{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 338,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05921539600296077,
      "grad_norm": 2.1660487179402046,
      "learning_rate": 2.647058823529412e-06,
      "loss": 1.0315340042114258,
      "step": 10
    },
    {
      "epoch": 0.11843079200592153,
      "grad_norm": 0.8206090153367834,
      "learning_rate": 4.999521098917384e-06,
      "loss": 0.804750633239746,
      "step": 20
    },
    {
      "epoch": 0.17764618800888232,
      "grad_norm": 0.5076999300528826,
      "learning_rate": 4.982778818239101e-06,
      "loss": 0.6803584098815918,
      "step": 30
    },
    {
      "epoch": 0.23686158401184307,
      "grad_norm": 0.44804853650579485,
      "learning_rate": 4.942274644707778e-06,
      "loss": 0.6373716354370117,
      "step": 40
    },
    {
      "epoch": 0.29607698001480387,
      "grad_norm": 0.37795082026085236,
      "learning_rate": 4.8783962309908564e-06,
      "loss": 0.6100860595703125,
      "step": 50
    },
    {
      "epoch": 0.35529237601776464,
      "grad_norm": 0.3758350984694742,
      "learning_rate": 4.791754937234962e-06,
      "loss": 0.590767765045166,
      "step": 60
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 0.38356117820332386,
      "learning_rate": 4.683179979930808e-06,
      "loss": 0.5830053329467774,
      "step": 70
    },
    {
      "epoch": 0.47372316802368614,
      "grad_norm": 0.3748549546750847,
      "learning_rate": 4.553710495743744e-06,
      "loss": 0.5752785682678223,
      "step": 80
    },
    {
      "epoch": 0.532938564026647,
      "grad_norm": 0.3721638230346843,
      "learning_rate": 4.404585596264537e-06,
      "loss": 0.5685394763946533,
      "step": 90
    },
    {
      "epoch": 0.5921539600296077,
      "grad_norm": 0.43645633412402157,
      "learning_rate": 4.237232508863226e-06,
      "loss": 0.5654382705688477,
      "step": 100
    },
    {
      "epoch": 0.6513693560325685,
      "grad_norm": 0.3653519256229323,
      "learning_rate": 4.053252917146198e-06,
      "loss": 0.5606998920440673,
      "step": 110
    },
    {
      "epoch": 0.7105847520355293,
      "grad_norm": 0.3804875776663665,
      "learning_rate": 3.854407631747653e-06,
      "loss": 0.5562047004699707,
      "step": 120
    },
    {
      "epoch": 0.7698001480384901,
      "grad_norm": 0.37849834925954745,
      "learning_rate": 3.6425997381664955e-06,
      "loss": 0.5520612716674804,
      "step": 130
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 0.36345124508854665,
      "learning_rate": 3.4198563829353624e-06,
      "loss": 0.5482186794281005,
      "step": 140
    },
    {
      "epoch": 0.8882309400444115,
      "grad_norm": 0.356819991535798,
      "learning_rate": 3.18830937244065e-06,
      "loss": 0.5448985576629639,
      "step": 150
    },
    {
      "epoch": 0.9474463360473723,
      "grad_norm": 0.35213034846229774,
      "learning_rate": 2.9501747700760834e-06,
      "loss": 0.5447245597839355,
      "step": 160
    },
    {
      "epoch": 1.005921539600296,
      "grad_norm": 0.35217982001012155,
      "learning_rate": 2.707731686999056e-06,
      "loss": 0.5407782554626465,
      "step": 170
    },
    {
      "epoch": 1.065136935603257,
      "grad_norm": 0.41406905497263247,
      "learning_rate": 2.463300469476709e-06,
      "loss": 0.5257899284362793,
      "step": 180
    },
    {
      "epoch": 1.1243523316062176,
      "grad_norm": 0.3522008707002714,
      "learning_rate": 2.219220491583782e-06,
      "loss": 0.526216697692871,
      "step": 190
    },
    {
      "epoch": 1.1835677276091783,
      "grad_norm": 0.32789759467818624,
      "learning_rate": 1.9778277657913246e-06,
      "loss": 0.5256593704223633,
      "step": 200
    },
    {
      "epoch": 1.2427831236121392,
      "grad_norm": 0.3413013546117959,
      "learning_rate": 1.7414325857282528e-06,
      "loss": 0.5215062618255615,
      "step": 210
    },
    {
      "epoch": 1.3019985196151,
      "grad_norm": 0.3556859796231501,
      "learning_rate": 1.512297415089829e-06,
      "loss": 0.5243502616882324,
      "step": 220
    },
    {
      "epoch": 1.3612139156180607,
      "grad_norm": 0.3191258457379017,
      "learning_rate": 1.2926152343113525e-06,
      "loss": 0.5235335350036621,
      "step": 230
    },
    {
      "epoch": 1.4204293116210214,
      "grad_norm": 0.34855340489664327,
      "learning_rate": 1.0844885522442076e-06,
      "loss": 0.5246813774108887,
      "step": 240
    },
    {
      "epoch": 1.4796447076239823,
      "grad_norm": 0.3214714055714591,
      "learning_rate": 8.899092837069081e-07,
      "loss": 0.5199584007263184,
      "step": 250
    },
    {
      "epoch": 1.5388601036269431,
      "grad_norm": 0.3125573988440219,
      "learning_rate": 7.107396854967322e-07,
      "loss": 0.5219683647155762,
      "step": 260
    },
    {
      "epoch": 1.5980754996299038,
      "grad_norm": 0.32908992567819323,
      "learning_rate": 5.486945333173852e-07,
      "loss": 0.5197880744934082,
      "step": 270
    },
    {
      "epoch": 1.6572908956328645,
      "grad_norm": 0.31235586614735955,
      "learning_rate": 4.0532471020168386e-07,
      "loss": 0.5178247451782226,
      "step": 280
    },
    {
      "epoch": 1.7165062916358254,
      "grad_norm": 0.31283261644659427,
      "learning_rate": 2.820023634992855e-07,
      "loss": 0.5193904876708985,
      "step": 290
    },
    {
      "epoch": 1.7757216876387862,
      "grad_norm": 0.3151190787137027,
      "learning_rate": 1.7990777248726443e-07,
      "loss": 0.5182641983032227,
      "step": 300
    },
    {
      "epoch": 1.834937083641747,
      "grad_norm": 0.30052108490202145,
      "learning_rate": 1.0001805228948253e-07,
      "loss": 0.5201420307159423,
      "step": 310
    },
    {
      "epoch": 1.8941524796447076,
      "grad_norm": 0.2956110113897423,
      "learning_rate": 4.309780221597587e-08,
      "loss": 0.5192756175994873,
      "step": 320
    },
    {
      "epoch": 1.9533678756476682,
      "grad_norm": 0.31661711471068515,
      "learning_rate": 9.691788024160376e-09,
      "loss": 0.5177091598510742,
      "step": 330
    }
  ],
  "logging_steps": 10,
  "max_steps": 338,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.899437194464461e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}