{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 11793,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1271940981938438,
      "grad_norm": 20.986921310424805,
      "learning_rate": 2.873060290002544e-05,
      "loss": 1.7205758056640625,
      "step": 500
    },
    {
      "epoch": 0.2543881963876876,
      "grad_norm": 12.114559173583984,
      "learning_rate": 2.7458661918087002e-05,
      "loss": 1.1848350830078125,
      "step": 1000
    },
    {
      "epoch": 0.3815822945815314,
      "grad_norm": 14.860601425170898,
      "learning_rate": 2.6186720936148565e-05,
      "loss": 1.0746712646484375,
      "step": 1500
    },
    {
      "epoch": 0.5087763927753752,
      "grad_norm": 11.910303115844727,
      "learning_rate": 2.4914779954210127e-05,
      "loss": 1.0038060302734375,
      "step": 2000
    },
    {
      "epoch": 0.635970490969219,
      "grad_norm": 8.553890228271484,
      "learning_rate": 2.3642838972271685e-05,
      "loss": 0.9559959106445313,
      "step": 2500
    },
    {
      "epoch": 0.7631645891630628,
      "grad_norm": 9.562394142150879,
      "learning_rate": 2.2370897990333247e-05,
      "loss": 0.9281796875,
      "step": 3000
    },
    {
      "epoch": 0.8903586873569066,
      "grad_norm": 8.361549377441406,
      "learning_rate": 2.1098957008394813e-05,
      "loss": 0.9157453002929687,
      "step": 3500
    },
    {
      "epoch": 1.0175527855507505,
      "grad_norm": 7.545825004577637,
      "learning_rate": 1.9827016026456375e-05,
      "loss": 0.8658336181640625,
      "step": 4000
    },
    {
      "epoch": 1.1447468837445942,
      "grad_norm": 13.105203628540039,
      "learning_rate": 1.8555075044517934e-05,
      "loss": 0.6820219116210937,
      "step": 4500
    },
    {
      "epoch": 1.271940981938438,
      "grad_norm": 9.773395538330078,
      "learning_rate": 1.7283134062579496e-05,
      "loss": 0.6653152465820312,
      "step": 5000
    },
    {
      "epoch": 1.399135080132282,
      "grad_norm": 9.450806617736816,
      "learning_rate": 1.6011193080641058e-05,
      "loss": 0.6671427612304688,
      "step": 5500
    },
    {
      "epoch": 1.5263291783261257,
      "grad_norm": 10.44336223602295,
      "learning_rate": 1.4739252098702622e-05,
      "loss": 0.6522406616210937,
      "step": 6000
    },
    {
      "epoch": 1.6535232765199694,
      "grad_norm": 10.461090087890625,
      "learning_rate": 1.3467311116764182e-05,
      "loss": 0.6547742309570312,
      "step": 6500
    },
    {
      "epoch": 1.7807173747138134,
      "grad_norm": 6.990764141082764,
      "learning_rate": 1.2195370134825746e-05,
      "loss": 0.6391011352539062,
      "step": 7000
    },
    {
      "epoch": 1.907911472907657,
      "grad_norm": 11.571297645568848,
      "learning_rate": 1.0923429152887306e-05,
      "loss": 0.6334611206054688,
      "step": 7500
    },
    {
      "epoch": 2.035105571101501,
      "grad_norm": 7.267425060272217,
      "learning_rate": 9.651488170948868e-06,
      "loss": 0.5740706176757813,
      "step": 8000
    },
    {
      "epoch": 2.162299669295345,
      "grad_norm": 20.655519485473633,
      "learning_rate": 8.37954718901043e-06,
      "loss": 0.4668221435546875,
      "step": 8500
    },
    {
      "epoch": 2.2894937674891884,
      "grad_norm": 8.184877395629883,
      "learning_rate": 7.107606207071992e-06,
      "loss": 0.44616903686523435,
      "step": 9000
    },
    {
      "epoch": 2.4166878656830324,
      "grad_norm": 10.177411079406738,
      "learning_rate": 5.8356652251335545e-06,
      "loss": 0.4526641235351562,
      "step": 9500
    },
    {
      "epoch": 2.543881963876876,
      "grad_norm": 13.613941192626953,
      "learning_rate": 4.563724243195116e-06,
      "loss": 0.43699600219726564,
      "step": 10000
    },
    {
      "epoch": 2.67107606207072,
      "grad_norm": 14.783905982971191,
      "learning_rate": 3.291783261256678e-06,
      "loss": 0.4329667663574219,
      "step": 10500
    },
    {
      "epoch": 2.798270160264564,
      "grad_norm": 12.480794906616211,
      "learning_rate": 2.0198422793182395e-06,
      "loss": 0.4396368408203125,
      "step": 11000
    },
    {
      "epoch": 2.9254642584584074,
      "grad_norm": 14.206427574157715,
      "learning_rate": 7.479012973798015e-07,
      "loss": 0.4308229064941406,
      "step": 11500
    },
    {
      "epoch": 3.0,
      "step": 11793,
      "total_flos": 1.2323538937939968e+17,
      "train_loss": 0.7285093832974275,
      "train_runtime": 30100.617,
      "train_samples_per_second": 15.668,
      "train_steps_per_second": 0.392
    }
  ],
  "logging_steps": 500,
  "max_steps": 11793,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2323538937939968e+17,
  "train_batch_size": 40,
  "trial_name": null,
  "trial_params": null
}