{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 396,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07590132827324478,
      "grad_norm": 22.0,
      "learning_rate": 9e-08,
      "loss": 1.0496648788452148,
      "step": 10
    },
    {
      "epoch": 0.15180265654648956,
      "grad_norm": 21.5,
      "learning_rate": 1.8999999999999998e-07,
      "loss": 1.0672600746154786,
      "step": 20
    },
    {
      "epoch": 0.22770398481973433,
      "grad_norm": 23.375,
      "learning_rate": 2.9e-07,
      "loss": 1.074104118347168,
      "step": 30
    },
    {
      "epoch": 0.3036053130929791,
      "grad_norm": 19.0,
      "learning_rate": 3.8999999999999997e-07,
      "loss": 1.0784456253051757,
      "step": 40
    },
    {
      "epoch": 0.3795066413662239,
      "grad_norm": 21.25,
      "learning_rate": 4.9e-07,
      "loss": 1.0631229400634765,
      "step": 50
    },
    {
      "epoch": 0.45540796963946867,
      "grad_norm": 18.625,
      "learning_rate": 5.9e-07,
      "loss": 1.0021364212036132,
      "step": 60
    },
    {
      "epoch": 0.5313092979127134,
      "grad_norm": 19.625,
      "learning_rate": 6.9e-07,
      "loss": 1.0368730545043945,
      "step": 70
    },
    {
      "epoch": 0.6072106261859582,
      "grad_norm": 13.1875,
      "learning_rate": 7.9e-07,
      "loss": 0.9585152626037597,
      "step": 80
    },
    {
      "epoch": 0.683111954459203,
      "grad_norm": 10.4375,
      "learning_rate": 8.9e-07,
      "loss": 0.8780872344970703,
      "step": 90
    },
    {
      "epoch": 0.7590132827324478,
      "grad_norm": 6.84375,
      "learning_rate": 9.9e-07,
      "loss": 0.8695860862731933,
      "step": 100
    },
    {
      "epoch": 0.8349146110056926,
      "grad_norm": 3.3125,
      "learning_rate": 9.977206495402552e-07,
      "loss": 0.8098324775695801,
      "step": 110
    },
    {
      "epoch": 0.9108159392789373,
      "grad_norm": 2.96875,
      "learning_rate": 9.898680903107666e-07,
      "loss": 0.8349854469299316,
      "step": 120
    },
    {
      "epoch": 0.9867172675521821,
      "grad_norm": 2.9375,
      "learning_rate": 9.76502534086636e-07,
      "loss": 0.8502012252807617,
      "step": 130
    },
    {
      "epoch": 1.060721062618596,
      "grad_norm": 2.78125,
      "learning_rate": 9.577743974243872e-07,
      "loss": 0.7735446929931641,
      "step": 140
    },
    {
      "epoch": 1.1366223908918407,
      "grad_norm": 3.359375,
      "learning_rate": 9.338944475962236e-07,
      "loss": 0.8373490333557129,
      "step": 150
    },
    {
      "epoch": 1.2125237191650853,
      "grad_norm": 2.59375,
      "learning_rate": 9.051314306058933e-07,
      "loss": 0.8185565948486329,
      "step": 160
    },
    {
      "epoch": 1.2884250474383303,
      "grad_norm": 2.9375,
      "learning_rate": 8.718090467093653e-07,
      "loss": 0.8056498527526855,
      "step": 170
    },
    {
      "epoch": 1.364326375711575,
      "grad_norm": 2.59375,
      "learning_rate": 8.343023074779368e-07,
      "loss": 0.8409146308898926,
      "step": 180
    },
    {
      "epoch": 1.4402277039848197,
      "grad_norm": 3.390625,
      "learning_rate": 7.930333154015465e-07,
      "loss": 0.7972420215606689,
      "step": 190
    },
    {
      "epoch": 1.5161290322580645,
      "grad_norm": 2.546875,
      "learning_rate": 7.484665135288213e-07,
      "loss": 0.8233073234558106,
      "step": 200
    },
    {
      "epoch": 1.5920303605313093,
      "grad_norm": 2.640625,
      "learning_rate": 7.011034586046176e-07,
      "loss": 0.8327888488769531,
      "step": 210
    },
    {
      "epoch": 1.6679316888045541,
      "grad_norm": 2.65625,
      "learning_rate": 6.514771765283942e-07,
      "loss": 0.7899296283721924,
      "step": 220
    },
    {
      "epoch": 1.7438330170777987,
      "grad_norm": 2.984375,
      "learning_rate": 6.001461636573396e-07,
      "loss": 0.7956095695495605,
      "step": 230
    },
    {
      "epoch": 1.8197343453510437,
      "grad_norm": 3.625,
      "learning_rate": 5.47688101463849e-07,
      "loss": 0.8178939819335938,
      "step": 240
    },
    {
      "epoch": 1.8956356736242883,
      "grad_norm": 2.828125,
      "learning_rate": 4.946933552828719e-07,
      "loss": 0.8414199829101563,
      "step": 250
    },
    {
      "epoch": 1.9715370018975333,
      "grad_norm": 2.375,
      "learning_rate": 4.417583303145147e-07,
      "loss": 0.797624921798706,
      "step": 260
    },
    {
      "epoch": 2.0455407969639468,
      "grad_norm": 2.890625,
      "learning_rate": 3.894787596537351e-07,
      "loss": 0.8394969940185547,
      "step": 270
    },
    {
      "epoch": 2.121442125237192,
      "grad_norm": 2.375,
      "learning_rate": 3.384429998839375e-07,
      "loss": 0.799235200881958,
      "step": 280
    },
    {
      "epoch": 2.1973434535104364,
      "grad_norm": 2.46875,
      "learning_rate": 2.8922540968615283e-07,
      "loss": 0.8156853675842285,
      "step": 290
    },
    {
      "epoch": 2.2732447817836814,
      "grad_norm": 2.421875,
      "learning_rate": 2.423798859812275e-07,
      "loss": 0.8007305145263672,
      "step": 300
    },
    {
      "epoch": 2.349146110056926,
      "grad_norm": 2.5,
      "learning_rate": 1.9843363034955795e-07,
      "loss": 0.8174427032470704,
      "step": 310
    },
    {
      "epoch": 2.4250474383301706,
      "grad_norm": 2.203125,
      "learning_rate": 1.5788121588135972e-07,
      "loss": 0.7784779071807861,
      "step": 320
    },
    {
      "epoch": 2.5009487666034156,
      "grad_norm": 2.703125,
      "learning_rate": 1.211790212293986e-07,
      "loss": 0.8244176864624023,
      "step": 330
    },
    {
      "epoch": 2.5768500948766606,
      "grad_norm": 2.828125,
      "learning_rate": 8.874009450359426e-08,
      "loss": 0.831035041809082,
      "step": 340
    },
    {
      "epoch": 2.652751423149905,
      "grad_norm": 2.34375,
      "learning_rate": 6.092950480945897e-08,
      "loss": 0.7749196052551269,
      "step": 350
    },
    {
      "epoch": 2.72865275142315,
      "grad_norm": 2.328125,
      "learning_rate": 3.806023374435663e-08,
      "loss": 0.8048405647277832,
      "step": 360
    },
    {
      "epoch": 2.804554079696395,
      "grad_norm": 2.625,
      "learning_rate": 2.0389653088865033e-08,
      "loss": 0.8310153961181641,
      "step": 370
    },
    {
      "epoch": 2.8804554079696394,
      "grad_norm": 2.78125,
      "learning_rate": 8.11662833345822e-09,
      "loss": 0.8102119445800782,
      "step": 380
    },
    {
      "epoch": 2.956356736242884,
      "grad_norm": 2.453125,
      "learning_rate": 1.3792806375464427e-09,
      "loss": 0.7998002052307129,
      "step": 390
    }
  ],
  "logging_steps": 10,
  "max_steps": 396,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.087240815119319e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}