{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.936347103143674,
  "global_step": 19000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 1.9480384515458563e-05,
      "loss": 2.3177,
      "step": 500
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.8960769030917124e-05,
      "loss": 1.998,
      "step": 1000
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.8441153546375682e-05,
      "loss": 1.8707,
      "step": 1500
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.7921538061834244e-05,
      "loss": 1.8186,
      "step": 2000
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.7401922577292805e-05,
      "loss": 1.766,
      "step": 2500
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.6882307092751363e-05,
      "loss": 1.7102,
      "step": 3000
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.6362691608209928e-05,
      "loss": 1.6835,
      "step": 3500
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.5456233024597168,
      "eval_runtime": 14.4448,
      "eval_samples_per_second": 1065.508,
      "eval_steps_per_second": 133.197,
      "step": 3849
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.5843076123668486e-05,
      "loss": 1.6502,
      "step": 4000
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.5323460639127047e-05,
      "loss": 1.6152,
      "step": 4500
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.4803845154585607e-05,
      "loss": 1.6067,
      "step": 5000
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.4284229670044167e-05,
      "loss": 1.5855,
      "step": 5500
    },
    {
      "epoch": 1.56,
      "learning_rate": 1.376461418550273e-05,
      "loss": 1.5687,
      "step": 6000
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.324499870096129e-05,
      "loss": 1.5541,
      "step": 6500
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.272538321641985e-05,
      "loss": 1.5415,
      "step": 7000
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.220576773187841e-05,
      "loss": 1.5347,
      "step": 7500
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.433572769165039,
      "eval_runtime": 12.6009,
      "eval_samples_per_second": 1221.422,
      "eval_steps_per_second": 152.688,
      "step": 7698
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.1686152247336972e-05,
      "loss": 1.513,
      "step": 8000
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.1166536762795532e-05,
      "loss": 1.5097,
      "step": 8500
    },
    {
      "epoch": 2.34,
      "learning_rate": 1.0646921278254091e-05,
      "loss": 1.5,
      "step": 9000
    },
    {
      "epoch": 2.47,
      "learning_rate": 1.0127305793712654e-05,
      "loss": 1.4931,
      "step": 9500
    },
    {
      "epoch": 2.6,
      "learning_rate": 9.607690309171214e-06,
      "loss": 1.4868,
      "step": 10000
    },
    {
      "epoch": 2.73,
      "learning_rate": 9.088074824629775e-06,
      "loss": 1.4732,
      "step": 10500
    },
    {
      "epoch": 2.86,
      "learning_rate": 8.568459340088335e-06,
      "loss": 1.4793,
      "step": 11000
    },
    {
      "epoch": 2.99,
      "learning_rate": 8.048843855546896e-06,
      "loss": 1.4488,
      "step": 11500
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3860989809036255,
      "eval_runtime": 14.3478,
      "eval_samples_per_second": 1072.711,
      "eval_steps_per_second": 134.098,
      "step": 11547
    },
    {
      "epoch": 3.12,
      "learning_rate": 7.529228371005457e-06,
      "loss": 1.4531,
      "step": 12000
    },
    {
      "epoch": 3.25,
      "learning_rate": 7.009612886464017e-06,
      "loss": 1.4495,
      "step": 12500
    },
    {
      "epoch": 3.38,
      "learning_rate": 6.489997401922577e-06,
      "loss": 1.4453,
      "step": 13000
    },
    {
      "epoch": 3.51,
      "learning_rate": 5.9703819173811386e-06,
      "loss": 1.4387,
      "step": 13500
    },
    {
      "epoch": 3.64,
      "learning_rate": 5.450766432839699e-06,
      "loss": 1.4305,
      "step": 14000
    },
    {
      "epoch": 3.77,
      "learning_rate": 4.93115094829826e-06,
      "loss": 1.4403,
      "step": 14500
    },
    {
      "epoch": 3.9,
      "learning_rate": 4.41153546375682e-06,
      "loss": 1.4434,
      "step": 15000
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.3605549335479736,
      "eval_runtime": 14.4,
      "eval_samples_per_second": 1068.818,
      "eval_steps_per_second": 133.611,
      "step": 15396
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.8919199792153815e-06,
      "loss": 1.4402,
      "step": 15500
    },
    {
      "epoch": 4.16,
      "learning_rate": 3.3723044946739412e-06,
      "loss": 1.4151,
      "step": 16000
    },
    {
      "epoch": 4.29,
      "learning_rate": 2.852689010132502e-06,
      "loss": 1.4172,
      "step": 16500
    },
    {
      "epoch": 4.42,
      "learning_rate": 2.3330735255910627e-06,
      "loss": 1.4282,
      "step": 17000
    },
    {
      "epoch": 4.55,
      "learning_rate": 1.8134580410496232e-06,
      "loss": 1.4168,
      "step": 17500
    },
    {
      "epoch": 4.68,
      "learning_rate": 1.2938425565081842e-06,
      "loss": 1.4168,
      "step": 18000
    },
    {
      "epoch": 4.81,
      "learning_rate": 7.742270719667447e-07,
      "loss": 1.4327,
      "step": 18500
    },
    {
      "epoch": 4.94,
      "learning_rate": 2.546115874253053e-07,
      "loss": 1.4071,
      "step": 19000
    }
  ],
  "max_steps": 19245,
  "num_train_epochs": 5,
  "total_flos": 969604875878400.0,
  "trial_name": null,
  "trial_params": null
}