{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 306,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09865885617388623,
      "grad_norm": 0.9921875,
      "learning_rate": 1.8e-05,
      "loss": 0.2051,
      "step": 10
    },
    {
      "epoch": 0.19731771234777246,
      "grad_norm": 0.9375,
      "learning_rate": 1.9954412990805107e-05,
      "loss": 0.2014,
      "step": 20
    },
    {
      "epoch": 0.2959765685216587,
      "grad_norm": 0.94921875,
      "learning_rate": 1.9797361806215335e-05,
      "loss": 0.1957,
      "step": 30
    },
    {
      "epoch": 0.3946354246955449,
      "grad_norm": 0.8359375,
      "learning_rate": 1.953005068173272e-05,
      "loss": 0.1947,
      "step": 40
    },
    {
      "epoch": 0.49329428086943117,
      "grad_norm": 1.1015625,
      "learning_rate": 1.915548794848775e-05,
      "loss": 0.1977,
      "step": 50
    },
    {
      "epoch": 0.5919531370433174,
      "grad_norm": 0.8984375,
      "learning_rate": 1.8677888951924473e-05,
      "loss": 0.1832,
      "step": 60
    },
    {
      "epoch": 0.6906119932172037,
      "grad_norm": 0.875,
      "learning_rate": 1.8102628612117868e-05,
      "loss": 0.1791,
      "step": 70
    },
    {
      "epoch": 0.7892708493910898,
      "grad_norm": 0.84765625,
      "learning_rate": 1.7436180934187307e-05,
      "loss": 0.1733,
      "step": 80
    },
    {
      "epoch": 0.8879297055649761,
      "grad_norm": 0.8828125,
      "learning_rate": 1.6686046149558736e-05,
      "loss": 0.1715,
      "step": 90
    },
    {
      "epoch": 0.9865885617388623,
      "grad_norm": 0.84765625,
      "learning_rate": 1.5860666308030933e-05,
      "loss": 0.1689,
      "step": 100
    },
    {
      "epoch": 1.078927084939109,
      "grad_norm": 0.7109375,
      "learning_rate": 1.4969330270576428e-05,
      "loss": 0.1384,
      "step": 110
    },
    {
      "epoch": 1.1775859411129952,
      "grad_norm": 0.69921875,
      "learning_rate": 1.4022069172092354e-05,
      "loss": 0.1265,
      "step": 120
    },
    {
      "epoch": 1.2762447972868816,
      "grad_norm": 0.69921875,
      "learning_rate": 1.3029543530567884e-05,
      "loss": 0.126,
      "step": 130
    },
    {
      "epoch": 1.3749036534607677,
      "grad_norm": 0.6328125,
      "learning_rate": 1.2002923273146793e-05,
      "loss": 0.125,
      "step": 140
    },
    {
      "epoch": 1.4735625096346538,
      "grad_norm": 0.7265625,
      "learning_rate": 1.0953762029276982e-05,
      "loss": 0.1207,
      "step": 150
    },
    {
      "epoch": 1.5722213658085402,
      "grad_norm": 0.67578125,
      "learning_rate": 9.89386710565744e-06,
      "loss": 0.1223,
      "step": 160
    },
    {
      "epoch": 1.6708802219824264,
      "grad_norm": 0.66796875,
      "learning_rate": 8.835166606290295e-06,
      "loss": 0.1246,
      "step": 170
    },
    {
      "epoch": 1.7695390781563125,
      "grad_norm": 0.70703125,
      "learning_rate": 7.789575193074703e-06,
      "loss": 0.1226,
      "step": 180
    },
    {
      "epoch": 1.8681979343301989,
      "grad_norm": 0.66796875,
      "learning_rate": 6.768859997678751e-06,
      "loss": 0.1195,
      "step": 190
    },
    {
      "epoch": 1.9668567905040852,
      "grad_norm": 0.62890625,
      "learning_rate": 5.784508193723058e-06,
      "loss": 0.1193,
      "step": 200
    },
    {
      "epoch": 2.0591953137043317,
      "grad_norm": 0.58203125,
      "learning_rate": 4.84759771962455e-06,
      "loss": 0.1124,
      "step": 210
    },
    {
      "epoch": 2.157854169878218,
      "grad_norm": 0.59765625,
      "learning_rate": 3.96867260699116e-06,
      "loss": 0.11,
      "step": 220
    },
    {
      "epoch": 2.256513026052104,
      "grad_norm": 0.55859375,
      "learning_rate": 3.157624317627195e-06,
      "loss": 0.1041,
      "step": 230
    },
    {
      "epoch": 2.3551718822259904,
      "grad_norm": 0.6171875,
      "learning_rate": 2.4235804245879723e-06,
      "loss": 0.1072,
      "step": 240
    },
    {
      "epoch": 2.4538307383998768,
      "grad_norm": 0.57421875,
      "learning_rate": 1.7748018900718856e-06,
      "loss": 0.1069,
      "step": 250
    },
    {
      "epoch": 2.552489594573763,
      "grad_norm": 0.6171875,
      "learning_rate": 1.2185900961891794e-06,
      "loss": 0.1069,
      "step": 260
    },
    {
      "epoch": 2.651148450747649,
      "grad_norm": 0.58203125,
      "learning_rate": 7.612046748871327e-07,
      "loss": 0.1049,
      "step": 270
    },
    {
      "epoch": 2.7498073069215354,
      "grad_norm": 0.55859375,
      "learning_rate": 4.077930617773007e-07,
      "loss": 0.1079,
      "step": 280
    },
    {
      "epoch": 2.8484661630954218,
      "grad_norm": 0.59765625,
      "learning_rate": 1.623325666691644e-07,
      "loss": 0.1078,
      "step": 290
    },
    {
      "epoch": 2.9471250192693077,
      "grad_norm": 0.578125,
      "learning_rate": 2.758561275092886e-08,
      "loss": 0.1049,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 306,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.229308927818568e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}