{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 100,
  "global_step": 1944,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010290712631849757,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 14.6258,
      "step": 1
    },
    {
      "epoch": 0.10290712631849755,
      "grad_norm": 88.1055908203125,
      "learning_rate": 2.544987146529563e-07,
      "loss": 10.8465,
      "step": 100
    },
    {
      "epoch": 0.10290712631849755,
      "eval_loss": 5.158095359802246,
      "eval_runtime": 112.1444,
      "eval_samples_per_second": 50.257,
      "eval_steps_per_second": 12.564,
      "step": 100
    },
    {
      "epoch": 0.2058142526369951,
      "grad_norm": 94.28155517578125,
      "learning_rate": 5.115681233933161e-07,
      "loss": 4.6022,
      "step": 200
    },
    {
      "epoch": 0.2058142526369951,
      "eval_loss": 4.419423580169678,
      "eval_runtime": 112.0575,
      "eval_samples_per_second": 50.296,
      "eval_steps_per_second": 12.574,
      "step": 200
    },
    {
      "epoch": 0.3087213789554927,
      "grad_norm": 97.87965393066406,
      "learning_rate": 7.686375321336761e-07,
      "loss": 4.1479,
      "step": 300
    },
    {
      "epoch": 0.3087213789554927,
      "eval_loss": 4.014382839202881,
      "eval_runtime": 111.7852,
      "eval_samples_per_second": 50.418,
      "eval_steps_per_second": 12.605,
      "step": 300
    },
    {
      "epoch": 0.4116285052739902,
      "grad_norm": 95.3952865600586,
      "learning_rate": 9.998979614695782e-07,
      "loss": 3.7252,
      "step": 400
    },
    {
      "epoch": 0.4116285052739902,
      "eval_loss": 3.551706075668335,
      "eval_runtime": 108.3373,
      "eval_samples_per_second": 52.023,
      "eval_steps_per_second": 13.006,
      "step": 400
    },
    {
      "epoch": 0.5145356315924878,
      "grad_norm": 95.16962432861328,
      "learning_rate": 9.877036510787077e-07,
      "loss": 3.2177,
      "step": 500
    },
    {
      "epoch": 0.5145356315924878,
      "eval_loss": 3.0623891353607178,
      "eval_runtime": 108.2531,
      "eval_samples_per_second": 52.063,
      "eval_steps_per_second": 13.016,
      "step": 500
    },
    {
      "epoch": 0.6174427579109854,
      "grad_norm": 94.3937759399414,
      "learning_rate": 9.556704559847638e-07,
      "loss": 2.7197,
      "step": 600
    },
    {
      "epoch": 0.6174427579109854,
      "eval_loss": 2.5705835819244385,
      "eval_runtime": 108.2066,
      "eval_samples_per_second": 52.086,
      "eval_steps_per_second": 13.021,
      "step": 600
    },
    {
      "epoch": 0.7203498842294829,
      "grad_norm": 93.52433013916016,
      "learning_rate": 9.051014274622946e-07,
      "loss": 2.2819,
      "step": 700
    },
    {
      "epoch": 0.7203498842294829,
      "eval_loss": 2.1427197456359863,
      "eval_runtime": 108.5307,
      "eval_samples_per_second": 51.93,
      "eval_steps_per_second": 12.982,
      "step": 700
    },
    {
      "epoch": 0.8232570105479804,
      "grad_norm": 89.10120391845703,
      "learning_rate": 8.380536202907438e-07,
      "loss": 1.8746,
      "step": 800
    },
    {
      "epoch": 0.8232570105479804,
      "eval_loss": 1.7777544260025024,
      "eval_runtime": 108.8216,
      "eval_samples_per_second": 51.791,
      "eval_steps_per_second": 12.948,
      "step": 800
    },
    {
      "epoch": 0.926164136866478,
      "grad_norm": 85.86779022216797,
      "learning_rate": 7.572544155613299e-07,
      "loss": 1.5386,
      "step": 900
    },
    {
      "epoch": 0.926164136866478,
      "eval_loss": 1.478671908378601,
      "eval_runtime": 107.9148,
      "eval_samples_per_second": 52.226,
      "eval_steps_per_second": 13.057,
      "step": 900
    },
    {
      "epoch": 1.0288139953691793,
      "grad_norm": 75.19822692871094,
      "learning_rate": 6.65990575846327e-07,
      "loss": 1.2553,
      "step": 1000
    },
    {
      "epoch": 1.0288139953691793,
      "eval_loss": 1.2369881868362427,
      "eval_runtime": 108.6334,
      "eval_samples_per_second": 51.881,
      "eval_steps_per_second": 12.97,
      "step": 1000
    },
    {
      "epoch": 1.1317211216876768,
      "grad_norm": 67.07587432861328,
      "learning_rate": 5.67974545761766e-07,
      "loss": 1.0161,
      "step": 1100
    },
    {
      "epoch": 1.1317211216876768,
      "eval_loss": 1.0523114204406738,
      "eval_runtime": 108.4002,
      "eval_samples_per_second": 51.993,
      "eval_steps_per_second": 12.998,
      "step": 1100
    },
    {
      "epoch": 1.2346282480061745,
      "grad_norm": 58.74506759643555,
      "learning_rate": 4.671934365699874e-07,
      "loss": 0.8586,
      "step": 1200
    },
    {
      "epoch": 1.2346282480061745,
      "eval_loss": 0.9369459748268127,
      "eval_runtime": 109.3483,
      "eval_samples_per_second": 51.542,
      "eval_steps_per_second": 12.885,
      "step": 1200
    },
    {
      "epoch": 1.337535374324672,
      "grad_norm": 52.68925857543945,
      "learning_rate": 3.677468378497882e-07,
      "loss": 0.7547,
      "step": 1300
    },
    {
      "epoch": 1.337535374324672,
      "eval_loss": 0.8299320340156555,
      "eval_runtime": 108.4143,
      "eval_samples_per_second": 51.986,
      "eval_steps_per_second": 12.996,
      "step": 1300
    },
    {
      "epoch": 1.4404425006431696,
      "grad_norm": 43.96974563598633,
      "learning_rate": 2.736800537561799e-07,
      "loss": 0.6964,
      "step": 1400
    },
    {
      "epoch": 1.4404425006431696,
      "eval_loss": 0.7713428139686584,
      "eval_runtime": 108.6974,
      "eval_samples_per_second": 51.85,
      "eval_steps_per_second": 12.963,
      "step": 1400
    },
    {
      "epoch": 1.543349626961667,
      "grad_norm": 41.54279708862305,
      "learning_rate": 1.888195475110272e-07,
      "loss": 0.641,
      "step": 1500
    },
    {
      "epoch": 1.543349626961667,
      "eval_loss": 0.7353219389915466,
      "eval_runtime": 108.5089,
      "eval_samples_per_second": 51.94,
      "eval_steps_per_second": 12.985,
      "step": 1500
    },
    {
      "epoch": 1.6462567532801646,
      "grad_norm": 42.50430679321289,
      "learning_rate": 1.1661728793908349e-07,
      "loss": 0.5969,
      "step": 1600
    },
    {
      "epoch": 1.6462567532801646,
      "eval_loss": 0.7152444124221802,
      "eval_runtime": 108.3835,
      "eval_samples_per_second": 52.001,
      "eval_steps_per_second": 13.0,
      "step": 1600
    },
    {
      "epoch": 1.7491638795986622,
      "grad_norm": 37.6126708984375,
      "learning_rate": 6.001032974514946e-08,
      "loss": 0.5822,
      "step": 1700
    },
    {
      "epoch": 1.7491638795986622,
      "eval_loss": 0.6989532709121704,
      "eval_runtime": 109.1511,
      "eval_samples_per_second": 51.635,
      "eval_steps_per_second": 12.909,
      "step": 1700
    },
    {
      "epoch": 1.8520710059171597,
      "grad_norm": 40.5544548034668,
      "learning_rate": 2.130133954760538e-08,
      "loss": 0.5755,
      "step": 1800
    },
    {
      "epoch": 1.8520710059171597,
      "eval_loss": 0.6931490898132324,
      "eval_runtime": 108.3612,
      "eval_samples_per_second": 52.011,
      "eval_steps_per_second": 13.003,
      "step": 1800
    },
    {
      "epoch": 1.9549781322356572,
      "grad_norm": 41.48668670654297,
      "learning_rate": 2.0649276488408084e-09,
      "loss": 0.5698,
      "step": 1900
    },
    {
      "epoch": 1.9549781322356572,
      "eval_loss": 0.6919553279876709,
      "eval_runtime": 109.2179,
      "eval_samples_per_second": 51.603,
      "eval_steps_per_second": 12.901,
      "step": 1900
    }
  ],
  "logging_steps": 100,
  "max_steps": 1944,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 900,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.415299181635174e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}