{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4953560371517028,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02476780185758514,
      "grad_norm": 1.5924395322799683,
      "learning_rate": 1e-05,
      "loss": 3.0005,
      "step": 1
    },
    {
      "epoch": 0.02476780185758514,
      "eval_loss": 3.629472017288208,
      "eval_runtime": 24.8533,
      "eval_samples_per_second": 10.944,
      "eval_steps_per_second": 2.736,
      "step": 1
    },
    {
      "epoch": 0.04953560371517028,
      "grad_norm": 1.5567954778671265,
      "learning_rate": 2e-05,
      "loss": 3.2024,
      "step": 2
    },
    {
      "epoch": 0.07430340557275542,
      "grad_norm": 1.6604158878326416,
      "learning_rate": 3e-05,
      "loss": 3.127,
      "step": 3
    },
    {
      "epoch": 0.09907120743034056,
      "grad_norm": 1.6006828546524048,
      "learning_rate": 4e-05,
      "loss": 3.2154,
      "step": 4
    },
    {
      "epoch": 0.1238390092879257,
      "grad_norm": 1.695847749710083,
      "learning_rate": 5e-05,
      "loss": 3.2129,
      "step": 5
    },
    {
      "epoch": 0.1238390092879257,
      "eval_loss": 3.4975993633270264,
      "eval_runtime": 24.8759,
      "eval_samples_per_second": 10.934,
      "eval_steps_per_second": 2.734,
      "step": 5
    },
    {
      "epoch": 0.14860681114551083,
      "grad_norm": 2.19637131690979,
      "learning_rate": 6e-05,
      "loss": 3.0675,
      "step": 6
    },
    {
      "epoch": 0.17337461300309598,
      "grad_norm": 2.39349102973938,
      "learning_rate": 7e-05,
      "loss": 2.8079,
      "step": 7
    },
    {
      "epoch": 0.19814241486068113,
      "grad_norm": 2.0309243202209473,
      "learning_rate": 8e-05,
      "loss": 2.6371,
      "step": 8
    },
    {
      "epoch": 0.22291021671826625,
      "grad_norm": 1.8185498714447021,
      "learning_rate": 9e-05,
      "loss": 2.5964,
      "step": 9
    },
    {
      "epoch": 0.2476780185758514,
      "grad_norm": 2.2358932495117188,
      "learning_rate": 0.0001,
      "loss": 2.3791,
      "step": 10
    },
    {
      "epoch": 0.2476780185758514,
      "eval_loss": 2.525038719177246,
      "eval_runtime": 24.804,
      "eval_samples_per_second": 10.966,
      "eval_steps_per_second": 2.741,
      "step": 10
    },
    {
      "epoch": 0.2724458204334365,
      "grad_norm": 1.872157335281372,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3498,
      "step": 11
    },
    {
      "epoch": 0.29721362229102166,
      "grad_norm": 1.768731713294983,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.0483,
      "step": 12
    },
    {
      "epoch": 0.3219814241486068,
      "grad_norm": 2.154233455657959,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.0541,
      "step": 13
    },
    {
      "epoch": 0.34674922600619196,
      "grad_norm": 2.210120677947998,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1021,
      "step": 14
    },
    {
      "epoch": 0.3715170278637771,
      "grad_norm": 1.6423015594482422,
      "learning_rate": 5e-05,
      "loss": 2.1531,
      "step": 15
    },
    {
      "epoch": 0.3715170278637771,
      "eval_loss": 2.1677563190460205,
      "eval_runtime": 24.832,
      "eval_samples_per_second": 10.954,
      "eval_steps_per_second": 2.738,
      "step": 15
    },
    {
      "epoch": 0.39628482972136225,
      "grad_norm": 1.3480126857757568,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.9427,
      "step": 16
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 1.2827550172805786,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.8725,
      "step": 17
    },
    {
      "epoch": 0.4458204334365325,
      "grad_norm": 1.2564868927001953,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.8995,
      "step": 18
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.3051279783248901,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.9913,
      "step": 19
    },
    {
      "epoch": 0.4953560371517028,
      "grad_norm": 1.0693706274032593,
      "learning_rate": 0.0,
      "loss": 1.8631,
      "step": 20
    },
    {
      "epoch": 0.4953560371517028,
      "eval_loss": 2.093961000442505,
      "eval_runtime": 24.8198,
      "eval_samples_per_second": 10.959,
      "eval_steps_per_second": 2.74,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.748078614786867e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}