{
  "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": 0.9947701096534729,
      "learning_rate": 0.0002,
      "loss": 0.8859,
      "step": 250
    },
    {
      "epoch": 0.1817520901490367,
      "grad_norm": 1.0397032499313354,
      "learning_rate": 0.0002,
      "loss": 0.5293,
      "step": 500
    },
    {
      "epoch": 0.27262813522355506,
      "grad_norm": 0.829135000705719,
      "learning_rate": 0.0002,
      "loss": 0.416,
      "step": 750
    },
    {
      "epoch": 0.3635041802980734,
      "grad_norm": 1.429752230644226,
      "learning_rate": 0.0002,
      "loss": 0.3512,
      "step": 1000
    },
    {
      "epoch": 0.45438022537259176,
      "grad_norm": 0.743159830570221,
      "learning_rate": 0.0002,
      "loss": 0.3115,
      "step": 1250
    },
    {
      "epoch": 0.5452562704471101,
      "grad_norm": 1.0643532276153564,
      "learning_rate": 0.0002,
      "loss": 0.2675,
      "step": 1500
    },
    {
      "epoch": 0.6361323155216285,
      "grad_norm": 1.1772961616516113,
      "learning_rate": 0.0002,
      "loss": 0.2451,
      "step": 1750
    },
    {
      "epoch": 0.7270083605961468,
      "grad_norm": 0.7212278246879578,
      "learning_rate": 0.0002,
      "loss": 0.2253,
      "step": 2000
    },
    {
      "epoch": 0.8178844056706652,
      "grad_norm": 0.6244780421257019,
      "learning_rate": 0.0002,
      "loss": 0.2086,
      "step": 2250
    },
    {
      "epoch": 0.9087604507451835,
      "grad_norm": 0.4592975974082947,
      "learning_rate": 0.0002,
      "loss": 0.1942,
      "step": 2500
    },
    {
      "epoch": 0.9996364958197019,
      "grad_norm": 0.49654462933540344,
      "learning_rate": 0.0002,
      "loss": 0.1881,
      "step": 2750
    },
    {
      "epoch": 1.0905125408942202,
      "grad_norm": 0.31279975175857544,
      "learning_rate": 0.0002,
      "loss": 0.1778,
      "step": 3000
    },
    {
      "epoch": 1.1813885859687385,
      "grad_norm": 0.5960599184036255,
      "learning_rate": 0.0002,
      "loss": 0.1748,
      "step": 3250
    },
    {
      "epoch": 1.272264631043257,
      "grad_norm": 0.6937021017074585,
      "learning_rate": 0.0002,
      "loss": 0.1714,
      "step": 3500
    },
    {
      "epoch": 1.3631406761177753,
      "grad_norm": 0.8301833868026733,
      "learning_rate": 0.0002,
      "loss": 0.1682,
      "step": 3750
    },
    {
      "epoch": 1.4540167211922936,
      "grad_norm": 0.7386170029640198,
      "learning_rate": 0.0002,
      "loss": 0.164,
      "step": 4000
    },
    {
      "epoch": 1.5448927662668122,
      "grad_norm": 0.38632941246032715,
      "learning_rate": 0.0002,
      "loss": 0.1611,
      "step": 4250
    },
    {
      "epoch": 1.6357688113413305,
      "grad_norm": 0.5749744176864624,
      "learning_rate": 0.0002,
      "loss": 0.157,
      "step": 4500
    },
    {
      "epoch": 1.7266448564158487,
      "grad_norm": 0.2920248806476593,
      "learning_rate": 0.0002,
      "loss": 0.1582,
      "step": 4750
    },
    {
      "epoch": 1.8175209014903673,
      "grad_norm": 0.9443007111549377,
      "learning_rate": 0.0002,
      "loss": 0.1556,
      "step": 5000
    },
    {
      "epoch": 1.9083969465648853,
      "grad_norm": 0.15055648982524872,
      "learning_rate": 0.0002,
      "loss": 0.1517,
      "step": 5250
    },
    {
      "epoch": 1.9992729916394039,
      "grad_norm": 0.8988580703735352,
      "learning_rate": 0.0002,
      "loss": 0.1499,
      "step": 5500
    },
    {
      "epoch": 2.0901490367139224,
      "grad_norm": 0.508490264415741,
      "learning_rate": 0.0002,
      "loss": 0.1456,
      "step": 5750
    },
    {
      "epoch": 2.1810250817884405,
      "grad_norm": 0.34680867195129395,
      "learning_rate": 0.0002,
      "loss": 0.1461,
      "step": 6000
    },
    {
      "epoch": 2.271901126862959,
      "grad_norm": 0.4722088873386383,
      "learning_rate": 0.0002,
      "loss": 0.1445,
      "step": 6250
    },
    {
      "epoch": 2.362777171937477,
      "grad_norm": 0.23285579681396484,
      "learning_rate": 0.0002,
      "loss": 0.1441,
      "step": 6500
    },
    {
      "epoch": 2.4536532170119956,
      "grad_norm": 0.23250743746757507,
      "learning_rate": 0.0002,
      "loss": 0.1453,
      "step": 6750
    },
    {
      "epoch": 2.544529262086514,
      "grad_norm": 0.556717574596405,
      "learning_rate": 0.0002,
      "loss": 0.1435,
      "step": 7000
    },
    {
      "epoch": 2.635405307161032,
      "grad_norm": 0.5958181619644165,
      "learning_rate": 0.0002,
      "loss": 0.1423,
      "step": 7250
    },
    {
      "epoch": 2.7262813522355507,
      "grad_norm": 0.19208361208438873,
      "learning_rate": 0.0002,
      "loss": 0.1421,
      "step": 7500
    },
    {
      "epoch": 2.817157397310069,
      "grad_norm": 0.16563953459262848,
      "learning_rate": 0.0002,
      "loss": 0.1413,
      "step": 7750
    },
    {
      "epoch": 2.9080334423845873,
      "grad_norm": 0.2165914922952652,
      "learning_rate": 0.0002,
      "loss": 0.1418,
      "step": 8000
    },
    {
      "epoch": 2.998909487459106,
      "grad_norm": 0.19384734332561493,
      "learning_rate": 0.0002,
      "loss": 0.1392,
      "step": 8250
    },
    {
      "epoch": 3.0897855325336243,
      "grad_norm": 0.26262977719306946,
      "learning_rate": 0.0002,
      "loss": 0.1374,
      "step": 8500
    },
    {
      "epoch": 3.1806615776081424,
      "grad_norm": 0.5448735356330872,
      "learning_rate": 0.0002,
      "loss": 0.1377,
      "step": 8750
    },
    {
      "epoch": 3.271537622682661,
      "grad_norm": 1.667397379875183,
      "learning_rate": 0.0002,
      "loss": 0.1363,
      "step": 9000
    },
    {
      "epoch": 3.3624136677571794,
      "grad_norm": 0.3163931965827942,
      "learning_rate": 0.0002,
      "loss": 0.1389,
      "step": 9250
    },
    {
      "epoch": 3.4532897128316975,
      "grad_norm": 0.12541094422340393,
      "learning_rate": 0.0002,
      "loss": 0.1358,
      "step": 9500
    },
    {
      "epoch": 3.544165757906216,
      "grad_norm": 0.2061050981283188,
      "learning_rate": 0.0002,
      "loss": 0.138,
      "step": 9750
    },
    {
      "epoch": 3.6350418029807345,
      "grad_norm": 0.16666942834854126,
      "learning_rate": 0.0002,
      "loss": 0.1376,
      "step": 10000
    },
    {
      "epoch": 3.7259178480552526,
      "grad_norm": 0.1463419646024704,
      "learning_rate": 0.0002,
      "loss": 0.135,
      "step": 10250
    },
    {
      "epoch": 3.816793893129771,
      "grad_norm": 0.5884085297584534,
      "learning_rate": 0.0002,
      "loss": 0.1366,
      "step": 10500
    },
    {
      "epoch": 3.907669938204289,
      "grad_norm": 0.7532073259353638,
      "learning_rate": 0.0002,
      "loss": 0.1354,
      "step": 10750
    },
    {
      "epoch": 3.9985459832788077,
      "grad_norm": 0.26780351996421814,
      "learning_rate": 0.0002,
      "loss": 0.1372,
      "step": 11000
    },
    {
      "epoch": 4.089422028353326,
      "grad_norm": 0.14930292963981628,
      "learning_rate": 0.0002,
      "loss": 0.1316,
      "step": 11250
    },
    {
      "epoch": 4.180298073427845,
      "grad_norm": 0.7845057249069214,
      "learning_rate": 0.0002,
      "loss": 0.1306,
      "step": 11500
    },
    {
      "epoch": 4.271174118502363,
      "grad_norm": 0.17285725474357605,
      "learning_rate": 0.0002,
      "loss": 0.1337,
      "step": 11750
    },
    {
      "epoch": 4.362050163576881,
      "grad_norm": 0.2153194695711136,
      "learning_rate": 0.0002,
      "loss": 0.1316,
      "step": 12000
    },
    {
      "epoch": 4.4529262086514,
      "grad_norm": 0.1834075003862381,
      "learning_rate": 0.0002,
      "loss": 0.1333,
      "step": 12250
    },
    {
      "epoch": 4.543802253725918,
      "grad_norm": 0.24754942953586578,
      "learning_rate": 0.0002,
      "loss": 0.1339,
      "step": 12500
    },
    {
      "epoch": 4.634678298800436,
      "grad_norm": 0.18696901202201843,
      "learning_rate": 0.0002,
      "loss": 0.1343,
      "step": 12750
    },
    {
      "epoch": 4.725554343874954,
      "grad_norm": 0.21711142361164093,
      "learning_rate": 0.0002,
      "loss": 0.1325,
      "step": 13000
    },
    {
      "epoch": 4.816430388949473,
      "grad_norm": 0.21040861308574677,
      "learning_rate": 0.0002,
      "loss": 0.1332,
      "step": 13250
    },
    {
      "epoch": 4.907306434023991,
      "grad_norm": 0.12491606175899506,
      "learning_rate": 0.0002,
      "loss": 0.1318,
      "step": 13500
    },
    {
      "epoch": 4.99818247909851,
      "grad_norm": 0.10389845818281174,
      "learning_rate": 0.0002,
      "loss": 0.1305,
      "step": 13750
    },
    {
      "epoch": 5.089058524173028,
      "grad_norm": 0.20623929798603058,
      "learning_rate": 0.0002,
      "loss": 0.1297,
      "step": 14000
    },
    {
      "epoch": 5.179934569247546,
      "grad_norm": 0.11614017933607101,
      "learning_rate": 0.0002,
      "loss": 0.13,
      "step": 14250
    },
    {
      "epoch": 5.270810614322064,
      "grad_norm": 0.15157075226306915,
      "learning_rate": 0.0002,
      "loss": 0.131,
      "step": 14500
    },
    {
      "epoch": 5.361686659396583,
      "grad_norm": 0.17859354615211487,
      "learning_rate": 0.0002,
      "loss": 0.1314,
      "step": 14750
    },
    {
      "epoch": 5.452562704471101,
      "grad_norm": 0.12577855587005615,
      "learning_rate": 0.0002,
      "loss": 0.1307,
      "step": 15000
    },
    {
      "epoch": 5.543438749545619,
      "grad_norm": 0.1493530571460724,
      "learning_rate": 0.0002,
      "loss": 0.1319,
      "step": 15250
    },
    {
      "epoch": 5.634314794620138,
      "grad_norm": 0.7619848847389221,
      "learning_rate": 0.0002,
      "loss": 0.1306,
      "step": 15500
    },
    {
      "epoch": 5.7251908396946565,
      "grad_norm": 0.1405993402004242,
      "learning_rate": 0.0002,
      "loss": 0.1311,
      "step": 15750
    },
    {
      "epoch": 5.8160668847691745,
      "grad_norm": 0.11307677626609802,
      "learning_rate": 0.0002,
      "loss": 0.1315,
      "step": 16000
    },
    {
      "epoch": 5.9069429298436935,
      "grad_norm": 0.09996064007282257,
      "learning_rate": 0.0002,
      "loss": 0.1315,
      "step": 16250
    },
    {
      "epoch": 5.997818974918212,
      "grad_norm": 0.18245843052864075,
      "learning_rate": 0.0002,
      "loss": 0.1315,
      "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": 2.098309604079698e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}