{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01954365564078761,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009771827820393806,
      "grad_norm": 0.5417118072509766,
      "learning_rate": 4.995602247740044e-05,
      "loss": 1.378,
      "step": 100
    },
    {
      "epoch": 0.001954365564078761,
      "grad_norm": 0.6493918895721436,
      "learning_rate": 4.990715856340093e-05,
      "loss": 1.3304,
      "step": 200
    },
    {
      "epoch": 0.0029315483461181415,
      "grad_norm": 0.9062462449073792,
      "learning_rate": 4.9858294649401425e-05,
      "loss": 1.3284,
      "step": 300
    },
    {
      "epoch": 0.003908731128157522,
      "grad_norm": 0.750052273273468,
      "learning_rate": 4.9809430735401906e-05,
      "loss": 1.3166,
      "step": 400
    },
    {
      "epoch": 0.004885913910196903,
      "grad_norm": 0.6602022051811218,
      "learning_rate": 4.97605668214024e-05,
      "loss": 1.3166,
      "step": 500
    },
    {
      "epoch": 0.005863096692236283,
      "grad_norm": 0.4193927049636841,
      "learning_rate": 4.971170290740288e-05,
      "loss": 1.3098,
      "step": 600
    },
    {
      "epoch": 0.006840279474275663,
      "grad_norm": 0.6095415949821472,
      "learning_rate": 4.966283899340338e-05,
      "loss": 1.3103,
      "step": 700
    },
    {
      "epoch": 0.007817462256315045,
      "grad_norm": 0.9943467378616333,
      "learning_rate": 4.9613975079403865e-05,
      "loss": 1.3096,
      "step": 800
    },
    {
      "epoch": 0.008794645038354424,
      "grad_norm": 1.2263585329055786,
      "learning_rate": 4.9565111165404346e-05,
      "loss": 1.3067,
      "step": 900
    },
    {
      "epoch": 0.009771827820393805,
      "grad_norm": 0.7198677659034729,
      "learning_rate": 4.951624725140484e-05,
      "loss": 1.3041,
      "step": 1000
    },
    {
      "epoch": 0.010749010602433185,
      "grad_norm": 0.7370775938034058,
      "learning_rate": 4.946738333740533e-05,
      "loss": 1.302,
      "step": 1100
    },
    {
      "epoch": 0.011726193384472566,
      "grad_norm": 0.5109437704086304,
      "learning_rate": 4.941851942340582e-05,
      "loss": 1.3089,
      "step": 1200
    },
    {
      "epoch": 0.012703376166511945,
      "grad_norm": 0.1879555583000183,
      "learning_rate": 4.9369655509406305e-05,
      "loss": 1.3043,
      "step": 1300
    },
    {
      "epoch": 0.013680558948551327,
      "grad_norm": 0.951046884059906,
      "learning_rate": 4.932079159540679e-05,
      "loss": 1.3098,
      "step": 1400
    },
    {
      "epoch": 0.014657741730590706,
      "grad_norm": 0.2478829026222229,
      "learning_rate": 4.927192768140728e-05,
      "loss": 1.3026,
      "step": 1500
    },
    {
      "epoch": 0.01563492451263009,
      "grad_norm": 0.5585843324661255,
      "learning_rate": 4.9223063767407776e-05,
      "loss": 1.3014,
      "step": 1600
    },
    {
      "epoch": 0.016612107294669467,
      "grad_norm": 0.48532453179359436,
      "learning_rate": 4.917419985340826e-05,
      "loss": 1.2981,
      "step": 1700
    },
    {
      "epoch": 0.017589290076708848,
      "grad_norm": 0.4233573079109192,
      "learning_rate": 4.912533593940875e-05,
      "loss": 1.2992,
      "step": 1800
    },
    {
      "epoch": 0.01856647285874823,
      "grad_norm": 0.3272475600242615,
      "learning_rate": 4.9076472025409234e-05,
      "loss": 1.292,
      "step": 1900
    },
    {
      "epoch": 0.01954365564078761,
      "grad_norm": 0.5299385786056519,
      "learning_rate": 4.902760811140973e-05,
      "loss": 1.2963,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 102335,
  "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": 2.508584634023936e+16,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}