{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 16506,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09087604507451835,
      "grad_norm": 0.4355389475822449,
      "learning_rate": 0.0002,
      "loss": 0.8037,
      "step": 250
    },
    {
      "epoch": 0.1817520901490367,
      "grad_norm": 0.3333398103713989,
      "learning_rate": 0.0002,
      "loss": 0.472,
      "step": 500
    },
    {
      "epoch": 0.27262813522355506,
      "grad_norm": 0.4328073561191559,
      "learning_rate": 0.0002,
      "loss": 0.3581,
      "step": 750
    },
    {
      "epoch": 0.3635041802980734,
      "grad_norm": 0.5728178024291992,
      "learning_rate": 0.0002,
      "loss": 0.29,
      "step": 1000
    },
    {
      "epoch": 0.45438022537259176,
      "grad_norm": 0.7130202054977417,
      "learning_rate": 0.0002,
      "loss": 0.2542,
      "step": 1250
    },
    {
      "epoch": 0.5452562704471101,
      "grad_norm": 0.4695929288864136,
      "learning_rate": 0.0002,
      "loss": 0.2186,
      "step": 1500
    },
    {
      "epoch": 0.6361323155216285,
      "grad_norm": 0.5198377966880798,
      "learning_rate": 0.0002,
      "loss": 0.2042,
      "step": 1750
    },
    {
      "epoch": 0.7270083605961468,
      "grad_norm": 0.4845351278781891,
      "learning_rate": 0.0002,
      "loss": 0.1857,
      "step": 2000
    },
    {
      "epoch": 0.8178844056706652,
      "grad_norm": 0.3002346456050873,
      "learning_rate": 0.0002,
      "loss": 0.1727,
      "step": 2250
    },
    {
      "epoch": 0.9087604507451835,
      "grad_norm": 0.3961799740791321,
      "learning_rate": 0.0002,
      "loss": 0.1647,
      "step": 2500
    },
    {
      "epoch": 0.9996364958197019,
      "grad_norm": 0.19754305481910706,
      "learning_rate": 0.0002,
      "loss": 0.1561,
      "step": 2750
    },
    {
      "epoch": 1.0905125408942202,
      "grad_norm": 0.4301386773586273,
      "learning_rate": 0.0002,
      "loss": 0.1478,
      "step": 3000
    },
    {
      "epoch": 1.1813885859687385,
      "grad_norm": 0.33132612705230713,
      "learning_rate": 0.0002,
      "loss": 0.1451,
      "step": 3250
    },
    {
      "epoch": 1.272264631043257,
      "grad_norm": 0.2488761842250824,
      "learning_rate": 0.0002,
      "loss": 0.1445,
      "step": 3500
    },
    {
      "epoch": 1.3631406761177753,
      "grad_norm": 0.16658537089824677,
      "learning_rate": 0.0002,
      "loss": 0.1403,
      "step": 3750
    },
    {
      "epoch": 1.4540167211922936,
      "grad_norm": 0.1872565895318985,
      "learning_rate": 0.0002,
      "loss": 0.1365,
      "step": 4000
    },
    {
      "epoch": 1.5448927662668122,
      "grad_norm": 0.1460885852575302,
      "learning_rate": 0.0002,
      "loss": 0.1344,
      "step": 4250
    },
    {
      "epoch": 1.6357688113413305,
      "grad_norm": 0.35161587595939636,
      "learning_rate": 0.0002,
      "loss": 0.134,
      "step": 4500
    },
    {
      "epoch": 1.7266448564158487,
      "grad_norm": 0.2876887917518616,
      "learning_rate": 0.0002,
      "loss": 0.1332,
      "step": 4750
    },
    {
      "epoch": 1.8175209014903673,
      "grad_norm": 0.18391716480255127,
      "learning_rate": 0.0002,
      "loss": 0.1312,
      "step": 5000
    },
    {
      "epoch": 1.9083969465648853,
      "grad_norm": 0.18932031095027924,
      "learning_rate": 0.0002,
      "loss": 0.1306,
      "step": 5250
    },
    {
      "epoch": 1.9992729916394039,
      "grad_norm": 0.2454090714454651,
      "learning_rate": 0.0002,
      "loss": 0.1291,
      "step": 5500
    },
    {
      "epoch": 2.0901490367139224,
      "grad_norm": 0.15890659391880035,
      "learning_rate": 0.0002,
      "loss": 0.1241,
      "step": 5750
    },
    {
      "epoch": 2.1810250817884405,
      "grad_norm": 0.13456985354423523,
      "learning_rate": 0.0002,
      "loss": 0.1255,
      "step": 6000
    },
    {
      "epoch": 2.271901126862959,
      "grad_norm": 0.18098081648349762,
      "learning_rate": 0.0002,
      "loss": 0.1249,
      "step": 6250
    },
    {
      "epoch": 2.362777171937477,
      "grad_norm": 0.21501798927783966,
      "learning_rate": 0.0002,
      "loss": 0.1272,
      "step": 6500
    },
    {
      "epoch": 2.4536532170119956,
      "grad_norm": 0.10344691574573517,
      "learning_rate": 0.0002,
      "loss": 0.1266,
      "step": 6750
    },
    {
      "epoch": 2.544529262086514,
      "grad_norm": 0.16723701357841492,
      "learning_rate": 0.0002,
      "loss": 0.1265,
      "step": 7000
    },
    {
      "epoch": 2.635405307161032,
      "grad_norm": 0.15142661333084106,
      "learning_rate": 0.0002,
      "loss": 0.1253,
      "step": 7250
    },
    {
      "epoch": 2.7262813522355507,
      "grad_norm": 0.18276916444301605,
      "learning_rate": 0.0002,
      "loss": 0.1247,
      "step": 7500
    },
    {
      "epoch": 2.817157397310069,
      "grad_norm": 0.10605284571647644,
      "learning_rate": 0.0002,
      "loss": 0.125,
      "step": 7750
    },
    {
      "epoch": 2.9080334423845873,
      "grad_norm": 0.13421468436717987,
      "learning_rate": 0.0002,
      "loss": 0.1235,
      "step": 8000
    },
    {
      "epoch": 2.998909487459106,
      "grad_norm": 0.117579385638237,
      "learning_rate": 0.0002,
      "loss": 0.1216,
      "step": 8250
    },
    {
      "epoch": 3.0897855325336243,
      "grad_norm": 0.09406478703022003,
      "learning_rate": 0.0002,
      "loss": 0.1208,
      "step": 8500
    },
    {
      "epoch": 3.1806615776081424,
      "grad_norm": 0.13346560299396515,
      "learning_rate": 0.0002,
      "loss": 0.1211,
      "step": 8750
    },
    {
      "epoch": 3.271537622682661,
      "grad_norm": 0.2320273071527481,
      "learning_rate": 0.0002,
      "loss": 0.1199,
      "step": 9000
    },
    {
      "epoch": 3.3624136677571794,
      "grad_norm": 0.1322121024131775,
      "learning_rate": 0.0002,
      "loss": 0.1206,
      "step": 9250
    },
    {
      "epoch": 3.4532897128316975,
      "grad_norm": 0.12291130423545837,
      "learning_rate": 0.0002,
      "loss": 0.1203,
      "step": 9500
    },
    {
      "epoch": 3.544165757906216,
      "grad_norm": 0.1050431877374649,
      "learning_rate": 0.0002,
      "loss": 0.1206,
      "step": 9750
    },
    {
      "epoch": 3.6350418029807345,
      "grad_norm": 0.10830684006214142,
      "learning_rate": 0.0002,
      "loss": 0.1204,
      "step": 10000
    },
    {
      "epoch": 3.7259178480552526,
      "grad_norm": 0.16537795960903168,
      "learning_rate": 0.0002,
      "loss": 0.1214,
      "step": 10250
    },
    {
      "epoch": 3.816793893129771,
      "grad_norm": 0.13683146238327026,
      "learning_rate": 0.0002,
      "loss": 0.1231,
      "step": 10500
    },
    {
      "epoch": 3.907669938204289,
      "grad_norm": 0.10453382879495621,
      "learning_rate": 0.0002,
      "loss": 0.1193,
      "step": 10750
    },
    {
      "epoch": 3.9985459832788077,
      "grad_norm": 0.08612716197967529,
      "learning_rate": 0.0002,
      "loss": 0.1191,
      "step": 11000
    },
    {
      "epoch": 4.089422028353326,
      "grad_norm": 0.08494025468826294,
      "learning_rate": 0.0002,
      "loss": 0.1171,
      "step": 11250
    },
    {
      "epoch": 4.180298073427845,
      "grad_norm": 0.05780186131596565,
      "learning_rate": 0.0002,
      "loss": 0.1172,
      "step": 11500
    },
    {
      "epoch": 4.271174118502363,
      "grad_norm": 0.10587610304355621,
      "learning_rate": 0.0002,
      "loss": 0.1189,
      "step": 11750
    },
    {
      "epoch": 4.362050163576881,
      "grad_norm": 0.09237153828144073,
      "learning_rate": 0.0002,
      "loss": 0.1178,
      "step": 12000
    },
    {
      "epoch": 4.4529262086514,
      "grad_norm": 0.22916856408119202,
      "learning_rate": 0.0002,
      "loss": 0.1191,
      "step": 12250
    },
    {
      "epoch": 4.543802253725918,
      "grad_norm": 0.12149995565414429,
      "learning_rate": 0.0002,
      "loss": 0.118,
      "step": 12500
    },
    {
      "epoch": 4.634678298800436,
      "grad_norm": 0.10446422547101974,
      "learning_rate": 0.0002,
      "loss": 0.1187,
      "step": 12750
    },
    {
      "epoch": 4.725554343874954,
      "grad_norm": 0.09491357207298279,
      "learning_rate": 0.0002,
      "loss": 0.1181,
      "step": 13000
    },
    {
      "epoch": 4.816430388949473,
      "grad_norm": 0.15105749666690826,
      "learning_rate": 0.0002,
      "loss": 0.1192,
      "step": 13250
    },
    {
      "epoch": 4.907306434023991,
      "grad_norm": 0.11921977251768112,
      "learning_rate": 0.0002,
      "loss": 0.1168,
      "step": 13500
    },
    {
      "epoch": 4.99818247909851,
      "grad_norm": 0.07625231146812439,
      "learning_rate": 0.0002,
      "loss": 0.1172,
      "step": 13750
    },
    {
      "epoch": 5.089058524173028,
      "grad_norm": 0.09381510317325592,
      "learning_rate": 0.0002,
      "loss": 0.1151,
      "step": 14000
    },
    {
      "epoch": 5.179934569247546,
      "grad_norm": 0.08833180367946625,
      "learning_rate": 0.0002,
      "loss": 0.1156,
      "step": 14250
    },
    {
      "epoch": 5.270810614322064,
      "grad_norm": 0.08934313803911209,
      "learning_rate": 0.0002,
      "loss": 0.1164,
      "step": 14500
    },
    {
      "epoch": 5.361686659396583,
      "grad_norm": 0.08423677831888199,
      "learning_rate": 0.0002,
      "loss": 0.1162,
      "step": 14750
    },
    {
      "epoch": 5.452562704471101,
      "grad_norm": 0.08956829458475113,
      "learning_rate": 0.0002,
      "loss": 0.1147,
      "step": 15000
    },
    {
      "epoch": 5.543438749545619,
      "grad_norm": 0.07213614135980606,
      "learning_rate": 0.0002,
      "loss": 0.1166,
      "step": 15250
    },
    {
      "epoch": 5.634314794620138,
      "grad_norm": 0.24475565552711487,
      "learning_rate": 0.0002,
      "loss": 0.1172,
      "step": 15500
    },
    {
      "epoch": 5.7251908396946565,
      "grad_norm": 0.10199423879384995,
      "learning_rate": 0.0002,
      "loss": 0.1171,
      "step": 15750
    },
    {
      "epoch": 5.8160668847691745,
      "grad_norm": 0.2594470679759979,
      "learning_rate": 0.0002,
      "loss": 0.1165,
      "step": 16000
    },
    {
      "epoch": 5.9069429298436935,
      "grad_norm": 0.08738715201616287,
      "learning_rate": 0.0002,
      "loss": 0.115,
      "step": 16250
    },
    {
      "epoch": 5.997818974918212,
      "grad_norm": 0.07172822952270508,
      "learning_rate": 0.0002,
      "loss": 0.1153,
      "step": 16500
    }
  ],
  "logging_steps": 250,
  "max_steps": 16506,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0312668928252314e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}