{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.449438202247191,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 1e-05,
      "loss": 1.6702,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.5e-05,
      "loss": 1.5262,
      "step": 2
    },
    {
      "epoch": 0.05,
      "learning_rate": 2e-05,
      "loss": 1.8831,
      "step": 3
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.5e-05,
      "loss": 1.6531,
      "step": 4
    },
    {
      "epoch": 0.09,
      "learning_rate": 3e-05,
      "loss": 1.6833,
      "step": 5
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.5e-05,
      "loss": 1.7288,
      "step": 6
    },
    {
      "epoch": 0.13,
      "learning_rate": 4e-05,
      "loss": 1.5015,
      "step": 7
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.5e-05,
      "loss": 1.6876,
      "step": 8
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 1.6648,
      "step": 9
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.998766400914329e-05,
      "loss": 1.8044,
      "step": 10
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.995066821070679e-05,
      "loss": 1.6566,
      "step": 11
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.9889049115077005e-05,
      "loss": 1.6917,
      "step": 12
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.980286753286195e-05,
      "loss": 1.6271,
      "step": 13
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 1.7478,
      "step": 14
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.9557181268217227e-05,
      "loss": 1.606,
      "step": 15
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.939791904846869e-05,
      "loss": 1.6176,
      "step": 16
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.9214579028215776e-05,
      "loss": 1.7205,
      "step": 17
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.900734214192358e-05,
      "loss": 1.5682,
      "step": 18
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.877641290737884e-05,
      "loss": 1.6807,
      "step": 19
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.852201922385564e-05,
      "loss": 1.6137,
      "step": 20
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.8244412147206284e-05,
      "loss": 1.6352,
      "step": 21
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.794386564209953e-05,
      "loss": 1.5979,
      "step": 22
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.762067631165049e-05,
      "loss": 1.6163,
      "step": 23
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.72751631047092e-08,
      "loss": 1.6513,
      "step": 24
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.5667160778366258e-05,
      "loss": 1.5181,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 110,
  "num_train_epochs": 2,
  "save_steps": 25,
  "total_flos": 8.938661976735744e+16,
  "trial_name": null,
  "trial_params": null
}