muril-en-hi-codemixed / trainer_state.json
Matej U
first version
3183e00
raw history blame
No virus
93.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"global_step": 862850,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.112668990819203e-05,
"loss": 8.0034,
"step": 1000
},
{
"epoch": 0.0,
"learning_rate": 4.533733258325905e-05,
"loss": 7.5343,
"step": 2000
},
{
"epoch": 0.01,
"learning_rate": 4.7778615089460934e-05,
"loss": 7.2281,
"step": 3000
},
{
"epoch": 0.01,
"learning_rate": 4.9509713131658946e-05,
"loss": 6.5225,
"step": 4000
},
{
"epoch": 0.01,
"learning_rate": 5e-05,
"loss": 6.0666,
"step": 5000
},
{
"epoch": 0.01,
"learning_rate": 5e-05,
"loss": 5.7596,
"step": 6000
},
{
"epoch": 0.02,
"learning_rate": 5e-05,
"loss": 5.5413,
"step": 7000
},
{
"epoch": 0.02,
"learning_rate": 5e-05,
"loss": 5.3661,
"step": 8000
},
{
"epoch": 0.02,
"learning_rate": 5e-05,
"loss": 5.2017,
"step": 9000
},
{
"epoch": 0.02,
"learning_rate": 5e-05,
"loss": 5.052,
"step": 10000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 4.9005,
"step": 11000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 4.7597,
"step": 12000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 4.6439,
"step": 13000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 4.5544,
"step": 14000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 4.4742,
"step": 15000
},
{
"epoch": 0.04,
"learning_rate": 5e-05,
"loss": 4.4085,
"step": 16000
},
{
"epoch": 0.04,
"learning_rate": 5e-05,
"loss": 4.3437,
"step": 17000
},
{
"epoch": 0.04,
"learning_rate": 5e-05,
"loss": 4.2957,
"step": 18000
},
{
"epoch": 0.04,
"learning_rate": 5e-05,
"loss": 4.2381,
"step": 19000
},
{
"epoch": 0.05,
"learning_rate": 5e-05,
"loss": 4.1846,
"step": 20000
},
{
"epoch": 0.05,
"learning_rate": 5e-05,
"loss": 4.1399,
"step": 21000
},
{
"epoch": 0.05,
"learning_rate": 5e-05,
"loss": 4.1097,
"step": 22000
},
{
"epoch": 0.05,
"learning_rate": 5e-05,
"loss": 4.0513,
"step": 23000
},
{
"epoch": 0.06,
"learning_rate": 5e-05,
"loss": 4.0177,
"step": 24000
},
{
"epoch": 0.06,
"learning_rate": 5e-05,
"loss": 3.9807,
"step": 25000
},
{
"epoch": 0.06,
"learning_rate": 5e-05,
"loss": 3.9417,
"step": 26000
},
{
"epoch": 0.06,
"learning_rate": 5e-05,
"loss": 3.9119,
"step": 27000
},
{
"epoch": 0.06,
"learning_rate": 5e-05,
"loss": 3.8789,
"step": 28000
},
{
"epoch": 0.07,
"learning_rate": 5e-05,
"loss": 3.8467,
"step": 29000
},
{
"epoch": 0.07,
"learning_rate": 5e-05,
"loss": 3.8162,
"step": 30000
},
{
"epoch": 0.07,
"learning_rate": 5e-05,
"loss": 3.7815,
"step": 31000
},
{
"epoch": 0.07,
"learning_rate": 5e-05,
"loss": 3.755,
"step": 32000
},
{
"epoch": 0.08,
"learning_rate": 5e-05,
"loss": 3.7321,
"step": 33000
},
{
"epoch": 0.08,
"learning_rate": 5e-05,
"loss": 3.7082,
"step": 34000
},
{
"epoch": 0.08,
"learning_rate": 5e-05,
"loss": 3.6796,
"step": 35000
},
{
"epoch": 0.08,
"learning_rate": 5e-05,
"loss": 3.6481,
"step": 36000
},
{
"epoch": 0.09,
"learning_rate": 5e-05,
"loss": 3.6342,
"step": 37000
},
{
"epoch": 0.09,
"learning_rate": 5e-05,
"loss": 3.5971,
"step": 38000
},
{
"epoch": 0.09,
"learning_rate": 5e-05,
"loss": 3.5824,
"step": 39000
},
{
"epoch": 0.09,
"learning_rate": 5e-05,
"loss": 3.5602,
"step": 40000
},
{
"epoch": 0.1,
"learning_rate": 5e-05,
"loss": 3.5299,
"step": 41000
},
{
"epoch": 0.1,
"learning_rate": 5e-05,
"loss": 3.5166,
"step": 42000
},
{
"epoch": 0.1,
"learning_rate": 5e-05,
"loss": 3.494,
"step": 43000
},
{
"epoch": 0.1,
"learning_rate": 5e-05,
"loss": 3.4759,
"step": 44000
},
{
"epoch": 0.1,
"learning_rate": 5e-05,
"loss": 3.4558,
"step": 45000
},
{
"epoch": 0.11,
"learning_rate": 5e-05,
"loss": 3.4323,
"step": 46000
},
{
"epoch": 0.11,
"learning_rate": 5e-05,
"loss": 3.415,
"step": 47000
},
{
"epoch": 0.11,
"learning_rate": 5e-05,
"loss": 3.396,
"step": 48000
},
{
"epoch": 0.11,
"learning_rate": 5e-05,
"loss": 3.3864,
"step": 49000
},
{
"epoch": 0.12,
"learning_rate": 5e-05,
"loss": 3.3646,
"step": 50000
},
{
"epoch": 0.12,
"learning_rate": 5e-05,
"loss": 3.3441,
"step": 51000
},
{
"epoch": 0.12,
"learning_rate": 5e-05,
"loss": 3.3341,
"step": 52000
},
{
"epoch": 0.12,
"learning_rate": 5e-05,
"loss": 3.3227,
"step": 53000
},
{
"epoch": 0.13,
"learning_rate": 5e-05,
"loss": 3.3056,
"step": 54000
},
{
"epoch": 0.13,
"learning_rate": 5e-05,
"loss": 3.289,
"step": 55000
},
{
"epoch": 0.13,
"learning_rate": 5e-05,
"loss": 3.2696,
"step": 56000
},
{
"epoch": 0.13,
"learning_rate": 5e-05,
"loss": 3.258,
"step": 57000
},
{
"epoch": 0.13,
"learning_rate": 5e-05,
"loss": 3.2438,
"step": 58000
},
{
"epoch": 0.14,
"learning_rate": 5e-05,
"loss": 3.223,
"step": 59000
},
{
"epoch": 0.14,
"learning_rate": 5e-05,
"loss": 3.2181,
"step": 60000
},
{
"epoch": 0.14,
"learning_rate": 5e-05,
"loss": 3.2049,
"step": 61000
},
{
"epoch": 0.14,
"learning_rate": 5e-05,
"loss": 3.1886,
"step": 62000
},
{
"epoch": 0.15,
"learning_rate": 5e-05,
"loss": 3.183,
"step": 63000
},
{
"epoch": 0.15,
"learning_rate": 5e-05,
"loss": 3.1623,
"step": 64000
},
{
"epoch": 0.15,
"learning_rate": 5e-05,
"loss": 3.1553,
"step": 65000
},
{
"epoch": 0.15,
"learning_rate": 5e-05,
"loss": 3.1407,
"step": 66000
},
{
"epoch": 0.16,
"learning_rate": 5e-05,
"loss": 3.1316,
"step": 67000
},
{
"epoch": 0.16,
"learning_rate": 5e-05,
"loss": 3.1209,
"step": 68000
},
{
"epoch": 0.16,
"learning_rate": 5e-05,
"loss": 3.1047,
"step": 69000
},
{
"epoch": 0.16,
"learning_rate": 5e-05,
"loss": 3.0984,
"step": 70000
},
{
"epoch": 0.16,
"learning_rate": 5e-05,
"loss": 3.0901,
"step": 71000
},
{
"epoch": 0.17,
"learning_rate": 5e-05,
"loss": 3.0713,
"step": 72000
},
{
"epoch": 0.17,
"learning_rate": 5e-05,
"loss": 3.0674,
"step": 73000
},
{
"epoch": 0.17,
"learning_rate": 5e-05,
"loss": 3.0568,
"step": 74000
},
{
"epoch": 0.17,
"learning_rate": 5e-05,
"loss": 3.0448,
"step": 75000
},
{
"epoch": 0.18,
"learning_rate": 5e-05,
"loss": 3.0282,
"step": 76000
},
{
"epoch": 0.18,
"learning_rate": 5e-05,
"loss": 3.0217,
"step": 77000
},
{
"epoch": 0.18,
"learning_rate": 5e-05,
"loss": 3.0215,
"step": 78000
},
{
"epoch": 0.18,
"learning_rate": 5e-05,
"loss": 3.0051,
"step": 79000
},
{
"epoch": 0.19,
"learning_rate": 5e-05,
"loss": 2.9998,
"step": 80000
},
{
"epoch": 0.19,
"learning_rate": 5e-05,
"loss": 2.9937,
"step": 81000
},
{
"epoch": 0.19,
"learning_rate": 5e-05,
"loss": 2.9874,
"step": 82000
},
{
"epoch": 0.19,
"learning_rate": 5e-05,
"loss": 2.9712,
"step": 83000
},
{
"epoch": 0.19,
"learning_rate": 5e-05,
"loss": 2.9656,
"step": 84000
},
{
"epoch": 0.2,
"learning_rate": 5e-05,
"loss": 2.9621,
"step": 85000
},
{
"epoch": 0.2,
"learning_rate": 5e-05,
"loss": 2.9509,
"step": 86000
},
{
"epoch": 0.2,
"learning_rate": 5e-05,
"loss": 2.9423,
"step": 87000
},
{
"epoch": 0.2,
"learning_rate": 5e-05,
"loss": 2.9436,
"step": 88000
},
{
"epoch": 0.21,
"learning_rate": 5e-05,
"loss": 2.9297,
"step": 89000
},
{
"epoch": 0.21,
"learning_rate": 5e-05,
"loss": 2.9205,
"step": 90000
},
{
"epoch": 0.21,
"learning_rate": 5e-05,
"loss": 2.9103,
"step": 91000
},
{
"epoch": 0.21,
"learning_rate": 5e-05,
"loss": 2.9019,
"step": 92000
},
{
"epoch": 0.22,
"learning_rate": 5e-05,
"loss": 2.8987,
"step": 93000
},
{
"epoch": 0.22,
"learning_rate": 5e-05,
"loss": 2.8913,
"step": 94000
},
{
"epoch": 0.22,
"learning_rate": 5e-05,
"loss": 2.8863,
"step": 95000
},
{
"epoch": 0.22,
"learning_rate": 5e-05,
"loss": 2.8781,
"step": 96000
},
{
"epoch": 0.22,
"learning_rate": 5e-05,
"loss": 2.8695,
"step": 97000
},
{
"epoch": 0.23,
"learning_rate": 5e-05,
"loss": 2.8731,
"step": 98000
},
{
"epoch": 0.23,
"learning_rate": 5e-05,
"loss": 2.8595,
"step": 99000
},
{
"epoch": 0.23,
"learning_rate": 5e-05,
"loss": 2.8548,
"step": 100000
},
{
"epoch": 0.23,
"learning_rate": 5e-05,
"loss": 2.8471,
"step": 101000
},
{
"epoch": 0.24,
"learning_rate": 5e-05,
"loss": 2.84,
"step": 102000
},
{
"epoch": 0.24,
"learning_rate": 5e-05,
"loss": 2.8328,
"step": 103000
},
{
"epoch": 0.24,
"learning_rate": 5e-05,
"loss": 2.8317,
"step": 104000
},
{
"epoch": 0.24,
"learning_rate": 5e-05,
"loss": 2.8278,
"step": 105000
},
{
"epoch": 0.25,
"learning_rate": 5e-05,
"loss": 2.821,
"step": 106000
},
{
"epoch": 0.25,
"learning_rate": 5e-05,
"loss": 2.8145,
"step": 107000
},
{
"epoch": 0.25,
"learning_rate": 5e-05,
"loss": 2.8083,
"step": 108000
},
{
"epoch": 0.25,
"learning_rate": 5e-05,
"loss": 2.7986,
"step": 109000
},
{
"epoch": 0.25,
"learning_rate": 5e-05,
"loss": 2.7942,
"step": 110000
},
{
"epoch": 0.26,
"learning_rate": 5e-05,
"loss": 2.7862,
"step": 111000
},
{
"epoch": 0.26,
"learning_rate": 5e-05,
"loss": 2.782,
"step": 112000
},
{
"epoch": 0.26,
"learning_rate": 5e-05,
"loss": 2.7773,
"step": 113000
},
{
"epoch": 0.26,
"learning_rate": 5e-05,
"loss": 2.7767,
"step": 114000
},
{
"epoch": 0.27,
"learning_rate": 5e-05,
"loss": 2.771,
"step": 115000
},
{
"epoch": 0.27,
"learning_rate": 5e-05,
"loss": 2.7649,
"step": 116000
},
{
"epoch": 0.27,
"learning_rate": 5e-05,
"loss": 2.7632,
"step": 117000
},
{
"epoch": 0.27,
"learning_rate": 5e-05,
"loss": 2.755,
"step": 118000
},
{
"epoch": 0.28,
"learning_rate": 5e-05,
"loss": 2.7415,
"step": 119000
},
{
"epoch": 0.28,
"learning_rate": 5e-05,
"loss": 2.7435,
"step": 120000
},
{
"epoch": 0.28,
"learning_rate": 5e-05,
"loss": 2.7405,
"step": 121000
},
{
"epoch": 0.28,
"learning_rate": 5e-05,
"loss": 2.7348,
"step": 122000
},
{
"epoch": 0.29,
"learning_rate": 5e-05,
"loss": 2.7296,
"step": 123000
},
{
"epoch": 0.29,
"learning_rate": 5e-05,
"loss": 2.7244,
"step": 124000
},
{
"epoch": 0.29,
"learning_rate": 5e-05,
"loss": 2.7208,
"step": 125000
},
{
"epoch": 0.29,
"learning_rate": 5e-05,
"loss": 2.7157,
"step": 126000
},
{
"epoch": 0.29,
"learning_rate": 5e-05,
"loss": 2.7143,
"step": 127000
},
{
"epoch": 0.3,
"learning_rate": 5e-05,
"loss": 2.7108,
"step": 128000
},
{
"epoch": 0.3,
"learning_rate": 5e-05,
"loss": 2.7009,
"step": 129000
},
{
"epoch": 0.3,
"learning_rate": 5e-05,
"loss": 2.7023,
"step": 130000
},
{
"epoch": 0.3,
"learning_rate": 5e-05,
"loss": 2.6931,
"step": 131000
},
{
"epoch": 0.31,
"learning_rate": 5e-05,
"loss": 2.6901,
"step": 132000
},
{
"epoch": 0.31,
"learning_rate": 5e-05,
"loss": 2.6871,
"step": 133000
},
{
"epoch": 0.31,
"learning_rate": 5e-05,
"loss": 2.6843,
"step": 134000
},
{
"epoch": 0.31,
"learning_rate": 5e-05,
"loss": 2.6842,
"step": 135000
},
{
"epoch": 0.32,
"learning_rate": 5e-05,
"loss": 2.6771,
"step": 136000
},
{
"epoch": 0.32,
"learning_rate": 5e-05,
"loss": 2.6708,
"step": 137000
},
{
"epoch": 0.32,
"learning_rate": 5e-05,
"loss": 2.6638,
"step": 138000
},
{
"epoch": 0.32,
"learning_rate": 5e-05,
"loss": 2.6617,
"step": 139000
},
{
"epoch": 0.32,
"learning_rate": 5e-05,
"loss": 2.6626,
"step": 140000
},
{
"epoch": 0.33,
"learning_rate": 5e-05,
"loss": 2.655,
"step": 141000
},
{
"epoch": 0.33,
"learning_rate": 5e-05,
"loss": 2.6576,
"step": 142000
},
{
"epoch": 0.33,
"learning_rate": 5e-05,
"loss": 2.6408,
"step": 143000
},
{
"epoch": 0.33,
"learning_rate": 5e-05,
"loss": 2.6422,
"step": 144000
},
{
"epoch": 0.34,
"learning_rate": 5e-05,
"loss": 2.6416,
"step": 145000
},
{
"epoch": 0.34,
"learning_rate": 5e-05,
"loss": 2.6411,
"step": 146000
},
{
"epoch": 0.34,
"learning_rate": 5e-05,
"loss": 2.6327,
"step": 147000
},
{
"epoch": 0.34,
"learning_rate": 5e-05,
"loss": 2.6334,
"step": 148000
},
{
"epoch": 0.35,
"learning_rate": 5e-05,
"loss": 2.6208,
"step": 149000
},
{
"epoch": 0.35,
"learning_rate": 5e-05,
"loss": 2.6232,
"step": 150000
},
{
"epoch": 0.35,
"eval_accuracy": 0.5274870522655163,
"eval_loss": 2.509765625,
"eval_runtime": 4883.386,
"eval_samples_per_second": 114.367,
"eval_steps_per_second": 0.894,
"step": 150000
},
{
"epoch": 0.35,
"learning_rate": 5e-05,
"loss": 2.6229,
"step": 151000
},
{
"epoch": 0.35,
"learning_rate": 5e-05,
"loss": 2.6185,
"step": 152000
},
{
"epoch": 0.35,
"learning_rate": 5e-05,
"loss": 2.6103,
"step": 153000
},
{
"epoch": 0.36,
"learning_rate": 5e-05,
"loss": 2.6089,
"step": 154000
},
{
"epoch": 0.36,
"learning_rate": 5e-05,
"loss": 2.6157,
"step": 155000
},
{
"epoch": 0.36,
"learning_rate": 5e-05,
"loss": 2.6045,
"step": 156000
},
{
"epoch": 0.36,
"learning_rate": 5e-05,
"loss": 2.6045,
"step": 157000
},
{
"epoch": 0.37,
"learning_rate": 5e-05,
"loss": 2.5938,
"step": 158000
},
{
"epoch": 0.37,
"learning_rate": 5e-05,
"loss": 2.5924,
"step": 159000
},
{
"epoch": 0.37,
"learning_rate": 5e-05,
"loss": 2.5943,
"step": 160000
},
{
"epoch": 0.37,
"learning_rate": 5e-05,
"loss": 2.589,
"step": 161000
},
{
"epoch": 0.38,
"learning_rate": 5e-05,
"loss": 2.5906,
"step": 162000
},
{
"epoch": 0.38,
"learning_rate": 5e-05,
"loss": 2.575,
"step": 163000
},
{
"epoch": 0.38,
"learning_rate": 5e-05,
"loss": 2.5799,
"step": 164000
},
{
"epoch": 0.38,
"learning_rate": 5e-05,
"loss": 2.576,
"step": 165000
},
{
"epoch": 0.38,
"learning_rate": 5e-05,
"loss": 2.574,
"step": 166000
},
{
"epoch": 0.39,
"learning_rate": 5e-05,
"loss": 2.5697,
"step": 167000
},
{
"epoch": 0.39,
"learning_rate": 5e-05,
"loss": 2.5699,
"step": 168000
},
{
"epoch": 0.39,
"learning_rate": 5e-05,
"loss": 2.5694,
"step": 169000
},
{
"epoch": 0.39,
"learning_rate": 5e-05,
"loss": 2.5629,
"step": 170000
},
{
"epoch": 0.4,
"learning_rate": 5e-05,
"loss": 2.563,
"step": 171000
},
{
"epoch": 0.4,
"learning_rate": 5e-05,
"loss": 2.5618,
"step": 172000
},
{
"epoch": 0.4,
"learning_rate": 5e-05,
"loss": 2.551,
"step": 173000
},
{
"epoch": 0.4,
"learning_rate": 5e-05,
"loss": 2.5494,
"step": 174000
},
{
"epoch": 0.41,
"learning_rate": 5e-05,
"loss": 2.544,
"step": 175000
},
{
"epoch": 0.41,
"learning_rate": 5e-05,
"loss": 2.5483,
"step": 176000
},
{
"epoch": 0.41,
"learning_rate": 5e-05,
"loss": 2.5458,
"step": 177000
},
{
"epoch": 0.41,
"learning_rate": 5e-05,
"loss": 2.5463,
"step": 178000
},
{
"epoch": 0.41,
"learning_rate": 5e-05,
"loss": 2.5353,
"step": 179000
},
{
"epoch": 0.42,
"learning_rate": 5e-05,
"loss": 2.5317,
"step": 180000
},
{
"epoch": 0.42,
"learning_rate": 5e-05,
"loss": 2.5352,
"step": 181000
},
{
"epoch": 0.42,
"learning_rate": 5e-05,
"loss": 2.5295,
"step": 182000
},
{
"epoch": 0.42,
"learning_rate": 5e-05,
"loss": 2.5286,
"step": 183000
},
{
"epoch": 0.43,
"learning_rate": 5e-05,
"loss": 2.5196,
"step": 184000
},
{
"epoch": 0.43,
"learning_rate": 5e-05,
"loss": 2.5222,
"step": 185000
},
{
"epoch": 0.43,
"learning_rate": 5e-05,
"loss": 2.5245,
"step": 186000
},
{
"epoch": 0.43,
"learning_rate": 5e-05,
"loss": 2.5154,
"step": 187000
},
{
"epoch": 0.44,
"learning_rate": 5e-05,
"loss": 2.509,
"step": 188000
},
{
"epoch": 0.44,
"learning_rate": 5e-05,
"loss": 2.5131,
"step": 189000
},
{
"epoch": 0.44,
"learning_rate": 5e-05,
"loss": 2.5072,
"step": 190000
},
{
"epoch": 0.44,
"learning_rate": 5e-05,
"loss": 2.5079,
"step": 191000
},
{
"epoch": 0.45,
"learning_rate": 5e-05,
"loss": 2.5062,
"step": 192000
},
{
"epoch": 0.45,
"learning_rate": 5e-05,
"loss": 2.5008,
"step": 193000
},
{
"epoch": 0.45,
"learning_rate": 5e-05,
"loss": 2.504,
"step": 194000
},
{
"epoch": 0.45,
"learning_rate": 5e-05,
"loss": 2.5013,
"step": 195000
},
{
"epoch": 0.45,
"learning_rate": 5e-05,
"loss": 2.4979,
"step": 196000
},
{
"epoch": 0.46,
"learning_rate": 5e-05,
"loss": 2.4919,
"step": 197000
},
{
"epoch": 0.46,
"learning_rate": 5e-05,
"loss": 2.4892,
"step": 198000
},
{
"epoch": 0.46,
"learning_rate": 5e-05,
"loss": 2.4897,
"step": 199000
},
{
"epoch": 0.46,
"learning_rate": 5e-05,
"loss": 2.4897,
"step": 200000
},
{
"epoch": 0.47,
"learning_rate": 5e-05,
"loss": 2.4859,
"step": 201000
},
{
"epoch": 0.47,
"learning_rate": 5e-05,
"loss": 2.4766,
"step": 202000
},
{
"epoch": 0.47,
"learning_rate": 5e-05,
"loss": 2.4815,
"step": 203000
},
{
"epoch": 0.47,
"learning_rate": 5e-05,
"loss": 2.4797,
"step": 204000
},
{
"epoch": 0.48,
"learning_rate": 5e-05,
"loss": 2.4782,
"step": 205000
},
{
"epoch": 0.48,
"learning_rate": 5e-05,
"loss": 2.477,
"step": 206000
},
{
"epoch": 0.48,
"learning_rate": 5e-05,
"loss": 2.4714,
"step": 207000
},
{
"epoch": 0.48,
"learning_rate": 5e-05,
"loss": 2.4693,
"step": 208000
},
{
"epoch": 0.48,
"learning_rate": 5e-05,
"loss": 2.4647,
"step": 209000
},
{
"epoch": 0.49,
"learning_rate": 5e-05,
"loss": 2.4675,
"step": 210000
},
{
"epoch": 0.49,
"learning_rate": 5e-05,
"loss": 2.4628,
"step": 211000
},
{
"epoch": 0.49,
"learning_rate": 5e-05,
"loss": 2.458,
"step": 212000
},
{
"epoch": 0.49,
"learning_rate": 5e-05,
"loss": 2.4575,
"step": 213000
},
{
"epoch": 0.5,
"learning_rate": 5e-05,
"loss": 2.4588,
"step": 214000
},
{
"epoch": 0.5,
"learning_rate": 5e-05,
"loss": 2.4541,
"step": 215000
},
{
"epoch": 0.5,
"learning_rate": 5e-05,
"loss": 2.4556,
"step": 216000
},
{
"epoch": 0.5,
"learning_rate": 5e-05,
"loss": 2.4419,
"step": 217000
},
{
"epoch": 0.51,
"learning_rate": 5e-05,
"loss": 2.4505,
"step": 218000
},
{
"epoch": 0.51,
"learning_rate": 5e-05,
"loss": 2.4469,
"step": 219000
},
{
"epoch": 0.51,
"learning_rate": 5e-05,
"loss": 2.4488,
"step": 220000
},
{
"epoch": 0.51,
"learning_rate": 5e-05,
"loss": 2.4493,
"step": 221000
},
{
"epoch": 0.51,
"learning_rate": 5e-05,
"loss": 2.4399,
"step": 222000
},
{
"epoch": 0.52,
"learning_rate": 5e-05,
"loss": 2.4408,
"step": 223000
},
{
"epoch": 0.52,
"learning_rate": 5e-05,
"loss": 2.4413,
"step": 224000
},
{
"epoch": 0.52,
"learning_rate": 5e-05,
"loss": 2.4375,
"step": 225000
},
{
"epoch": 0.52,
"learning_rate": 5e-05,
"loss": 2.4306,
"step": 226000
},
{
"epoch": 0.53,
"learning_rate": 5e-05,
"loss": 2.4354,
"step": 227000
},
{
"epoch": 0.53,
"learning_rate": 5e-05,
"loss": 2.426,
"step": 228000
},
{
"epoch": 0.53,
"learning_rate": 5e-05,
"loss": 2.4307,
"step": 229000
},
{
"epoch": 0.53,
"learning_rate": 5e-05,
"loss": 2.4297,
"step": 230000
},
{
"epoch": 0.54,
"learning_rate": 5e-05,
"loss": 2.4268,
"step": 231000
},
{
"epoch": 0.54,
"learning_rate": 5e-05,
"loss": 2.4249,
"step": 232000
},
{
"epoch": 0.54,
"learning_rate": 5e-05,
"loss": 2.4211,
"step": 233000
},
{
"epoch": 0.54,
"learning_rate": 5e-05,
"loss": 2.4233,
"step": 234000
},
{
"epoch": 0.54,
"learning_rate": 5e-05,
"loss": 2.415,
"step": 235000
},
{
"epoch": 0.55,
"learning_rate": 5e-05,
"loss": 2.4163,
"step": 236000
},
{
"epoch": 0.55,
"learning_rate": 5e-05,
"loss": 2.4185,
"step": 237000
},
{
"epoch": 0.55,
"learning_rate": 5e-05,
"loss": 2.4148,
"step": 238000
},
{
"epoch": 0.55,
"learning_rate": 5e-05,
"loss": 2.4089,
"step": 239000
},
{
"epoch": 0.56,
"learning_rate": 5e-05,
"loss": 2.411,
"step": 240000
},
{
"epoch": 0.56,
"learning_rate": 5e-05,
"loss": 2.4061,
"step": 241000
},
{
"epoch": 0.56,
"learning_rate": 5e-05,
"loss": 2.4056,
"step": 242000
},
{
"epoch": 0.56,
"learning_rate": 5e-05,
"loss": 2.402,
"step": 243000
},
{
"epoch": 0.57,
"learning_rate": 5e-05,
"loss": 2.4042,
"step": 244000
},
{
"epoch": 0.57,
"learning_rate": 5e-05,
"loss": 2.4025,
"step": 245000
},
{
"epoch": 0.57,
"learning_rate": 5e-05,
"loss": 2.3981,
"step": 246000
},
{
"epoch": 0.57,
"learning_rate": 5e-05,
"loss": 2.4005,
"step": 247000
},
{
"epoch": 0.57,
"learning_rate": 5e-05,
"loss": 2.3938,
"step": 248000
},
{
"epoch": 0.58,
"learning_rate": 5e-05,
"loss": 2.3914,
"step": 249000
},
{
"epoch": 0.58,
"learning_rate": 5e-05,
"loss": 2.3901,
"step": 250000
},
{
"epoch": 0.58,
"learning_rate": 5e-05,
"loss": 2.3912,
"step": 251000
},
{
"epoch": 0.58,
"learning_rate": 5e-05,
"loss": 2.3881,
"step": 252000
},
{
"epoch": 0.59,
"learning_rate": 5e-05,
"loss": 2.3904,
"step": 253000
},
{
"epoch": 0.59,
"learning_rate": 5e-05,
"loss": 2.3907,
"step": 254000
},
{
"epoch": 0.59,
"learning_rate": 5e-05,
"loss": 2.3827,
"step": 255000
},
{
"epoch": 0.59,
"learning_rate": 5e-05,
"loss": 2.3832,
"step": 256000
},
{
"epoch": 0.6,
"learning_rate": 5e-05,
"loss": 2.3824,
"step": 257000
},
{
"epoch": 0.6,
"learning_rate": 5e-05,
"loss": 2.3831,
"step": 258000
},
{
"epoch": 0.6,
"learning_rate": 5e-05,
"loss": 2.377,
"step": 259000
},
{
"epoch": 0.6,
"learning_rate": 5e-05,
"loss": 2.3732,
"step": 260000
},
{
"epoch": 0.6,
"learning_rate": 5e-05,
"loss": 2.3753,
"step": 261000
},
{
"epoch": 0.61,
"learning_rate": 5e-05,
"loss": 2.3747,
"step": 262000
},
{
"epoch": 0.61,
"learning_rate": 5e-05,
"loss": 2.3684,
"step": 263000
},
{
"epoch": 0.61,
"learning_rate": 5e-05,
"loss": 2.3716,
"step": 264000
},
{
"epoch": 0.61,
"learning_rate": 5e-05,
"loss": 2.3681,
"step": 265000
},
{
"epoch": 0.62,
"learning_rate": 5e-05,
"loss": 2.3694,
"step": 266000
},
{
"epoch": 0.62,
"learning_rate": 5e-05,
"loss": 2.3622,
"step": 267000
},
{
"epoch": 0.62,
"learning_rate": 5e-05,
"loss": 2.3646,
"step": 268000
},
{
"epoch": 0.62,
"learning_rate": 5e-05,
"loss": 2.367,
"step": 269000
},
{
"epoch": 0.63,
"learning_rate": 5e-05,
"loss": 2.365,
"step": 270000
},
{
"epoch": 0.63,
"learning_rate": 5e-05,
"loss": 2.3608,
"step": 271000
},
{
"epoch": 0.63,
"learning_rate": 5e-05,
"loss": 2.3558,
"step": 272000
},
{
"epoch": 0.63,
"learning_rate": 5e-05,
"loss": 2.3627,
"step": 273000
},
{
"epoch": 0.64,
"learning_rate": 5e-05,
"loss": 2.3541,
"step": 274000
},
{
"epoch": 0.64,
"learning_rate": 5e-05,
"loss": 2.3541,
"step": 275000
},
{
"epoch": 0.64,
"learning_rate": 5e-05,
"loss": 2.3516,
"step": 276000
},
{
"epoch": 0.64,
"learning_rate": 5e-05,
"loss": 2.354,
"step": 277000
},
{
"epoch": 0.64,
"learning_rate": 5e-05,
"loss": 2.3494,
"step": 278000
},
{
"epoch": 0.65,
"learning_rate": 5e-05,
"loss": 2.3529,
"step": 279000
},
{
"epoch": 0.65,
"learning_rate": 5e-05,
"loss": 2.3493,
"step": 280000
},
{
"epoch": 0.65,
"learning_rate": 5e-05,
"loss": 2.3519,
"step": 281000
},
{
"epoch": 0.65,
"learning_rate": 5e-05,
"loss": 2.3442,
"step": 282000
},
{
"epoch": 0.66,
"learning_rate": 5e-05,
"loss": 2.3431,
"step": 283000
},
{
"epoch": 0.66,
"learning_rate": 5e-05,
"loss": 2.3489,
"step": 284000
},
{
"epoch": 0.66,
"learning_rate": 5e-05,
"loss": 2.3446,
"step": 285000
},
{
"epoch": 0.66,
"learning_rate": 5e-05,
"loss": 2.3451,
"step": 286000
},
{
"epoch": 0.67,
"learning_rate": 5e-05,
"loss": 2.3307,
"step": 287000
},
{
"epoch": 0.67,
"learning_rate": 5e-05,
"loss": 2.3336,
"step": 288000
},
{
"epoch": 0.67,
"learning_rate": 5e-05,
"loss": 2.3383,
"step": 289000
},
{
"epoch": 0.67,
"learning_rate": 5e-05,
"loss": 2.3376,
"step": 290000
},
{
"epoch": 0.67,
"learning_rate": 5e-05,
"loss": 2.3336,
"step": 291000
},
{
"epoch": 0.68,
"learning_rate": 5e-05,
"loss": 2.3351,
"step": 292000
},
{
"epoch": 0.68,
"learning_rate": 5e-05,
"loss": 2.3296,
"step": 293000
},
{
"epoch": 0.68,
"learning_rate": 5e-05,
"loss": 2.3295,
"step": 294000
},
{
"epoch": 0.68,
"learning_rate": 5e-05,
"loss": 2.3274,
"step": 295000
},
{
"epoch": 0.69,
"learning_rate": 5e-05,
"loss": 2.3268,
"step": 296000
},
{
"epoch": 0.69,
"learning_rate": 5e-05,
"loss": 2.3289,
"step": 297000
},
{
"epoch": 0.69,
"learning_rate": 5e-05,
"loss": 2.3293,
"step": 298000
},
{
"epoch": 0.69,
"learning_rate": 5e-05,
"loss": 2.3212,
"step": 299000
},
{
"epoch": 0.7,
"learning_rate": 5e-05,
"loss": 2.3189,
"step": 300000
},
{
"epoch": 0.7,
"eval_accuracy": 0.5684444981680046,
"eval_loss": 2.2109375,
"eval_runtime": 4880.4554,
"eval_samples_per_second": 114.436,
"eval_steps_per_second": 0.894,
"step": 300000
},
{
"epoch": 0.7,
"learning_rate": 5e-05,
"loss": 2.3193,
"step": 301000
},
{
"epoch": 0.7,
"learning_rate": 5e-05,
"loss": 2.317,
"step": 302000
},
{
"epoch": 0.7,
"learning_rate": 5e-05,
"loss": 2.3212,
"step": 303000
},
{
"epoch": 0.7,
"learning_rate": 5e-05,
"loss": 2.317,
"step": 304000
},
{
"epoch": 0.71,
"learning_rate": 5e-05,
"loss": 2.3183,
"step": 305000
},
{
"epoch": 0.71,
"learning_rate": 5e-05,
"loss": 2.3178,
"step": 306000
},
{
"epoch": 0.71,
"learning_rate": 5e-05,
"loss": 2.3085,
"step": 307000
},
{
"epoch": 0.71,
"learning_rate": 5e-05,
"loss": 2.3127,
"step": 308000
},
{
"epoch": 0.72,
"learning_rate": 5e-05,
"loss": 2.3149,
"step": 309000
},
{
"epoch": 0.72,
"learning_rate": 5e-05,
"loss": 2.3091,
"step": 310000
},
{
"epoch": 0.72,
"learning_rate": 5e-05,
"loss": 2.3088,
"step": 311000
},
{
"epoch": 0.72,
"learning_rate": 5e-05,
"loss": 2.3097,
"step": 312000
},
{
"epoch": 0.73,
"learning_rate": 5e-05,
"loss": 2.3131,
"step": 313000
},
{
"epoch": 0.73,
"learning_rate": 5e-05,
"loss": 2.3031,
"step": 314000
},
{
"epoch": 0.73,
"learning_rate": 5e-05,
"loss": 2.302,
"step": 315000
},
{
"epoch": 0.73,
"learning_rate": 5e-05,
"loss": 2.3056,
"step": 316000
},
{
"epoch": 0.73,
"learning_rate": 5e-05,
"loss": 2.3046,
"step": 317000
},
{
"epoch": 0.74,
"learning_rate": 5e-05,
"loss": 2.2997,
"step": 318000
},
{
"epoch": 0.74,
"learning_rate": 5e-05,
"loss": 2.2933,
"step": 319000
},
{
"epoch": 0.74,
"learning_rate": 5e-05,
"loss": 2.2992,
"step": 320000
},
{
"epoch": 0.74,
"learning_rate": 5e-05,
"loss": 2.2947,
"step": 321000
},
{
"epoch": 0.75,
"learning_rate": 5e-05,
"loss": 2.2933,
"step": 322000
},
{
"epoch": 0.75,
"learning_rate": 5e-05,
"loss": 2.295,
"step": 323000
},
{
"epoch": 0.75,
"learning_rate": 5e-05,
"loss": 2.2935,
"step": 324000
},
{
"epoch": 0.75,
"learning_rate": 5e-05,
"loss": 2.2926,
"step": 325000
},
{
"epoch": 0.76,
"learning_rate": 5e-05,
"loss": 2.2887,
"step": 326000
},
{
"epoch": 0.76,
"learning_rate": 5e-05,
"loss": 2.2966,
"step": 327000
},
{
"epoch": 0.76,
"learning_rate": 5e-05,
"loss": 2.2924,
"step": 328000
},
{
"epoch": 0.76,
"learning_rate": 5e-05,
"loss": 2.2897,
"step": 329000
},
{
"epoch": 0.76,
"learning_rate": 5e-05,
"loss": 2.2903,
"step": 330000
},
{
"epoch": 0.77,
"learning_rate": 5e-05,
"loss": 2.282,
"step": 331000
},
{
"epoch": 0.77,
"learning_rate": 5e-05,
"loss": 2.281,
"step": 332000
},
{
"epoch": 0.77,
"learning_rate": 5e-05,
"loss": 2.2903,
"step": 333000
},
{
"epoch": 0.77,
"learning_rate": 5e-05,
"loss": 2.2831,
"step": 334000
},
{
"epoch": 0.78,
"learning_rate": 5e-05,
"loss": 2.2874,
"step": 335000
},
{
"epoch": 0.78,
"learning_rate": 5e-05,
"loss": 2.2722,
"step": 336000
},
{
"epoch": 0.78,
"learning_rate": 5e-05,
"loss": 2.2823,
"step": 337000
},
{
"epoch": 0.78,
"learning_rate": 5e-05,
"loss": 2.2793,
"step": 338000
},
{
"epoch": 0.79,
"learning_rate": 5e-05,
"loss": 2.2839,
"step": 339000
},
{
"epoch": 0.79,
"learning_rate": 5e-05,
"loss": 2.2808,
"step": 340000
},
{
"epoch": 0.79,
"learning_rate": 5e-05,
"loss": 2.2782,
"step": 341000
},
{
"epoch": 0.79,
"learning_rate": 5e-05,
"loss": 2.2751,
"step": 342000
},
{
"epoch": 0.8,
"learning_rate": 5e-05,
"loss": 2.2728,
"step": 343000
},
{
"epoch": 0.8,
"learning_rate": 5e-05,
"loss": 2.2736,
"step": 344000
},
{
"epoch": 0.8,
"learning_rate": 5e-05,
"loss": 2.2761,
"step": 345000
},
{
"epoch": 0.8,
"learning_rate": 5e-05,
"loss": 2.2692,
"step": 346000
},
{
"epoch": 0.8,
"learning_rate": 5e-05,
"loss": 2.269,
"step": 347000
},
{
"epoch": 0.81,
"learning_rate": 5e-05,
"loss": 2.2704,
"step": 348000
},
{
"epoch": 0.81,
"learning_rate": 5e-05,
"loss": 2.2673,
"step": 349000
},
{
"epoch": 0.81,
"learning_rate": 5e-05,
"loss": 2.2657,
"step": 350000
},
{
"epoch": 0.81,
"learning_rate": 5e-05,
"loss": 2.2731,
"step": 351000
},
{
"epoch": 0.82,
"learning_rate": 5e-05,
"loss": 2.2677,
"step": 352000
},
{
"epoch": 0.82,
"learning_rate": 5e-05,
"loss": 2.2628,
"step": 353000
},
{
"epoch": 0.82,
"learning_rate": 5e-05,
"loss": 2.2665,
"step": 354000
},
{
"epoch": 0.82,
"learning_rate": 5e-05,
"loss": 2.2649,
"step": 355000
},
{
"epoch": 0.83,
"learning_rate": 5e-05,
"loss": 2.266,
"step": 356000
},
{
"epoch": 0.83,
"learning_rate": 5e-05,
"loss": 2.2626,
"step": 357000
},
{
"epoch": 0.83,
"learning_rate": 5e-05,
"loss": 2.2605,
"step": 358000
},
{
"epoch": 0.83,
"learning_rate": 5e-05,
"loss": 2.2598,
"step": 359000
},
{
"epoch": 0.83,
"learning_rate": 5e-05,
"loss": 2.2541,
"step": 360000
},
{
"epoch": 0.84,
"learning_rate": 5e-05,
"loss": 2.2527,
"step": 361000
},
{
"epoch": 0.84,
"learning_rate": 5e-05,
"loss": 2.2495,
"step": 362000
},
{
"epoch": 0.84,
"learning_rate": 5e-05,
"loss": 2.2552,
"step": 363000
},
{
"epoch": 0.84,
"learning_rate": 5e-05,
"loss": 2.2575,
"step": 364000
},
{
"epoch": 0.85,
"learning_rate": 5e-05,
"loss": 2.2532,
"step": 365000
},
{
"epoch": 0.85,
"learning_rate": 5e-05,
"loss": 2.2531,
"step": 366000
},
{
"epoch": 0.85,
"learning_rate": 5e-05,
"loss": 2.2512,
"step": 367000
},
{
"epoch": 0.85,
"learning_rate": 5e-05,
"loss": 2.2536,
"step": 368000
},
{
"epoch": 0.86,
"learning_rate": 5e-05,
"loss": 2.25,
"step": 369000
},
{
"epoch": 0.86,
"learning_rate": 5e-05,
"loss": 2.2494,
"step": 370000
},
{
"epoch": 0.86,
"learning_rate": 5e-05,
"loss": 2.2454,
"step": 371000
},
{
"epoch": 0.86,
"learning_rate": 5e-05,
"loss": 2.2416,
"step": 372000
},
{
"epoch": 0.86,
"learning_rate": 5e-05,
"loss": 2.2417,
"step": 373000
},
{
"epoch": 0.87,
"learning_rate": 5e-05,
"loss": 2.2418,
"step": 374000
},
{
"epoch": 0.87,
"learning_rate": 5e-05,
"loss": 2.2467,
"step": 375000
},
{
"epoch": 0.87,
"learning_rate": 5e-05,
"loss": 2.2409,
"step": 376000
},
{
"epoch": 0.87,
"learning_rate": 5e-05,
"loss": 2.2451,
"step": 377000
},
{
"epoch": 0.88,
"learning_rate": 5e-05,
"loss": 2.2397,
"step": 378000
},
{
"epoch": 0.88,
"learning_rate": 5e-05,
"loss": 2.2392,
"step": 379000
},
{
"epoch": 0.88,
"learning_rate": 5e-05,
"loss": 2.2388,
"step": 380000
},
{
"epoch": 0.88,
"learning_rate": 5e-05,
"loss": 2.2369,
"step": 381000
},
{
"epoch": 0.89,
"learning_rate": 5e-05,
"loss": 2.2354,
"step": 382000
},
{
"epoch": 0.89,
"learning_rate": 5e-05,
"loss": 2.2367,
"step": 383000
},
{
"epoch": 0.89,
"learning_rate": 5e-05,
"loss": 2.2383,
"step": 384000
},
{
"epoch": 0.89,
"learning_rate": 5e-05,
"loss": 2.2352,
"step": 385000
},
{
"epoch": 0.89,
"learning_rate": 5e-05,
"loss": 2.236,
"step": 386000
},
{
"epoch": 0.9,
"learning_rate": 5e-05,
"loss": 2.2327,
"step": 387000
},
{
"epoch": 0.9,
"learning_rate": 5e-05,
"loss": 2.2345,
"step": 388000
},
{
"epoch": 0.9,
"learning_rate": 5e-05,
"loss": 2.2361,
"step": 389000
},
{
"epoch": 0.9,
"learning_rate": 5e-05,
"loss": 2.2316,
"step": 390000
},
{
"epoch": 0.91,
"learning_rate": 5e-05,
"loss": 2.2315,
"step": 391000
},
{
"epoch": 0.91,
"learning_rate": 5e-05,
"loss": 2.2315,
"step": 392000
},
{
"epoch": 0.91,
"learning_rate": 5e-05,
"loss": 2.227,
"step": 393000
},
{
"epoch": 0.91,
"learning_rate": 5e-05,
"loss": 2.2307,
"step": 394000
},
{
"epoch": 0.92,
"learning_rate": 5e-05,
"loss": 2.2276,
"step": 395000
},
{
"epoch": 0.92,
"learning_rate": 5e-05,
"loss": 2.219,
"step": 396000
},
{
"epoch": 0.92,
"learning_rate": 5e-05,
"loss": 2.222,
"step": 397000
},
{
"epoch": 0.92,
"learning_rate": 5e-05,
"loss": 2.2262,
"step": 398000
},
{
"epoch": 0.92,
"learning_rate": 5e-05,
"loss": 2.2224,
"step": 399000
},
{
"epoch": 0.93,
"learning_rate": 5e-05,
"loss": 2.217,
"step": 400000
},
{
"epoch": 0.93,
"learning_rate": 5e-05,
"loss": 2.2236,
"step": 401000
},
{
"epoch": 0.93,
"learning_rate": 5e-05,
"loss": 2.2256,
"step": 402000
},
{
"epoch": 0.93,
"learning_rate": 5e-05,
"loss": 2.2181,
"step": 403000
},
{
"epoch": 0.94,
"learning_rate": 5e-05,
"loss": 2.2209,
"step": 404000
},
{
"epoch": 0.94,
"learning_rate": 5e-05,
"loss": 2.2246,
"step": 405000
},
{
"epoch": 0.94,
"learning_rate": 5e-05,
"loss": 2.223,
"step": 406000
},
{
"epoch": 0.94,
"learning_rate": 5e-05,
"loss": 2.2164,
"step": 407000
},
{
"epoch": 0.95,
"learning_rate": 5e-05,
"loss": 2.2105,
"step": 408000
},
{
"epoch": 0.95,
"learning_rate": 5e-05,
"loss": 2.2181,
"step": 409000
},
{
"epoch": 0.95,
"learning_rate": 5e-05,
"loss": 2.2212,
"step": 410000
},
{
"epoch": 0.95,
"learning_rate": 5e-05,
"loss": 2.2138,
"step": 411000
},
{
"epoch": 0.95,
"learning_rate": 5e-05,
"loss": 2.208,
"step": 412000
},
{
"epoch": 0.96,
"learning_rate": 5e-05,
"loss": 2.217,
"step": 413000
},
{
"epoch": 0.96,
"learning_rate": 5e-05,
"loss": 2.2128,
"step": 414000
},
{
"epoch": 0.96,
"learning_rate": 5e-05,
"loss": 2.2139,
"step": 415000
},
{
"epoch": 0.96,
"learning_rate": 5e-05,
"loss": 2.206,
"step": 416000
},
{
"epoch": 0.97,
"learning_rate": 5e-05,
"loss": 2.213,
"step": 417000
},
{
"epoch": 0.97,
"learning_rate": 5e-05,
"loss": 2.2072,
"step": 418000
},
{
"epoch": 0.97,
"learning_rate": 5e-05,
"loss": 2.2115,
"step": 419000
},
{
"epoch": 0.97,
"learning_rate": 5e-05,
"loss": 2.2064,
"step": 420000
},
{
"epoch": 0.98,
"learning_rate": 5e-05,
"loss": 2.2061,
"step": 421000
},
{
"epoch": 0.98,
"learning_rate": 5e-05,
"loss": 2.2079,
"step": 422000
},
{
"epoch": 0.98,
"learning_rate": 5e-05,
"loss": 2.2088,
"step": 423000
},
{
"epoch": 0.98,
"learning_rate": 5e-05,
"loss": 2.2069,
"step": 424000
},
{
"epoch": 0.99,
"learning_rate": 5e-05,
"loss": 2.2037,
"step": 425000
},
{
"epoch": 0.99,
"learning_rate": 5e-05,
"loss": 2.2074,
"step": 426000
},
{
"epoch": 0.99,
"learning_rate": 5e-05,
"loss": 2.2036,
"step": 427000
},
{
"epoch": 0.99,
"learning_rate": 5e-05,
"loss": 2.202,
"step": 428000
},
{
"epoch": 0.99,
"learning_rate": 5e-05,
"loss": 2.2022,
"step": 429000
},
{
"epoch": 1.0,
"learning_rate": 5e-05,
"loss": 2.2031,
"step": 430000
},
{
"epoch": 1.0,
"learning_rate": 5e-05,
"loss": 2.1998,
"step": 431000
},
{
"epoch": 1.0,
"learning_rate": 5e-05,
"loss": 2.202,
"step": 432000
},
{
"epoch": 1.0,
"learning_rate": 5e-05,
"loss": 2.1916,
"step": 433000
},
{
"epoch": 1.01,
"learning_rate": 5e-05,
"loss": 2.1934,
"step": 434000
},
{
"epoch": 1.01,
"learning_rate": 5e-05,
"loss": 2.1958,
"step": 435000
},
{
"epoch": 1.01,
"learning_rate": 5e-05,
"loss": 2.1933,
"step": 436000
},
{
"epoch": 1.01,
"learning_rate": 5e-05,
"loss": 2.1945,
"step": 437000
},
{
"epoch": 1.02,
"learning_rate": 5e-05,
"loss": 2.1889,
"step": 438000
},
{
"epoch": 1.02,
"learning_rate": 5e-05,
"loss": 2.1929,
"step": 439000
},
{
"epoch": 1.02,
"learning_rate": 5e-05,
"loss": 2.1935,
"step": 440000
},
{
"epoch": 1.02,
"learning_rate": 5e-05,
"loss": 2.1883,
"step": 441000
},
{
"epoch": 1.02,
"learning_rate": 5e-05,
"loss": 2.1882,
"step": 442000
},
{
"epoch": 1.03,
"learning_rate": 5e-05,
"loss": 2.1835,
"step": 443000
},
{
"epoch": 1.03,
"learning_rate": 5e-05,
"loss": 2.1862,
"step": 444000
},
{
"epoch": 1.03,
"learning_rate": 5e-05,
"loss": 2.1869,
"step": 445000
},
{
"epoch": 1.03,
"learning_rate": 5e-05,
"loss": 2.1906,
"step": 446000
},
{
"epoch": 1.04,
"learning_rate": 5e-05,
"loss": 2.1825,
"step": 447000
},
{
"epoch": 1.04,
"learning_rate": 5e-05,
"loss": 2.1902,
"step": 448000
},
{
"epoch": 1.04,
"learning_rate": 5e-05,
"loss": 2.1843,
"step": 449000
},
{
"epoch": 1.04,
"learning_rate": 5e-05,
"loss": 2.1811,
"step": 450000
},
{
"epoch": 1.04,
"eval_accuracy": 0.5877310925035356,
"eval_loss": 2.078125,
"eval_runtime": 4896.1088,
"eval_samples_per_second": 114.07,
"eval_steps_per_second": 0.891,
"step": 450000
},
{
"epoch": 1.05,
"learning_rate": 5e-05,
"loss": 2.1848,
"step": 451000
},
{
"epoch": 1.05,
"learning_rate": 5e-05,
"loss": 2.1788,
"step": 452000
},
{
"epoch": 1.05,
"learning_rate": 5e-05,
"loss": 2.185,
"step": 453000
},
{
"epoch": 1.05,
"learning_rate": 5e-05,
"loss": 2.1827,
"step": 454000
},
{
"epoch": 1.05,
"learning_rate": 5e-05,
"loss": 2.1772,
"step": 455000
},
{
"epoch": 1.06,
"learning_rate": 5e-05,
"loss": 2.1792,
"step": 456000
},
{
"epoch": 1.06,
"learning_rate": 5e-05,
"loss": 2.1799,
"step": 457000
},
{
"epoch": 1.06,
"learning_rate": 5e-05,
"loss": 2.1831,
"step": 458000
},
{
"epoch": 1.06,
"learning_rate": 5e-05,
"loss": 2.1763,
"step": 459000
},
{
"epoch": 1.07,
"learning_rate": 5e-05,
"loss": 2.1773,
"step": 460000
},
{
"epoch": 1.07,
"learning_rate": 5e-05,
"loss": 2.1804,
"step": 461000
},
{
"epoch": 1.07,
"learning_rate": 5e-05,
"loss": 2.1711,
"step": 462000
},
{
"epoch": 1.07,
"learning_rate": 5e-05,
"loss": 2.1788,
"step": 463000
},
{
"epoch": 1.08,
"learning_rate": 5e-05,
"loss": 2.174,
"step": 464000
},
{
"epoch": 1.08,
"learning_rate": 5e-05,
"loss": 2.1708,
"step": 465000
},
{
"epoch": 1.08,
"learning_rate": 5e-05,
"loss": 2.1772,
"step": 466000
},
{
"epoch": 1.08,
"learning_rate": 5e-05,
"loss": 2.174,
"step": 467000
},
{
"epoch": 1.08,
"learning_rate": 5e-05,
"loss": 2.1663,
"step": 468000
},
{
"epoch": 1.09,
"learning_rate": 5e-05,
"loss": 2.1737,
"step": 469000
},
{
"epoch": 1.09,
"learning_rate": 5e-05,
"loss": 2.1696,
"step": 470000
},
{
"epoch": 1.09,
"learning_rate": 5e-05,
"loss": 2.1726,
"step": 471000
},
{
"epoch": 1.09,
"learning_rate": 5e-05,
"loss": 2.1681,
"step": 472000
},
{
"epoch": 1.1,
"learning_rate": 5e-05,
"loss": 2.174,
"step": 473000
},
{
"epoch": 1.1,
"learning_rate": 5e-05,
"loss": 2.1679,
"step": 474000
},
{
"epoch": 1.1,
"learning_rate": 5e-05,
"loss": 2.17,
"step": 475000
},
{
"epoch": 1.1,
"learning_rate": 5e-05,
"loss": 2.1664,
"step": 476000
},
{
"epoch": 1.11,
"learning_rate": 5e-05,
"loss": 2.1657,
"step": 477000
},
{
"epoch": 1.11,
"learning_rate": 5e-05,
"loss": 2.1664,
"step": 478000
},
{
"epoch": 1.11,
"learning_rate": 5e-05,
"loss": 2.1674,
"step": 479000
},
{
"epoch": 1.11,
"learning_rate": 5e-05,
"loss": 2.1616,
"step": 480000
},
{
"epoch": 1.11,
"learning_rate": 5e-05,
"loss": 2.1597,
"step": 481000
},
{
"epoch": 1.12,
"learning_rate": 5e-05,
"loss": 2.161,
"step": 482000
},
{
"epoch": 1.12,
"learning_rate": 5e-05,
"loss": 2.1626,
"step": 483000
},
{
"epoch": 1.12,
"learning_rate": 5e-05,
"loss": 2.1643,
"step": 484000
},
{
"epoch": 1.12,
"learning_rate": 5e-05,
"loss": 2.1597,
"step": 485000
},
{
"epoch": 1.13,
"learning_rate": 5e-05,
"loss": 2.1575,
"step": 486000
},
{
"epoch": 1.13,
"learning_rate": 5e-05,
"loss": 2.1551,
"step": 487000
},
{
"epoch": 1.13,
"learning_rate": 5e-05,
"loss": 2.1561,
"step": 488000
},
{
"epoch": 1.13,
"learning_rate": 5e-05,
"loss": 2.1524,
"step": 489000
},
{
"epoch": 1.14,
"learning_rate": 5e-05,
"loss": 2.1631,
"step": 490000
},
{
"epoch": 1.14,
"learning_rate": 5e-05,
"loss": 2.1553,
"step": 491000
},
{
"epoch": 1.14,
"learning_rate": 5e-05,
"loss": 2.1595,
"step": 492000
},
{
"epoch": 1.14,
"learning_rate": 5e-05,
"loss": 2.1556,
"step": 493000
},
{
"epoch": 1.15,
"learning_rate": 5e-05,
"loss": 2.1572,
"step": 494000
},
{
"epoch": 1.15,
"learning_rate": 5e-05,
"loss": 2.1586,
"step": 495000
},
{
"epoch": 1.15,
"learning_rate": 5e-05,
"loss": 2.161,
"step": 496000
},
{
"epoch": 1.15,
"learning_rate": 5e-05,
"loss": 2.152,
"step": 497000
},
{
"epoch": 1.15,
"learning_rate": 5e-05,
"loss": 2.1611,
"step": 498000
},
{
"epoch": 1.16,
"learning_rate": 5e-05,
"loss": 2.1484,
"step": 499000
},
{
"epoch": 1.16,
"learning_rate": 5e-05,
"loss": 2.1516,
"step": 500000
},
{
"epoch": 1.16,
"learning_rate": 5e-05,
"loss": 2.1504,
"step": 501000
},
{
"epoch": 1.16,
"learning_rate": 5e-05,
"loss": 2.1493,
"step": 502000
},
{
"epoch": 1.17,
"learning_rate": 5e-05,
"loss": 2.1494,
"step": 503000
},
{
"epoch": 1.17,
"learning_rate": 5e-05,
"loss": 2.1507,
"step": 504000
},
{
"epoch": 1.17,
"learning_rate": 5e-05,
"loss": 2.1555,
"step": 505000
},
{
"epoch": 1.17,
"learning_rate": 5e-05,
"loss": 2.1522,
"step": 506000
},
{
"epoch": 1.18,
"learning_rate": 5e-05,
"loss": 2.1477,
"step": 507000
},
{
"epoch": 1.18,
"learning_rate": 5e-05,
"loss": 2.1452,
"step": 508000
},
{
"epoch": 1.18,
"learning_rate": 5e-05,
"loss": 2.1516,
"step": 509000
},
{
"epoch": 1.18,
"learning_rate": 5e-05,
"loss": 2.1486,
"step": 510000
},
{
"epoch": 1.18,
"learning_rate": 5e-05,
"loss": 2.1481,
"step": 511000
},
{
"epoch": 1.19,
"learning_rate": 5e-05,
"loss": 2.1461,
"step": 512000
},
{
"epoch": 1.19,
"learning_rate": 5e-05,
"loss": 2.1393,
"step": 513000
},
{
"epoch": 1.19,
"learning_rate": 5e-05,
"loss": 2.1419,
"step": 514000
},
{
"epoch": 1.19,
"learning_rate": 5e-05,
"loss": 2.1376,
"step": 515000
},
{
"epoch": 1.2,
"learning_rate": 5e-05,
"loss": 2.1486,
"step": 516000
},
{
"epoch": 1.2,
"learning_rate": 5e-05,
"loss": 2.1425,
"step": 517000
},
{
"epoch": 1.2,
"learning_rate": 5e-05,
"loss": 2.147,
"step": 518000
},
{
"epoch": 1.2,
"learning_rate": 5e-05,
"loss": 2.1458,
"step": 519000
},
{
"epoch": 1.21,
"learning_rate": 5e-05,
"loss": 2.1393,
"step": 520000
},
{
"epoch": 1.21,
"learning_rate": 5e-05,
"loss": 2.141,
"step": 521000
},
{
"epoch": 1.21,
"learning_rate": 5e-05,
"loss": 2.1375,
"step": 522000
},
{
"epoch": 1.21,
"learning_rate": 5e-05,
"loss": 2.143,
"step": 523000
},
{
"epoch": 1.21,
"learning_rate": 5e-05,
"loss": 2.1395,
"step": 524000
},
{
"epoch": 1.22,
"learning_rate": 5e-05,
"loss": 2.1376,
"step": 525000
},
{
"epoch": 1.22,
"learning_rate": 5e-05,
"loss": 2.1365,
"step": 526000
},
{
"epoch": 1.22,
"learning_rate": 5e-05,
"loss": 2.1378,
"step": 527000
},
{
"epoch": 1.22,
"learning_rate": 5e-05,
"loss": 2.1361,
"step": 528000
},
{
"epoch": 1.23,
"learning_rate": 5e-05,
"loss": 2.1397,
"step": 529000
},
{
"epoch": 1.23,
"learning_rate": 5e-05,
"loss": 2.1319,
"step": 530000
},
{
"epoch": 1.23,
"learning_rate": 5e-05,
"loss": 2.1341,
"step": 531000
},
{
"epoch": 1.23,
"learning_rate": 5e-05,
"loss": 2.1307,
"step": 532000
},
{
"epoch": 1.24,
"learning_rate": 5e-05,
"loss": 2.1273,
"step": 533000
},
{
"epoch": 1.24,
"learning_rate": 5e-05,
"loss": 2.1317,
"step": 534000
},
{
"epoch": 1.24,
"learning_rate": 5e-05,
"loss": 2.1268,
"step": 535000
},
{
"epoch": 1.24,
"learning_rate": 5e-05,
"loss": 2.1342,
"step": 536000
},
{
"epoch": 1.24,
"learning_rate": 5e-05,
"loss": 2.1372,
"step": 537000
},
{
"epoch": 1.25,
"learning_rate": 5e-05,
"loss": 2.1311,
"step": 538000
},
{
"epoch": 1.25,
"learning_rate": 5e-05,
"loss": 2.1301,
"step": 539000
},
{
"epoch": 1.25,
"learning_rate": 5e-05,
"loss": 2.1283,
"step": 540000
},
{
"epoch": 1.25,
"learning_rate": 5e-05,
"loss": 2.1264,
"step": 541000
},
{
"epoch": 1.26,
"learning_rate": 5e-05,
"loss": 2.1296,
"step": 542000
},
{
"epoch": 1.26,
"learning_rate": 5e-05,
"loss": 2.1277,
"step": 543000
},
{
"epoch": 1.26,
"learning_rate": 5e-05,
"loss": 2.1296,
"step": 544000
},
{
"epoch": 1.26,
"learning_rate": 5e-05,
"loss": 2.1264,
"step": 545000
},
{
"epoch": 1.27,
"learning_rate": 5e-05,
"loss": 2.1244,
"step": 546000
},
{
"epoch": 1.27,
"learning_rate": 5e-05,
"loss": 2.1227,
"step": 547000
},
{
"epoch": 1.27,
"learning_rate": 5e-05,
"loss": 2.1258,
"step": 548000
},
{
"epoch": 1.27,
"learning_rate": 5e-05,
"loss": 2.1238,
"step": 549000
},
{
"epoch": 1.27,
"learning_rate": 5e-05,
"loss": 2.1293,
"step": 550000
},
{
"epoch": 1.28,
"learning_rate": 5e-05,
"loss": 2.1263,
"step": 551000
},
{
"epoch": 1.28,
"learning_rate": 5e-05,
"loss": 2.117,
"step": 552000
},
{
"epoch": 1.28,
"learning_rate": 5e-05,
"loss": 2.1237,
"step": 553000
},
{
"epoch": 1.28,
"learning_rate": 5e-05,
"loss": 2.1251,
"step": 554000
},
{
"epoch": 1.29,
"learning_rate": 5e-05,
"loss": 2.1243,
"step": 555000
},
{
"epoch": 1.29,
"learning_rate": 5e-05,
"loss": 2.1187,
"step": 556000
},
{
"epoch": 1.29,
"learning_rate": 5e-05,
"loss": 2.1179,
"step": 557000
},
{
"epoch": 1.29,
"learning_rate": 5e-05,
"loss": 2.1226,
"step": 558000
},
{
"epoch": 1.3,
"learning_rate": 5e-05,
"loss": 2.1182,
"step": 559000
},
{
"epoch": 1.3,
"learning_rate": 5e-05,
"loss": 2.1159,
"step": 560000
},
{
"epoch": 1.3,
"learning_rate": 5e-05,
"loss": 2.1186,
"step": 561000
},
{
"epoch": 1.3,
"learning_rate": 5e-05,
"loss": 2.116,
"step": 562000
},
{
"epoch": 1.3,
"learning_rate": 5e-05,
"loss": 2.1152,
"step": 563000
},
{
"epoch": 1.31,
"learning_rate": 5e-05,
"loss": 2.1195,
"step": 564000
},
{
"epoch": 1.31,
"learning_rate": 5e-05,
"loss": 2.1144,
"step": 565000
},
{
"epoch": 1.31,
"learning_rate": 5e-05,
"loss": 2.125,
"step": 566000
},
{
"epoch": 1.31,
"learning_rate": 5e-05,
"loss": 2.1127,
"step": 567000
},
{
"epoch": 1.32,
"learning_rate": 5e-05,
"loss": 2.1177,
"step": 568000
},
{
"epoch": 1.32,
"learning_rate": 5e-05,
"loss": 2.1148,
"step": 569000
},
{
"epoch": 1.32,
"learning_rate": 5e-05,
"loss": 2.1185,
"step": 570000
},
{
"epoch": 1.32,
"learning_rate": 5e-05,
"loss": 2.115,
"step": 571000
},
{
"epoch": 1.33,
"learning_rate": 5e-05,
"loss": 2.1127,
"step": 572000
},
{
"epoch": 1.33,
"learning_rate": 5e-05,
"loss": 2.1075,
"step": 573000
},
{
"epoch": 1.33,
"learning_rate": 5e-05,
"loss": 2.111,
"step": 574000
},
{
"epoch": 1.33,
"learning_rate": 5e-05,
"loss": 2.1139,
"step": 575000
},
{
"epoch": 1.34,
"learning_rate": 5e-05,
"loss": 2.1092,
"step": 576000
},
{
"epoch": 1.34,
"learning_rate": 5e-05,
"loss": 2.1126,
"step": 577000
},
{
"epoch": 1.34,
"learning_rate": 5e-05,
"loss": 2.112,
"step": 578000
},
{
"epoch": 1.34,
"learning_rate": 5e-05,
"loss": 2.1093,
"step": 579000
},
{
"epoch": 1.34,
"learning_rate": 5e-05,
"loss": 2.1008,
"step": 580000
},
{
"epoch": 1.35,
"learning_rate": 5e-05,
"loss": 2.1119,
"step": 581000
},
{
"epoch": 1.35,
"learning_rate": 5e-05,
"loss": 2.1105,
"step": 582000
},
{
"epoch": 1.35,
"learning_rate": 5e-05,
"loss": 2.1078,
"step": 583000
},
{
"epoch": 1.35,
"learning_rate": 5e-05,
"loss": 2.1109,
"step": 584000
},
{
"epoch": 1.36,
"learning_rate": 5e-05,
"loss": 2.1093,
"step": 585000
},
{
"epoch": 1.36,
"learning_rate": 5e-05,
"loss": 2.1047,
"step": 586000
},
{
"epoch": 1.36,
"learning_rate": 5e-05,
"loss": 2.1038,
"step": 587000
},
{
"epoch": 1.36,
"learning_rate": 5e-05,
"loss": 2.1074,
"step": 588000
},
{
"epoch": 1.37,
"learning_rate": 5e-05,
"loss": 2.105,
"step": 589000
},
{
"epoch": 1.37,
"learning_rate": 5e-05,
"loss": 2.1114,
"step": 590000
},
{
"epoch": 1.37,
"learning_rate": 5e-05,
"loss": 2.1002,
"step": 591000
},
{
"epoch": 1.37,
"learning_rate": 5e-05,
"loss": 2.0985,
"step": 592000
},
{
"epoch": 1.37,
"learning_rate": 5e-05,
"loss": 2.1004,
"step": 593000
},
{
"epoch": 1.38,
"learning_rate": 5e-05,
"loss": 2.1008,
"step": 594000
},
{
"epoch": 1.38,
"learning_rate": 5e-05,
"loss": 2.0989,
"step": 595000
},
{
"epoch": 1.38,
"learning_rate": 5e-05,
"loss": 2.102,
"step": 596000
},
{
"epoch": 1.38,
"learning_rate": 5e-05,
"loss": 2.1039,
"step": 597000
},
{
"epoch": 1.39,
"learning_rate": 5e-05,
"loss": 2.0943,
"step": 598000
},
{
"epoch": 1.39,
"learning_rate": 5e-05,
"loss": 2.1032,
"step": 599000
},
{
"epoch": 1.39,
"learning_rate": 5e-05,
"loss": 2.1048,
"step": 600000
},
{
"epoch": 1.39,
"eval_accuracy": 0.6001050830453463,
"eval_loss": 1.994140625,
"eval_runtime": 4891.4227,
"eval_samples_per_second": 114.179,
"eval_steps_per_second": 0.892,
"step": 600000
},
{
"epoch": 1.39,
"learning_rate": 5e-05,
"loss": 2.0963,
"step": 601000
},
{
"epoch": 1.4,
"learning_rate": 5e-05,
"loss": 2.1025,
"step": 602000
},
{
"epoch": 1.4,
"learning_rate": 5e-05,
"loss": 2.0995,
"step": 603000
},
{
"epoch": 1.4,
"learning_rate": 5e-05,
"loss": 2.1012,
"step": 604000
},
{
"epoch": 1.4,
"learning_rate": 5e-05,
"loss": 2.0948,
"step": 605000
},
{
"epoch": 1.4,
"learning_rate": 5e-05,
"loss": 2.0975,
"step": 606000
},
{
"epoch": 1.41,
"learning_rate": 5e-05,
"loss": 2.0955,
"step": 607000
},
{
"epoch": 1.41,
"learning_rate": 5e-05,
"loss": 2.0978,
"step": 608000
},
{
"epoch": 1.41,
"learning_rate": 5e-05,
"loss": 2.0966,
"step": 609000
},
{
"epoch": 1.41,
"learning_rate": 5e-05,
"loss": 2.0921,
"step": 610000
},
{
"epoch": 1.42,
"learning_rate": 5e-05,
"loss": 2.092,
"step": 611000
},
{
"epoch": 1.42,
"learning_rate": 5e-05,
"loss": 2.0944,
"step": 612000
},
{
"epoch": 1.42,
"learning_rate": 5e-05,
"loss": 2.095,
"step": 613000
},
{
"epoch": 1.42,
"learning_rate": 5e-05,
"loss": 2.0939,
"step": 614000
},
{
"epoch": 1.43,
"learning_rate": 5e-05,
"loss": 2.0952,
"step": 615000
},
{
"epoch": 1.43,
"learning_rate": 5e-05,
"loss": 2.0928,
"step": 616000
},
{
"epoch": 1.43,
"learning_rate": 5e-05,
"loss": 2.0932,
"step": 617000
},
{
"epoch": 1.43,
"learning_rate": 5e-05,
"loss": 2.0881,
"step": 618000
},
{
"epoch": 1.43,
"learning_rate": 5e-05,
"loss": 2.0912,
"step": 619000
},
{
"epoch": 1.44,
"learning_rate": 5e-05,
"loss": 2.0909,
"step": 620000
},
{
"epoch": 1.44,
"learning_rate": 5e-05,
"loss": 2.0856,
"step": 621000
},
{
"epoch": 1.44,
"learning_rate": 5e-05,
"loss": 2.0906,
"step": 622000
},
{
"epoch": 1.44,
"learning_rate": 5e-05,
"loss": 2.0905,
"step": 623000
},
{
"epoch": 1.45,
"learning_rate": 5e-05,
"loss": 2.0824,
"step": 624000
},
{
"epoch": 1.45,
"learning_rate": 5e-05,
"loss": 2.0874,
"step": 625000
},
{
"epoch": 1.45,
"learning_rate": 5e-05,
"loss": 2.0894,
"step": 626000
},
{
"epoch": 1.45,
"learning_rate": 5e-05,
"loss": 2.0824,
"step": 627000
},
{
"epoch": 1.46,
"learning_rate": 5e-05,
"loss": 2.0874,
"step": 628000
},
{
"epoch": 1.46,
"learning_rate": 5e-05,
"loss": 2.088,
"step": 629000
},
{
"epoch": 1.46,
"learning_rate": 5e-05,
"loss": 2.088,
"step": 630000
},
{
"epoch": 1.46,
"learning_rate": 5e-05,
"loss": 2.0815,
"step": 631000
},
{
"epoch": 1.46,
"learning_rate": 5e-05,
"loss": 2.0835,
"step": 632000
},
{
"epoch": 1.47,
"learning_rate": 5e-05,
"loss": 2.0886,
"step": 633000
},
{
"epoch": 1.47,
"learning_rate": 5e-05,
"loss": 2.0842,
"step": 634000
},
{
"epoch": 1.47,
"learning_rate": 5e-05,
"loss": 2.0814,
"step": 635000
},
{
"epoch": 1.47,
"learning_rate": 5e-05,
"loss": 2.0822,
"step": 636000
},
{
"epoch": 1.48,
"learning_rate": 5e-05,
"loss": 2.0811,
"step": 637000
},
{
"epoch": 1.48,
"learning_rate": 5e-05,
"loss": 2.0883,
"step": 638000
},
{
"epoch": 1.48,
"learning_rate": 5e-05,
"loss": 2.0858,
"step": 639000
},
{
"epoch": 1.48,
"learning_rate": 5e-05,
"loss": 2.0841,
"step": 640000
},
{
"epoch": 1.49,
"learning_rate": 5e-05,
"loss": 2.0893,
"step": 641000
},
{
"epoch": 1.49,
"learning_rate": 5e-05,
"loss": 2.0807,
"step": 642000
},
{
"epoch": 1.49,
"learning_rate": 5e-05,
"loss": 2.0841,
"step": 643000
},
{
"epoch": 1.49,
"learning_rate": 5e-05,
"loss": 2.0803,
"step": 644000
},
{
"epoch": 1.5,
"learning_rate": 5e-05,
"loss": 2.086,
"step": 645000
},
{
"epoch": 1.5,
"learning_rate": 5e-05,
"loss": 2.0816,
"step": 646000
},
{
"epoch": 1.5,
"learning_rate": 5e-05,
"loss": 2.083,
"step": 647000
},
{
"epoch": 1.5,
"learning_rate": 5e-05,
"loss": 2.0751,
"step": 648000
},
{
"epoch": 1.5,
"learning_rate": 5e-05,
"loss": 2.0836,
"step": 649000
},
{
"epoch": 1.51,
"learning_rate": 5e-05,
"loss": 2.0757,
"step": 650000
},
{
"epoch": 1.51,
"learning_rate": 5e-05,
"loss": 2.0795,
"step": 651000
},
{
"epoch": 1.51,
"learning_rate": 5e-05,
"loss": 2.0755,
"step": 652000
},
{
"epoch": 1.51,
"learning_rate": 5e-05,
"loss": 2.0811,
"step": 653000
},
{
"epoch": 1.52,
"learning_rate": 5e-05,
"loss": 2.0769,
"step": 654000
},
{
"epoch": 1.52,
"learning_rate": 5e-05,
"loss": 2.0737,
"step": 655000
},
{
"epoch": 1.52,
"learning_rate": 5e-05,
"loss": 2.0803,
"step": 656000
},
{
"epoch": 1.52,
"learning_rate": 5e-05,
"loss": 2.0739,
"step": 657000
},
{
"epoch": 1.53,
"learning_rate": 5e-05,
"loss": 2.0783,
"step": 658000
},
{
"epoch": 1.53,
"learning_rate": 5e-05,
"loss": 2.0744,
"step": 659000
},
{
"epoch": 1.53,
"learning_rate": 5e-05,
"loss": 2.0696,
"step": 660000
},
{
"epoch": 1.53,
"learning_rate": 5e-05,
"loss": 2.0785,
"step": 661000
},
{
"epoch": 1.53,
"learning_rate": 5e-05,
"loss": 2.0742,
"step": 662000
},
{
"epoch": 1.54,
"learning_rate": 5e-05,
"loss": 2.0715,
"step": 663000
},
{
"epoch": 1.54,
"learning_rate": 5e-05,
"loss": 2.0705,
"step": 664000
},
{
"epoch": 1.54,
"learning_rate": 5e-05,
"loss": 2.0698,
"step": 665000
},
{
"epoch": 1.54,
"learning_rate": 5e-05,
"loss": 2.0703,
"step": 666000
},
{
"epoch": 1.55,
"learning_rate": 5e-05,
"loss": 2.075,
"step": 667000
},
{
"epoch": 1.55,
"learning_rate": 5e-05,
"loss": 2.0694,
"step": 668000
},
{
"epoch": 1.55,
"learning_rate": 5e-05,
"loss": 2.0708,
"step": 669000
},
{
"epoch": 1.55,
"learning_rate": 5e-05,
"loss": 2.0656,
"step": 670000
},
{
"epoch": 1.56,
"learning_rate": 5e-05,
"loss": 2.069,
"step": 671000
},
{
"epoch": 1.56,
"learning_rate": 5e-05,
"loss": 2.0724,
"step": 672000
},
{
"epoch": 1.56,
"learning_rate": 5e-05,
"loss": 2.0699,
"step": 673000
},
{
"epoch": 1.56,
"learning_rate": 5e-05,
"loss": 2.0695,
"step": 674000
},
{
"epoch": 1.56,
"learning_rate": 5e-05,
"loss": 2.068,
"step": 675000
},
{
"epoch": 1.57,
"learning_rate": 5e-05,
"loss": 2.0671,
"step": 676000
},
{
"epoch": 1.57,
"learning_rate": 5e-05,
"loss": 2.0716,
"step": 677000
},
{
"epoch": 1.57,
"learning_rate": 5e-05,
"loss": 2.0689,
"step": 678000
},
{
"epoch": 1.57,
"learning_rate": 5e-05,
"loss": 2.062,
"step": 679000
},
{
"epoch": 1.58,
"learning_rate": 5e-05,
"loss": 2.0733,
"step": 680000
},
{
"epoch": 1.58,
"learning_rate": 5e-05,
"loss": 2.0671,
"step": 681000
},
{
"epoch": 1.58,
"learning_rate": 5e-05,
"loss": 2.0676,
"step": 682000
},
{
"epoch": 1.58,
"learning_rate": 5e-05,
"loss": 2.0651,
"step": 683000
},
{
"epoch": 1.59,
"learning_rate": 5e-05,
"loss": 2.0594,
"step": 684000
},
{
"epoch": 1.59,
"learning_rate": 5e-05,
"loss": 2.0658,
"step": 685000
},
{
"epoch": 1.59,
"learning_rate": 5e-05,
"loss": 2.0686,
"step": 686000
},
{
"epoch": 1.59,
"learning_rate": 5e-05,
"loss": 2.0685,
"step": 687000
},
{
"epoch": 1.59,
"learning_rate": 5e-05,
"loss": 2.0632,
"step": 688000
},
{
"epoch": 1.6,
"learning_rate": 5e-05,
"loss": 2.0662,
"step": 689000
},
{
"epoch": 1.6,
"learning_rate": 5e-05,
"loss": 2.0615,
"step": 690000
},
{
"epoch": 1.6,
"learning_rate": 5e-05,
"loss": 2.0546,
"step": 691000
},
{
"epoch": 1.6,
"learning_rate": 5e-05,
"loss": 2.0593,
"step": 692000
},
{
"epoch": 1.61,
"learning_rate": 5e-05,
"loss": 2.0599,
"step": 693000
},
{
"epoch": 1.61,
"learning_rate": 5e-05,
"loss": 2.0635,
"step": 694000
},
{
"epoch": 1.61,
"learning_rate": 5e-05,
"loss": 2.0621,
"step": 695000
},
{
"epoch": 1.61,
"learning_rate": 5e-05,
"loss": 2.0654,
"step": 696000
},
{
"epoch": 1.62,
"learning_rate": 5e-05,
"loss": 2.0576,
"step": 697000
},
{
"epoch": 1.62,
"learning_rate": 5e-05,
"loss": 2.0563,
"step": 698000
},
{
"epoch": 1.62,
"learning_rate": 5e-05,
"loss": 2.059,
"step": 699000
},
{
"epoch": 1.62,
"learning_rate": 5e-05,
"loss": 2.0616,
"step": 700000
},
{
"epoch": 1.62,
"learning_rate": 5e-05,
"loss": 2.0642,
"step": 701000
},
{
"epoch": 1.63,
"learning_rate": 5e-05,
"loss": 2.052,
"step": 702000
},
{
"epoch": 1.63,
"learning_rate": 5e-05,
"loss": 2.0569,
"step": 703000
},
{
"epoch": 1.63,
"learning_rate": 5e-05,
"loss": 2.0617,
"step": 704000
},
{
"epoch": 1.63,
"learning_rate": 5e-05,
"loss": 2.0613,
"step": 705000
},
{
"epoch": 1.64,
"learning_rate": 5e-05,
"loss": 2.0593,
"step": 706000
},
{
"epoch": 1.64,
"learning_rate": 5e-05,
"loss": 2.0582,
"step": 707000
},
{
"epoch": 1.64,
"learning_rate": 5e-05,
"loss": 2.0587,
"step": 708000
},
{
"epoch": 1.64,
"learning_rate": 5e-05,
"loss": 2.0518,
"step": 709000
},
{
"epoch": 1.65,
"learning_rate": 5e-05,
"loss": 2.0585,
"step": 710000
},
{
"epoch": 1.65,
"learning_rate": 5e-05,
"loss": 2.052,
"step": 711000
},
{
"epoch": 1.65,
"learning_rate": 5e-05,
"loss": 2.056,
"step": 712000
},
{
"epoch": 1.65,
"learning_rate": 5e-05,
"loss": 2.0559,
"step": 713000
},
{
"epoch": 1.65,
"learning_rate": 5e-05,
"loss": 2.0538,
"step": 714000
},
{
"epoch": 1.66,
"learning_rate": 5e-05,
"loss": 2.0566,
"step": 715000
},
{
"epoch": 1.66,
"learning_rate": 5e-05,
"loss": 2.0519,
"step": 716000
},
{
"epoch": 1.66,
"learning_rate": 5e-05,
"loss": 2.058,
"step": 717000
},
{
"epoch": 1.66,
"learning_rate": 5e-05,
"loss": 2.0627,
"step": 718000
},
{
"epoch": 1.67,
"learning_rate": 5e-05,
"loss": 2.0476,
"step": 719000
},
{
"epoch": 1.67,
"learning_rate": 5e-05,
"loss": 2.0484,
"step": 720000
},
{
"epoch": 1.67,
"learning_rate": 5e-05,
"loss": 2.0545,
"step": 721000
},
{
"epoch": 1.67,
"learning_rate": 5e-05,
"loss": 2.0558,
"step": 722000
},
{
"epoch": 1.68,
"learning_rate": 5e-05,
"loss": 2.0547,
"step": 723000
},
{
"epoch": 1.68,
"learning_rate": 5e-05,
"loss": 2.0501,
"step": 724000
},
{
"epoch": 1.68,
"learning_rate": 5e-05,
"loss": 2.0562,
"step": 725000
},
{
"epoch": 1.68,
"learning_rate": 5e-05,
"loss": 2.0467,
"step": 726000
},
{
"epoch": 1.69,
"learning_rate": 5e-05,
"loss": 2.0438,
"step": 727000
},
{
"epoch": 1.69,
"learning_rate": 5e-05,
"loss": 2.0458,
"step": 728000
},
{
"epoch": 1.69,
"learning_rate": 5e-05,
"loss": 2.0504,
"step": 729000
},
{
"epoch": 1.69,
"learning_rate": 5e-05,
"loss": 2.0501,
"step": 730000
},
{
"epoch": 1.69,
"learning_rate": 5e-05,
"loss": 2.0498,
"step": 731000
},
{
"epoch": 1.7,
"learning_rate": 5e-05,
"loss": 2.0495,
"step": 732000
},
{
"epoch": 1.7,
"learning_rate": 5e-05,
"loss": 2.0494,
"step": 733000
},
{
"epoch": 1.7,
"learning_rate": 5e-05,
"loss": 2.0469,
"step": 734000
},
{
"epoch": 1.7,
"learning_rate": 5e-05,
"loss": 2.0503,
"step": 735000
},
{
"epoch": 1.71,
"learning_rate": 5e-05,
"loss": 2.0492,
"step": 736000
},
{
"epoch": 1.71,
"learning_rate": 5e-05,
"loss": 2.0445,
"step": 737000
},
{
"epoch": 1.71,
"learning_rate": 5e-05,
"loss": 2.044,
"step": 738000
},
{
"epoch": 1.71,
"learning_rate": 5e-05,
"loss": 2.0418,
"step": 739000
},
{
"epoch": 1.72,
"learning_rate": 5e-05,
"loss": 2.0473,
"step": 740000
},
{
"epoch": 1.72,
"learning_rate": 5e-05,
"loss": 2.0503,
"step": 741000
},
{
"epoch": 1.72,
"learning_rate": 5e-05,
"loss": 2.0513,
"step": 742000
},
{
"epoch": 1.72,
"learning_rate": 5e-05,
"loss": 2.0492,
"step": 743000
},
{
"epoch": 1.72,
"learning_rate": 5e-05,
"loss": 2.0471,
"step": 744000
},
{
"epoch": 1.73,
"learning_rate": 5e-05,
"loss": 2.0357,
"step": 745000
},
{
"epoch": 1.73,
"learning_rate": 5e-05,
"loss": 2.045,
"step": 746000
},
{
"epoch": 1.73,
"learning_rate": 5e-05,
"loss": 2.042,
"step": 747000
},
{
"epoch": 1.73,
"learning_rate": 5e-05,
"loss": 2.0485,
"step": 748000
},
{
"epoch": 1.74,
"learning_rate": 5e-05,
"loss": 2.043,
"step": 749000
},
{
"epoch": 1.74,
"learning_rate": 5e-05,
"loss": 2.0345,
"step": 750000
},
{
"epoch": 1.74,
"eval_accuracy": 0.6086964451170365,
"eval_loss": 1.935546875,
"eval_runtime": 4905.4193,
"eval_samples_per_second": 113.853,
"eval_steps_per_second": 0.89,
"step": 750000
},
{
"epoch": 1.74,
"learning_rate": 5e-05,
"loss": 2.0407,
"step": 751000
},
{
"epoch": 1.74,
"learning_rate": 5e-05,
"loss": 2.042,
"step": 752000
},
{
"epoch": 1.75,
"learning_rate": 5e-05,
"loss": 2.0446,
"step": 753000
},
{
"epoch": 1.75,
"learning_rate": 5e-05,
"loss": 2.0447,
"step": 754000
},
{
"epoch": 1.75,
"learning_rate": 5e-05,
"loss": 2.0402,
"step": 755000
},
{
"epoch": 1.75,
"learning_rate": 5e-05,
"loss": 2.0392,
"step": 756000
},
{
"epoch": 1.75,
"learning_rate": 5e-05,
"loss": 2.037,
"step": 757000
},
{
"epoch": 1.76,
"learning_rate": 5e-05,
"loss": 2.0341,
"step": 758000
},
{
"epoch": 1.76,
"learning_rate": 5e-05,
"loss": 2.0381,
"step": 759000
},
{
"epoch": 1.76,
"learning_rate": 5e-05,
"loss": 2.0374,
"step": 760000
},
{
"epoch": 1.76,
"learning_rate": 5e-05,
"loss": 2.0347,
"step": 761000
},
{
"epoch": 1.77,
"learning_rate": 5e-05,
"loss": 2.0345,
"step": 762000
},
{
"epoch": 1.77,
"learning_rate": 5e-05,
"loss": 2.036,
"step": 763000
},
{
"epoch": 1.77,
"learning_rate": 5e-05,
"loss": 2.0357,
"step": 764000
},
{
"epoch": 1.77,
"learning_rate": 5e-05,
"loss": 2.0386,
"step": 765000
},
{
"epoch": 1.78,
"learning_rate": 5e-05,
"loss": 2.0363,
"step": 766000
},
{
"epoch": 1.78,
"learning_rate": 5e-05,
"loss": 2.0406,
"step": 767000
},
{
"epoch": 1.78,
"learning_rate": 5e-05,
"loss": 2.0332,
"step": 768000
},
{
"epoch": 1.78,
"learning_rate": 5e-05,
"loss": 2.0358,
"step": 769000
},
{
"epoch": 1.78,
"learning_rate": 5e-05,
"loss": 2.0359,
"step": 770000
},
{
"epoch": 1.79,
"learning_rate": 5e-05,
"loss": 2.0429,
"step": 771000
},
{
"epoch": 1.79,
"learning_rate": 5e-05,
"loss": 2.0402,
"step": 772000
},
{
"epoch": 1.79,
"learning_rate": 5e-05,
"loss": 2.0372,
"step": 773000
},
{
"epoch": 1.79,
"learning_rate": 5e-05,
"loss": 2.0343,
"step": 774000
},
{
"epoch": 1.8,
"learning_rate": 5e-05,
"loss": 2.0351,
"step": 775000
},
{
"epoch": 1.8,
"learning_rate": 5e-05,
"loss": 2.0366,
"step": 776000
},
{
"epoch": 1.8,
"learning_rate": 5e-05,
"loss": 2.0364,
"step": 777000
},
{
"epoch": 1.8,
"learning_rate": 5e-05,
"loss": 2.034,
"step": 778000
},
{
"epoch": 1.81,
"learning_rate": 5e-05,
"loss": 2.0313,
"step": 779000
},
{
"epoch": 1.81,
"learning_rate": 5e-05,
"loss": 2.0281,
"step": 780000
},
{
"epoch": 1.81,
"learning_rate": 5e-05,
"loss": 2.0316,
"step": 781000
},
{
"epoch": 1.81,
"learning_rate": 5e-05,
"loss": 2.0298,
"step": 782000
},
{
"epoch": 1.81,
"learning_rate": 5e-05,
"loss": 2.0292,
"step": 783000
},
{
"epoch": 1.82,
"learning_rate": 5e-05,
"loss": 2.0269,
"step": 784000
},
{
"epoch": 1.82,
"learning_rate": 5e-05,
"loss": 2.0309,
"step": 785000
},
{
"epoch": 1.82,
"learning_rate": 5e-05,
"loss": 2.0316,
"step": 786000
},
{
"epoch": 1.82,
"learning_rate": 5e-05,
"loss": 2.0379,
"step": 787000
},
{
"epoch": 1.83,
"learning_rate": 5e-05,
"loss": 2.0298,
"step": 788000
},
{
"epoch": 1.83,
"learning_rate": 5e-05,
"loss": 2.028,
"step": 789000
},
{
"epoch": 1.83,
"learning_rate": 5e-05,
"loss": 2.0278,
"step": 790000
},
{
"epoch": 1.83,
"learning_rate": 5e-05,
"loss": 2.0316,
"step": 791000
},
{
"epoch": 1.84,
"learning_rate": 5e-05,
"loss": 2.0269,
"step": 792000
},
{
"epoch": 1.84,
"learning_rate": 5e-05,
"loss": 2.031,
"step": 793000
},
{
"epoch": 1.84,
"learning_rate": 5e-05,
"loss": 2.0281,
"step": 794000
},
{
"epoch": 1.84,
"learning_rate": 5e-05,
"loss": 2.0237,
"step": 795000
},
{
"epoch": 1.85,
"learning_rate": 5e-05,
"loss": 2.0244,
"step": 796000
},
{
"epoch": 1.85,
"learning_rate": 5e-05,
"loss": 2.0262,
"step": 797000
},
{
"epoch": 1.85,
"learning_rate": 5e-05,
"loss": 2.0275,
"step": 798000
},
{
"epoch": 1.85,
"learning_rate": 5e-05,
"loss": 2.0253,
"step": 799000
},
{
"epoch": 1.85,
"learning_rate": 5e-05,
"loss": 2.0336,
"step": 800000
},
{
"epoch": 1.86,
"learning_rate": 5e-05,
"loss": 2.029,
"step": 801000
},
{
"epoch": 1.86,
"learning_rate": 5e-05,
"loss": 2.0271,
"step": 802000
},
{
"epoch": 1.86,
"learning_rate": 5e-05,
"loss": 2.0221,
"step": 803000
},
{
"epoch": 1.86,
"learning_rate": 5e-05,
"loss": 2.0287,
"step": 804000
},
{
"epoch": 1.87,
"learning_rate": 5e-05,
"loss": 2.0264,
"step": 805000
},
{
"epoch": 1.87,
"learning_rate": 5e-05,
"loss": 2.0263,
"step": 806000
},
{
"epoch": 1.87,
"learning_rate": 5e-05,
"loss": 2.0242,
"step": 807000
},
{
"epoch": 1.87,
"learning_rate": 5e-05,
"loss": 2.0221,
"step": 808000
},
{
"epoch": 1.88,
"learning_rate": 5e-05,
"loss": 2.0242,
"step": 809000
},
{
"epoch": 1.88,
"learning_rate": 5e-05,
"loss": 2.0212,
"step": 810000
},
{
"epoch": 1.88,
"learning_rate": 5e-05,
"loss": 2.0213,
"step": 811000
},
{
"epoch": 1.88,
"learning_rate": 5e-05,
"loss": 2.0182,
"step": 812000
},
{
"epoch": 1.88,
"learning_rate": 5e-05,
"loss": 2.0195,
"step": 813000
},
{
"epoch": 1.89,
"learning_rate": 5e-05,
"loss": 2.0245,
"step": 814000
},
{
"epoch": 1.89,
"learning_rate": 5e-05,
"loss": 2.018,
"step": 815000
},
{
"epoch": 1.89,
"learning_rate": 5e-05,
"loss": 2.0219,
"step": 816000
},
{
"epoch": 1.89,
"learning_rate": 5e-05,
"loss": 2.0221,
"step": 817000
},
{
"epoch": 1.9,
"learning_rate": 5e-05,
"loss": 2.019,
"step": 818000
},
{
"epoch": 1.9,
"learning_rate": 5e-05,
"loss": 2.0199,
"step": 819000
},
{
"epoch": 1.9,
"learning_rate": 5e-05,
"loss": 2.0166,
"step": 820000
},
{
"epoch": 1.9,
"learning_rate": 5e-05,
"loss": 2.0192,
"step": 821000
},
{
"epoch": 1.91,
"learning_rate": 5e-05,
"loss": 2.0217,
"step": 822000
},
{
"epoch": 1.91,
"learning_rate": 5e-05,
"loss": 2.0179,
"step": 823000
},
{
"epoch": 1.91,
"learning_rate": 5e-05,
"loss": 2.0242,
"step": 824000
},
{
"epoch": 1.91,
"learning_rate": 5e-05,
"loss": 2.0158,
"step": 825000
},
{
"epoch": 1.91,
"learning_rate": 5e-05,
"loss": 2.013,
"step": 826000
},
{
"epoch": 1.92,
"learning_rate": 5e-05,
"loss": 2.0196,
"step": 827000
},
{
"epoch": 1.92,
"learning_rate": 5e-05,
"loss": 2.02,
"step": 828000
},
{
"epoch": 1.92,
"learning_rate": 5e-05,
"loss": 2.021,
"step": 829000
},
{
"epoch": 1.92,
"learning_rate": 5e-05,
"loss": 2.0192,
"step": 830000
},
{
"epoch": 1.93,
"learning_rate": 5e-05,
"loss": 2.0191,
"step": 831000
},
{
"epoch": 1.93,
"learning_rate": 5e-05,
"loss": 2.0184,
"step": 832000
},
{
"epoch": 1.93,
"learning_rate": 5e-05,
"loss": 2.0196,
"step": 833000
},
{
"epoch": 1.93,
"learning_rate": 5e-05,
"loss": 2.0183,
"step": 834000
},
{
"epoch": 1.94,
"learning_rate": 5e-05,
"loss": 2.0134,
"step": 835000
},
{
"epoch": 1.94,
"learning_rate": 5e-05,
"loss": 2.0163,
"step": 836000
},
{
"epoch": 1.94,
"learning_rate": 5e-05,
"loss": 2.0113,
"step": 837000
},
{
"epoch": 1.94,
"learning_rate": 5e-05,
"loss": 2.0206,
"step": 838000
},
{
"epoch": 1.94,
"learning_rate": 5e-05,
"loss": 2.0166,
"step": 839000
},
{
"epoch": 1.95,
"learning_rate": 5e-05,
"loss": 2.0181,
"step": 840000
},
{
"epoch": 1.95,
"learning_rate": 5e-05,
"loss": 2.0168,
"step": 841000
},
{
"epoch": 1.95,
"learning_rate": 5e-05,
"loss": 2.01,
"step": 842000
},
{
"epoch": 1.95,
"learning_rate": 5e-05,
"loss": 2.0153,
"step": 843000
},
{
"epoch": 1.96,
"learning_rate": 5e-05,
"loss": 2.0084,
"step": 844000
},
{
"epoch": 1.96,
"learning_rate": 5e-05,
"loss": 2.0169,
"step": 845000
},
{
"epoch": 1.96,
"learning_rate": 5e-05,
"loss": 2.0142,
"step": 846000
},
{
"epoch": 1.96,
"learning_rate": 5e-05,
"loss": 2.0132,
"step": 847000
},
{
"epoch": 1.97,
"learning_rate": 5e-05,
"loss": 2.0126,
"step": 848000
},
{
"epoch": 1.97,
"learning_rate": 5e-05,
"loss": 2.0121,
"step": 849000
},
{
"epoch": 1.97,
"learning_rate": 5e-05,
"loss": 2.0122,
"step": 850000
},
{
"epoch": 1.97,
"learning_rate": 5e-05,
"loss": 2.0149,
"step": 851000
},
{
"epoch": 1.97,
"learning_rate": 5e-05,
"loss": 2.0125,
"step": 852000
},
{
"epoch": 1.98,
"learning_rate": 5e-05,
"loss": 2.0074,
"step": 853000
},
{
"epoch": 1.98,
"learning_rate": 5e-05,
"loss": 2.0136,
"step": 854000
},
{
"epoch": 1.98,
"learning_rate": 5e-05,
"loss": 2.0118,
"step": 855000
},
{
"epoch": 1.98,
"learning_rate": 5e-05,
"loss": 2.0139,
"step": 856000
},
{
"epoch": 1.99,
"learning_rate": 5e-05,
"loss": 2.0158,
"step": 857000
},
{
"epoch": 1.99,
"learning_rate": 5e-05,
"loss": 2.0105,
"step": 858000
},
{
"epoch": 1.99,
"learning_rate": 5e-05,
"loss": 2.0075,
"step": 859000
},
{
"epoch": 1.99,
"learning_rate": 5e-05,
"loss": 2.007,
"step": 860000
},
{
"epoch": 2.0,
"learning_rate": 5e-05,
"loss": 2.0143,
"step": 861000
},
{
"epoch": 2.0,
"learning_rate": 5e-05,
"loss": 2.0067,
"step": 862000
},
{
"epoch": 2.0,
"step": 862850,
"total_flos": 1.5713271682523202e+19,
"train_loss": 0.02994945877374942,
"train_runtime": 24111.6962,
"train_samples_per_second": 9161.097,
"train_steps_per_second": 35.786
}
],
"max_steps": 862850,
"num_train_epochs": 2,
"total_flos": 1.5713271682523202e+19,
"trial_name": null,
"trial_params": null
}