{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 228,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 2.899078607559204,
      "learning_rate": 4.802631578947368e-05,
      "loss": 3.1521,
      "step": 10
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 1.7488285303115845,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 1.8117,
      "step": 20
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 1.4853039979934692,
      "learning_rate": 4.3640350877192985e-05,
      "loss": 1.1022,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.39769628643989563,
      "eval_runtime": 1.2274,
      "eval_samples_per_second": 54.586,
      "eval_steps_per_second": 4.074,
      "step": 38
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 1.5847415924072266,
      "learning_rate": 4.1447368421052636e-05,
      "loss": 0.6598,
      "step": 40
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 0.9697686433792114,
      "learning_rate": 3.925438596491228e-05,
      "loss": 0.3928,
      "step": 50
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 0.9429943561553955,
      "learning_rate": 3.706140350877193e-05,
      "loss": 0.3304,
      "step": 60
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 0.6725138425827026,
      "learning_rate": 3.4868421052631575e-05,
      "loss": 0.2518,
      "step": 70
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.21954849362373352,
      "eval_runtime": 1.2543,
      "eval_samples_per_second": 53.415,
      "eval_steps_per_second": 3.986,
      "step": 76
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.7255578637123108,
      "learning_rate": 3.267543859649123e-05,
      "loss": 0.2021,
      "step": 80
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 0.6046363711357117,
      "learning_rate": 3.048245614035088e-05,
      "loss": 0.1985,
      "step": 90
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 0.6143187284469604,
      "learning_rate": 2.8289473684210528e-05,
      "loss": 0.1569,
      "step": 100
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 0.6633556485176086,
      "learning_rate": 2.6096491228070176e-05,
      "loss": 0.1494,
      "step": 110
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.18648472428321838,
      "eval_runtime": 1.2933,
      "eval_samples_per_second": 51.805,
      "eval_steps_per_second": 3.866,
      "step": 114
    },
    {
      "epoch": 3.1578947368421053,
      "grad_norm": 0.6238264441490173,
      "learning_rate": 2.3903508771929827e-05,
      "loss": 0.1512,
      "step": 120
    },
    {
      "epoch": 3.4210526315789473,
      "grad_norm": 0.6060639023780823,
      "learning_rate": 2.1710526315789474e-05,
      "loss": 0.1389,
      "step": 130
    },
    {
      "epoch": 3.6842105263157894,
      "grad_norm": 0.7906181216239929,
      "learning_rate": 1.9517543859649122e-05,
      "loss": 0.1255,
      "step": 140
    },
    {
      "epoch": 3.9473684210526314,
      "grad_norm": 0.5497557520866394,
      "learning_rate": 1.7324561403508773e-05,
      "loss": 0.1469,
      "step": 150
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.16589778661727905,
      "eval_runtime": 1.3206,
      "eval_samples_per_second": 50.736,
      "eval_steps_per_second": 3.786,
      "step": 152
    },
    {
      "epoch": 4.2105263157894735,
      "grad_norm": 0.46307989954948425,
      "learning_rate": 1.5131578947368422e-05,
      "loss": 0.1569,
      "step": 160
    },
    {
      "epoch": 4.473684210526316,
      "grad_norm": 0.7654393315315247,
      "learning_rate": 1.2938596491228071e-05,
      "loss": 0.1275,
      "step": 170
    },
    {
      "epoch": 4.7368421052631575,
      "grad_norm": 0.4429921805858612,
      "learning_rate": 1.074561403508772e-05,
      "loss": 0.1107,
      "step": 180
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.017843246459961,
      "learning_rate": 8.552631578947368e-06,
      "loss": 0.121,
      "step": 190
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.16079868376255035,
      "eval_runtime": 1.3018,
      "eval_samples_per_second": 51.466,
      "eval_steps_per_second": 3.841,
      "step": 190
    },
    {
      "epoch": 5.2631578947368425,
      "grad_norm": 0.6578242182731628,
      "learning_rate": 6.3596491228070184e-06,
      "loss": 0.1198,
      "step": 200
    },
    {
      "epoch": 5.526315789473684,
      "grad_norm": 0.5638905763626099,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.1338,
      "step": 210
    },
    {
      "epoch": 5.7894736842105265,
      "grad_norm": 0.6466283798217773,
      "learning_rate": 1.9736842105263157e-06,
      "loss": 0.1272,
      "step": 220
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.15732161700725555,
      "eval_runtime": 1.355,
      "eval_samples_per_second": 49.446,
      "eval_steps_per_second": 3.69,
      "step": 228
    }
  ],
  "logging_steps": 10,
  "max_steps": 228,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 460047467013120.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}