{
  "best_metric": 1.9091793298721313,
  "best_model_checkpoint": "output/lovv66/checkpoint-130",
  "epoch": 2.0,
  "global_step": 130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 0.00013520660867542716,
      "loss": 2.5547,
      "step": 5
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00012934228335981018,
      "loss": 2.3522,
      "step": 10
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00011994783732453754,
      "loss": 2.167,
      "step": 15
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00010756924162575728,
      "loss": 2.1046,
      "step": 20
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.292589525111794e-05,
      "loss": 2.077,
      "step": 25
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.686881626551515e-05,
      "loss": 1.9938,
      "step": 30
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.033118373448485e-05,
      "loss": 1.8638,
      "step": 35
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.427410474888205e-05,
      "loss": 2.0056,
      "step": 40
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.963075837424272e-05,
      "loss": 2.0102,
      "step": 45
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.725216267546246e-05,
      "loss": 1.9461,
      "step": 50
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.857716640189809e-06,
      "loss": 2.0685,
      "step": 55
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.993391324572832e-06,
      "loss": 1.9764,
      "step": 60
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.9014,
      "step": 65
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.979666829109192,
      "eval_runtime": 4.4495,
      "eval_samples_per_second": 21.126,
      "eval_steps_per_second": 2.697,
      "step": 65
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.9933913245728244e-06,
      "loss": 1.8835,
      "step": 70
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.857716640189785e-06,
      "loss": 1.968,
      "step": 75
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.7252162675462473e-05,
      "loss": 1.9068,
      "step": 80
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.9630758374242703e-05,
      "loss": 1.8999,
      "step": 85
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.427410474888204e-05,
      "loss": 1.8825,
      "step": 90
    },
    {
      "epoch": 1.46,
      "learning_rate": 6.03311837344848e-05,
      "loss": 1.909,
      "step": 95
    },
    {
      "epoch": 1.54,
      "learning_rate": 7.686881626551516e-05,
      "loss": 1.924,
      "step": 100
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.292589525111794e-05,
      "loss": 1.8846,
      "step": 105
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00010756924162575728,
      "loss": 1.8094,
      "step": 110
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001199478373245375,
      "loss": 1.896,
      "step": 115
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001293422833598102,
      "loss": 1.8081,
      "step": 120
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00013520660867542716,
      "loss": 1.7367,
      "step": 125
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001372,
      "loss": 1.7623,
      "step": 130
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.9091793298721313,
      "eval_runtime": 4.4369,
      "eval_samples_per_second": 21.186,
      "eval_steps_per_second": 2.705,
      "step": 130
    }
  ],
  "max_steps": 130,
  "num_train_epochs": 2,
  "total_flos": 135610564608000.0,
  "trial_name": null,
  "trial_params": null
}