{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007894061692092124,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.894061692092124e-05,
      "grad_norm": 2.0472960472106934,
      "learning_rate": 2e-05,
      "loss": 2.0986,
      "step": 1
    },
    {
      "epoch": 7.894061692092124e-05,
      "eval_loss": 2.721665143966675,
      "eval_runtime": 1032.2865,
      "eval_samples_per_second": 5.167,
      "eval_steps_per_second": 2.584,
      "step": 1
    },
    {
      "epoch": 0.00015788123384184247,
      "grad_norm": 3.8498690128326416,
      "learning_rate": 4e-05,
      "loss": 3.3723,
      "step": 2
    },
    {
      "epoch": 0.00023682185076276372,
      "grad_norm": 4.112257957458496,
      "learning_rate": 6e-05,
      "loss": 2.9867,
      "step": 3
    },
    {
      "epoch": 0.00023682185076276372,
      "eval_loss": 2.6779043674468994,
      "eval_runtime": 1036.1544,
      "eval_samples_per_second": 5.148,
      "eval_steps_per_second": 2.574,
      "step": 3
    },
    {
      "epoch": 0.00031576246768368494,
      "grad_norm": 3.055581569671631,
      "learning_rate": 8e-05,
      "loss": 2.7807,
      "step": 4
    },
    {
      "epoch": 0.0003947030846046062,
      "grad_norm": 3.604985475540161,
      "learning_rate": 0.0001,
      "loss": 3.0494,
      "step": 5
    },
    {
      "epoch": 0.00047364370152552744,
      "grad_norm": 2.5712947845458984,
      "learning_rate": 0.00012,
      "loss": 1.9739,
      "step": 6
    },
    {
      "epoch": 0.00047364370152552744,
      "eval_loss": 2.181999921798706,
      "eval_runtime": 1036.9224,
      "eval_samples_per_second": 5.144,
      "eval_steps_per_second": 2.572,
      "step": 6
    },
    {
      "epoch": 0.0005525843184464486,
      "grad_norm": 2.8870301246643066,
      "learning_rate": 0.00014,
      "loss": 2.1759,
      "step": 7
    },
    {
      "epoch": 0.0006315249353673699,
      "grad_norm": 2.637096405029297,
      "learning_rate": 0.00016,
      "loss": 1.7298,
      "step": 8
    },
    {
      "epoch": 0.0007104655522882911,
      "grad_norm": 2.800448417663574,
      "learning_rate": 0.00018,
      "loss": 2.2445,
      "step": 9
    },
    {
      "epoch": 0.0007104655522882911,
      "eval_loss": 1.7051926851272583,
      "eval_runtime": 1035.9377,
      "eval_samples_per_second": 5.149,
      "eval_steps_per_second": 2.574,
      "step": 9
    },
    {
      "epoch": 0.0007894061692092124,
      "grad_norm": 3.807906150817871,
      "learning_rate": 0.0002,
      "loss": 2.1952,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "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": 4104787234652160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}