{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.2526315789473683,
  "eval_steps": 25,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 1.6458312273025513,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.6363,
      "step": 1
    },
    {
      "epoch": 0.16842105263157894,
      "eval_loss": 5.683743476867676,
      "eval_runtime": 2.6775,
      "eval_samples_per_second": 14.939,
      "eval_steps_per_second": 1.867,
      "step": 1
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 1.8324257135391235,
      "learning_rate": 9.698463103929542e-05,
      "loss": 5.4749,
      "step": 2
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 1.3670103549957275,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.2773,
      "step": 3
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 1.190866470336914,
      "learning_rate": 8.83022221559489e-05,
      "loss": 5.066,
      "step": 4
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 1.5695290565490723,
      "learning_rate": 8.213938048432697e-05,
      "loss": 5.1387,
      "step": 5
    },
    {
      "epoch": 1.0842105263157895,
      "grad_norm": 1.7884435653686523,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.5384,
      "step": 6
    },
    {
      "epoch": 1.2526315789473683,
      "grad_norm": 0.9453433752059937,
      "learning_rate": 6.710100716628344e-05,
      "loss": 3.7915,
      "step": 7
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 0.8627495765686035,
      "learning_rate": 5.868240888334653e-05,
      "loss": 3.2481,
      "step": 8
    },
    {
      "epoch": 1.5894736842105264,
      "grad_norm": 1.2350523471832275,
      "learning_rate": 5e-05,
      "loss": 5.1455,
      "step": 9
    },
    {
      "epoch": 1.7578947368421054,
      "grad_norm": 1.4544273614883423,
      "learning_rate": 4.131759111665349e-05,
      "loss": 5.3455,
      "step": 10
    },
    {
      "epoch": 1.9263157894736842,
      "grad_norm": 1.2949740886688232,
      "learning_rate": 3.289899283371657e-05,
      "loss": 5.6034,
      "step": 11
    },
    {
      "epoch": 2.168421052631579,
      "grad_norm": 0.874649703502655,
      "learning_rate": 2.500000000000001e-05,
      "loss": 4.0481,
      "step": 12
    },
    {
      "epoch": 2.336842105263158,
      "grad_norm": 0.818899393081665,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 4.0591,
      "step": 13
    },
    {
      "epoch": 2.5052631578947366,
      "grad_norm": 0.8536515235900879,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 4.0291,
      "step": 14
    },
    {
      "epoch": 2.6736842105263157,
      "grad_norm": 0.9671108722686768,
      "learning_rate": 6.698729810778065e-06,
      "loss": 4.0958,
      "step": 15
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 1.2295182943344116,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 4.1651,
      "step": 16
    },
    {
      "epoch": 3.0842105263157893,
      "grad_norm": 1.4174128770828247,
      "learning_rate": 7.596123493895991e-07,
      "loss": 6.4532,
      "step": 17
    },
    {
      "epoch": 3.2526315789473683,
      "grad_norm": 1.005539894104004,
      "learning_rate": 0.0,
      "loss": 3.2941,
      "step": 18
    }
  ],
  "logging_steps": 1,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8932788789405286e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}