{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.788732394366197,
  "eval_steps": 54,
  "global_step": 594,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 1.6846675872802734,
      "learning_rate": 1.267605633802817e-05,
      "loss": 1.5207,
      "step": 54
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.452208399772644,
      "eval_runtime": 65.0594,
      "eval_samples_per_second": 3.458,
      "eval_steps_per_second": 0.876,
      "step": 54
    },
    {
      "epoch": 0.51,
      "grad_norm": 2.186245918273926,
      "learning_rate": 2.535211267605634e-05,
      "loss": 1.3334,
      "step": 108
    },
    {
      "epoch": 0.51,
      "eval_loss": 1.2234439849853516,
      "eval_runtime": 65.0532,
      "eval_samples_per_second": 3.459,
      "eval_steps_per_second": 0.876,
      "step": 108
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.9971559047698975,
      "learning_rate": 3.802816901408451e-05,
      "loss": 1.1975,
      "step": 162
    },
    {
      "epoch": 0.76,
      "eval_loss": 1.1602058410644531,
      "eval_runtime": 65.0465,
      "eval_samples_per_second": 3.459,
      "eval_steps_per_second": 0.876,
      "step": 162
    },
    {
      "epoch": 1.01,
      "grad_norm": 2.290921211242676,
      "learning_rate": 4.992175273865415e-05,
      "loss": 1.176,
      "step": 216
    },
    {
      "epoch": 1.01,
      "eval_loss": 1.136144757270813,
      "eval_runtime": 65.0485,
      "eval_samples_per_second": 3.459,
      "eval_steps_per_second": 0.876,
      "step": 216
    },
    {
      "epoch": 1.27,
      "grad_norm": 2.3056328296661377,
      "learning_rate": 4.85133020344288e-05,
      "loss": 1.0848,
      "step": 270
    },
    {
      "epoch": 1.27,
      "eval_loss": 1.12163245677948,
      "eval_runtime": 65.0381,
      "eval_samples_per_second": 3.46,
      "eval_steps_per_second": 0.876,
      "step": 270
    },
    {
      "epoch": 1.52,
      "grad_norm": 2.3068666458129883,
      "learning_rate": 4.710485133020345e-05,
      "loss": 1.1128,
      "step": 324
    },
    {
      "epoch": 1.52,
      "eval_loss": 1.1216281652450562,
      "eval_runtime": 65.046,
      "eval_samples_per_second": 3.459,
      "eval_steps_per_second": 0.876,
      "step": 324
    },
    {
      "epoch": 1.77,
      "grad_norm": 2.432443857192993,
      "learning_rate": 4.569640062597809e-05,
      "loss": 1.1251,
      "step": 378
    },
    {
      "epoch": 1.77,
      "eval_loss": 1.1107735633850098,
      "eval_runtime": 65.0478,
      "eval_samples_per_second": 3.459,
      "eval_steps_per_second": 0.876,
      "step": 378
    },
    {
      "epoch": 2.03,
      "grad_norm": 2.9780454635620117,
      "learning_rate": 4.428794992175274e-05,
      "loss": 1.0871,
      "step": 432
    },
    {
      "epoch": 2.03,
      "eval_loss": 1.1087101697921753,
      "eval_runtime": 65.0472,
      "eval_samples_per_second": 3.459,
      "eval_steps_per_second": 0.876,
      "step": 432
    },
    {
      "epoch": 2.28,
      "grad_norm": 2.2136361598968506,
      "learning_rate": 4.287949921752739e-05,
      "loss": 1.0251,
      "step": 486
    },
    {
      "epoch": 2.28,
      "eval_loss": 1.1033940315246582,
      "eval_runtime": 65.0443,
      "eval_samples_per_second": 3.459,
      "eval_steps_per_second": 0.876,
      "step": 486
    },
    {
      "epoch": 2.54,
      "grad_norm": 2.69734525680542,
      "learning_rate": 4.1471048513302035e-05,
      "loss": 1.0428,
      "step": 540
    },
    {
      "epoch": 2.54,
      "eval_loss": 1.1007825136184692,
      "eval_runtime": 65.0402,
      "eval_samples_per_second": 3.459,
      "eval_steps_per_second": 0.876,
      "step": 540
    },
    {
      "epoch": 2.79,
      "grad_norm": 1.920812726020813,
      "learning_rate": 4.0062597809076686e-05,
      "loss": 1.0549,
      "step": 594
    },
    {
      "epoch": 2.79,
      "eval_loss": 1.1003143787384033,
      "eval_runtime": 65.0548,
      "eval_samples_per_second": 3.459,
      "eval_steps_per_second": 0.876,
      "step": 594
    }
  ],
  "logging_steps": 54,
  "max_steps": 2130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 54,
  "total_flos": 5.28414268636201e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}