{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8265142857142858,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07314285714285715,
      "grad_norm": 1.250452995300293,
      "learning_rate": 2.8499999999999998e-05,
      "loss": 11.532991027832031,
      "step": 20
    },
    {
      "epoch": 0.1462857142857143,
      "grad_norm": 0.9911406636238098,
      "learning_rate": 5.85e-05,
      "loss": 11.35167236328125,
      "step": 40
    },
    {
      "epoch": 0.21942857142857142,
      "grad_norm": 0.9821921586990356,
      "learning_rate": 8.849999999999998e-05,
      "loss": 11.14882583618164,
      "step": 60
    },
    {
      "epoch": 0.2925714285714286,
      "grad_norm": 0.9792555570602417,
      "learning_rate": 0.0001185,
      "loss": 10.891434478759766,
      "step": 80
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 0.9883681535720825,
      "learning_rate": 0.00014849999999999998,
      "loss": 10.563937377929687,
      "step": 100
    },
    {
      "epoch": 0.43885714285714283,
      "grad_norm": 0.9853702783584595,
      "learning_rate": 0.00017849999999999997,
      "loss": 10.18422622680664,
      "step": 120
    },
    {
      "epoch": 0.512,
      "grad_norm": 1.0101815462112427,
      "learning_rate": 0.00020849999999999997,
      "loss": 9.786434936523438,
      "step": 140
    },
    {
      "epoch": 0.5851428571428572,
      "grad_norm": 0.9789732098579407,
      "learning_rate": 0.0002385,
      "loss": 9.40113525390625,
      "step": 160
    },
    {
      "epoch": 0.6582857142857143,
      "grad_norm": 0.9101362824440002,
      "learning_rate": 0.00026849999999999997,
      "loss": 9.05419464111328,
      "step": 180
    },
    {
      "epoch": 0.7314285714285714,
      "grad_norm": 0.8724201917648315,
      "learning_rate": 0.0002985,
      "loss": 8.751616668701171,
      "step": 200
    },
    {
      "epoch": 0.8045714285714286,
      "grad_norm": 0.7059838175773621,
      "learning_rate": 0.0002908360128617363,
      "loss": 8.522535705566407,
      "step": 220
    },
    {
      "epoch": 0.8777142857142857,
      "grad_norm": 0.5502440929412842,
      "learning_rate": 0.00028118971061093245,
      "loss": 8.364321899414062,
      "step": 240
    },
    {
      "epoch": 0.9508571428571428,
      "grad_norm": 0.46737125515937805,
      "learning_rate": 0.0002715434083601286,
      "loss": 8.275575256347656,
      "step": 260
    },
    {
      "epoch": 1.021942857142857,
      "grad_norm": 0.387386679649353,
      "learning_rate": 0.00026189710610932475,
      "loss": 8.194184875488281,
      "step": 280
    },
    {
      "epoch": 1.0950857142857142,
      "grad_norm": 0.5874072909355164,
      "learning_rate": 0.0002522508038585209,
      "loss": 8.096188354492188,
      "step": 300
    },
    {
      "epoch": 1.1682285714285714,
      "grad_norm": 0.6955321431159973,
      "learning_rate": 0.00024260450160771703,
      "loss": 8.026647186279297,
      "step": 320
    },
    {
      "epoch": 1.2413714285714286,
      "grad_norm": 0.49530029296875,
      "learning_rate": 0.00023295819935691315,
      "loss": 7.971723937988282,
      "step": 340
    },
    {
      "epoch": 1.3145142857142857,
      "grad_norm": 0.9392899870872498,
      "learning_rate": 0.0002233118971061093,
      "loss": 7.904925537109375,
      "step": 360
    },
    {
      "epoch": 1.387657142857143,
      "grad_norm": 0.6055660843849182,
      "learning_rate": 0.00021366559485530546,
      "loss": 7.842314147949219,
      "step": 380
    },
    {
      "epoch": 1.4607999999999999,
      "grad_norm": 0.4336493909358978,
      "learning_rate": 0.00020401929260450158,
      "loss": 7.779663848876953,
      "step": 400
    },
    {
      "epoch": 1.5339428571428573,
      "grad_norm": 0.532171368598938,
      "learning_rate": 0.00019437299035369773,
      "loss": 7.732464599609375,
      "step": 420
    },
    {
      "epoch": 1.6070857142857142,
      "grad_norm": 0.5588330626487732,
      "learning_rate": 0.00018472668810289386,
      "loss": 7.665067291259765,
      "step": 440
    },
    {
      "epoch": 1.6802285714285714,
      "grad_norm": 0.5427436828613281,
      "learning_rate": 0.00017508038585209004,
      "loss": 7.601129150390625,
      "step": 460
    },
    {
      "epoch": 1.7533714285714286,
      "grad_norm": 0.8764950633049011,
      "learning_rate": 0.00016543408360128616,
      "loss": 7.574497985839844,
      "step": 480
    },
    {
      "epoch": 1.8265142857142858,
      "grad_norm": 0.48415958881378174,
      "learning_rate": 0.0001557877813504823,
      "loss": 7.537950134277343,
      "step": 500
    }
  ],
  "logging_steps": 20,
  "max_steps": 822,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 118333073522688.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}