{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9946917109024094,
  "eval_steps": 612,
  "global_step": 2448,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08166598611678236,
      "grad_norm": 1.7321007251739502,
      "learning_rate": 2.5e-05,
      "loss": 3.105,
      "step": 50
    },
    {
      "epoch": 0.16333197223356472,
      "grad_norm": 2.5774662494659424,
      "learning_rate": 5e-05,
      "loss": 2.1147,
      "step": 100
    },
    {
      "epoch": 0.24499795835034707,
      "grad_norm": 2.3063881397247314,
      "learning_rate": 4.9964806340932865e-05,
      "loss": 1.7456,
      "step": 150
    },
    {
      "epoch": 0.32666394446712943,
      "grad_norm": 2.3037455081939697,
      "learning_rate": 4.985932445122257e-05,
      "loss": 1.5373,
      "step": 200
    },
    {
      "epoch": 0.4083299305839118,
      "grad_norm": 3.1852424144744873,
      "learning_rate": 4.968385131436222e-05,
      "loss": 1.4322,
      "step": 250
    },
    {
      "epoch": 0.48999591670069415,
      "grad_norm": 2.7717628479003906,
      "learning_rate": 4.943888097369216e-05,
      "loss": 1.3964,
      "step": 300
    },
    {
      "epoch": 0.5716619028174765,
      "grad_norm": 2.9692201614379883,
      "learning_rate": 4.912510314142448e-05,
      "loss": 1.3724,
      "step": 350
    },
    {
      "epoch": 0.6533278889342589,
      "grad_norm": 2.7853329181671143,
      "learning_rate": 4.87434012567633e-05,
      "loss": 1.2211,
      "step": 400
    },
    {
      "epoch": 0.7349938750510412,
      "grad_norm": 3.02131986618042,
      "learning_rate": 4.829484999858815e-05,
      "loss": 1.2873,
      "step": 450
    },
    {
      "epoch": 0.8166598611678236,
      "grad_norm": 2.9002573490142822,
      "learning_rate": 4.77807122597034e-05,
      "loss": 1.1954,
      "step": 500
    },
    {
      "epoch": 0.898325847284606,
      "grad_norm": 3.3557584285736084,
      "learning_rate": 4.7202435591172676e-05,
      "loss": 1.1836,
      "step": 550
    },
    {
      "epoch": 0.9799918334013883,
      "grad_norm": 2.2068400382995605,
      "learning_rate": 4.656164812674951e-05,
      "loss": 1.1539,
      "step": 600
    },
    {
      "epoch": 0.9995916700694161,
      "eval_loss": 1.0969716310501099,
      "eval_runtime": 142.2066,
      "eval_samples_per_second": 3.832,
      "eval_steps_per_second": 3.832,
      "step": 612
    },
    {
      "epoch": 1.060432829726419,
      "grad_norm": 3.3319382667541504,
      "learning_rate": 4.5860153998878494e-05,
      "loss": 1.0427,
      "step": 650
    },
    {
      "epoch": 1.1420988158432013,
      "grad_norm": 3.4751930236816406,
      "learning_rate": 4.5099928259173516e-05,
      "loss": 0.9736,
      "step": 700
    },
    {
      "epoch": 1.2237648019599836,
      "grad_norm": 2.9710006713867188,
      "learning_rate": 4.4283111317674374e-05,
      "loss": 1.0045,
      "step": 750
    },
    {
      "epoch": 1.305430788076766,
      "grad_norm": 3.5268781185150146,
      "learning_rate": 4.341200291653781e-05,
      "loss": 0.9427,
      "step": 800
    },
    {
      "epoch": 1.3870967741935485,
      "grad_norm": 2.7967159748077393,
      "learning_rate": 4.248905565513023e-05,
      "loss": 0.9968,
      "step": 850
    },
    {
      "epoch": 1.4687627603103308,
      "grad_norm": 3.274461030960083,
      "learning_rate": 4.151686808475204e-05,
      "loss": 0.8969,
      "step": 900
    },
    {
      "epoch": 1.5504287464271131,
      "grad_norm": 3.7996115684509277,
      "learning_rate": 4.049817739243532e-05,
      "loss": 0.9398,
      "step": 950
    },
    {
      "epoch": 1.6320947325438955,
      "grad_norm": 3.434795379638672,
      "learning_rate": 3.94358516944137e-05,
      "loss": 0.9255,
      "step": 1000
    },
    {
      "epoch": 1.7137607186606778,
      "grad_norm": 2.722684383392334,
      "learning_rate": 3.833288196096194e-05,
      "loss": 0.9775,
      "step": 1050
    },
    {
      "epoch": 1.7954267047774601,
      "grad_norm": 4.152195930480957,
      "learning_rate": 3.719237359534087e-05,
      "loss": 0.8806,
      "step": 1100
    },
    {
      "epoch": 1.8770926908942425,
      "grad_norm": 2.783254623413086,
      "learning_rate": 3.6017537690557115e-05,
      "loss": 0.9433,
      "step": 1150
    },
    {
      "epoch": 1.958758677011025,
      "grad_norm": 3.3357818126678467,
      "learning_rate": 3.481168198855409e-05,
      "loss": 0.9619,
      "step": 1200
    },
    {
      "epoch": 1.9979583503470804,
      "eval_loss": 0.9826937913894653,
      "eval_runtime": 141.9315,
      "eval_samples_per_second": 3.84,
      "eval_steps_per_second": 3.84,
      "step": 1224
    },
    {
      "epoch": 2.0391996733360553,
      "grad_norm": 3.218412160873413,
      "learning_rate": 3.357820156728867e-05,
      "loss": 0.8787,
      "step": 1250
    },
    {
      "epoch": 2.120865659452838,
      "grad_norm": 3.419764280319214,
      "learning_rate": 3.232056928191376e-05,
      "loss": 0.7141,
      "step": 1300
    },
    {
      "epoch": 2.2025316455696204,
      "grad_norm": 3.141345739364624,
      "learning_rate": 3.1042325986980064e-05,
      "loss": 0.7485,
      "step": 1350
    },
    {
      "epoch": 2.2841976316864026,
      "grad_norm": 2.911731719970703,
      "learning_rate": 2.974707056718571e-05,
      "loss": 0.7787,
      "step": 1400
    },
    {
      "epoch": 2.365863617803185,
      "grad_norm": 3.447298765182495,
      "learning_rate": 2.8438449804742628e-05,
      "loss": 0.7358,
      "step": 1450
    },
    {
      "epoch": 2.447529603919967,
      "grad_norm": 3.8683292865753174,
      "learning_rate": 2.7120148111887732e-05,
      "loss": 0.7281,
      "step": 1500
    },
    {
      "epoch": 2.5291955900367498,
      "grad_norm": 3.7542524337768555,
      "learning_rate": 2.579587715744712e-05,
      "loss": 0.7169,
      "step": 1550
    },
    {
      "epoch": 2.610861576153532,
      "grad_norm": 2.9598772525787354,
      "learning_rate": 2.446936541665941e-05,
      "loss": 0.7425,
      "step": 1600
    },
    {
      "epoch": 2.6925275622703144,
      "grad_norm": 3.7450504302978516,
      "learning_rate": 2.3144347673680936e-05,
      "loss": 0.699,
      "step": 1650
    },
    {
      "epoch": 2.774193548387097,
      "grad_norm": 3.8803372383117676,
      "learning_rate": 2.182455450632803e-05,
      "loss": 0.751,
      "step": 1700
    },
    {
      "epoch": 2.855859534503879,
      "grad_norm": 3.553741216659546,
      "learning_rate": 2.0513701782662366e-05,
      "loss": 0.7451,
      "step": 1750
    },
    {
      "epoch": 2.9375255206206616,
      "grad_norm": 3.795320987701416,
      "learning_rate": 1.9215480198991466e-05,
      "loss": 0.7101,
      "step": 1800
    },
    {
      "epoch": 2.9963250306247446,
      "eval_loss": 0.9423996210098267,
      "eval_runtime": 141.7974,
      "eval_samples_per_second": 3.844,
      "eval_steps_per_second": 3.844,
      "step": 1836
    },
    {
      "epoch": 3.017966516945692,
      "grad_norm": 3.2628490924835205,
      "learning_rate": 1.793354488874006e-05,
      "loss": 0.681,
      "step": 1850
    },
    {
      "epoch": 3.0996325030624745,
      "grad_norm": 3.2649693489074707,
      "learning_rate": 1.6696527865384627e-05,
      "loss": 0.6026,
      "step": 1900
    },
    {
      "epoch": 3.181298489179257,
      "grad_norm": 2.9757375717163086,
      "learning_rate": 1.5457433537180068e-05,
      "loss": 0.5814,
      "step": 1950
    },
    {
      "epoch": 3.262964475296039,
      "grad_norm": 2.891662836074829,
      "learning_rate": 1.424520623543294e-05,
      "loss": 0.5761,
      "step": 2000
    },
    {
      "epoch": 3.3446304614128217,
      "grad_norm": 3.558239221572876,
      "learning_rate": 1.3063258977292814e-05,
      "loss": 0.5863,
      "step": 2050
    },
    {
      "epoch": 3.426296447529604,
      "grad_norm": 3.837745428085327,
      "learning_rate": 1.1914919526666754e-05,
      "loss": 0.5972,
      "step": 2100
    },
    {
      "epoch": 3.5079624336463864,
      "grad_norm": 3.7010719776153564,
      "learning_rate": 1.0803421024924246e-05,
      "loss": 0.5797,
      "step": 2150
    },
    {
      "epoch": 3.5896284197631685,
      "grad_norm": 3.509216785430908,
      "learning_rate": 9.731892888011207e-06,
      "loss": 0.5959,
      "step": 2200
    },
    {
      "epoch": 3.671294405879951,
      "grad_norm": 4.380457878112793,
      "learning_rate": 8.703351995602158e-06,
      "loss": 0.5605,
      "step": 2250
    },
    {
      "epoch": 3.7529603919967336,
      "grad_norm": 3.9303319454193115,
      "learning_rate": 7.720694197097405e-06,
      "loss": 0.5507,
      "step": 2300
    },
    {
      "epoch": 3.8346263781135157,
      "grad_norm": 3.130398988723755,
      "learning_rate": 6.786686158380176e-06,
      "loss": 0.5661,
      "step": 2350
    },
    {
      "epoch": 3.916292364230298,
      "grad_norm": 3.736706495285034,
      "learning_rate": 5.903957572288923e-06,
      "loss": 0.5643,
      "step": 2400
    },
    {
      "epoch": 3.9946917109024094,
      "eval_loss": 0.9574249982833862,
      "eval_runtime": 141.5072,
      "eval_samples_per_second": 3.851,
      "eval_steps_per_second": 3.851,
      "step": 2448
    }
  ],
  "logging_steps": 50,
  "max_steps": 3060,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 612,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.802763943153664e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}