{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23450880873712818,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.3501258391018316e-05,
      "grad_norm": 0.8195101618766785,
      "learning_rate": 5e-05,
      "loss": 14.0675,
      "step": 1
    },
    {
      "epoch": 0.0033501258391018312,
      "grad_norm": 0.6814610958099365,
      "learning_rate": 4.999864297594039e-05,
      "loss": 9.6991,
      "step": 100
    },
    {
      "epoch": 0.0067002516782036625,
      "grad_norm": 0.6981404423713684,
      "learning_rate": 4.999451708687114e-05,
      "loss": 5.8251,
      "step": 200
    },
    {
      "epoch": 0.010050377517305495,
      "grad_norm": 0.71510249376297,
      "learning_rate": 4.998762265134215e-05,
      "loss": 4.8931,
      "step": 300
    },
    {
      "epoch": 0.013400503356407325,
      "grad_norm": 0.7365719676017761,
      "learning_rate": 4.9977960433023496e-05,
      "loss": 3.7625,
      "step": 400
    },
    {
      "epoch": 0.016750629195509157,
      "grad_norm": 0.7549176812171936,
      "learning_rate": 4.9965531502161924e-05,
      "loss": 2.5786,
      "step": 500
    },
    {
      "epoch": 0.02010075503461099,
      "grad_norm": 0.7549782395362854,
      "learning_rate": 4.995033723546226e-05,
      "loss": 2.3343,
      "step": 600
    },
    {
      "epoch": 0.023450880873712818,
      "grad_norm": 0.7549582123756409,
      "learning_rate": 4.993237931593496e-05,
      "loss": 2.3209,
      "step": 700
    },
    {
      "epoch": 0.02680100671281465,
      "grad_norm": 0.754852831363678,
      "learning_rate": 4.991165973270965e-05,
      "loss": 2.3182,
      "step": 800
    },
    {
      "epoch": 0.030151132551916482,
      "grad_norm": 0.7546794414520264,
      "learning_rate": 4.988818078081481e-05,
      "loss": 2.3295,
      "step": 900
    },
    {
      "epoch": 0.033501258391018314,
      "grad_norm": 0.7546112537384033,
      "learning_rate": 4.9861945060923584e-05,
      "loss": 2.3221,
      "step": 1000
    },
    {
      "epoch": 0.036851384230120146,
      "grad_norm": 0.7547661662101746,
      "learning_rate": 4.983295547906569e-05,
      "loss": 2.3251,
      "step": 1100
    },
    {
      "epoch": 0.04020151006922198,
      "grad_norm": 0.7546742558479309,
      "learning_rate": 4.980121524630554e-05,
      "loss": 2.3214,
      "step": 1200
    },
    {
      "epoch": 0.0435516359083238,
      "grad_norm": 0.7544980049133301,
      "learning_rate": 4.976672787838654e-05,
      "loss": 2.3259,
      "step": 1300
    },
    {
      "epoch": 0.046901761747425635,
      "grad_norm": 0.7544678449630737,
      "learning_rate": 4.9729497195341726e-05,
      "loss": 2.3197,
      "step": 1400
    },
    {
      "epoch": 0.05025188758652747,
      "grad_norm": 0.7546402215957642,
      "learning_rate": 4.968952732107054e-05,
      "loss": 2.3209,
      "step": 1500
    },
    {
      "epoch": 0.0536020134256293,
      "grad_norm": 0.754619300365448,
      "learning_rate": 4.964682268288213e-05,
      "loss": 2.3188,
      "step": 1600
    },
    {
      "epoch": 0.05695213926473113,
      "grad_norm": 0.754672110080719,
      "learning_rate": 4.9601388011004926e-05,
      "loss": 2.3247,
      "step": 1700
    },
    {
      "epoch": 0.12060453020766593,
      "grad_norm": 2.730647087097168,
      "learning_rate": 4.822888174568335e-05,
      "loss": 28.8747,
      "step": 1800
    },
    {
      "epoch": 0.12730478188586958,
      "grad_norm": 2.763967275619507,
      "learning_rate": 4.802920851560973e-05,
      "loss": 17.4519,
      "step": 1900
    },
    {
      "epoch": 0.13400503356407326,
      "grad_norm": 2.815877676010132,
      "learning_rate": 4.7819332140911445e-05,
      "loss": 15.0003,
      "step": 2000
    },
    {
      "epoch": 0.1407052852422769,
      "grad_norm": 2.8834288120269775,
      "learning_rate": 4.7599345607806536e-05,
      "loss": 11.9449,
      "step": 2100
    },
    {
      "epoch": 0.14740553692048058,
      "grad_norm": 2.9614415168762207,
      "learning_rate": 4.7369346381842344e-05,
      "loss": 8.1434,
      "step": 2200
    },
    {
      "epoch": 0.15410578859868423,
      "grad_norm": 3.032062292098999,
      "learning_rate": 4.7129436364713164e-05,
      "loss": 3.7118,
      "step": 2300
    },
    {
      "epoch": 0.1608060402768879,
      "grad_norm": 3.026526689529419,
      "learning_rate": 4.687972184911246e-05,
      "loss": 2.0568,
      "step": 2400
    },
    {
      "epoch": 0.16750629195509156,
      "grad_norm": 3.0271811485290527,
      "learning_rate": 4.6620313471639675e-05,
      "loss": 1.9842,
      "step": 2500
    },
    {
      "epoch": 0.1742065436332952,
      "grad_norm": 3.027158737182617,
      "learning_rate": 4.635132616378236e-05,
      "loss": 1.9426,
      "step": 2600
    },
    {
      "epoch": 0.1809067953114989,
      "grad_norm": 3.0273852348327637,
      "learning_rate": 4.607287910099557e-05,
      "loss": 1.9186,
      "step": 2700
    },
    {
      "epoch": 0.18760704698970254,
      "grad_norm": 3.0235822200775146,
      "learning_rate": 4.578509564990087e-05,
      "loss": 1.8787,
      "step": 2800
    },
    {
      "epoch": 0.19430729866790622,
      "grad_norm": 3.0256638526916504,
      "learning_rate": 4.5488103313628474e-05,
      "loss": 1.8544,
      "step": 2900
    },
    {
      "epoch": 0.20100755034610987,
      "grad_norm": 3.028939962387085,
      "learning_rate": 4.5182033675326696e-05,
      "loss": 1.8332,
      "step": 3000
    },
    {
      "epoch": 0.20770780202431355,
      "grad_norm": 3.027080535888672,
      "learning_rate": 4.4867022339863685e-05,
      "loss": 1.81,
      "step": 3100
    },
    {
      "epoch": 0.2144080537025172,
      "grad_norm": 3.0254549980163574,
      "learning_rate": 4.454320887374743e-05,
      "loss": 1.7835,
      "step": 3200
    },
    {
      "epoch": 0.22110830538072088,
      "grad_norm": 3.025289535522461,
      "learning_rate": 4.4210736743290485e-05,
      "loss": 1.7494,
      "step": 3300
    },
    {
      "epoch": 0.22780855705892453,
      "grad_norm": 3.02748441696167,
      "learning_rate": 4.3869753251046806e-05,
      "loss": 1.7233,
      "step": 3400
    },
    {
      "epoch": 0.23450880873712818,
      "grad_norm": 3.0303146839141846,
      "learning_rate": 4.352040947054912e-05,
      "loss": 1.6755,
      "step": 3500
    }
  ],
  "logging_steps": 100,
  "max_steps": 14925,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4305806868430477e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}