{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00461968447555032,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001847873790220128,
      "grad_norm": 4.357386112213135,
      "learning_rate": 6.4e-07,
      "loss": 2.7993131637573243,
      "step": 20
    },
    {
      "epoch": 0.0003695747580440256,
      "grad_norm": 4.551547527313232,
      "learning_rate": 1.44e-06,
      "loss": 2.639370155334473,
      "step": 40
    },
    {
      "epoch": 0.0005543621370660384,
      "grad_norm": 4.46128511428833,
      "learning_rate": 2.24e-06,
      "loss": 2.696819877624512,
      "step": 60
    },
    {
      "epoch": 0.0007391495160880512,
      "grad_norm": 1.5103334188461304,
      "learning_rate": 3.04e-06,
      "loss": 2.2109146118164062,
      "step": 80
    },
    {
      "epoch": 0.000923936895110064,
      "grad_norm": 1.0658206939697266,
      "learning_rate": 3.84e-06,
      "loss": 2.2014698028564452,
      "step": 100
    },
    {
      "epoch": 0.0011087242741320768,
      "grad_norm": 1.4809857606887817,
      "learning_rate": 4.64e-06,
      "loss": 1.9168745040893556,
      "step": 120
    },
    {
      "epoch": 0.0012935116531540896,
      "grad_norm": 1.5375170707702637,
      "learning_rate": 5.44e-06,
      "loss": 1.8440933227539062,
      "step": 140
    },
    {
      "epoch": 0.0014782990321761025,
      "grad_norm": 0.745366096496582,
      "learning_rate": 6.24e-06,
      "loss": 1.7943439483642578,
      "step": 160
    },
    {
      "epoch": 0.001663086411198115,
      "grad_norm": 0.5929296612739563,
      "learning_rate": 7.04e-06,
      "loss": 1.6178794860839845,
      "step": 180
    },
    {
      "epoch": 0.001847873790220128,
      "grad_norm": 0.8178684115409851,
      "learning_rate": 7.8e-06,
      "loss": 1.495293140411377,
      "step": 200
    },
    {
      "epoch": 0.002032661169242141,
      "grad_norm": 1.090906023979187,
      "learning_rate": 8.599999999999999e-06,
      "loss": 1.5392029762268067,
      "step": 220
    },
    {
      "epoch": 0.0022174485482641536,
      "grad_norm": 0.7013095021247864,
      "learning_rate": 9.4e-06,
      "loss": 1.4353426933288573,
      "step": 240
    },
    {
      "epoch": 0.002402235927286166,
      "grad_norm": 0.8774408102035522,
      "learning_rate": 1.02e-05,
      "loss": 1.508979892730713,
      "step": 260
    },
    {
      "epoch": 0.0025870233063081793,
      "grad_norm": 0.6000725626945496,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.4708028793334962,
      "step": 280
    },
    {
      "epoch": 0.002771810685330192,
      "grad_norm": 2.499645471572876,
      "learning_rate": 1.18e-05,
      "loss": 1.4927824020385743,
      "step": 300
    },
    {
      "epoch": 0.002956598064352205,
      "grad_norm": 0.46313002705574036,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 1.4648756980895996,
      "step": 320
    },
    {
      "epoch": 0.0031413854433742176,
      "grad_norm": 0.44169697165489197,
      "learning_rate": 1.3400000000000002e-05,
      "loss": 1.3465867042541504,
      "step": 340
    },
    {
      "epoch": 0.00332617282239623,
      "grad_norm": 0.6739365458488464,
      "learning_rate": 1.42e-05,
      "loss": 1.425154209136963,
      "step": 360
    },
    {
      "epoch": 0.0035109602014182432,
      "grad_norm": 1.1867340803146362,
      "learning_rate": 1.5e-05,
      "loss": 1.4140001296997071,
      "step": 380
    },
    {
      "epoch": 0.003695747580440256,
      "grad_norm": 0.5072050094604492,
      "learning_rate": 1.58e-05,
      "loss": 1.3576015472412108,
      "step": 400
    },
    {
      "epoch": 0.003880534959462269,
      "grad_norm": 0.7821234464645386,
      "learning_rate": 1.66e-05,
      "loss": 1.3783547401428222,
      "step": 420
    },
    {
      "epoch": 0.004065322338484282,
      "grad_norm": 0.547825813293457,
      "learning_rate": 1.74e-05,
      "loss": 1.3415006637573241,
      "step": 440
    },
    {
      "epoch": 0.004250109717506294,
      "grad_norm": 0.5836990475654602,
      "learning_rate": 1.8200000000000002e-05,
      "loss": 1.3484737396240234,
      "step": 460
    },
    {
      "epoch": 0.004434897096528307,
      "grad_norm": 0.4791603982448578,
      "learning_rate": 1.9e-05,
      "loss": 1.3799403190612793,
      "step": 480
    },
    {
      "epoch": 0.00461968447555032,
      "grad_norm": 1.0716239213943481,
      "learning_rate": 1.9800000000000004e-05,
      "loss": 1.3633416175842286,
      "step": 500
    }
  ],
  "logging_steps": 20,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.004783929950208e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}