0.0002,
"loss": 1.5842,
"step": 234000
},
{
"epoch": 13.07,
"learning_rate": 0.0002,
"loss": 1.5848,
"step": 234500
},
{
"epoch": 13.1,
"learning_rate": 0.0002,
"loss": 1.5831,
"step": 235000
},
{
"epoch": 13.12,
"learning_rate": 0.0002,
"loss": 1.5997,
"step": 235500
},
{
"epoch": 13.15,
"learning_rate": 0.0002,
"loss": 1.611,
"step": 236000
},
{
"epoch": 13.18,
"learning_rate": 0.0002,
"loss": 1.5924,
"step": 236500
},
{
"epoch": 13.21,
"learning_rate": 0.0002,
"loss": 1.5971,
"step": 237000
},
{
"epoch": 13.23,
"learning_rate": 0.0002,
"loss": 1.602,
"step": 237500
},
{
"epoch": 13.26,
"learning_rate": 0.0002,
"loss": 1.605,
"step": 238000
},
{
"epoch": 13.29,
"learning_rate": 0.0002,
"loss": 1.5989,
"step": 238500
},
{
"epoch": 13.32,
"learning_rate": 0.0002,
"loss": 1.6018,
"step": 239000
},
{
"epoch": 13.35,
"learning_rate": 0.0002,
"loss": 1.5973,
"step": 239500
},
{
"epoch": 13.37,
"learning_rate": 0.0002,
"loss": 1.5923,
"step": 240000
},
{
"epoch": 13.4,
"learning_rate": 0.0002,
"loss": 1.5977,
"step": 240500
},
{
"epoch": 13.43,
"learning_rate": 0.0002,
"loss": 1.6096,
"step": 241000
},
{
"epoch": 13.46,
"learning_rate": 0.0002,
"loss": 1.5989,
"step": 241500
},
{
"epoch": 13.49,
"learning_rate": 0.0002,
"loss": 1.6125,
"step": 242000
},
{
"epoch": 13.51,
"learning_rate": 0.0002,
"loss": 1.5945,
"step": 242500
},
{
"epoch": 13.54,
"learning_rate": 0.0002,
"loss": 1.607,
"step": 243000
},
{
"epoch": 13.57,
"learning_rate": 0.0002,
"loss": 1.6113,
"step": 243500
},
{
"epoch": 13.6,
"learning_rate": 0.0002,
"loss": 1.6116,
"step": 244000
},
{
"epoch": 13.62,
"learning_rate": 0.0002,
"loss": 1.611,
"step": 244500
},
{
"epoch": 13.65,
"learning_rate": 0.0002,
"loss": 1.6075,
"step": 245000
},
{
"epoch": 13.68,
"learning_rate": 0.0002,
"loss": 1.6051,
"step": 245500
},
{
"epoch": 13.71,
"learning_rate": 0.0002,
"loss": 1.6178,
"step": 246000
},
{
"epoch": 13.74,
"learning_rate": 0.0002,
"loss": 1.6016,
"step": 246500
},
{
"epoch": 13.76,
"learning_rate": 0.0002,
"loss": 1.6053,
"step": 247000
},
{
"epoch": 13.79,
"learning_rate": 0.0002,
"loss": 1.5952,
"step": 247500
},
{
"epoch": 13.82,
"learning_rate": 0.0002,
"loss": 1.6014,
"step": 248000
},
{
"epoch": 13.85,
"learning_rate": 0.0002,
"loss": 1.6135,
"step": 248500
},
{
"epoch": 13.88,
"learning_rate": 0.0002,
"loss": 1.607,
"step": 249000
},
{
"epoch": 13.9,
"learning_rate": 0.0002,
"loss": 1.6075,
"step": 249500
},
{
"epoch": 13.93,
"learning_rate": 0.0002,
"loss": 1.6,
"step": 250000
},
{
"epoch": 13.96,
"learning_rate": 0.0002,
"loss": 1.6118,
"step": 250500
},
{
"epoch": 13.99,
"learning_rate": 0.0002,
"loss": 1.6161,
"step": 251000
},
{
"epoch": 14.0,
"eval_gen_len": 18.99985038898863,
"eval_loss": 1.595921516418457,
"eval_rouge1": 24.7781,
"eval_rouge2": 11.9972,
"eval_rougeL": 20.528,
"eval_rougeLsum": 23.3812,
"eval_runtime": 455.5258,
"eval_samples_per_second": 29.346,
"eval_steps_per_second": 1.835,
"step": 251230
},
{
"epoch": 14.02,
"learning_rate": 0.0002,
"loss": 1.5911,
"step": 251500
},
{
"epoch": 14.04,
"learning_rate": 0.0002,
"loss": 1.5784,
"step": 252000
},
{
"epoch": 14.07,
"learning_rate": 0.0002,
"loss": 1.5951,
"step": 252500
},
{
"epoch": 14.1,
"learning_rate": 0.0002,
"loss": 1.5895,
"step": 253000
},
{
"epoch": 14.13,
"learning_rate": 0.0002,
"loss": 1.5816,
"step": 253500
},
{
"epoch": 14.15,
"learning_rate": 0.0002,
"loss": 1.5841,
"step": 254000
},
{
"epoch": 14.18,
"learning_rate": 0.0002,
"loss": 1.5853,
"step": 254500
},
{
"epoch": 14.21,
"learning_rate": 0.0002,
"loss": 1.6008,
"step": 255000
},
{
"epoch": 14.24,
"learning_rate": 0.0002,
"loss": 1.5872,
"step": 255500
},
{
"epoch": 14.27,
"learning_rate": 0.0002,
"loss": 1.5905,
"step": 256000
},
{
"epoch": 14.29,
"learning_rate": 0.0002,
"loss": 1.5932,
"step": 256500
},
{
"epoch": 14.32,
"learning_rate": 0.0002,
"loss": 1.5858,
"step": 257000
},
{
"epoch": 14.35,
"learning_rate": 0.0002,
"loss": 1.599,
"step": 257500
},
{
"epoch": 14.38,
"learning_rate": 0.0002,
"loss": 1.5923,
"step": 258000
},
{
"epoch": 14.41,
"learning_rate": 0.0002,
"loss": 1.5867,
"step": 258500
},
{
"epoch": 14.43,
"learning_rate": 0.0002,
"loss": 1.5827,
"step": 259000
},
{
"epoch": 14.46,
"learning_rate": 0.0002,
"loss": 1.5939,
"step": 259500
},
{
"epoch": 14.49,
"learning_rate": 0.0002,
"loss": 1.5957,
"step": 260000
},
{
"epoch": 14.52,
"learning_rate": 0.0002,
"loss": 1.604,
"step": 260500
},
{
"epoch": 14.54,
"learning_rate": 0.0002,
"loss": 1.5808,
"step": 261000
},
{
"epoch": 14.57,
"learning_rate": 0.0002,
"loss": 1.5959,
"step": 261500
},
{
"epoch": 14.6,
"learning_rate": 0.0002,
"loss": 1.5903,
"step": 262000
},
{
"epoch": 14.63,
"learning_rate": 0.0002,
"loss": 1.5961,
"step": 262500
},
{
"epoch": 14.66,
"learning_rate": 0.0002,
"loss": 1.6006,
"step": 263000
},
{
"epoch": 14.68,
"learning_rate": 0.0002,
"loss": 1.6035,
"step": 263500
},
{
"epoch": 14.71,
"learning_rate": 0.0002,
"loss": 1.591,
"step": 264000
},
{
"epoch": 14.74,
"learning_rate": 0.0002,
"loss": 1.598,
"step": 264500
},
{
"epoch": 14.77,
"learning_rate": 0.0002,
"loss": 1.5885,
"step": 265000
},
{
"epoch": 14.8,
"learning_rate": 0.0002,
"loss": 1.6016,
"step": 265500
},
{
"epoch": 14.82,
"learning_rate": 0.0002,
"loss": 1.5957,
"step": 266000
},
{
"epoch": 14.85,
"learning_rate": 0.0002,
"loss": 1.5909,
"step": 266500
},
{
"epoch": 14.88,
"learning_rate": 0.0002,
"loss": 1.6083,
"step": 267000
},
{
"epoch": 14.91,
"learning_rate": 0.0002,
"loss": 1.5981,
"step": 267500
},
{
"epoch": 14.93,
"learning_rate": 0.0002,
"loss": 1.5951,
"step": 268000
},
{
"epoch": 14.96,
"learning_rate": 0.0002,
"loss": 1.608,
"step": 268500
},
{
"epoch": 14.99,
"learning_rate": 0.0002,
"loss": 1.6085,
"step": 269000
},
{
"epoch": 15.0,
"eval_gen_len": 18.999925194494313,
"eval_loss": 1.5895360708236694,
"eval_rouge1": 24.7245,
"eval_rouge2": 12.0165,
"eval_rougeL": 20.4687,
"eval_rougeLsum": 23.3264,
"eval_runtime": 455.5133,
"eval_samples_per_second": 29.347,
"eval_steps_per_second": 1.835,
"step": 269175
},
{
"epoch": 15.02,
"learning_rate": 0.0002,
"loss": 1.5819,
"step": 269500
},
{
"epoch": 15.05,
"learning_rate": 0.0002,
"loss": 1.5829,
"step": 270000
},
{
"epoch": 15.07,
"learning_rate": 0.0002,
"loss": 1.5706,
"step": 270500
},
{
"epoch": 15.1,
"learning_rate": 0.0002,
"loss": 1.5773,
"step": 271000
},
{
"epoch": 15.13,
"learning_rate": 0.0002,
"loss": 1.5853,
"step": 271500
},
{
"epoch": 15.16,
"learning_rate": 0.0002,
"loss": 1.5695,
"step": 272000
},
{
"epoch": 15.19,
"learning_rate": 0.0002,
"loss": 1.5754,
"step": 272500
},
{
"epoch": 15.21,
"learning_rate": 0.0002,
"loss": 1.5814,
"step": 273000
},
{
"epoch": 15.24,
"learning_rate": 0.0002,
"loss": 1.5754,
"step": 273500
},
{
"epoch": 15.27,
"learning_rate": 0.0002,
"loss": 1.5761,
"step": 274000
},
{
"epoch": 15.3,
"learning_rate": 0.0002,
"loss": 1.5771,
"step": 274500
},
{
"epoch": 15.32,
"learning_rate": 0.0002,
"loss": 1.5822,
"step": 275000
},
{
"epoch": 15.35,
"learning_rate": 0.0002,
"loss": 1.5791,
"step": 275500
},
{
"epoch": 15.38,
"learning_rate": 0.0002,
"loss": 1.5969,
"step": 276000
},
{
"epoch": 15.41,
"learning_rate": 0.0002,
"loss": 1.5833,
"step": 276500
},
{
"epoch": 15.44,
"learning_rate": 0.0002,
"loss": 1.5827,
"step": 277000
},
{
"epoch": 15.46,
"learning_rate": 0.0002,
"loss": 1.582,
"step": 277500
},
{
"epoch": 15.49,
"learning_rate": 0.0002,
"loss": 1.5845,
"step": 278000
},
{
"epoch": 15.52,
"learning_rate": 0.0002,
"loss": 1.5911,
"step": 278500
},
{
"epoch": 15.55,
"learning_rate": 0.0002,
"loss": 1.5941,
"step": 279000
},
{
"epoch": 15.58,
"learning_rate": 0.0002,
"loss": 1.6005,
"step": 279500
},
{
"epoch": 15.6,
"learning_rate": 0.0002,
"loss": 1.5797,
"step": 280000
},
{
"epoch": 15.63,
"learning_rate": 0.0002,
"loss": 1.5917,
"step": 280500
},
{
"epoch": 15.66,
"learning_rate": 0.0002,
"loss": 1.5978,
"step": 281000
},
{
"epoch": 15.69,
"learning_rate": 0.0002,
"loss": 1.5856,
"step": 281500
},
{
"epoch": 15.71,
"learning_rate": 0.0002,
"loss": 1.5882,
"step": 282000
},
{
"epoch": 15.74,
"learning_rate": 0.0002,
"loss": 1.5849,
"step": 282500
},
{
"epoch": 15.77,
"learning_rate": 0.0002,
"loss": 1.5887,
"step": 283000
},
{
"epoch": 15.8,
"learning_rate": 0.0002,
"loss": 1.5889,
"step": 283500
},
{
"epoch": 15.83,
"learning_rate": 0.0002,
"loss": 1.5852,
"step": 284000
},
{
"epoch": 15.85,
"learning_rate": 0.0002,
"loss": 1.5997,
"step": 284500
},
{
"epoch": 15.88,
"learning_rate": 0.0002,
"loss": 1.596,
"step": 285000
},
{
"epoch": 15.91,
"learning_rate": 0.0002,
"loss": 1.5869,
"step": 285500
},
{
"epoch": 15.94,
"learning_rate": 0.0002,
"loss": 1.5904,
"step": 286000
},
{
"epoch": 15.97,
"learning_rate": 0.0002,
"loss": 1.586,
"step": 286500
},
{
"epoch": 15.99,
"learning_rate": 0.0002,
"loss": 1.5874,
"step": 287000
},
{
"epoch": 16.0,
"eval_gen_len": 18.999925194494313,
"eval_loss": 1.5896196365356445,
"eval_rouge1": 24.6479,
"eval_rouge2": 11.9044,
"eval_rougeL": 20.357,
"eval_rougeLsum": 23.2246,
"eval_runtime": 457.4929,
"eval_samples_per_second": 29.22,
"eval_steps_per_second": 1.827,
"step": 287120
},
{
"epoch": 16.02,
"learning_rate": 0.0002,
"loss": 1.563,
"step": 287500
},
{
"epoch": 16.05,
"learning_rate": 0.0002,
"loss": 1.5579,
"step": 288000
},
{
"epoch": 16.08,
"learning_rate": 0.0002,
"loss": 1.565,
"step": 288500
},
{
"epoch": 16.1,
"learning_rate": 0.0002,
"loss": 1.5685,
"step": 289000
},
{
"epoch": 16.13,
"learning_rate": 0.0002,
"loss": 1.5732,
"step": 289500
},
{
"epoch": 16.16,
"learning_rate": 0.0002,
"loss": 1.57,
"step": 290000
},
{
"epoch": 16.19,
"learning_rate": 0.0002,
"loss": 1.5724,
"step": 290500
},
{
"epoch": 16.22,
"learning_rate": 0.0002,
"loss": 1.5858,
"step": 291000
},
{
"epoch": 16.24,
"learning_rate": 0.0002,
"loss": 1.5675,
"step": 291500
},
{
"epoch": 16.27,
"learning_rate": 0.0002,
"loss": 1.5711,
"step": 292000
},
{
"epoch": 16.3,
"learning_rate": 0.0002,
"loss": 1.5711,
"step": 292500
},
{
"epoch": 16.33,
"learning_rate": 0.0002,
"loss": 1.5695,
"step": 293000
},
{
"epoch": 16.36,
"learning_rate": 0.0002,
"loss": 1.5673,
"step": 293500
},
{
"epoch": 16.38,
"learning_rate": 0.0002,
"loss": 1.58,
"step": 294000
},
{
"epoch": 16.41,
"learning_rate": 0.0002,
"loss": 1.5585,
"step": 294500
},
{
"epoch": 16.44,
"learning_rate": 0.0002,
"loss": 1.5959,
"step": 295000
},
{
"epoch": 16.47,
"learning_rate": 0.0002,
"loss": 1.5816,
"step": 295500
},
{
"epoch": 16.49,
"learning_rate": 0.0002,
"loss": 1.589,
"step": 296000
},
{
"epoch": 16.52,
"learning_rate": 0.0002,
"loss": 1.579,
"step": 296500
},
{
"epoch": 16.55,
"learning_rate": 0.0002,
"loss": 1.5806,
"step": 297000
},
{
"epoch": 16.58,
"learning_rate": 0.0002,
"loss": 1.5735,
"step": 297500
},
{
"epoch": 16.61,
"learning_rate": 0.0002,
"loss": 1.5772,
"step": 298000
},
{
"epoch": 16.63,
"learning_rate": 0.0002,
"loss": 1.5707,
"step": 298500
},
{
"epoch": 16.66,
"learning_rate": 0.0002,
"loss": 1.5749,
"step": 299000
},
{
"epoch": 16.69,
"learning_rate": 0.0002,
"loss": 1.5837,
"step": 299500
},
{
"epoch": 16.72,
"learning_rate": 0.0002,
"loss": 1.5848,
"step": 300000
},
{
"epoch": 16.75,
"learning_rate": 0.0002,
"loss": 1.5859,
"step": 300500
},
{
"epoch": 16.77,
"learning_rate": 0.0002,
"loss": 1.5755,
"step": 301000
},
{
"epoch": 16.8,
"learning_rate": 0.0002,
"loss": 1.5761,
"step": 301500
},
{
"epoch": 16.83,
"learning_rate": 0.0002,
"loss": 1.5726,
"step": 302000
},
{
"epoch": 16.86,
"learning_rate": 0.0002,
"loss": 1.5777,
"step": 302500
},
{
"epoch": 16.88,
"learning_rate": 0.0002,
"loss": 1.5935,
"step": 303000
},
{
"epoch": 16.91,
"learning_rate": 0.0002,
"loss": 1.5891,
"step": 303500
},
{
"epoch": 16.94,
"learning_rate": 0.0002,
"loss": 1.5844,
"step": 304000
},
{
"epoch": 16.97,
"learning_rate": 0.0002,
"loss": 1.587,
"step": 304500
},
{
"epoch": 17.0,
"learning_rate": 0.0002,
"loss": 1.5963,
"step": 305000
},
{
"epoch": 17.0,
"eval_gen_len": 18.99985038898863,
"eval_loss": 1.5875639915466309,
"eval_rouge1": 24.8499,
"eval_rouge2": 12.0533,
"eval_rougeL": 20.5578,
"eval_rougeLsum": 23.4369,
"eval_runtime": 454.7479,
"eval_samples_per_second": 29.397,
"eval_steps_per_second": 1.838,
"step": 305065
},
{
"epoch": 17.02,
"learning_rate": 0.0002,
"loss": 1.5646,
"step": 305500
},
{
"epoch": 17.05,
"learning_rate": 0.0002,
"loss": 1.5419,
"step": 306000
},
{
"epoch": 17.08,
"learning_rate": 0.0002,
"loss": 1.5507,
"step": 306500
},
{
"epoch": 17.11,
"learning_rate": 0.0002,
"loss": 1.5575,
"step": 307000
},
{
"epoch": 17.14,
"learning_rate": 0.0002,
"loss": 1.5638,
"step": 307500
},
{
"epoch": 17.16,
"learning_rate": 0.0002,
"loss": 1.5664,
"step": 308000
},
{
"epoch": 17.19,
"learning_rate": 0.0002,
"loss": 1.5498,
"step": 308500
},
{
"epoch": 17.22,
"learning_rate": 0.0002,
"loss": 1.5623,
"step": 309000
},
{
"epoch": 17.25,
"learning_rate": 0.0002,
"loss": 1.5609,
"step": 309500
},
{
"epoch": 17.28,
"learning_rate": 0.0002,
"loss": 1.5647,
"step": 310000
},
{
"epoch": 17.3,
"learning_rate": 0.0002,
"loss": 1.566,
"step": 310500
},
{
"epoch": 17.33,
"learning_rate": 0.0002,
"loss": 1.5685,
"step": 311000
},
{
"epoch": 17.36,
"learning_rate": 0.0002,
"loss": 1.563,
"step": 311500
},
{
"epoch": 17.39,
"learning_rate": 0.0002,
"loss": 1.5685,
"step": 312000
},
{
"epoch": 17.41,
"learning_rate": 0.0002,
"loss": 1.5675,
"step": 312500
},
{
"epoch": 17.44,
"learning_rate": 0.0002,
"loss": 1.5798,
"step": 313000
},
{
"epoch": 17.47,
"learning_rate": 0.0002,
"loss": 1.5784,
"step": 313500
},
{
"epoch": 17.5,
"learning_rate": 0.0002,
"loss": 1.5672,
"step": 314000
},
{
"epoch": 17.53,
"learning_rate": 0.0002,
"loss": 1.5636,
"step": 314500
},
{
"epoch": 17.55,
"learning_rate": 0.0002,
"loss": 1.5748,
"step": 315000
},
{
"epoch": 17.58,
"learning_rate": 0.0002,
"loss": 1.5745,
"step": 315500
},
{
"epoch": 17.61,
"learning_rate": 0.0002,
"loss": 1.571,
"step": 316000
},
{
"epoch": 17.64,
"learning_rate": 0.0002,
"loss": 1.5817,
"step": 316500
},
{
"epoch": 17.67,
"learning_rate": 0.0002,
"loss": 1.5717,
"step": 317000
},
{
"epoch": 17.69,
"learning_rate": 0.0002,
"loss": 1.5713,
"step": 317500
},
{
"epoch": 17.72,
"learning_rate": 0.0002,
"loss": 1.567,
"step": 318000
},
{
"epoch": 17.75,
"learning_rate": 0.0002,
"loss": 1.5712,
"step": 318500
},
{
"epoch": 17.78,
"learning_rate": 0.0002,
"loss": 1.5778,
"step": 319000
},
{
"epoch": 17.8,
"learning_rate": 0.0002,
"loss": 1.5687,
"step": 319500
},
{
"epoch": 17.83,
"learning_rate": 0.0002,
"loss": 1.584,
"step": 320000
},
{
"epoch": 17.86,
"learning_rate": 0.0002,
"loss": 1.5823,
"step": 320500
},
{
"epoch": 17.89,
"learning_rate": 0.0002,
"loss": 1.5791,
"step": 321000
},
{
"epoch": 17.92,
"learning_rate": 0.0002,
"loss": 1.5743,
"step": 321500
},
{
"epoch": 17.94,
"learning_rate": 0.0002,
"loss": 1.5762,
"step": 322000
},
{
"epoch": 17.97,
"learning_rate": 0.0002,
"loss": 1.5777,
"step": 322500
},
{
"epoch": 18.0,
"learning_rate": 0.0002,
"loss": 1.5884,
"step": 323000
},
{
"epoch": 18.0,
"eval_gen_len": 18.999625972471573,
"eval_loss": 1.5868136882781982,
"eval_rouge1": 24.8052,
"eval_rouge2": 12.0432,
"eval_rougeL": 20.5093,
"eval_rougeLsum": 23.3853,
"eval_runtime": 453.6378,
"eval_samples_per_second": 29.468,
"eval_steps_per_second": 1.843,
"step": 323010
},
{
"epoch": 18.03,
"learning_rate": 0.0002,
"loss": 1.5496,
"step": 323500
},
{
"epoch": 18.06,
"learning_rate": 0.0002,
"loss": 1.5482,
"step": 324000
},
{
"epoch": 18.08,
"learning_rate": 0.0002,
"loss": 1.5439,
"step": 324500
},
{
"epoch": 18.11,
"learning_rate": 0.0002,
"loss": 1.5517,
"step": 325000
},
{
"epoch": 18.14,
"learning_rate": 0.0002,
"loss": 1.5523,
"step": 325500
},
{
"epoch": 18.17,
"learning_rate": 0.0002,
"loss": 1.5683,
"step": 326000
},
{
"epoch": 18.19,
"learning_rate": 0.0002,
"loss": 1.5628,
"step": 326500
},
{
"epoch": 18.22,
"learning_rate": 0.0002,
"loss": 1.5485,
"step": 327000
},
{
"epoch": 18.25,
"learning_rate": 0.0002,
"loss": 1.5628,
"step": 327500
},
{
"epoch": 18.28,
"learning_rate": 0.0002,
"loss": 1.5538,
"step": 328000
},
{
"epoch": 18.31,
"learning_rate": 0.0002,
"loss": 1.5706,
"step": 328500
},
{
"epoch": 18.33,
"learning_rate": 0.0002,
"loss": 1.5614,
"step": 329000
},
{
"epoch": 18.36,
"learning_rate": 0.0002,
"loss": 1.5634,
"step": 329500
},
{
"epoch": 18.39,
"learning_rate": 0.0002,
"loss": 1.5653,
"step": 330000
},
{
"epoch": 18.42,
"learning_rate": 0.0002,
"loss": 1.5546,
"step": 330500
},
{
"epoch": 18.45,
"learning_rate": 0.0002,
"loss": 1.5501,
"step": 331000
},
{
"epoch": 18.47,
"learning_rate": 0.0002,
"loss": 1.5603,
"step": 331500
},
{
"epoch": 18.5,
"learning_rate": 0.0002,
"loss": 1.5652,
"step": 332000
},
{
"epoch": 18.53,
"learning_rate": 0.0002,
"loss": 1.5707,
"step": 332500
},
{
"epoch": 18.56,
"learning_rate": 0.0002,
"loss": 1.5603,
"step": 333000
},
{
"epoch": 18.58,
"learning_rate": 0.0002,
"loss": 1.5664,
"step": 333500
},
{
"epoch": 18.61,
"learning_rate": 0.0002,
"loss": 1.572,
"step": 334000
},
{
"epoch": 18.64,
"learning_rate": 0.0002,
"loss": 1.5637,
"step": 334500
},
{
"epoch": 18.67,
"learning_rate": 0.0002,
"loss": 1.5703,
"step": 335000
},
{
"epoch": 18.7,
"learning_rate": 0.0002,
"loss": 1.557,
"step": 335500
},
{
"epoch": 18.72,
"learning_rate": 0.0002,
"loss": 1.5577,
"step": 336000
},
{
"epoch": 18.75,
"learning_rate": 0.0002,
"loss": 1.57,
"step": 336500
},
{
"epoch": 18.78,
"learning_rate": 0.0002,
"loss": 1.571,
"step": 337000
},
{
"epoch": 18.81,
"learning_rate": 0.0002,
"loss": 1.5559,
"step": 337500
},
{
"epoch": 18.84,
"learning_rate": 0.0002,
"loss": 1.556,
"step": 338000
},
{
"epoch": 18.86,
"learning_rate": 0.0002,
"loss": 1.5865,
"step": 338500
},
{
"epoch": 18.89,
"learning_rate": 0.0002,
"loss": 1.563,
"step": 339000
},
{
"epoch": 18.92,
"learning_rate": 0.0002,
"loss": 1.5696,
"step": 339500
},
{
"epoch": 18.95,
"learning_rate": 0.0002,
"loss": 1.5569,
"step": 340000
},
{
"epoch": 18.97,
"learning_rate": 0.0002,
"loss": 1.5783,
"step": 340500
},
{
"epoch": 19.0,
"eval_gen_len": 18.999625972471573,
"eval_loss": 1.6005514860153198,
"eval_rouge1": 24.7356,
"eval_rouge2": 12.0038,
"eval_rougeL": 20.4853,
"eval_rougeLsum": 23.353,
"eval_runtime": 454.2953,
"eval_samples_per_second": 29.426,
"eval_steps_per_second": 1.84,
"step": 340955
},
{
"epoch": 19.0,
"learning_rate": 0.0002,
"loss": 1.567,
"step": 341000
},
{
"epoch": 19.03,
"learning_rate": 0.0002,
"loss": 1.5507,
"step": 341500
},
{
"epoch": 19.06,
"learning_rate": 0.0002,
"loss": 1.5444,
"step": 342000
},
{
"epoch": 19.09,
"learning_rate": 0.0002,
"loss": 1.5496,
"step": 342500
},
{
"epoch": 19.11,
"learning_rate": 0.0002,
"loss": 1.5376,
"step": 343000
},
{
"epoch": 19.14,
"learning_rate": 0.0002,
"loss": 1.5417,
"step": 343500
},
{
"epoch": 19.17,
"learning_rate": 0.0002,
"loss": 1.5505,
"step": 344000
},
{
"epoch": 19.2,
"learning_rate": 0.0002,
"loss": 1.5457,
"step": 344500
},
{
"epoch": 19.23,
"learning_rate": 0.0002,
"loss": 1.5399,
"step": 345000
},
{
"epoch": 19.25,
"learning_rate": 0.0002,
"loss": 1.5456,
"step": 345500
},
{
"epoch": 19.28,
"learning_rate": 0.0002,
"loss": 1.5581,
"step": 346000
},
{
"epoch": 19.31,
"learning_rate": 0.0002,
"loss": 1.5395,
"step": 346500
},
{
"epoch": 19.34,
"learning_rate": 0.0002,
"loss": 1.5609,
"step": 347000
},
{
"epoch": 19.36,
"learning_rate": 0.0002,
"loss": 1.5519,
"step": 347500
},
{
"epoch": 19.39,
"learning_rate": 0.0002,
"loss": 1.5487,
"step": 348000
},
{
"epoch": 19.42,
"learning_rate": 0.0002,
"loss": 1.5646,
"step": 348500
},
{
"epoch": 19.45,
"learning_rate": 0.0002,
"loss": 1.5558,
"step": 349000
},
{
"epoch": 19.48,
"learning_rate": 0.0002,
"loss": 1.5545,
"step": 349500
},
{
"epoch": 19.5,
"learning_rate": 0.0002,
"loss": 1.5482,
"step": 350000
},
{
"epoch": 19.53,
"learning_rate": 0.0002,
"loss": 1.553,
"step": 350500
},
{
"epoch": 19.56,
"learning_rate": 0.0002,
"loss": 1.5541,
"step": 351000
},
{
"epoch": 19.59,
"learning_rate": 0.0002,
"loss": 1.549,
"step": 351500
},
{
"epoch": 19.62,
"learning_rate": 0.0002,
"loss": 1.5617,
"step": 352000
},
{
"epoch": 19.64,
"learning_rate": 0.0002,
"loss": 1.5504,
"step": 352500
},
{
"epoch": 19.67,
"learning_rate": 0.0002,
"loss": 1.5645,
"step": 353000
},
{
"epoch": 19.7,
"learning_rate": 0.0002,
"loss": 1.5535,
"step": 353500
},
{
"epoch": 19.73,
"learning_rate": 0.0002,
"loss": 1.5597,
"step": 354000
},
{
"epoch": 19.75,
"learning_rate": 0.0002,
"loss": 1.5644,
"step": 354500
},
{
"epoch": 19.78,
"learning_rate": 0.0002,
"loss": 1.5598,
"step": 355000
},
{
"epoch": 19.81,
"learning_rate": 0.0002,
"loss": 1.5527,
"step": 355500
},
{
"epoch": 19.84,
"learning_rate": 0.0002,
"loss": 1.5691,
"step": 356000
},
{
"epoch": 19.87,
"learning_rate": 0.0002,
"loss": 1.5699,
"step": 356500
},
{
"epoch": 19.89,
"learning_rate": 0.0002,
"loss": 1.5692,
"step": 357000
},
{
"epoch": 19.92,
"learning_rate": 0.0002,
"loss": 1.565,
"step": 357500
},
{
"epoch": 19.95,
"learning_rate": 0.0002,
"loss": 1.57,
"step": 358000
},
{
"epoch": 19.98,
"learning_rate": 0.0002,
"loss": 1.5615,
"step": 358500
},
{
"epoch": 20.0,
"eval_gen_len": 18.999925194494313,
"eval_loss": 1.5914615392684937,
"eval_rouge1": 24.7644,
"eval_rouge2": 12.0064,
"eval_rougeL": 20.5076,
"eval_rougeLsum": 23.3719,
"eval_runtime": 453.4878,
"eval_samples_per_second": 29.478,
"eval_steps_per_second": 1.843,
"step": 358900
},
{
"epoch": 20.01,
"learning_rate": 0.0002,
"loss": 1.5598,
"step": 359000
},
{
"epoch": 20.03,
"learning_rate": 0.0002,
"loss": 1.5369,
"step": 359500
},
{
"epoch": 20.06,
"learning_rate": 0.0002,
"loss": 1.5369,
"step": 360000
},
{
"epoch": 20.09,
"learning_rate": 0.0002,
"loss": 1.5283,
"step": 360500
},
{
"epoch": 20.12,
"learning_rate": 0.0002,
"loss": 1.5302,
"step": 361000
},
{
"epoch": 20.14,
"learning_rate": 0.0002,
"loss": 1.5405,
"step": 361500
},
{
"epoch": 20.17,
"learning_rate": 0.0002,
"loss": 1.5361,
"step": 362000
},
{
"epoch": 20.2,
"learning_rate": 0.0002,
"loss": 1.5469,
"step": 362500
},
{
"epoch": 20.23,
"learning_rate": 0.0002,
"loss": 1.5402,
"step": 363000
},
{
"epoch": 20.26,
"learning_rate": 0.0002,
"loss": 1.5235,
"step": 363500
},
{
"epoch": 20.28,
"learning_rate": 0.0002,
"loss": 1.5473,
"step": 364000
},
{
"epoch": 20.31,
"learning_rate": 0.0002,
"loss": 1.5539,
"step": 364500
},
{
"epoch": 20.34,
"learning_rate": 0.0002,
"loss": 1.5541,
"step": 365000
},
{
"epoch": 20.37,
"learning_rate": 0.0002,
"loss": 1.5527,
"step": 365500
},
{
"epoch": 20.4,
"learning_rate": 0.0002,
"loss": 1.5533,
"step": 366000
},
{
"epoch": 20.42,
"learning_rate": 0.0002,
"loss": 1.5525,
"step": 366500
},
{
"epoch": 20.45,
"learning_rate": 0.0002,
"loss": 1.5438,
"step": 367000
},
{
"epoch": 20.48,
"learning_rate": 0.0002,
"loss": 1.5486,
"step": 367500
},
{
"epoch": 20.51,
"learning_rate": 0.0002,
"loss": 1.5514,
"step": 368000
},
{
"epoch": 20.53,
"learning_rate": 0.0002,
"loss": 1.5496,
"step": 368500
},
{
"epoch": 20.56,
"learning_rate": 0.0002,
"loss": 1.5455,
"step": 369000
},
{
"epoch": 20.59,
"learning_rate": 0.0002,
"loss": 1.5437,
"step": 369500
},
{
"epoch": 20.62,
"learning_rate": 0.0002,
"loss": 1.5502,
"step": 370000
},
{
"epoch": 20.65,
"learning_rate": 0.0002,
"loss": 1.557,
"step": 370500
},
{
"epoch": 20.67,
"learning_rate": 0.0002,
"loss": 1.5448,
"step": 371000
},
{
"epoch": 20.7,
"learning_rate": 0.0002,
"loss": 1.5604,
"step": 371500
},
{
"epoch": 20.73,
"learning_rate": 0.0002,
"loss": 1.5404,
"step": 372000
},
{
"epoch": 20.76,
"learning_rate": 0.0002,
"loss": 1.5557,
"step": 372500
},
{
"epoch": 20.79,
"learning_rate": 0.0002,
"loss": 1.5617,
"step": 373000
},
{
"epoch": 20.81,
"learning_rate": 0.0002,
"loss": 1.5447,
"step": 373500
},
{
"epoch": 20.84,
"learning_rate": 0.0002,
"loss": 1.5612,
"step": 374000
},
{
"epoch": 20.87,
"learning_rate": 0.0002,
"loss": 1.5514,
"step": 374500
},
{
"epoch": 20.9,
"learning_rate": 0.0002,
"loss": 1.5533,
"step": 375000
},
{
"epoch": 20.93,
"learning_rate": 0.0002,
"loss": 1.5532,
"step": 375500
},
{
"epoch": 20.95,
"learning_rate": 0.0002,
"loss": 1.5649,
"step": 376000
},
{
"epoch": 20.98,
"learning_rate": 0.0002,
"loss": 1.5652,
"step": 376500
},
{
"epoch": 21.0,
"eval_gen_len": 18.999625972471573,
"eval_loss": 1.5916765928268433,
"eval_rouge1": 24.7552,
"eval_rouge2": 11.9691,
"eval_rougeL": 20.4797,
"eval_rougeLsum": 23.3411,
"eval_runtime": 454.0277,
"eval_samples_per_second": 29.443,
"eval_steps_per_second": 1.841,
"step": 376845
},
{
"epoch": 21.01,
"learning_rate": 0.0002,
"loss": 1.546,
"step": 377000
},
{
"epoch": 21.04,
"learning_rate": 0.0002,
"loss": 1.5266,
"step": 377500
},
{
"epoch": 21.06,
"learning_rate": 0.0002,
"loss": 1.5275,
"step": 378000
},
{
"epoch": 21.09,
"learning_rate": 0.0002,
"loss": 1.5358,
"step": 378500
},
{
"epoch": 21.12,
"learning_rate": 0.0002,
"loss": 1.5219,
"step": 379000
},
{
"epoch": 21.15,
"learning_rate": 0.0002,
"loss": 1.5309,
"step": 379500
},
{
"epoch": 21.18,
"learning_rate": 0.0002,
"loss": 1.5345,
"step": 380000
},
{
"epoch": 21.2,
"learning_rate": 0.0002,
"loss": 1.5414,
"step": 380500
},
{
"epoch": 21.23,
"learning_rate": 0.0002,
"loss": 1.5386,
"step": 381000
},
{
"epoch": 21.26,
"learning_rate": 0.0002,
"loss": 1.5355,
"step": 381500
},
{
"epoch": 21.29,
"learning_rate": 0.0002,
"loss": 1.5272,
"step": 382000
},
{
"epoch": 21.32,
"learning_rate": 0.0002,
"loss": 1.5349,
"step": 382500
},
{
"epoch": 21.34,
"learning_rate": 0.0002,
"loss": 1.5336,
"step": 383000
},
{
"epoch": 21.37,
"learning_rate": 0.0002,
"loss": 1.5346,
"step": 383500
},
{
"epoch": 21.4,
"learning_rate": 0.0002,
"loss": 1.5475,
"step": 384000
},
{
"epoch": 21.43,
"learning_rate": 0.0002,
"loss": 1.5468,
"step": 384500
},
{
"epoch": 21.45,
"learning_rate": 0.0002,
"loss": 1.5408,
"step": 385000
},
{
"epoch": 21.48,
"learning_rate": 0.0002,
"loss": 1.5389,
"step": 385500
},
{
"epoch": 21.51,
"learning_rate": 0.0002,
"loss": 1.5502,
"step": 386000
},
{
"epoch": 21.54,
"learning_rate": 0.0002,
"loss": 1.5437,
"step": 386500
},
{
"epoch": 21.57,
"learning_rate": 0.0002,
"loss": 1.5451,
"step": 387000
},
{
"epoch": 21.59,
"learning_rate": 0.0002,
"loss": 1.5439,
"step": 387500
},
{
"epoch": 21.62,
"learning_rate": 0.0002,
"loss": 1.5447,
"step": 388000
},
{
"epoch": 21.65,
"learning_rate": 0.0002,
"loss": 1.5463,
"step": 388500
},
{
"epoch": 21.68,
"learning_rate": 0.0002,
"loss": 1.5417,
"step": 389000
},
{
"epoch": 21.71,
"learning_rate": 0.0002,
"loss": 1.5509,
"step": 389500
},
{
"epoch": 21.73,
"learning_rate": 0.0002,
"loss": 1.554,
"step": 390000
},
{
"epoch": 21.76,
"learning_rate": 0.0002,
"loss": 1.5397,
"step": 390500
},
{
"epoch": 21.79,
"learning_rate": 0.0002,
"loss": 1.5585,
"step": 391000
},
{
"epoch": 21.82,
"learning_rate": 0.0002,
"loss": 1.5474,
"step": 391500
},
{
"epoch": 21.84,
"learning_rate": 0.0002,
"loss": 1.5332,
"step": 392000
},
{
"epoch": 21.87,
"learning_rate": 0.0002,
"loss": 1.5471,
"step": 392500
},
{
"epoch": 21.9,
"learning_rate": 0.0002,
"loss": 1.5479,
"step": 393000
},
{
"epoch": 21.93,
"learning_rate": 0.0002,
"loss": 1.545,
"step": 393500
},
{
"epoch": 21.96,
"learning_rate": 0.0002,
"loss": 1.5565,
"step": 394000
},
{
"epoch": 21.98,
"learning_rate": 0.0002,
"loss": 1.5635,
"step": 394500
},
{
"epoch": 22.0,
"eval_gen_len": 18.99985038898863,
"eval_loss": 1.5907750129699707,
"eval_rouge1": 24.8457,
"eval_rouge2": 12.0955,
"eval_rougeL": 20.5316,
"eval_rougeLsum": 23.433,
"eval_runtime": 454.9481,
"eval_samples_per_second": 29.384,
"eval_steps_per_second": 1.838,
"step": 394790
},
{
"epoch": 22.01,
"learning_rate": 0.0002,
"loss": 1.5393,
"step": 395000
},
{
"epoch": 22.04,
"learning_rate": 0.0002,
"loss": 1.5191,
"step": 395500
},
{
"epoch": 22.07,
"learning_rate": 0.0002,
"loss": 1.5304,
"step": 396000
},
{
"epoch": 22.1,
"learning_rate": 0.0002,
"loss": 1.5254,
"step": 396500
},
{
"epoch": 22.12,
"learning_rate": 0.0002,
"loss": 1.5217,
"step": 397000
},
{
"epoch": 22.15,
"learning_rate": 0.0002,
"loss": 1.5239,
"step": 397500
},
{
"epoch": 22.18,
"learning_rate": 0.0002,
"loss": 1.5382,
"step": 398000
},
{
"epoch": 22.21,
"learning_rate": 0.0002,
"loss": 1.5273,
"step": 398500
},
{
"epoch": 22.23,
"learning_rate": 0.0002,
"loss": 1.5399,
"step": 399000
},
{
"epoch": 22.26,
"learning_rate": 0.0002,
"loss": 1.528,
"step": 399500
},
{
"epoch": 22.29,
"learning_rate": 0.0002,
"loss": 1.5326,
"step": 400000
},
{
"epoch": 22.32,
"learning_rate": 0.0002,
"loss": 1.5331,
"step": 400500
},
{
"epoch": 22.35,
"learning_rate": 0.0002,
"loss": 1.5251,
"step": 401000
},
{
"epoch": 22.37,
"learning_rate": 0.0002,
"loss": 1.5401,
"step": 401500
},
{
"epoch": 22.4,
"learning_rate": 0.0002,
"loss": 1.5356,
"step": 402000
},
{
"epoch": 22.43,
"learning_rate": 0.0002,
"loss": 1.5302,
"step": 402500
},
{
"epoch": 22.46,
"learning_rate": 0.0002,
"loss": 1.533,
"step": 403000
},
{
"epoch": 22.49,
"learning_rate": 0.0002,
"loss": 1.5308,
"step": 403500
},
{
"epoch": 22.51,
"learning_rate": 0.0002,
"loss": 1.5372,
"step": 404000
},
{
"epoch": 22.54,
"learning_rate": 0.0002,
"loss": 1.5372,
"step": 404500
},
{
"epoch": 22.57,
"learning_rate": 0.0002,
"loss": 1.5302,
"step": 405000
},
{
"epoch": 22.6,
"learning_rate": 0.0002,
"loss": 1.532,
"step": 405500
},
{
"epoch": 22.62,
"learning_rate": 0.0002,
"loss": 1.5374,
"step": 406000
},
{
"epoch": 22.65,
"learning_rate": 0.0002,
"loss": 1.5357,
"step": 406500
},
{
"epoch": 22.68,
"learning_rate": 0.0002,
"loss": 1.5458,
"step": 407000
},
{
"epoch": 22.71,
"learning_rate": 0.0002,
"loss": 1.5435,
"step": 407500
},
{
"epoch": 22.74,
"learning_rate": 0.0002,
"loss": 1.5396,
"step": 408000
},
{
"epoch": 22.76,
"learning_rate": 0.0002,
"loss": 1.5419,
"step": 408500
},
{
"epoch": 22.79,
"learning_rate": 0.0002,
"loss": 1.54,
"step": 409000
},
{
"epoch": 22.82,
"learning_rate": 0.0002,
"loss": 1.5392,
"step": 409500
},
{
"epoch": 22.85,
"learning_rate": 0.0002,
"loss": 1.5498,
"step": 410000
},
{
"epoch": 22.88,
"learning_rate": 0.0002,
"loss": 1.5403,
"step": 410500
},
{
"epoch": 22.9,
"learning_rate": 0.0002,
"loss": 1.5558,
"step": 411000
},
{
"epoch": 22.93,
"learning_rate": 0.0002,
"loss": 1.542,
"step": 411500
},
{
"epoch": 22.96,
"learning_rate": 0.0002,
"loss": 1.5365,
"step": 412000
},
{
"epoch": 22.99,
"learning_rate": 0.0002,
"loss": 1.5433,
"step": 412500
},
{
"epoch": 23.0,
"eval_gen_len": 18.99985038898863,
"eval_loss": 1.6024245023727417,
"eval_rouge1": 24.8366,
"eval_rouge2": 12.0534,
"eval_rougeL": 20.5687,
"eval_rougeLsum": 23.4081,
"eval_runtime": 454.875,
"eval_samples_per_second": 29.388,
"eval_steps_per_second": 1.838,
"step": 412735
},
{
"epoch": 23.01,
"learning_rate": 0.0002,
"loss": 1.5296,
"step": 413000
},
{
"epoch": 23.04,
"learning_rate": 0.0002,
"loss": 1.522,
"step": 413500
},
{
"epoch": 23.07,
"learning_rate": 0.0002,
"loss": 1.5241,
"step": 414000
},
{
"epoch": 23.1,
"learning_rate": 0.0002,
"loss": 1.5137,
"step": 414500
},
{
"epoch": 23.13,
"learning_rate": 0.0002,
"loss": 1.5226,
"step": 415000
},
{
"epoch": 23.15,
"learning_rate": 0.0002,
"loss": 1.5331,
"step": 415500
},
{
"epoch": 23.18,
"learning_rate": 0.0002,
"loss": 1.5244,
"step": 416000
},
{
"epoch": 23.21,
"learning_rate": 0.0002,
"loss": 1.5195,
"step": 416500
},
{
"epoch": 23.24,
"learning_rate": 0.0002,
"loss": 1.519,
"step": 417000
},
{
"epoch": 23.27,
"learning_rate": 0.0002,
"loss": 1.525,
"step": 417500
},
{
"epoch": 23.29,
"learning_rate": 0.0002,
"loss": 1.5315,
"step": 418000
},
{
"epoch": 23.32,
"learning_rate": 0.0002,
"loss": 1.5217,
"step": 418500
},
{
"epoch": 23.35,
"learning_rate": 0.0002,
"loss": 1.5133,
"step": 419000
},
{
"epoch": 23.38,
"learning_rate": 0.0002,
"loss": 1.5287,
"step": 419500
},
{
"epoch": 23.4,
"learning_rate": 0.0002,
"loss": 1.5257,
"step": 420000
},
{
"epoch": 23.43,
"learning_rate": 0.0002,
"loss": 1.5242,
"step": 420500
},
{
"epoch": 23.46,
"learning_rate": 0.0002,
"loss": 1.5287,
"step": 421000
},
{
"epoch": 23.49,
"learning_rate": 0.0002,
"loss": 1.5259,
"step": 421500
},
{
"epoch": 23.52,
"learning_rate": 0.0002,
"loss": 1.5292,
"step": 422000
},
{
"epoch": 23.54,
"learning_rate": 0.0002,
"loss": 1.5182,
"step": 422500
},
{
"epoch": 23.57,
"learning_rate": 0.0002,
"loss": 1.5363,
"step": 423000
},
{
"epoch": 23.6,
"learning_rate": 0.0002,
"loss": 1.5316,
"step": 423500
},
{
"epoch": 23.63,
"learning_rate": 0.0002,
"loss": 1.5271,
"step": 424000
},
{
"epoch": 23.66,
"learning_rate": 0.0002,
"loss": 1.5436,
"step": 424500
},
{
"epoch": 23.68,
"learning_rate": 0.0002,
"loss": 1.5275,
"step": 425000
},
{
"epoch": 23.71,
"learning_rate": 0.0002,
"loss": 1.5291,
"step": 425500
},
{
"epoch": 23.74,
"learning_rate": 0.0002,
"loss": 1.5288,
"step": 426000
},
{
"epoch": 23.77,
"learning_rate": 0.0002,
"loss": 1.5276,
"step": 426500
},
{
"epoch": 23.79,
"learning_rate": 0.0002,
"loss": 1.5451,
"step": 427000
},
{
"epoch": 23.82,
"learning_rate": 0.0002,
"loss": 1.5279,
"step": 427500
},
{
"epoch": 23.85,
"learning_rate": 0.0002,
"loss": 1.537,
"step": 428000
},
{
"epoch": 23.88,
"learning_rate": 0.0002,
"loss": 1.5367,
"step": 428500
},
{
"epoch": 23.91,
"learning_rate": 0.0002,
"loss": 1.5385,
"step": 429000
},
{
"epoch": 23.93,
"learning_rate": 0.0002,
"loss": 1.5293,
"step": 429500
},
{
"epoch": 23.96,
"learning_rate": 0.0002,
"loss": 1.557,
"step": 430000
},
{
"epoch": 23.99,
"learning_rate": 0.0002,
"loss": 1.5432,
"step": 430500
},
{
"epoch": 24.0,
"eval_gen_len": 18.999251944943147,
"eval_loss": 1.5907658338546753,
"eval_rouge1": 24.8365,
"eval_rouge2": 12.0916,
"eval_rougeL": 20.5302,
"eval_rougeLsum": 23.4212,
"eval_runtime": 455.0271,
"eval_samples_per_second": 29.378,
"eval_steps_per_second": 1.837,
"step": 430680
},
{
"epoch": 24.02,
"learning_rate": 0.0002,
"loss": 1.5214,
"step": 431000
},
{
"epoch": 24.05,
"learning_rate": 0.0002,
"loss": 1.5122,
"step": 431500
},
{
"epoch": 24.07,
"learning_rate": 0.0002,
"loss": 1.5128,
"step": 432000
},
{
"epoch": 24.1,
"learning_rate": 0.0002,
"loss": 1.5011,
"step": 432500
},
{
"epoch": 24.13,
"learning_rate": 0.0002,
"loss": 1.5144,
"step": 433000
},
{
"epoch": 24.16,
"learning_rate": 0.0002,
"loss": 1.5092,
"step": 433500
},
{
"epoch": 24.19,
"learning_rate": 0.0002,
"loss": 1.5026,
"step": 434000
},
{
"epoch": 24.21,
"learning_rate": 0.0002,
"loss": 1.5027,
"step": 434500
},
{
"epoch": 24.24,
"learning_rate": 0.0002,
"loss": 1.5328,
"step": 435000
},
{
"epoch": 24.27,
"learning_rate": 0.0002,
"loss": 1.5119,
"step": 435500
},
{
"epoch": 24.3,
"learning_rate": 0.0002,
"loss": 1.5182,
"step": 436000
},
{
"epoch": 24.32,
"learning_rate": 0.0002,
"loss": 1.5296,
"step": 436500
},
{
"epoch": 24.35,
"learning_rate": 0.0002,
"loss": 1.5198,
"step": 437000
},
{
"epoch": 24.38,
"learning_rate": 0.0002,
"loss": 1.5193,
"step": 437500
},
{
"epoch": 24.41,
"learning_rate": 0.0002,
"loss": 1.5192,
"step": 438000
},
{
"epoch": 24.44,
"learning_rate": 0.0002,
"loss": 1.5244,
"step": 438500
},
{
"epoch": 24.46,
"learning_rate": 0.0002,
"loss": 1.5263,
"step": 439000
},
{
"epoch": 24.49,
"learning_rate": 0.0002,
"loss": 1.5257,
"step": 439500
},
{
"epoch": 24.52,
"learning_rate": 0.0002,
"loss": 1.5164,
"step": 440000
},
{
"epoch": 24.55,
"learning_rate": 0.0002,
"loss": 1.5275,
"step": 440500
},
{
"epoch": 24.58,
"learning_rate": 0.0002,
"loss": 1.5256,
"step": 441000
},
{
"epoch": 24.6,
"learning_rate": 0.0002,
"loss": 1.5432,
"step": 441500
},
{
"epoch": 24.63,
"learning_rate": 0.0002,
"loss": 1.5136,
"step": 442000
},
{
"epoch": 24.66,
"learning_rate": 0.0002,
"loss": 1.5186,
"step": 442500
},
{
"epoch": 24.69,
"learning_rate": 0.0002,
"loss": 1.5325,
"step": 443000
},
{
"epoch": 24.71,
"learning_rate": 0.0002,
"loss": 1.5246,
"step": 443500
},
{
"epoch": 24.74,
"learning_rate": 0.0002,
"loss": 1.521,
"step": 444000
},
{
"epoch": 24.77,
"learning_rate": 0.0002,
"loss": 1.5266,
"step": 444500
},
{
"epoch": 24.8,
"learning_rate": 0.0002,
"loss": 1.5428,
"step": 445000
},
{
"epoch": 24.83,
"learning_rate": 0.0002,
"loss": 1.5413,
"step": 445500
},
{
"epoch": 24.85,
"learning_rate": 0.0002,
"loss": 1.5301,
"step": 446000
},
{
"epoch": 24.88,
"learning_rate": 0.0002,
"loss": 1.5415,
"step": 446500
},
{
"epoch": 24.91,
"learning_rate": 0.0002,
"loss": 1.535,
"step": 447000
},
{
"epoch": 24.94,
"learning_rate": 0.0002,
"loss": 1.5389,
"step": 447500
},
{
"epoch": 24.97,
"learning_rate": 0.0002,
"loss": 1.5323,
"step": 448000
},
{
"epoch": 24.99,
"learning_rate": 0.0002,
"loss": 1.531,
"step": 448500
},
{
"epoch": 25.0,
"eval_gen_len": 19.0,
"eval_loss": 1.6025395393371582,
"eval_rouge1": 24.7463,
"eval_rouge2": 11.985,
"eval_rougeL": 20.4706,
"eval_rougeLsum": 23.2953,
"eval_runtime": 452.1354,
"eval_samples_per_second": 29.566,
"eval_steps_per_second": 1.849,
"step": 448625
},
{
"epoch": 25.02,
"learning_rate": 0.0002,
"loss": 1.5156,
"step": 449000
},
{
"epoch": 25.05,
"learning_rate": 0.0002,
"loss": 1.5051,
"step": 449500
},
{
"epoch": 25.08,
"learning_rate": 0.0002,
"loss": 1.5078,
"step": 450000
},
{
"epoch": 25.1,
"learning_rate": 0.0002,
"loss": 1.5021,
"step": 450500
},
{
"epoch": 25.13,
"learning_rate": 0.0002,
"loss": 1.5121,
"step": 451000
},
{
"epoch": 25.16,
"learning_rate": 0.0002,
"loss": 1.5094,
"step": 451500
},
{
"epoch": 25.19,
"learning_rate": 0.0002,
"loss": 1.5141,
"step": 452000
},
{
"epoch": 25.22,
"learning_rate": 0.0002,
"loss": 1.5186,
"step": 452500
},
{
"epoch": 25.24,
"learning_rate": 0.0002,
"loss": 1.5171,
"step": 453000
},
{
"epoch": 25.27,
"learning_rate": 0.0002,
"loss": 1.5154,
"step": 453500
},
{
"epoch": 25.3,
"learning_rate": 0.0002,
"loss": 1.5227,
"step": 454000
},
{
"epoch": 25.33,
"learning_rate": 0.0002,
"loss": 1.5051,
"step": 454500
},
{
"epoch": 25.36,
"learning_rate": 0.0002,
"loss": 1.5261,
"step": 455000
},
{
"epoch": 25.38,
"learning_rate": 0.0002,
"loss": 1.5196,
"step": 455500
},
{
"epoch": 25.41,
"learning_rate": 0.0002,
"loss": 1.5124,
"step": 456000
},
{
"epoch": 25.44,
"learning_rate": 0.0002,
"loss": 1.517,
"step": 456500
},
{
"epoch": 25.47,
"learning_rate": 0.0002,
"loss": 1.5102,
"step": 457000
},
{
"epoch": 25.49,
"learning_rate": 0.0002,
"loss": 1.5334,
"step": 457500
},
{
"epoch": 25.52,
"learning_rate": 0.0002,
"loss": 1.5125,
"step": 458000
},
{
"epoch": 25.55,
"learning_rate": 0.0002,
"loss": 1.5133,
"step": 458500
},
{
"epoch": 25.58,
"learning_rate": 0.0002,
"loss": 1.5173,
"step": 459000
},
{
"epoch": 25.61,
"learning_rate": 0.0002,
"loss": 1.5082,
"step": 459500
},
{
"epoch": 25.63,
"learning_rate": 0.0002,
"loss": 1.5171,
"step": 460000
},
{
"epoch": 25.66,
"learning_rate": 0.0002,
"loss": 1.5196,
"step": 460500
},
{
"epoch": 25.69,
"learning_rate": 0.0002,
"loss": 1.5381,
"step": 461000
},
{
"epoch": 25.72,
"learning_rate": 0.0002,
"loss": 1.5223,
"step": 461500
},
{
"epoch": 25.75,
"learning_rate": 0.0002,
"loss": 1.5174,
"step": 462000
},
{
"epoch": 25.77,
"learning_rate": 0.0002,
"loss": 1.5194,
"step": 462500
},
{
"epoch": 25.8,
"learning_rate": 0.0002,
"loss": 1.5337,
"step": 463000
},
{
"epoch": 25.83,
"learning_rate": 0.0002,
"loss": 1.5262,
"step": 463500
},
{
"epoch": 25.86,
"learning_rate": 0.0002,
"loss": 1.5206,
"step": 464000
},
{
"epoch": 25.88,
"learning_rate": 0.0002,
"loss": 1.5094,
"step": 464500
},
{
"epoch": 25.91,
"learning_rate": 0.0002,
"loss": 1.5223,
"step": 465000
},
{
"epoch": 25.94,
"learning_rate": 0.0002,
"loss": 1.5312,
"step": 465500
},
{
"epoch": 25.97,
"learning_rate": 0.0002,
"loss": 1.5248,
"step": 466000
},
{
"epoch": 26.0,
"learning_rate": 0.0002,
"loss": 1.5269,
"step": 466500
},
{
"epoch": 26.0,
"eval_gen_len": 19.0,
"eval_loss": 1.5949018001556396,
"eval_rouge1": 24.9535,
"eval_rouge2": 12.0763,
"eval_rougeL": 20.6432,
"eval_rougeLsum": 23.5531,
"eval_runtime": 451.3411,
"eval_samples_per_second": 29.618,
"eval_steps_per_second": 1.852,
"step": 466570
}
],
"max_steps": 538350,
"num_train_epochs": 30,
"total_flos": 2.0206105478981222e+18,
"trial_name": null,
"trial_params": null
}