{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 690,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0001927536231884058,
      "loss": 2.497,
      "step": 25
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001855072463768116,
      "loss": 1.0576,
      "step": 50
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001782608695652174,
      "loss": 1.063,
      "step": 75
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001710144927536232,
      "loss": 1.5434,
      "step": 100
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000163768115942029,
      "loss": 1.1751,
      "step": 125
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001565217391304348,
      "loss": 0.9868,
      "step": 150
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00014927536231884058,
      "loss": 1.0466,
      "step": 175
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00014202898550724638,
      "loss": 0.7962,
      "step": 200
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001347826086956522,
      "loss": 1.0158,
      "step": 225
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00012753623188405797,
      "loss": 0.8366,
      "step": 250
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00012028985507246378,
      "loss": 1.2794,
      "step": 275
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00011304347826086956,
      "loss": 1.6535,
      "step": 300
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010579710144927538,
      "loss": 0.878,
      "step": 325
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.855072463768117e-05,
      "loss": 0.6866,
      "step": 350
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.130434782608696e-05,
      "loss": 0.5021,
      "step": 375
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.405797101449276e-05,
      "loss": 0.4383,
      "step": 400
    },
    {
      "epoch": 1.23,
      "learning_rate": 7.681159420289855e-05,
      "loss": 0.4791,
      "step": 425
    },
    {
      "epoch": 1.3,
      "learning_rate": 6.956521739130436e-05,
      "loss": 0.5432,
      "step": 450
    },
    {
      "epoch": 1.38,
      "learning_rate": 6.231884057971015e-05,
      "loss": 0.3643,
      "step": 475
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.507246376811594e-05,
      "loss": 1.4377,
      "step": 500
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.782608695652174e-05,
      "loss": 0.4916,
      "step": 525
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.057971014492754e-05,
      "loss": 0.5831,
      "step": 550
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7232,
      "step": 575
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.608695652173913e-05,
      "loss": 0.7072,
      "step": 600
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.8840579710144928e-05,
      "loss": 0.5308,
      "step": 625
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.1594202898550725e-05,
      "loss": 0.4856,
      "step": 650
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.347826086956522e-06,
      "loss": 0.8379,
      "step": 675
    }
  ],
  "max_steps": 690,
  "num_train_epochs": 2,
  "start_time": 1678594586.128044,
  "total_flos": 3.1496986193182065e+19,
  "trial_name": null,
  "trial_params": null
}