{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 2250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 9.555555555555557e-05,
      "loss": 0.2797,
      "step": 100
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.111111111111112e-05,
      "loss": 0.2685,
      "step": 200
    },
    {
      "epoch": 0.27,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.233,
      "step": 300
    },
    {
      "epoch": 0.36,
      "learning_rate": 8.222222222222222e-05,
      "loss": 0.2162,
      "step": 400
    },
    {
      "epoch": 0.44,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.2058,
      "step": 500
    },
    {
      "epoch": 0.44,
      "eval_loss": 0.27426090836524963,
      "eval_macro-f1": 0.30734886729341776,
      "eval_micro-f1": 0.45783132530120485,
      "eval_runtime": 154.032,
      "eval_samples_per_second": 6.492,
      "eval_steps_per_second": 0.812,
      "step": 500
    },
    {
      "epoch": 0.53,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.1897,
      "step": 600
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.88888888888889e-05,
      "loss": 0.1881,
      "step": 700
    },
    {
      "epoch": 0.71,
      "learning_rate": 6.444444444444446e-05,
      "loss": 0.1913,
      "step": 800
    },
    {
      "epoch": 0.8,
      "learning_rate": 6e-05,
      "loss": 0.1777,
      "step": 900
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.1583,
      "step": 1000
    },
    {
      "epoch": 0.89,
      "eval_loss": 0.2576006054878235,
      "eval_macro-f1": 0.33354478819865846,
      "eval_micro-f1": 0.5014016820184222,
      "eval_runtime": 153.9992,
      "eval_samples_per_second": 6.494,
      "eval_steps_per_second": 0.812,
      "step": 1000
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.111111111111111e-05,
      "loss": 0.1776,
      "step": 1100
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.1606,
      "step": 1200
    },
    {
      "epoch": 1.16,
      "learning_rate": 4.222222222222222e-05,
      "loss": 0.1658,
      "step": 1300
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.777777777777778e-05,
      "loss": 0.1532,
      "step": 1400
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1602,
      "step": 1500
    },
    {
      "epoch": 1.33,
      "eval_loss": 0.2343183010816574,
      "eval_macro-f1": 0.36320960253779505,
      "eval_micro-f1": 0.5341176470588236,
      "eval_runtime": 153.838,
      "eval_samples_per_second": 6.5,
      "eval_steps_per_second": 0.813,
      "step": 1500
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 0.1647,
      "step": 1600
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 0.1588,
      "step": 1700
    },
    {
      "epoch": 1.6,
      "learning_rate": 2e-05,
      "loss": 0.1513,
      "step": 1800
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.5555555555555555e-05,
      "loss": 0.1518,
      "step": 1900
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.1474,
      "step": 2000
    },
    {
      "epoch": 1.78,
      "eval_loss": 0.2262774258852005,
      "eval_macro-f1": 0.3867760365271726,
      "eval_micro-f1": 0.546868922598211,
      "eval_runtime": 154.1091,
      "eval_samples_per_second": 6.489,
      "eval_steps_per_second": 0.811,
      "step": 2000
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.155,
      "step": 2100
    },
    {
      "epoch": 1.96,
      "learning_rate": 2.2222222222222225e-06,
      "loss": 0.1522,
      "step": 2200
    },
    {
      "epoch": 2.0,
      "step": 2250,
      "total_flos": 8.8324576837632e+16,
      "train_loss": 0.18118783251444498,
      "train_runtime": 3615.8229,
      "train_samples_per_second": 4.978,
      "train_steps_per_second": 0.622
    }
  ],
  "max_steps": 2250,
  "num_train_epochs": 2,
  "total_flos": 8.8324576837632e+16,
  "trial_name": null,
  "trial_params": null
}