{
  "best_metric": 0.9877104163169861,
  "best_model_checkpoint": "./opt_trained/checkpoint-3216",
  "epoch": 19.0,
  "eval_steps": 500,
  "global_step": 3819,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.0177865028381348,
      "eval_runtime": 77.0752,
      "eval_samples_per_second": 37.055,
      "eval_steps_per_second": 9.264,
      "step": 201
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0106526613235474,
      "eval_runtime": 77.338,
      "eval_samples_per_second": 36.929,
      "eval_steps_per_second": 9.232,
      "step": 402
    },
    {
      "epoch": 2.488169364881694,
      "grad_norm": 1.6413393020629883,
      "learning_rate": 0.0003501,
      "loss": 1.0175,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.0082063674926758,
      "eval_runtime": 77.1371,
      "eval_samples_per_second": 37.025,
      "eval_steps_per_second": 9.256,
      "step": 603
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0058513879776,
      "eval_runtime": 76.7488,
      "eval_samples_per_second": 37.212,
      "eval_steps_per_second": 9.303,
      "step": 804
    },
    {
      "epoch": 4.976338729763388,
      "grad_norm": 1.9620177745819092,
      "learning_rate": 0.00030010000000000003,
      "loss": 0.9962,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.0030816793441772,
      "eval_runtime": 76.8119,
      "eval_samples_per_second": 37.182,
      "eval_steps_per_second": 9.295,
      "step": 1005
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.0030088424682617,
      "eval_runtime": 76.8319,
      "eval_samples_per_second": 37.172,
      "eval_steps_per_second": 9.293,
      "step": 1206
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.9996200203895569,
      "eval_runtime": 77.0477,
      "eval_samples_per_second": 37.068,
      "eval_steps_per_second": 9.267,
      "step": 1407
    },
    {
      "epoch": 7.463262764632628,
      "grad_norm": 1.7347174882888794,
      "learning_rate": 0.0002501,
      "loss": 0.9871,
      "step": 1500
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.9977834820747375,
      "eval_runtime": 76.773,
      "eval_samples_per_second": 37.201,
      "eval_steps_per_second": 9.3,
      "step": 1608
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.9954783320426941,
      "eval_runtime": 76.956,
      "eval_samples_per_second": 37.112,
      "eval_steps_per_second": 9.278,
      "step": 1809
    },
    {
      "epoch": 9.951432129514322,
      "grad_norm": 1.4501839876174927,
      "learning_rate": 0.0002001,
      "loss": 0.9774,
      "step": 2000
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.995110273361206,
      "eval_runtime": 77.0387,
      "eval_samples_per_second": 37.072,
      "eval_steps_per_second": 9.268,
      "step": 2010
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.9924370050430298,
      "eval_runtime": 77.2049,
      "eval_samples_per_second": 36.992,
      "eval_steps_per_second": 9.248,
      "step": 2211
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.9905564785003662,
      "eval_runtime": 77.3311,
      "eval_samples_per_second": 36.932,
      "eval_steps_per_second": 9.233,
      "step": 2412
    },
    {
      "epoch": 12.438356164383562,
      "grad_norm": 1.4806139469146729,
      "learning_rate": 0.0001501,
      "loss": 0.9638,
      "step": 2500
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.990676999092102,
      "eval_runtime": 77.0729,
      "eval_samples_per_second": 37.056,
      "eval_steps_per_second": 9.264,
      "step": 2613
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.988075315952301,
      "eval_runtime": 77.0166,
      "eval_samples_per_second": 37.083,
      "eval_steps_per_second": 9.271,
      "step": 2814
    },
    {
      "epoch": 14.926525529265255,
      "grad_norm": 1.8893911838531494,
      "learning_rate": 0.0001001,
      "loss": 0.9428,
      "step": 3000
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.9882552027702332,
      "eval_runtime": 77.0864,
      "eval_samples_per_second": 37.049,
      "eval_steps_per_second": 9.262,
      "step": 3015
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.9877104163169861,
      "eval_runtime": 77.0222,
      "eval_samples_per_second": 37.08,
      "eval_steps_per_second": 9.27,
      "step": 3216
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.9905799031257629,
      "eval_runtime": 76.8333,
      "eval_samples_per_second": 37.171,
      "eval_steps_per_second": 9.293,
      "step": 3417
    },
    {
      "epoch": 17.413449564134496,
      "grad_norm": 1.899855136871338,
      "learning_rate": 5.0100000000000005e-05,
      "loss": 0.9154,
      "step": 3500
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.9950315952301025,
      "eval_runtime": 76.8254,
      "eval_samples_per_second": 37.175,
      "eval_steps_per_second": 9.294,
      "step": 3618
    },
    {
      "epoch": 19.0,
      "eval_loss": 0.9973178505897522,
      "eval_runtime": 77.4812,
      "eval_samples_per_second": 36.861,
      "eval_steps_per_second": 9.215,
      "step": 3819
    }
  ],
  "logging_steps": 500,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2856067083008e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}