{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 3530,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.056657223796033995,
      "grad_norm": 0.49070337414741516,
      "learning_rate": 6.289308176100629e-05,
      "loss": 1.948,
      "step": 100
    },
    {
      "epoch": 0.11331444759206799,
      "grad_norm": 0.35821089148521423,
      "learning_rate": 9.998427702677944e-05,
      "loss": 1.8537,
      "step": 200
    },
    {
      "epoch": 0.16997167138810199,
      "grad_norm": 0.8048006892204285,
      "learning_rate": 9.981415164444553e-05,
      "loss": 1.8535,
      "step": 300
    },
    {
      "epoch": 0.22662889518413598,
      "grad_norm": 0.3545685410499573,
      "learning_rate": 9.945770301725816e-05,
      "loss": 1.8401,
      "step": 400
    },
    {
      "epoch": 0.28328611898017,
      "grad_norm": 0.2784646451473236,
      "learning_rate": 9.892258840153075e-05,
      "loss": 1.8068,
      "step": 500
    },
    {
      "epoch": 0.33994334277620397,
      "grad_norm": 0.31996163725852966,
      "learning_rate": 9.820000233095179e-05,
      "loss": 1.8332,
      "step": 600
    },
    {
      "epoch": 0.39660056657223797,
      "grad_norm": 0.8525365591049194,
      "learning_rate": 9.729713052750826e-05,
      "loss": 1.8503,
      "step": 700
    },
    {
      "epoch": 0.45325779036827196,
      "grad_norm": 0.42982813715934753,
      "learning_rate": 9.621735006374983e-05,
      "loss": 1.8055,
      "step": 800
    },
    {
      "epoch": 0.509915014164306,
      "grad_norm": 0.3288513720035553,
      "learning_rate": 9.49646997156688e-05,
      "loss": 1.8356,
      "step": 900
    },
    {
      "epoch": 0.56657223796034,
      "grad_norm": 0.3136463165283203,
      "learning_rate": 9.354386485619264e-05,
      "loss": 1.8165,
      "step": 1000
    },
    {
      "epoch": 0.623229461756374,
      "grad_norm": 0.3262263238430023,
      "learning_rate": 9.196015993016642e-05,
      "loss": 1.7969,
      "step": 1100
    },
    {
      "epoch": 0.6798866855524079,
      "grad_norm": 0.3740326762199402,
      "learning_rate": 9.021950857637486e-05,
      "loss": 1.8197,
      "step": 1200
    },
    {
      "epoch": 0.7365439093484419,
      "grad_norm": 0.2732725739479065,
      "learning_rate": 8.832842147095495e-05,
      "loss": 1.7799,
      "step": 1300
    },
    {
      "epoch": 0.7932011331444759,
      "grad_norm": 0.3327942490577698,
      "learning_rate": 8.629397197507315e-05,
      "loss": 1.8248,
      "step": 1400
    },
    {
      "epoch": 0.8498583569405099,
      "grad_norm": 0.33730548620224,
      "learning_rate": 8.412376967795361e-05,
      "loss": 1.8325,
      "step": 1500
    },
    {
      "epoch": 0.9065155807365439,
      "grad_norm": 0.3892277181148529,
      "learning_rate": 8.182593193421625e-05,
      "loss": 1.8233,
      "step": 1600
    },
    {
      "epoch": 0.9631728045325779,
      "grad_norm": 0.31279096007347107,
      "learning_rate": 7.940905350198551e-05,
      "loss": 1.8086,
      "step": 1700
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.804076910018921,
      "eval_runtime": 252.4049,
      "eval_samples_per_second": 1.074,
      "eval_steps_per_second": 1.074,
      "step": 1765
    },
    {
      "epoch": 1.019830028328612,
      "grad_norm": 0.3374468684196472,
      "learning_rate": 7.68821743953346e-05,
      "loss": 1.7881,
      "step": 1800
    },
    {
      "epoch": 1.0764872521246458,
      "grad_norm": 0.3738987147808075,
      "learning_rate": 7.425474607130858e-05,
      "loss": 1.7664,
      "step": 1900
    },
    {
      "epoch": 1.13314447592068,
      "grad_norm": 0.44481009244918823,
      "learning_rate": 7.153659607799951e-05,
      "loss": 1.7459,
      "step": 2000
    },
    {
      "epoch": 1.1898016997167138,
      "grad_norm": 0.39869531989097595,
      "learning_rate": 6.873789129590286e-05,
      "loss": 1.7631,
      "step": 2100
    },
    {
      "epoch": 1.246458923512748,
      "grad_norm": 0.378170371055603,
      "learning_rate": 6.586909991004586e-05,
      "loss": 1.7557,
      "step": 2200
    },
    {
      "epoch": 1.3031161473087818,
      "grad_norm": 0.4261433780193329,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.7353,
      "step": 2300
    },
    {
      "epoch": 1.3597733711048159,
      "grad_norm": 0.3958815634250641,
      "learning_rate": 5.996440068011383e-05,
      "loss": 1.7579,
      "step": 2400
    },
    {
      "epoch": 1.41643059490085,
      "grad_norm": 0.37525269389152527,
      "learning_rate": 5.695057858243988e-05,
      "loss": 1.7623,
      "step": 2500
    },
    {
      "epoch": 1.4730878186968839,
      "grad_norm": 0.4011896252632141,
      "learning_rate": 5.391075876499483e-05,
      "loss": 1.7363,
      "step": 2600
    },
    {
      "epoch": 1.5297450424929178,
      "grad_norm": 0.45209965109825134,
      "learning_rate": 5.0856311271701064e-05,
      "loss": 1.7745,
      "step": 2700
    },
    {
      "epoch": 1.5864022662889519,
      "grad_norm": 0.4531945288181305,
      "learning_rate": 4.7798660859367615e-05,
      "loss": 1.7513,
      "step": 2800
    },
    {
      "epoch": 1.643059490084986,
      "grad_norm": 0.5212255120277405,
      "learning_rate": 4.474924426489847e-05,
      "loss": 1.7438,
      "step": 2900
    },
    {
      "epoch": 1.6997167138810199,
      "grad_norm": 0.4203312397003174,
      "learning_rate": 4.171946742769108e-05,
      "loss": 1.7491,
      "step": 3000
    },
    {
      "epoch": 1.7563739376770537,
      "grad_norm": 1.2426502704620361,
      "learning_rate": 3.872066282722877e-05,
      "loss": 1.7699,
      "step": 3100
    },
    {
      "epoch": 1.8130311614730878,
      "grad_norm": 1.147980809211731,
      "learning_rate": 3.576404709544031e-05,
      "loss": 1.7475,
      "step": 3200
    },
    {
      "epoch": 1.869688385269122,
      "grad_norm": 0.6595035791397095,
      "learning_rate": 3.286067906237188e-05,
      "loss": 1.7306,
      "step": 3300
    },
    {
      "epoch": 1.9263456090651558,
      "grad_norm": 0.42627865076065063,
      "learning_rate": 3.0021418392096213e-05,
      "loss": 1.7464,
      "step": 3400
    },
    {
      "epoch": 1.9830028328611897,
      "grad_norm": 0.5331133604049683,
      "learning_rate": 2.7256884963575536e-05,
      "loss": 1.7512,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.7998833656311035,
      "eval_runtime": 252.3326,
      "eval_samples_per_second": 1.074,
      "eval_steps_per_second": 1.074,
      "step": 3530
    }
  ],
  "logging_steps": 100,
  "max_steps": 5295,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 7.828436663001416e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}