{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.310344827586207,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 0.2723050117492676,
      "learning_rate": 0.008792554642694678,
      "loss": 7.2774,
      "step": 100
    },
    {
      "epoch": 0.43103448275862066,
      "eval_loss": 6.054980754852295,
      "eval_runtime": 20.3527,
      "eval_samples_per_second": 5.061,
      "eval_steps_per_second": 1.277,
      "step": 100
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.18630041182041168,
      "learning_rate": 0.007966186725148186,
      "loss": 5.427,
      "step": 200
    },
    {
      "epoch": 0.8620689655172413,
      "eval_loss": 4.836428642272949,
      "eval_runtime": 20.9898,
      "eval_samples_per_second": 4.907,
      "eval_steps_per_second": 1.239,
      "step": 200
    },
    {
      "epoch": 1.293103448275862,
      "grad_norm": 0.2724410593509674,
      "learning_rate": 0.007139818807601695,
      "loss": 4.768,
      "step": 300
    },
    {
      "epoch": 1.293103448275862,
      "eval_loss": 4.6033172607421875,
      "eval_runtime": 21.1004,
      "eval_samples_per_second": 4.881,
      "eval_steps_per_second": 1.232,
      "step": 300
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 0.14782890677452087,
      "learning_rate": 0.006313450890055201,
      "loss": 4.407,
      "step": 400
    },
    {
      "epoch": 1.7241379310344827,
      "eval_loss": 4.464559555053711,
      "eval_runtime": 21.3779,
      "eval_samples_per_second": 4.818,
      "eval_steps_per_second": 1.216,
      "step": 400
    },
    {
      "epoch": 2.1551724137931036,
      "grad_norm": 0.14380355179309845,
      "learning_rate": 0.005487082972508709,
      "loss": 4.4103,
      "step": 500
    },
    {
      "epoch": 2.1551724137931036,
      "eval_loss": 4.4448137283325195,
      "eval_runtime": 21.3614,
      "eval_samples_per_second": 4.822,
      "eval_steps_per_second": 1.217,
      "step": 500
    },
    {
      "epoch": 2.586206896551724,
      "grad_norm": 0.853726863861084,
      "learning_rate": 0.004660715054962217,
      "loss": 4.4563,
      "step": 600
    },
    {
      "epoch": 2.586206896551724,
      "eval_loss": 4.372040748596191,
      "eval_runtime": 21.4365,
      "eval_samples_per_second": 4.805,
      "eval_steps_per_second": 1.213,
      "step": 600
    },
    {
      "epoch": 3.0172413793103448,
      "grad_norm": 29.915081024169922,
      "learning_rate": 0.0038343471374157247,
      "loss": 4.3135,
      "step": 700
    },
    {
      "epoch": 3.0172413793103448,
      "eval_loss": 4.337521553039551,
      "eval_runtime": 21.4878,
      "eval_samples_per_second": 4.793,
      "eval_steps_per_second": 1.21,
      "step": 700
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 0.6140814423561096,
      "learning_rate": 0.003007979219869232,
      "loss": 4.1072,
      "step": 800
    },
    {
      "epoch": 3.4482758620689653,
      "eval_loss": 4.2883219718933105,
      "eval_runtime": 21.4591,
      "eval_samples_per_second": 4.8,
      "eval_steps_per_second": 1.212,
      "step": 800
    },
    {
      "epoch": 3.8793103448275863,
      "grad_norm": 0.20803356170654297,
      "learning_rate": 0.0021816113023227397,
      "loss": 4.3397,
      "step": 900
    },
    {
      "epoch": 3.8793103448275863,
      "eval_loss": 4.263036727905273,
      "eval_runtime": 21.4871,
      "eval_samples_per_second": 4.794,
      "eval_steps_per_second": 1.21,
      "step": 900
    },
    {
      "epoch": 4.310344827586207,
      "grad_norm": 0.19872911274433136,
      "learning_rate": 0.0013552433847762474,
      "loss": 3.9199,
      "step": 1000
    },
    {
      "epoch": 4.310344827586207,
      "eval_loss": 4.16709566116333,
      "eval_runtime": 21.4824,
      "eval_samples_per_second": 4.795,
      "eval_steps_per_second": 1.21,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 1160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.370747847573504e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 0.009172683884766065,
    "per_device_train_batch_size": 4,
    "weight_decay": 0.0003005652075108987
  }
}