{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03536724462638927,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 9.8e-05,
      "loss": 2.1045,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.6e-05,
      "loss": 2.0857,
      "step": 40
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.4e-05,
      "loss": 2.0659,
      "step": 60
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.200000000000001e-05,
      "loss": 2.083,
      "step": 80
    },
    {
      "epoch": 0.0,
      "learning_rate": 9e-05,
      "loss": 2.072,
      "step": 100
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.800000000000001e-05,
      "loss": 2.0661,
      "step": 120
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.6e-05,
      "loss": 2.1078,
      "step": 140
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.4e-05,
      "loss": 2.0923,
      "step": 160
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.2e-05,
      "loss": 2.1077,
      "step": 180
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 2.0772,
      "step": 200
    },
    {
      "epoch": 0.01,
      "eval_accuracy": 0.5588168810247175,
      "eval_loss": 2.072767972946167,
      "eval_runtime": 607.9248,
      "eval_samples_per_second": 83.366,
      "eval_steps_per_second": 1.303,
      "step": 200
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.800000000000001e-05,
      "loss": 2.0451,
      "step": 220
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.6e-05,
      "loss": 2.1015,
      "step": 240
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.4e-05,
      "loss": 2.0811,
      "step": 260
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.2e-05,
      "loss": 2.0635,
      "step": 280
    },
    {
      "epoch": 0.01,
      "learning_rate": 7e-05,
      "loss": 2.0652,
      "step": 300
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.0764,
      "step": 320
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.6e-05,
      "loss": 2.1036,
      "step": 340
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.400000000000001e-05,
      "loss": 2.1153,
      "step": 360
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.2e-05,
      "loss": 2.0797,
      "step": 380
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 2.0718,
      "step": 400
    },
    {
      "epoch": 0.01,
      "eval_accuracy": 0.5599554087888088,
      "eval_loss": 2.065608263015747,
      "eval_runtime": 606.8111,
      "eval_samples_per_second": 83.519,
      "eval_steps_per_second": 1.305,
      "step": 400
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.8e-05,
      "loss": 2.0823,
      "step": 420
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.0801,
      "step": 440
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 2.0904,
      "step": 460
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.0671,
      "step": 480
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 2.0941,
      "step": 500
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-05,
      "loss": 2.0872,
      "step": 520
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.600000000000001e-05,
      "loss": 2.085,
      "step": 540
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.0732,
      "step": 560
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.2e-05,
      "loss": 2.1002,
      "step": 580
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 2.0661,
      "step": 600
    },
    {
      "epoch": 0.02,
      "eval_accuracy": 0.5617092473862322,
      "eval_loss": 2.0560526847839355,
      "eval_runtime": 611.1674,
      "eval_samples_per_second": 82.923,
      "eval_steps_per_second": 1.296,
      "step": 600
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.8e-05,
      "loss": 2.0552,
      "step": 620
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-05,
      "loss": 2.0903,
      "step": 640
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 2.0686,
      "step": 660
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.0456,
      "step": 680
    },
    {
      "epoch": 0.02,
      "learning_rate": 3e-05,
      "loss": 2.0577,
      "step": 700
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.0556,
      "step": 720
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.0514,
      "step": 740
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.4e-05,
      "loss": 2.0377,
      "step": 760
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.0749,
      "step": 780
    },
    {
      "epoch": 0.03,
      "learning_rate": 2e-05,
      "loss": 2.0606,
      "step": 800
    },
    {
      "epoch": 0.03,
      "eval_accuracy": 0.563209045822219,
      "eval_loss": 2.0472447872161865,
      "eval_runtime": 607.4171,
      "eval_samples_per_second": 83.435,
      "eval_steps_per_second": 1.304,
      "step": 800
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.8e-05,
      "loss": 2.0604,
      "step": 820
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.0658,
      "step": 840
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.0515,
      "step": 860
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.2e-05,
      "loss": 2.0937,
      "step": 880
    },
    {
      "epoch": 0.03,
      "learning_rate": 1e-05,
      "loss": 2.0801,
      "step": 900
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0439,
      "step": 920
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-06,
      "loss": 2.0521,
      "step": 940
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.0591,
      "step": 960
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.0623,
      "step": 980
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0,
      "loss": 2.0514,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.5643423993376961,
      "eval_loss": 2.0413460731506348,
      "eval_runtime": 606.9861,
      "eval_samples_per_second": 83.494,
      "eval_steps_per_second": 1.305,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "step": 1000,
      "total_flos": 1.7866929733632e+17,
      "train_loss": 2.0741817893981933,
      "train_runtime": 4371.6709,
      "train_samples_per_second": 14.64,
      "train_steps_per_second": 0.229
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 1,
  "total_flos": 1.7866929733632e+17,
  "trial_name": null,
  "trial_params": null
}