{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.093150684931507,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 1.181526780128479,
      "learning_rate": 4.736842105263158e-05,
      "loss": 1.799,
      "step": 10
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.522590160369873,
      "learning_rate": 0.0001,
      "loss": 1.2094,
      "step": 20
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.3870140314102173,
      "learning_rate": 9.979522160511282e-05,
      "loss": 0.8021,
      "step": 30
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.3272338807582855,
      "learning_rate": 9.918256378809177e-05,
      "loss": 0.7125,
      "step": 40
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.39106306433677673,
      "learning_rate": 9.816704491231226e-05,
      "loss": 0.6694,
      "step": 50
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.5298248529434204,
      "learning_rate": 9.675698323078865e-05,
      "loss": 0.6647,
      "step": 60
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 0.33846038579940796,
      "learning_rate": 9.496392875023432e-05,
      "loss": 0.612,
      "step": 70
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.3002408444881439,
      "learning_rate": 9.280256862338821e-05,
      "loss": 0.5868,
      "step": 80
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 0.27812713384628296,
      "learning_rate": 9.029060684455229e-05,
      "loss": 0.599,
      "step": 90
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.3248140513896942,
      "learning_rate": 8.744861923377001e-05,
      "loss": 0.5933,
      "step": 100
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 0.36872419714927673,
      "learning_rate": 8.429988489749046e-05,
      "loss": 0.5952,
      "step": 110
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.3348616659641266,
      "learning_rate": 8.087019554624595e-05,
      "loss": 0.5813,
      "step": 120
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": 0.33727309107780457,
      "learning_rate": 7.718764423124892e-05,
      "loss": 0.5511,
      "step": 130
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 0.35852885246276855,
      "learning_rate": 7.32823952303943e-05,
      "loss": 0.5837,
      "step": 140
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.37122035026550293,
      "learning_rate": 6.918643696856333e-05,
      "loss": 0.5604,
      "step": 150
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.3272222578525543,
      "learning_rate": 6.493331999609131e-05,
      "loss": 0.5318,
      "step": 160
    },
    {
      "epoch": 0.9315068493150684,
      "grad_norm": 0.3521849513053894,
      "learning_rate": 6.055788217165383e-05,
      "loss": 0.5598,
      "step": 170
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": 0.3393417000770569,
      "learning_rate": 5.609596330063558e-05,
      "loss": 0.5626,
      "step": 180
    },
    {
      "epoch": 1.0383561643835617,
      "grad_norm": 0.29794371128082275,
      "learning_rate": 5.1584111566417515e-05,
      "loss": 0.5401,
      "step": 190
    },
    {
      "epoch": 1.093150684931507,
      "grad_norm": 0.40294867753982544,
      "learning_rate": 4.705928415924373e-05,
      "loss": 0.4977,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 366,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.928581998343168e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}