LEIA
/

LEIA-LM-base / trainer_state.json
saroyehun's picture
Upload with huggingface_hub
57dfa26
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.145919679862798,
"global_step": 100000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 4.975e-05,
"loss": 1.8403,
"step": 500
},
{
"epoch": 0.07,
"learning_rate": 4.9500000000000004e-05,
"loss": 1.7278,
"step": 1000
},
{
"epoch": 0.11,
"learning_rate": 4.9250000000000004e-05,
"loss": 1.7053,
"step": 1500
},
{
"epoch": 0.14,
"learning_rate": 4.9e-05,
"loss": 1.693,
"step": 2000
},
{
"epoch": 0.18,
"learning_rate": 4.875e-05,
"loss": 1.6754,
"step": 2500
},
{
"epoch": 0.21,
"learning_rate": 4.85e-05,
"loss": 1.6581,
"step": 3000
},
{
"epoch": 0.25,
"learning_rate": 4.825e-05,
"loss": 1.6582,
"step": 3500
},
{
"epoch": 0.29,
"learning_rate": 4.8e-05,
"loss": 1.6448,
"step": 4000
},
{
"epoch": 0.32,
"learning_rate": 4.775e-05,
"loss": 1.6327,
"step": 4500
},
{
"epoch": 0.36,
"learning_rate": 4.75e-05,
"loss": 1.626,
"step": 5000
},
{
"epoch": 0.39,
"learning_rate": 4.7249999999999997e-05,
"loss": 1.6194,
"step": 5500
},
{
"epoch": 0.43,
"learning_rate": 4.7e-05,
"loss": 1.6044,
"step": 6000
},
{
"epoch": 0.46,
"learning_rate": 4.6750000000000005e-05,
"loss": 1.6112,
"step": 6500
},
{
"epoch": 0.5,
"learning_rate": 4.6500000000000005e-05,
"loss": 1.6055,
"step": 7000
},
{
"epoch": 0.54,
"learning_rate": 4.6250000000000006e-05,
"loss": 1.6016,
"step": 7500
},
{
"epoch": 0.57,
"learning_rate": 4.600000000000001e-05,
"loss": 1.593,
"step": 8000
},
{
"epoch": 0.61,
"learning_rate": 4.575e-05,
"loss": 1.5908,
"step": 8500
},
{
"epoch": 0.64,
"learning_rate": 4.55e-05,
"loss": 1.5898,
"step": 9000
},
{
"epoch": 0.68,
"learning_rate": 4.525e-05,
"loss": 1.5832,
"step": 9500
},
{
"epoch": 0.71,
"learning_rate": 4.5e-05,
"loss": 1.5797,
"step": 10000
},
{
"epoch": 0.75,
"learning_rate": 4.4750000000000004e-05,
"loss": 1.5781,
"step": 10500
},
{
"epoch": 0.79,
"learning_rate": 4.4500000000000004e-05,
"loss": 1.5719,
"step": 11000
},
{
"epoch": 0.82,
"learning_rate": 4.4250000000000005e-05,
"loss": 1.5681,
"step": 11500
},
{
"epoch": 0.86,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.5713,
"step": 12000
},
{
"epoch": 0.89,
"learning_rate": 4.375e-05,
"loss": 1.5667,
"step": 12500
},
{
"epoch": 0.93,
"learning_rate": 4.35e-05,
"loss": 1.5627,
"step": 13000
},
{
"epoch": 0.96,
"learning_rate": 4.325e-05,
"loss": 1.561,
"step": 13500
},
{
"epoch": 1.0,
"learning_rate": 4.3e-05,
"loss": 1.5576,
"step": 14000
},
{
"epoch": 1.04,
"learning_rate": 4.275e-05,
"loss": 1.5482,
"step": 14500
},
{
"epoch": 1.07,
"learning_rate": 4.25e-05,
"loss": 1.5427,
"step": 15000
},
{
"epoch": 1.11,
"learning_rate": 4.2250000000000004e-05,
"loss": 1.5414,
"step": 15500
},
{
"epoch": 1.14,
"learning_rate": 4.2e-05,
"loss": 1.546,
"step": 16000
},
{
"epoch": 1.18,
"learning_rate": 4.175e-05,
"loss": 1.5386,
"step": 16500
},
{
"epoch": 1.21,
"learning_rate": 4.15e-05,
"loss": 1.5383,
"step": 17000
},
{
"epoch": 1.25,
"learning_rate": 4.125e-05,
"loss": 1.539,
"step": 17500
},
{
"epoch": 1.29,
"learning_rate": 4.1e-05,
"loss": 1.5326,
"step": 18000
},
{
"epoch": 1.32,
"learning_rate": 4.075e-05,
"loss": 1.5384,
"step": 18500
},
{
"epoch": 1.36,
"learning_rate": 4.05e-05,
"loss": 1.5269,
"step": 19000
},
{
"epoch": 1.39,
"learning_rate": 4.025e-05,
"loss": 1.5282,
"step": 19500
},
{
"epoch": 1.43,
"learning_rate": 4e-05,
"loss": 1.5301,
"step": 20000
},
{
"epoch": 1.46,
"learning_rate": 3.9750000000000004e-05,
"loss": 1.5339,
"step": 20500
},
{
"epoch": 1.5,
"learning_rate": 3.9500000000000005e-05,
"loss": 1.5234,
"step": 21000
},
{
"epoch": 1.54,
"learning_rate": 3.9250000000000005e-05,
"loss": 1.5255,
"step": 21500
},
{
"epoch": 1.57,
"learning_rate": 3.9000000000000006e-05,
"loss": 1.5244,
"step": 22000
},
{
"epoch": 1.61,
"learning_rate": 3.875e-05,
"loss": 1.5212,
"step": 22500
},
{
"epoch": 1.64,
"learning_rate": 3.85e-05,
"loss": 1.52,
"step": 23000
},
{
"epoch": 1.68,
"learning_rate": 3.825e-05,
"loss": 1.5201,
"step": 23500
},
{
"epoch": 1.72,
"learning_rate": 3.8e-05,
"loss": 1.5207,
"step": 24000
},
{
"epoch": 1.75,
"learning_rate": 3.775e-05,
"loss": 1.5157,
"step": 24500
},
{
"epoch": 1.79,
"learning_rate": 3.7500000000000003e-05,
"loss": 1.5162,
"step": 25000
},
{
"epoch": 1.82,
"learning_rate": 3.7250000000000004e-05,
"loss": 1.5073,
"step": 25500
},
{
"epoch": 1.86,
"learning_rate": 3.7e-05,
"loss": 1.5104,
"step": 26000
},
{
"epoch": 1.89,
"learning_rate": 3.675e-05,
"loss": 1.5136,
"step": 26500
},
{
"epoch": 1.93,
"learning_rate": 3.65e-05,
"loss": 1.5163,
"step": 27000
},
{
"epoch": 1.97,
"learning_rate": 3.625e-05,
"loss": 1.5116,
"step": 27500
},
{
"epoch": 2.0,
"learning_rate": 3.6e-05,
"loss": 1.5093,
"step": 28000
},
{
"epoch": 2.04,
"learning_rate": 3.575e-05,
"loss": 1.4918,
"step": 28500
},
{
"epoch": 2.07,
"learning_rate": 3.55e-05,
"loss": 1.4958,
"step": 29000
},
{
"epoch": 2.11,
"learning_rate": 3.525e-05,
"loss": 1.4981,
"step": 29500
},
{
"epoch": 2.14,
"learning_rate": 3.5e-05,
"loss": 1.4963,
"step": 30000
},
{
"epoch": 2.18,
"learning_rate": 3.475e-05,
"loss": 1.4881,
"step": 30500
},
{
"epoch": 2.22,
"learning_rate": 3.45e-05,
"loss": 1.4941,
"step": 31000
},
{
"epoch": 2.25,
"learning_rate": 3.4250000000000006e-05,
"loss": 1.4883,
"step": 31500
},
{
"epoch": 2.29,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.491,
"step": 32000
},
{
"epoch": 2.32,
"learning_rate": 3.375000000000001e-05,
"loss": 1.489,
"step": 32500
},
{
"epoch": 2.36,
"learning_rate": 3.35e-05,
"loss": 1.488,
"step": 33000
},
{
"epoch": 2.39,
"learning_rate": 3.325e-05,
"loss": 1.4846,
"step": 33500
},
{
"epoch": 2.43,
"learning_rate": 3.3e-05,
"loss": 1.4934,
"step": 34000
},
{
"epoch": 2.47,
"learning_rate": 3.275e-05,
"loss": 1.4885,
"step": 34500
},
{
"epoch": 2.5,
"learning_rate": 3.2500000000000004e-05,
"loss": 1.4823,
"step": 35000
},
{
"epoch": 2.54,
"learning_rate": 3.2250000000000005e-05,
"loss": 1.4874,
"step": 35500
},
{
"epoch": 2.57,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.4812,
"step": 36000
},
{
"epoch": 2.61,
"learning_rate": 3.175e-05,
"loss": 1.4838,
"step": 36500
},
{
"epoch": 2.64,
"learning_rate": 3.15e-05,
"loss": 1.4818,
"step": 37000
},
{
"epoch": 2.68,
"learning_rate": 3.125e-05,
"loss": 1.4829,
"step": 37500
},
{
"epoch": 2.72,
"learning_rate": 3.1e-05,
"loss": 1.48,
"step": 38000
},
{
"epoch": 2.75,
"learning_rate": 3.075e-05,
"loss": 1.4779,
"step": 38500
},
{
"epoch": 2.79,
"learning_rate": 3.05e-05,
"loss": 1.4791,
"step": 39000
},
{
"epoch": 2.82,
"learning_rate": 3.025e-05,
"loss": 1.4758,
"step": 39500
},
{
"epoch": 2.86,
"learning_rate": 3e-05,
"loss": 1.4749,
"step": 40000
},
{
"epoch": 2.89,
"learning_rate": 2.975e-05,
"loss": 1.4716,
"step": 40500
},
{
"epoch": 2.93,
"learning_rate": 2.95e-05,
"loss": 1.4783,
"step": 41000
},
{
"epoch": 2.97,
"learning_rate": 2.925e-05,
"loss": 1.4756,
"step": 41500
},
{
"epoch": 3.0,
"learning_rate": 2.9e-05,
"loss": 1.4686,
"step": 42000
},
{
"epoch": 3.04,
"learning_rate": 2.8749999999999997e-05,
"loss": 1.4646,
"step": 42500
},
{
"epoch": 3.07,
"learning_rate": 2.8499999999999998e-05,
"loss": 1.4662,
"step": 43000
},
{
"epoch": 3.11,
"learning_rate": 2.825e-05,
"loss": 1.4654,
"step": 43500
},
{
"epoch": 3.14,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.4693,
"step": 44000
},
{
"epoch": 3.18,
"learning_rate": 2.7750000000000004e-05,
"loss": 1.4574,
"step": 44500
},
{
"epoch": 3.22,
"learning_rate": 2.7500000000000004e-05,
"loss": 1.4581,
"step": 45000
},
{
"epoch": 3.25,
"learning_rate": 2.725e-05,
"loss": 1.4636,
"step": 45500
},
{
"epoch": 3.29,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.461,
"step": 46000
},
{
"epoch": 3.32,
"learning_rate": 2.6750000000000003e-05,
"loss": 1.457,
"step": 46500
},
{
"epoch": 3.36,
"learning_rate": 2.6500000000000004e-05,
"loss": 1.4548,
"step": 47000
},
{
"epoch": 3.39,
"learning_rate": 2.625e-05,
"loss": 1.4601,
"step": 47500
},
{
"epoch": 3.43,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.4525,
"step": 48000
},
{
"epoch": 3.47,
"learning_rate": 2.5750000000000002e-05,
"loss": 1.4563,
"step": 48500
},
{
"epoch": 3.5,
"learning_rate": 2.5500000000000003e-05,
"loss": 1.4565,
"step": 49000
},
{
"epoch": 3.54,
"learning_rate": 2.525e-05,
"loss": 1.456,
"step": 49500
},
{
"epoch": 3.57,
"learning_rate": 2.5e-05,
"loss": 1.4495,
"step": 50000
},
{
"epoch": 3.61,
"learning_rate": 2.4750000000000002e-05,
"loss": 1.4549,
"step": 50500
},
{
"epoch": 3.64,
"learning_rate": 2.45e-05,
"loss": 1.4526,
"step": 51000
},
{
"epoch": 3.68,
"learning_rate": 2.425e-05,
"loss": 1.4523,
"step": 51500
},
{
"epoch": 3.72,
"learning_rate": 2.4e-05,
"loss": 1.4487,
"step": 52000
},
{
"epoch": 3.75,
"learning_rate": 2.375e-05,
"loss": 1.4448,
"step": 52500
},
{
"epoch": 3.79,
"learning_rate": 2.35e-05,
"loss": 1.4491,
"step": 53000
},
{
"epoch": 3.82,
"learning_rate": 2.3250000000000003e-05,
"loss": 1.449,
"step": 53500
},
{
"epoch": 3.86,
"learning_rate": 2.3000000000000003e-05,
"loss": 1.4494,
"step": 54000
},
{
"epoch": 3.89,
"learning_rate": 2.275e-05,
"loss": 1.448,
"step": 54500
},
{
"epoch": 3.93,
"learning_rate": 2.25e-05,
"loss": 1.4458,
"step": 55000
},
{
"epoch": 3.97,
"learning_rate": 2.2250000000000002e-05,
"loss": 1.4424,
"step": 55500
},
{
"epoch": 4.0,
"learning_rate": 2.2000000000000003e-05,
"loss": 1.4448,
"step": 56000
},
{
"epoch": 4.04,
"learning_rate": 2.175e-05,
"loss": 1.4363,
"step": 56500
},
{
"epoch": 4.07,
"learning_rate": 2.15e-05,
"loss": 1.4347,
"step": 57000
},
{
"epoch": 4.11,
"learning_rate": 2.125e-05,
"loss": 1.4324,
"step": 57500
},
{
"epoch": 4.14,
"learning_rate": 2.1e-05,
"loss": 1.4384,
"step": 58000
},
{
"epoch": 4.18,
"learning_rate": 2.075e-05,
"loss": 1.437,
"step": 58500
},
{
"epoch": 4.22,
"learning_rate": 2.05e-05,
"loss": 1.4356,
"step": 59000
},
{
"epoch": 4.25,
"learning_rate": 2.025e-05,
"loss": 1.4357,
"step": 59500
},
{
"epoch": 4.29,
"learning_rate": 2e-05,
"loss": 1.4359,
"step": 60000
},
{
"epoch": 4.32,
"learning_rate": 1.9750000000000002e-05,
"loss": 1.4333,
"step": 60500
},
{
"epoch": 4.36,
"learning_rate": 1.9500000000000003e-05,
"loss": 1.4356,
"step": 61000
},
{
"epoch": 4.39,
"learning_rate": 1.925e-05,
"loss": 1.4347,
"step": 61500
},
{
"epoch": 4.43,
"learning_rate": 1.9e-05,
"loss": 1.4337,
"step": 62000
},
{
"epoch": 4.47,
"learning_rate": 1.8750000000000002e-05,
"loss": 1.4327,
"step": 62500
},
{
"epoch": 4.5,
"learning_rate": 1.85e-05,
"loss": 1.4289,
"step": 63000
},
{
"epoch": 4.54,
"learning_rate": 1.825e-05,
"loss": 1.4288,
"step": 63500
},
{
"epoch": 4.57,
"learning_rate": 1.8e-05,
"loss": 1.4253,
"step": 64000
},
{
"epoch": 4.61,
"learning_rate": 1.775e-05,
"loss": 1.4258,
"step": 64500
},
{
"epoch": 4.64,
"learning_rate": 1.75e-05,
"loss": 1.4308,
"step": 65000
},
{
"epoch": 4.68,
"learning_rate": 1.725e-05,
"loss": 1.4258,
"step": 65500
},
{
"epoch": 4.72,
"learning_rate": 1.7000000000000003e-05,
"loss": 1.4236,
"step": 66000
},
{
"epoch": 4.75,
"learning_rate": 1.675e-05,
"loss": 1.4192,
"step": 66500
},
{
"epoch": 4.79,
"learning_rate": 1.65e-05,
"loss": 1.4299,
"step": 67000
},
{
"epoch": 4.82,
"learning_rate": 1.6250000000000002e-05,
"loss": 1.4247,
"step": 67500
},
{
"epoch": 4.86,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.4192,
"step": 68000
},
{
"epoch": 4.89,
"learning_rate": 1.575e-05,
"loss": 1.4243,
"step": 68500
},
{
"epoch": 4.93,
"learning_rate": 1.55e-05,
"loss": 1.4241,
"step": 69000
},
{
"epoch": 4.97,
"learning_rate": 1.525e-05,
"loss": 1.4228,
"step": 69500
},
{
"epoch": 5.0,
"learning_rate": 1.5e-05,
"loss": 1.4232,
"step": 70000
},
{
"epoch": 5.04,
"learning_rate": 1.475e-05,
"loss": 1.422,
"step": 70500
},
{
"epoch": 5.07,
"learning_rate": 1.45e-05,
"loss": 1.4108,
"step": 71000
},
{
"epoch": 5.11,
"learning_rate": 1.4249999999999999e-05,
"loss": 1.4144,
"step": 71500
},
{
"epoch": 5.15,
"learning_rate": 1.4000000000000001e-05,
"loss": 1.4161,
"step": 72000
},
{
"epoch": 5.18,
"learning_rate": 1.3750000000000002e-05,
"loss": 1.4121,
"step": 72500
},
{
"epoch": 5.22,
"learning_rate": 1.3500000000000001e-05,
"loss": 1.4119,
"step": 73000
},
{
"epoch": 5.25,
"learning_rate": 1.3250000000000002e-05,
"loss": 1.417,
"step": 73500
},
{
"epoch": 5.29,
"learning_rate": 1.3000000000000001e-05,
"loss": 1.4105,
"step": 74000
},
{
"epoch": 5.32,
"learning_rate": 1.2750000000000002e-05,
"loss": 1.4179,
"step": 74500
},
{
"epoch": 5.36,
"learning_rate": 1.25e-05,
"loss": 1.4123,
"step": 75000
},
{
"epoch": 5.4,
"learning_rate": 1.225e-05,
"loss": 1.4086,
"step": 75500
},
{
"epoch": 5.43,
"learning_rate": 1.2e-05,
"loss": 1.4096,
"step": 76000
},
{
"epoch": 5.47,
"learning_rate": 1.175e-05,
"loss": 1.4066,
"step": 76500
},
{
"epoch": 5.5,
"learning_rate": 1.1500000000000002e-05,
"loss": 1.404,
"step": 77000
},
{
"epoch": 5.54,
"learning_rate": 1.125e-05,
"loss": 1.4096,
"step": 77500
},
{
"epoch": 5.57,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.4049,
"step": 78000
},
{
"epoch": 5.61,
"learning_rate": 1.075e-05,
"loss": 1.4117,
"step": 78500
},
{
"epoch": 5.65,
"learning_rate": 1.05e-05,
"loss": 1.4037,
"step": 79000
},
{
"epoch": 5.68,
"learning_rate": 1.025e-05,
"loss": 1.4091,
"step": 79500
},
{
"epoch": 5.72,
"learning_rate": 1e-05,
"loss": 1.4074,
"step": 80000
},
{
"epoch": 5.75,
"learning_rate": 9.750000000000002e-06,
"loss": 1.3992,
"step": 80500
},
{
"epoch": 5.79,
"learning_rate": 9.5e-06,
"loss": 1.404,
"step": 81000
},
{
"epoch": 5.82,
"learning_rate": 9.25e-06,
"loss": 1.4052,
"step": 81500
},
{
"epoch": 5.86,
"learning_rate": 9e-06,
"loss": 1.4028,
"step": 82000
},
{
"epoch": 5.9,
"learning_rate": 8.75e-06,
"loss": 1.4029,
"step": 82500
},
{
"epoch": 5.93,
"learning_rate": 8.500000000000002e-06,
"loss": 1.4066,
"step": 83000
},
{
"epoch": 5.97,
"learning_rate": 8.25e-06,
"loss": 1.4037,
"step": 83500
},
{
"epoch": 6.0,
"learning_rate": 8.000000000000001e-06,
"loss": 1.4013,
"step": 84000
},
{
"epoch": 6.04,
"learning_rate": 7.75e-06,
"loss": 1.4,
"step": 84500
},
{
"epoch": 6.07,
"learning_rate": 7.5e-06,
"loss": 1.3951,
"step": 85000
},
{
"epoch": 6.11,
"learning_rate": 7.25e-06,
"loss": 1.3977,
"step": 85500
},
{
"epoch": 6.15,
"learning_rate": 7.000000000000001e-06,
"loss": 1.4022,
"step": 86000
},
{
"epoch": 6.18,
"learning_rate": 6.750000000000001e-06,
"loss": 1.3916,
"step": 86500
},
{
"epoch": 6.22,
"learning_rate": 6.5000000000000004e-06,
"loss": 1.3993,
"step": 87000
},
{
"epoch": 6.25,
"learning_rate": 6.25e-06,
"loss": 1.3923,
"step": 87500
},
{
"epoch": 6.29,
"learning_rate": 6e-06,
"loss": 1.3963,
"step": 88000
},
{
"epoch": 6.32,
"learning_rate": 5.750000000000001e-06,
"loss": 1.3925,
"step": 88500
},
{
"epoch": 6.36,
"learning_rate": 5.500000000000001e-06,
"loss": 1.3956,
"step": 89000
},
{
"epoch": 6.4,
"learning_rate": 5.25e-06,
"loss": 1.3934,
"step": 89500
},
{
"epoch": 6.43,
"learning_rate": 5e-06,
"loss": 1.3901,
"step": 90000
},
{
"epoch": 6.47,
"learning_rate": 4.75e-06,
"loss": 1.3896,
"step": 90500
},
{
"epoch": 6.5,
"learning_rate": 4.5e-06,
"loss": 1.3962,
"step": 91000
},
{
"epoch": 6.54,
"learning_rate": 4.250000000000001e-06,
"loss": 1.3922,
"step": 91500
},
{
"epoch": 6.57,
"learning_rate": 4.000000000000001e-06,
"loss": 1.3956,
"step": 92000
},
{
"epoch": 6.61,
"learning_rate": 3.75e-06,
"loss": 1.3931,
"step": 92500
},
{
"epoch": 6.65,
"learning_rate": 3.5000000000000004e-06,
"loss": 1.3927,
"step": 93000
},
{
"epoch": 6.68,
"learning_rate": 3.2500000000000002e-06,
"loss": 1.3946,
"step": 93500
},
{
"epoch": 6.72,
"learning_rate": 3e-06,
"loss": 1.3907,
"step": 94000
},
{
"epoch": 6.75,
"learning_rate": 2.7500000000000004e-06,
"loss": 1.3904,
"step": 94500
},
{
"epoch": 6.79,
"learning_rate": 2.5e-06,
"loss": 1.3924,
"step": 95000
},
{
"epoch": 6.82,
"learning_rate": 2.25e-06,
"loss": 1.3971,
"step": 95500
},
{
"epoch": 6.86,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.3949,
"step": 96000
},
{
"epoch": 6.9,
"learning_rate": 1.7500000000000002e-06,
"loss": 1.3886,
"step": 96500
},
{
"epoch": 6.93,
"learning_rate": 1.5e-06,
"loss": 1.3875,
"step": 97000
},
{
"epoch": 6.97,
"learning_rate": 1.25e-06,
"loss": 1.3921,
"step": 97500
},
{
"epoch": 7.0,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.39,
"step": 98000
},
{
"epoch": 7.04,
"learning_rate": 7.5e-07,
"loss": 1.3857,
"step": 98500
},
{
"epoch": 7.07,
"learning_rate": 5.000000000000001e-07,
"loss": 1.3824,
"step": 99000
},
{
"epoch": 7.11,
"learning_rate": 2.5000000000000004e-07,
"loss": 1.387,
"step": 99500
},
{
"epoch": 7.15,
"learning_rate": 0.0,
"loss": 1.3809,
"step": 100000
}
],
"max_steps": 100000,
"num_train_epochs": 8,
"total_flos": 8.425757579418954e+17,
"trial_name": null,
"trial_params": null
}