{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 14.0,
  "eval_steps": 500,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4032258064516129,
      "grad_norm": 15.945989608764648,
      "learning_rate": 5.4e-07,
      "loss": 2.942,
      "step": 10
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 15.050374984741211,
      "learning_rate": 1.14e-06,
      "loss": 3.345,
      "step": 20
    },
    {
      "epoch": 1.2016129032258065,
      "grad_norm": 9.487156867980957,
      "learning_rate": 1.74e-06,
      "loss": 2.6443,
      "step": 30
    },
    {
      "epoch": 1.6048387096774195,
      "grad_norm": 14.825271606445312,
      "learning_rate": 2.34e-06,
      "loss": 3.0528,
      "step": 40
    },
    {
      "epoch": 2.0,
      "grad_norm": 15.298517227172852,
      "learning_rate": 2.9400000000000002e-06,
      "loss": 2.2951,
      "step": 50
    },
    {
      "epoch": 2.403225806451613,
      "grad_norm": 13.529952049255371,
      "learning_rate": 3.54e-06,
      "loss": 2.3061,
      "step": 60
    },
    {
      "epoch": 2.806451612903226,
      "grad_norm": 12.780255317687988,
      "learning_rate": 4.14e-06,
      "loss": 1.828,
      "step": 70
    },
    {
      "epoch": 3.2016129032258065,
      "grad_norm": 4.392550468444824,
      "learning_rate": 4.74e-06,
      "loss": 1.7883,
      "step": 80
    },
    {
      "epoch": 3.6048387096774195,
      "grad_norm": 6.868764400482178,
      "learning_rate": 5.34e-06,
      "loss": 1.3883,
      "step": 90
    },
    {
      "epoch": 4.0,
      "grad_norm": 11.529573440551758,
      "learning_rate": 5.940000000000001e-06,
      "loss": 1.2804,
      "step": 100
    },
    {
      "epoch": 4.403225806451613,
      "grad_norm": 3.888104200363159,
      "learning_rate": 6.54e-06,
      "loss": 1.1184,
      "step": 110
    },
    {
      "epoch": 4.806451612903226,
      "grad_norm": 5.543831825256348,
      "learning_rate": 7.14e-06,
      "loss": 0.8838,
      "step": 120
    },
    {
      "epoch": 5.201612903225806,
      "grad_norm": 3.6435844898223877,
      "learning_rate": 7.74e-06,
      "loss": 0.7359,
      "step": 130
    },
    {
      "epoch": 5.604838709677419,
      "grad_norm": 3.873931407928467,
      "learning_rate": 8.340000000000001e-06,
      "loss": 0.6677,
      "step": 140
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.526176929473877,
      "learning_rate": 8.939999999999999e-06,
      "loss": 0.5343,
      "step": 150
    },
    {
      "epoch": 6.403225806451613,
      "grad_norm": 2.3237783908843994,
      "learning_rate": 9.54e-06,
      "loss": 0.4596,
      "step": 160
    },
    {
      "epoch": 6.806451612903226,
      "grad_norm": 3.2708520889282227,
      "learning_rate": 1.0140000000000001e-05,
      "loss": 0.371,
      "step": 170
    },
    {
      "epoch": 7.201612903225806,
      "grad_norm": 1.420652985572815,
      "learning_rate": 1.074e-05,
      "loss": 0.397,
      "step": 180
    },
    {
      "epoch": 7.604838709677419,
      "grad_norm": 2.8168821334838867,
      "learning_rate": 1.134e-05,
      "loss": 0.2335,
      "step": 190
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.872466504573822,
      "learning_rate": 1.1940000000000001e-05,
      "loss": 0.2535,
      "step": 200
    },
    {
      "epoch": 8.403225806451612,
      "grad_norm": 1.6869771480560303,
      "learning_rate": 1.254e-05,
      "loss": 0.1642,
      "step": 210
    },
    {
      "epoch": 8.806451612903226,
      "grad_norm": 8.301424026489258,
      "learning_rate": 1.314e-05,
      "loss": 0.112,
      "step": 220
    },
    {
      "epoch": 9.201612903225806,
      "grad_norm": 0.7436397671699524,
      "learning_rate": 1.374e-05,
      "loss": 0.1257,
      "step": 230
    },
    {
      "epoch": 9.60483870967742,
      "grad_norm": 1.891860842704773,
      "learning_rate": 1.434e-05,
      "loss": 0.0623,
      "step": 240
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.5202131867408752,
      "learning_rate": 1.4940000000000001e-05,
      "loss": 0.0572,
      "step": 250
    },
    {
      "epoch": 10.403225806451612,
      "grad_norm": 0.0677497610449791,
      "learning_rate": 1.554e-05,
      "loss": 0.0212,
      "step": 260
    },
    {
      "epoch": 10.806451612903226,
      "grad_norm": 0.07801195234060287,
      "learning_rate": 1.614e-05,
      "loss": 0.0243,
      "step": 270
    },
    {
      "epoch": 11.201612903225806,
      "grad_norm": 0.11515898257493973,
      "learning_rate": 1.6740000000000002e-05,
      "loss": 0.0321,
      "step": 280
    },
    {
      "epoch": 11.60483870967742,
      "grad_norm": 0.11826858669519424,
      "learning_rate": 1.734e-05,
      "loss": 0.0254,
      "step": 290
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.13558819890022278,
      "learning_rate": 1.794e-05,
      "loss": 0.014,
      "step": 300
    },
    {
      "epoch": 12.403225806451612,
      "grad_norm": 0.03777763620018959,
      "learning_rate": 1.854e-05,
      "loss": 0.0301,
      "step": 310
    },
    {
      "epoch": 12.806451612903226,
      "grad_norm": 0.0405518114566803,
      "learning_rate": 1.914e-05,
      "loss": 0.0027,
      "step": 320
    },
    {
      "epoch": 13.201612903225806,
      "grad_norm": 0.03762541711330414,
      "learning_rate": 1.974e-05,
      "loss": 0.0026,
      "step": 330
    },
    {
      "epoch": 13.60483870967742,
      "grad_norm": 0.06563286483287811,
      "learning_rate": 2.0340000000000002e-05,
      "loss": 0.0279,
      "step": 340
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.12380703538656235,
      "learning_rate": 2.094e-05,
      "loss": 0.0063,
      "step": 350
    }
  ],
  "logging_steps": 10,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.651986705536446e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}