{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011243060923336379,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.621530461668189e-05,
      "eval_loss": 0.6979645490646362,
      "eval_runtime": 604.2731,
      "eval_samples_per_second": 12.395,
      "eval_steps_per_second": 6.198,
      "step": 1
    },
    {
      "epoch": 0.0005621530461668189,
      "grad_norm": 0.3639616370201111,
      "learning_rate": 0.0002,
      "loss": 0.6007,
      "step": 10
    },
    {
      "epoch": 0.0011243060923336377,
      "grad_norm": 0.3030410408973694,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.4756,
      "step": 20
    },
    {
      "epoch": 0.0016864591385004567,
      "grad_norm": 0.31223058700561523,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.4263,
      "step": 30
    },
    {
      "epoch": 0.0022486121846672755,
      "grad_norm": 0.37114638090133667,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.3905,
      "step": 40
    },
    {
      "epoch": 0.0028107652308340947,
      "grad_norm": 0.3727080225944519,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.3542,
      "step": 50
    },
    {
      "epoch": 0.0028107652308340947,
      "eval_loss": 0.34557685256004333,
      "eval_runtime": 604.0598,
      "eval_samples_per_second": 12.399,
      "eval_steps_per_second": 6.2,
      "step": 50
    },
    {
      "epoch": 0.0033729182770009134,
      "grad_norm": 0.4353717267513275,
      "learning_rate": 0.00016772815716257412,
      "loss": 0.3599,
      "step": 60
    },
    {
      "epoch": 0.003935071323167732,
      "grad_norm": 0.36681270599365234,
      "learning_rate": 0.00015469481581224272,
      "loss": 0.314,
      "step": 70
    },
    {
      "epoch": 0.004497224369334551,
      "grad_norm": 0.4415012300014496,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.3593,
      "step": 80
    },
    {
      "epoch": 0.005059377415501371,
      "grad_norm": 0.6700223684310913,
      "learning_rate": 0.00012454854871407994,
      "loss": 0.3281,
      "step": 90
    },
    {
      "epoch": 0.005621530461668189,
      "grad_norm": 0.3599109351634979,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.3252,
      "step": 100
    },
    {
      "epoch": 0.005621530461668189,
      "eval_loss": 0.3240654766559601,
      "eval_runtime": 604.4341,
      "eval_samples_per_second": 12.392,
      "eval_steps_per_second": 6.196,
      "step": 100
    },
    {
      "epoch": 0.006183683507835008,
      "grad_norm": 0.3366764485836029,
      "learning_rate": 9.174206545276677e-05,
      "loss": 0.3254,
      "step": 110
    },
    {
      "epoch": 0.006745836554001827,
      "grad_norm": 0.3522528409957886,
      "learning_rate": 7.54514512859201e-05,
      "loss": 0.2954,
      "step": 120
    },
    {
      "epoch": 0.007307989600168646,
      "grad_norm": 0.4563170373439789,
      "learning_rate": 5.983045753470308e-05,
      "loss": 0.3643,
      "step": 130
    },
    {
      "epoch": 0.007870142646335464,
      "grad_norm": 0.37896931171417236,
      "learning_rate": 4.530518418775733e-05,
      "loss": 0.3225,
      "step": 140
    },
    {
      "epoch": 0.008432295692502284,
      "grad_norm": 0.400496244430542,
      "learning_rate": 3.227184283742591e-05,
      "loss": 0.3304,
      "step": 150
    },
    {
      "epoch": 0.008432295692502284,
      "eval_loss": 0.315129816532135,
      "eval_runtime": 604.6819,
      "eval_samples_per_second": 12.387,
      "eval_steps_per_second": 6.193,
      "step": 150
    },
    {
      "epoch": 0.008994448738669102,
      "grad_norm": 0.3536452353000641,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 0.3237,
      "step": 160
    },
    {
      "epoch": 0.009556601784835922,
      "grad_norm": 0.44686853885650635,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 0.3141,
      "step": 170
    },
    {
      "epoch": 0.010118754831002741,
      "grad_norm": 0.3338298499584198,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.3081,
      "step": 180
    },
    {
      "epoch": 0.010680907877169559,
      "grad_norm": 0.4237058758735657,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 0.3302,
      "step": 190
    },
    {
      "epoch": 0.011243060923336379,
      "grad_norm": 0.41507238149642944,
      "learning_rate": 0.0,
      "loss": 0.3024,
      "step": 200
    },
    {
      "epoch": 0.011243060923336379,
      "eval_loss": 0.3131798803806305,
      "eval_runtime": 604.7459,
      "eval_samples_per_second": 12.385,
      "eval_steps_per_second": 6.193,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.880649602085683e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}