{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 416,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09615384615384616,
      "grad_norm": 1.2597733736038208,
      "learning_rate": 2.380952380952381e-06,
      "loss": 0.3483,
      "step": 10
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 0.9227814078330994,
      "learning_rate": 4.761904761904762e-06,
      "loss": 0.3115,
      "step": 20
    },
    {
      "epoch": 0.28846153846153844,
      "grad_norm": 0.5784149169921875,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.2758,
      "step": 30
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.5355926156044006,
      "learning_rate": 9.523809523809525e-06,
      "loss": 0.2754,
      "step": 40
    },
    {
      "epoch": 0.4807692307692308,
      "grad_norm": 0.5469948053359985,
      "learning_rate": 9.997469951095982e-06,
      "loss": 0.258,
      "step": 50
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 0.5373064875602722,
      "learning_rate": 9.987196015552742e-06,
      "loss": 0.2596,
      "step": 60
    },
    {
      "epoch": 0.6730769230769231,
      "grad_norm": 0.576485812664032,
      "learning_rate": 9.969036298013732e-06,
      "loss": 0.2583,
      "step": 70
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.5451536178588867,
      "learning_rate": 9.943019512725026e-06,
      "loss": 0.2672,
      "step": 80
    },
    {
      "epoch": 0.8653846153846154,
      "grad_norm": 0.6965824961662292,
      "learning_rate": 9.9091867975718e-06,
      "loss": 0.2573,
      "step": 90
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 0.6300221681594849,
      "learning_rate": 9.867591649030863e-06,
      "loss": 0.2636,
      "step": 100
    },
    {
      "epoch": 1.0576923076923077,
      "grad_norm": 0.4234144687652588,
      "learning_rate": 9.818299837581758e-06,
      "loss": 0.2199,
      "step": 110
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.4467966854572296,
      "learning_rate": 9.761389303710085e-06,
      "loss": 0.2019,
      "step": 120
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.44141167402267456,
      "learning_rate": 9.696950034667595e-06,
      "loss": 0.1926,
      "step": 130
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 0.5096948742866516,
      "learning_rate": 9.62508392218384e-06,
      "loss": 0.1994,
      "step": 140
    },
    {
      "epoch": 1.4423076923076923,
      "grad_norm": 0.4182388186454773,
      "learning_rate": 9.545904601354402e-06,
      "loss": 0.1918,
      "step": 150
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.5185367465019226,
      "learning_rate": 9.459537270960464e-06,
      "loss": 0.1948,
      "step": 160
    },
    {
      "epoch": 1.6346153846153846,
      "grad_norm": 0.5209194421768188,
      "learning_rate": 9.36611849550378e-06,
      "loss": 0.2015,
      "step": 170
    },
    {
      "epoch": 1.7307692307692308,
      "grad_norm": 0.5025277137756348,
      "learning_rate": 9.265795989270148e-06,
      "loss": 0.2022,
      "step": 180
    },
    {
      "epoch": 1.8269230769230769,
      "grad_norm": 0.4965076148509979,
      "learning_rate": 9.158728382762753e-06,
      "loss": 0.2023,
      "step": 190
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.5124719142913818,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.1962,
      "step": 200
    },
    {
      "epoch": 2.019230769230769,
      "grad_norm": 0.4854343831539154,
      "learning_rate": 8.925045450197593e-06,
      "loss": 0.1821,
      "step": 210
    },
    {
      "epoch": 2.1153846153846154,
      "grad_norm": 0.3944475054740906,
      "learning_rate": 8.798799624888665e-06,
      "loss": 0.1239,
      "step": 220
    },
    {
      "epoch": 2.2115384615384617,
      "grad_norm": 0.5081722736358643,
      "learning_rate": 8.666547116547015e-06,
      "loss": 0.1273,
      "step": 230
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.42684561014175415,
      "learning_rate": 8.528497043572222e-06,
      "loss": 0.1211,
      "step": 240
    },
    {
      "epoch": 2.4038461538461537,
      "grad_norm": 0.40685558319091797,
      "learning_rate": 8.38486769150522e-06,
      "loss": 0.1275,
      "step": 250
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.5295878648757935,
      "learning_rate": 8.235886167873975e-06,
      "loss": 0.1333,
      "step": 260
    },
    {
      "epoch": 2.5961538461538463,
      "grad_norm": 0.4011670649051666,
      "learning_rate": 8.081788043089818e-06,
      "loss": 0.124,
      "step": 270
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.4178542494773865,
      "learning_rate": 7.922816977962191e-06,
      "loss": 0.1271,
      "step": 280
    },
    {
      "epoch": 2.7884615384615383,
      "grad_norm": 0.39880824089050293,
      "learning_rate": 7.759224338420832e-06,
      "loss": 0.1277,
      "step": 290
    },
    {
      "epoch": 2.8846153846153846,
      "grad_norm": 0.4713616669178009,
      "learning_rate": 7.591268798054569e-06,
      "loss": 0.13,
      "step": 300
    },
    {
      "epoch": 2.980769230769231,
      "grad_norm": 0.4073733389377594,
      "learning_rate": 7.419215929095211e-06,
      "loss": 0.1268,
      "step": 310
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.5005382299423218,
      "learning_rate": 7.243337782493255e-06,
      "loss": 0.0846,
      "step": 320
    },
    {
      "epoch": 3.173076923076923,
      "grad_norm": 0.41398388147354126,
      "learning_rate": 7.063912457749426e-06,
      "loss": 0.0733,
      "step": 330
    },
    {
      "epoch": 3.269230769230769,
      "grad_norm": 0.46325525641441345,
      "learning_rate": 6.8812236631821886e-06,
      "loss": 0.0795,
      "step": 340
    },
    {
      "epoch": 3.3653846153846154,
      "grad_norm": 0.4737342596054077,
      "learning_rate": 6.695560267326599e-06,
      "loss": 0.0782,
      "step": 350
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 0.4067882299423218,
      "learning_rate": 6.507215842173758e-06,
      "loss": 0.0796,
      "step": 360
    },
    {
      "epoch": 3.5576923076923075,
      "grad_norm": 0.42072340846061707,
      "learning_rate": 6.316488198973162e-06,
      "loss": 0.0774,
      "step": 370
    },
    {
      "epoch": 3.6538461538461537,
      "grad_norm": 0.39316093921661377,
      "learning_rate": 6.123678917331902e-06,
      "loss": 0.0774,
      "step": 380
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.4232267439365387,
      "learning_rate": 5.9290928683553105e-06,
      "loss": 0.0789,
      "step": 390
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.45357951521873474,
      "learning_rate": 5.733037732583091e-06,
      "loss": 0.0808,
      "step": 400
    },
    {
      "epoch": 3.9423076923076925,
      "grad_norm": 0.5127453207969666,
      "learning_rate": 5.535823513483123e-06,
      "loss": 0.0806,
      "step": 410
    }
  ],
  "logging_steps": 10,
  "max_steps": 832,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 42586106445824.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}