{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9230769230769231,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 3.2268,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.9252,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.3646,
      "step": 30
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.1557,
      "step": 40
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00015,
      "loss": 2.0691,
      "step": 50
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.0406,
      "step": 60
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.9427,
      "step": 70
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.9141,
      "step": 80
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00027,
      "loss": 1.847,
      "step": 90
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8292,
      "step": 100
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00029501661129568106,
      "loss": 1.7893,
      "step": 110
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002900332225913621,
      "loss": 1.7282,
      "step": 120
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002850498338870432,
      "loss": 1.7105,
      "step": 130
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002800664451827242,
      "loss": 1.6879,
      "step": 140
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002750830564784053,
      "loss": 1.6557,
      "step": 150
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00027009966777408634,
      "loss": 1.6357,
      "step": 160
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00026511627906976743,
      "loss": 1.618,
      "step": 170
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00026013289036544847,
      "loss": 1.5717,
      "step": 180
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00025514950166112955,
      "loss": 1.5378,
      "step": 190
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00025016611295681064,
      "loss": 1.5166,
      "step": 200
    },
    {
      "epoch": 0.85,
      "eval_loss": 1.518738031387329,
      "eval_runtime": 35.8579,
      "eval_samples_per_second": 23.203,
      "eval_steps_per_second": 5.801,
      "step": 200
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002451827242524917,
      "loss": 1.4639,
      "step": 210
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00024019933554817274,
      "loss": 1.4595,
      "step": 220
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002352159468438538,
      "loss": 1.4605,
      "step": 230
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00023023255813953486,
      "loss": 1.3207,
      "step": 240
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00022524916943521595,
      "loss": 1.2496,
      "step": 250
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.000220265780730897,
      "loss": 1.2713,
      "step": 260
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00021528239202657807,
      "loss": 1.2369,
      "step": 270
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00021029900332225913,
      "loss": 1.2281,
      "step": 280
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002053156146179402,
      "loss": 1.2195,
      "step": 290
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00020033222591362126,
      "loss": 1.1612,
      "step": 300
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00019534883720930232,
      "loss": 1.1708,
      "step": 310
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00019036544850498338,
      "loss": 1.1457,
      "step": 320
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00018538205980066444,
      "loss": 1.1476,
      "step": 330
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001803986710963455,
      "loss": 1.0804,
      "step": 340
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001754152823920266,
      "loss": 1.1576,
      "step": 350
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001704318936877076,
      "loss": 1.1166,
      "step": 360
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016544850498338866,
      "loss": 1.0881,
      "step": 370
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00016046511627906975,
      "loss": 1.0565,
      "step": 380
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001554817275747508,
      "loss": 1.0939,
      "step": 390
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015049833887043187,
      "loss": 1.0449,
      "step": 400
    },
    {
      "epoch": 1.71,
      "eval_loss": 1.1572413444519043,
      "eval_runtime": 35.4584,
      "eval_samples_per_second": 23.464,
      "eval_steps_per_second": 5.866,
      "step": 400
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00014551495016611296,
      "loss": 1.0332,
      "step": 410
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014053156146179402,
      "loss": 1.0091,
      "step": 420
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00013554817275747508,
      "loss": 1.0268,
      "step": 430
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00013056478405315615,
      "loss": 1.0037,
      "step": 440
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001255813953488372,
      "loss": 0.972,
      "step": 450
    }
  ],
  "max_steps": 702,
  "num_train_epochs": 3,
  "total_flos": 1.3337998305086669e+17,
  "trial_name": null,
  "trial_params": null
}