{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 27036,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 4.907530699807664e-05,
      "loss": 1.4891,
      "step": 500
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.815061399615328e-05,
      "loss": 1.2214,
      "step": 1000
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.722592099422992e-05,
      "loss": 1.149,
      "step": 1500
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.6301227992306555e-05,
      "loss": 1.1007,
      "step": 2000
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.53765349903832e-05,
      "loss": 1.0858,
      "step": 2500
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.4451841988459835e-05,
      "loss": 1.0709,
      "step": 3000
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.352714898653647e-05,
      "loss": 1.0449,
      "step": 3500
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.260245598461311e-05,
      "loss": 1.0326,
      "step": 4000
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.167776298268975e-05,
      "loss": 1.0105,
      "step": 4500
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.075306998076639e-05,
      "loss": 0.9969,
      "step": 5000
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.9828376978843025e-05,
      "loss": 1.002,
      "step": 5500
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.890368397691966e-05,
      "loss": 0.9807,
      "step": 6000
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7978990974996304e-05,
      "loss": 0.9708,
      "step": 6500
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.705429797307294e-05,
      "loss": 0.9676,
      "step": 7000
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.612960497114958e-05,
      "loss": 0.9639,
      "step": 7500
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.520491196922622e-05,
      "loss": 0.9552,
      "step": 8000
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.428021896730286e-05,
      "loss": 0.9545,
      "step": 8500
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.3355525965379494e-05,
      "loss": 0.945,
      "step": 9000
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.243083296345613e-05,
      "loss": 0.8917,
      "step": 9500
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.1506139961532774e-05,
      "loss": 0.887,
      "step": 10000
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.058144695960941e-05,
      "loss": 0.881,
      "step": 10500
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.965675395768605e-05,
      "loss": 0.8809,
      "step": 11000
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.873206095576269e-05,
      "loss": 0.8785,
      "step": 11500
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.7807367953839327e-05,
      "loss": 0.8767,
      "step": 12000
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.6882674951915963e-05,
      "loss": 0.8786,
      "step": 12500
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.5957981949992603e-05,
      "loss": 0.8717,
      "step": 13000
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.5033288948069243e-05,
      "loss": 0.868,
      "step": 13500
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.4108595946145883e-05,
      "loss": 0.8642,
      "step": 14000
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.318390294422252e-05,
      "loss": 0.8561,
      "step": 14500
    },
    {
      "epoch": 1.66,
      "learning_rate": 2.225920994229916e-05,
      "loss": 0.8617,
      "step": 15000
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.1334516940375796e-05,
      "loss": 0.8619,
      "step": 15500
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.0409823938452436e-05,
      "loss": 0.8498,
      "step": 16000
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.9485130936529072e-05,
      "loss": 0.8526,
      "step": 16500
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.8560437934605712e-05,
      "loss": 0.8539,
      "step": 17000
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.763574493268235e-05,
      "loss": 0.8579,
      "step": 17500
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.671105193075899e-05,
      "loss": 0.8486,
      "step": 18000
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.5786358928835625e-05,
      "loss": 0.8047,
      "step": 18500
    },
    {
      "epoch": 2.11,
      "learning_rate": 1.4861665926912265e-05,
      "loss": 0.8095,
      "step": 19000
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.3936972924988904e-05,
      "loss": 0.8031,
      "step": 19500
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.3012279923065543e-05,
      "loss": 0.8102,
      "step": 20000
    },
    {
      "epoch": 2.27,
      "learning_rate": 1.2087586921142182e-05,
      "loss": 0.8054,
      "step": 20500
    },
    {
      "epoch": 2.33,
      "learning_rate": 1.116289391921882e-05,
      "loss": 0.8058,
      "step": 21000
    },
    {
      "epoch": 2.39,
      "learning_rate": 1.0238200917295458e-05,
      "loss": 0.8092,
      "step": 21500
    },
    {
      "epoch": 2.44,
      "learning_rate": 9.313507915372096e-06,
      "loss": 0.8111,
      "step": 22000
    },
    {
      "epoch": 2.5,
      "learning_rate": 8.388814913448735e-06,
      "loss": 0.7986,
      "step": 22500
    },
    {
      "epoch": 2.55,
      "learning_rate": 7.464121911525374e-06,
      "loss": 0.7973,
      "step": 23000
    },
    {
      "epoch": 2.61,
      "learning_rate": 6.539428909602012e-06,
      "loss": 0.7992,
      "step": 23500
    },
    {
      "epoch": 2.66,
      "learning_rate": 5.614735907678651e-06,
      "loss": 0.7957,
      "step": 24000
    },
    {
      "epoch": 2.72,
      "learning_rate": 4.690042905755289e-06,
      "loss": 0.7949,
      "step": 24500
    },
    {
      "epoch": 2.77,
      "learning_rate": 3.765349903831928e-06,
      "loss": 0.7967,
      "step": 25000
    },
    {
      "epoch": 2.83,
      "learning_rate": 2.8406569019085665e-06,
      "loss": 0.7966,
      "step": 25500
    },
    {
      "epoch": 2.89,
      "learning_rate": 1.9159638999852047e-06,
      "loss": 0.7906,
      "step": 26000
    },
    {
      "epoch": 2.94,
      "learning_rate": 9.912708980618436e-07,
      "loss": 0.7939,
      "step": 26500
    },
    {
      "epoch": 3.0,
      "learning_rate": 6.657789613848203e-08,
      "loss": 0.7894,
      "step": 27000
    },
    {
      "epoch": 3.0,
      "step": 27036,
      "total_flos": 5.02121819894784e+17,
      "train_loss": 0.9067944516654479,
      "train_runtime": 27064.5368,
      "train_samples_per_second": 7.991,
      "train_steps_per_second": 0.999
    }
  ],
  "logging_steps": 500,
  "max_steps": 27036,
  "num_train_epochs": 3,
  "save_steps": 10000,
  "total_flos": 5.02121819894784e+17,
  "trial_name": null,
  "trial_params": null
}