{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.56,
  "eval_steps": 0,
  "global_step": 16000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 9.120098114013672,
      "learning_rate": 5.2906666666666675e-06,
      "loss": 0.772038330078125,
      "step": 500
    },
    {
      "epoch": 0.16,
      "grad_norm": 16.881511688232422,
      "learning_rate": 1.0624e-05,
      "loss": 0.37112783813476563,
      "step": 1000
    },
    {
      "epoch": 0.24,
      "grad_norm": 9.139080047607422,
      "learning_rate": 1.5957333333333334e-05,
      "loss": 0.36207400512695315,
      "step": 1500
    },
    {
      "epoch": 0.32,
      "grad_norm": 3.8323566913604736,
      "learning_rate": 1.9856592592592595e-05,
      "loss": 0.34735809326171874,
      "step": 2000
    },
    {
      "epoch": 0.4,
      "grad_norm": 4.640134811401367,
      "learning_rate": 1.9265185185185186e-05,
      "loss": 0.329142578125,
      "step": 2500
    },
    {
      "epoch": 0.48,
      "grad_norm": 7.571471214294434,
      "learning_rate": 1.8672592592592594e-05,
      "loss": 0.3232558288574219,
      "step": 3000
    },
    {
      "epoch": 0.56,
      "grad_norm": 5.5788984298706055,
      "learning_rate": 1.8080000000000003e-05,
      "loss": 0.33851583862304685,
      "step": 3500
    },
    {
      "epoch": 0.64,
      "grad_norm": 4.823075771331787,
      "learning_rate": 1.748740740740741e-05,
      "loss": 0.3265293884277344,
      "step": 4000
    },
    {
      "epoch": 0.72,
      "grad_norm": 5.9052886962890625,
      "learning_rate": 1.6897185185185187e-05,
      "loss": 0.3228313903808594,
      "step": 4500
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.530646562576294,
      "learning_rate": 1.6304592592592593e-05,
      "loss": 0.3212389831542969,
      "step": 5000
    },
    {
      "epoch": 0.88,
      "grad_norm": 2.003970146179199,
      "learning_rate": 1.5712e-05,
      "loss": 0.3108310546875,
      "step": 5500
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.259843111038208,
      "learning_rate": 1.511940740740741e-05,
      "loss": 0.33287890625,
      "step": 6000
    },
    {
      "epoch": 1.04,
      "grad_norm": 1.1002967357635498,
      "learning_rate": 1.4526814814814815e-05,
      "loss": 0.3126535949707031,
      "step": 6500
    },
    {
      "epoch": 1.12,
      "grad_norm": 2.696305751800537,
      "learning_rate": 1.3934222222222222e-05,
      "loss": 0.3110744323730469,
      "step": 7000
    },
    {
      "epoch": 1.2,
      "grad_norm": 3.0759758949279785,
      "learning_rate": 1.3341629629629631e-05,
      "loss": 0.307027099609375,
      "step": 7500
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.2770161628723145,
      "learning_rate": 1.2749037037037038e-05,
      "loss": 0.31455657958984373,
      "step": 8000
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 2.4967329502105713,
      "learning_rate": 1.2156444444444447e-05,
      "loss": 0.31456546020507814,
      "step": 8500
    },
    {
      "epoch": 1.44,
      "grad_norm": 5.275321006774902,
      "learning_rate": 1.1565037037037039e-05,
      "loss": 0.3131004943847656,
      "step": 9000
    },
    {
      "epoch": 1.52,
      "grad_norm": 2.145164966583252,
      "learning_rate": 1.0972444444444446e-05,
      "loss": 0.30567279052734375,
      "step": 9500
    },
    {
      "epoch": 1.6,
      "grad_norm": 2.0739190578460693,
      "learning_rate": 1.0379851851851853e-05,
      "loss": 0.28998117065429685,
      "step": 10000
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 3.1562881469726562,
      "learning_rate": 9.78725925925926e-06,
      "loss": 0.29778146362304686,
      "step": 10500
    },
    {
      "epoch": 1.76,
      "grad_norm": 3.498109817504883,
      "learning_rate": 9.194666666666667e-06,
      "loss": 0.2988756103515625,
      "step": 11000
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 3.3291115760803223,
      "learning_rate": 8.602074074074076e-06,
      "loss": 0.2985075988769531,
      "step": 11500
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.631378173828125,
      "learning_rate": 8.009481481481483e-06,
      "loss": 0.2991393737792969,
      "step": 12000
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3230953216552734,
      "learning_rate": 7.416888888888889e-06,
      "loss": 0.30236148071289065,
      "step": 12500
    },
    {
      "epoch": 2.08,
      "grad_norm": 2.339695930480957,
      "learning_rate": 6.825481481481482e-06,
      "loss": 0.295860595703125,
      "step": 13000
    },
    {
      "epoch": 2.16,
      "grad_norm": 1.0685478448867798,
      "learning_rate": 6.234074074074075e-06,
      "loss": 0.2980207824707031,
      "step": 13500
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.947058379650116,
      "learning_rate": 5.6414814814814825e-06,
      "loss": 0.29257803344726563,
      "step": 14000
    },
    {
      "epoch": 2.32,
      "grad_norm": 2.2130205631256104,
      "learning_rate": 5.0488888888888895e-06,
      "loss": 0.2826576843261719,
      "step": 14500
    },
    {
      "epoch": 2.4,
      "grad_norm": 6.699328422546387,
      "learning_rate": 4.4562962962962965e-06,
      "loss": 0.30620053100585937,
      "step": 15000
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.5939074158668518,
      "learning_rate": 3.863703703703704e-06,
      "loss": 0.3044532470703125,
      "step": 15500
    },
    {
      "epoch": 2.56,
      "grad_norm": 2.3366057872772217,
      "learning_rate": 3.2711111111111117e-06,
      "loss": 0.28407180786132813,
      "step": 16000
    }
  ],
  "logging_steps": 500,
  "max_steps": 18750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}