{
  "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": 0.8166529536247253,
      "learning_rate": 0.0002,
      "loss": 0.8718,
      "step": 250
    },
    {
      "epoch": 0.1817520901490367,
      "grad_norm": 0.8011488914489746,
      "learning_rate": 0.0002,
      "loss": 0.5089,
      "step": 500
    },
    {
      "epoch": 0.27262813522355506,
      "grad_norm": 0.8325187563896179,
      "learning_rate": 0.0002,
      "loss": 0.3852,
      "step": 750
    },
    {
      "epoch": 0.3635041802980734,
      "grad_norm": 1.6889874935150146,
      "learning_rate": 0.0002,
      "loss": 0.3127,
      "step": 1000
    },
    {
      "epoch": 0.45438022537259176,
      "grad_norm": 0.6524374485015869,
      "learning_rate": 0.0002,
      "loss": 0.2749,
      "step": 1250
    },
    {
      "epoch": 0.5452562704471101,
      "grad_norm": 0.8681249022483826,
      "learning_rate": 0.0002,
      "loss": 0.2379,
      "step": 1500
    },
    {
      "epoch": 0.6361323155216285,
      "grad_norm": 0.9492128491401672,
      "learning_rate": 0.0002,
      "loss": 0.2204,
      "step": 1750
    },
    {
      "epoch": 0.7270083605961468,
      "grad_norm": 0.35517942905426025,
      "learning_rate": 0.0002,
      "loss": 0.2017,
      "step": 2000
    },
    {
      "epoch": 0.8178844056706652,
      "grad_norm": 0.5566073060035706,
      "learning_rate": 0.0002,
      "loss": 0.1898,
      "step": 2250
    },
    {
      "epoch": 0.9087604507451835,
      "grad_norm": 0.23202739655971527,
      "learning_rate": 0.0002,
      "loss": 0.1788,
      "step": 2500
    },
    {
      "epoch": 0.9996364958197019,
      "grad_norm": 0.4493115246295929,
      "learning_rate": 0.0002,
      "loss": 0.1736,
      "step": 2750
    },
    {
      "epoch": 1.0905125408942202,
      "grad_norm": 0.41077283024787903,
      "learning_rate": 0.0002,
      "loss": 0.1647,
      "step": 3000
    },
    {
      "epoch": 1.1813885859687385,
      "grad_norm": 0.24447296559810638,
      "learning_rate": 0.0002,
      "loss": 0.1598,
      "step": 3250
    },
    {
      "epoch": 1.272264631043257,
      "grad_norm": 0.3004068434238434,
      "learning_rate": 0.0002,
      "loss": 0.1594,
      "step": 3500
    },
    {
      "epoch": 1.3631406761177753,
      "grad_norm": 0.20352505147457123,
      "learning_rate": 0.0002,
      "loss": 0.1554,
      "step": 3750
    },
    {
      "epoch": 1.4540167211922936,
      "grad_norm": 0.2659279704093933,
      "learning_rate": 0.0002,
      "loss": 0.1502,
      "step": 4000
    },
    {
      "epoch": 1.5448927662668122,
      "grad_norm": 0.616990327835083,
      "learning_rate": 0.0002,
      "loss": 0.1485,
      "step": 4250
    },
    {
      "epoch": 1.6357688113413305,
      "grad_norm": 0.1787092685699463,
      "learning_rate": 0.0002,
      "loss": 0.1465,
      "step": 4500
    },
    {
      "epoch": 1.7266448564158487,
      "grad_norm": 0.26382288336753845,
      "learning_rate": 0.0002,
      "loss": 0.1452,
      "step": 4750
    },
    {
      "epoch": 1.8175209014903673,
      "grad_norm": 0.22121331095695496,
      "learning_rate": 0.0002,
      "loss": 0.1429,
      "step": 5000
    },
    {
      "epoch": 1.9083969465648853,
      "grad_norm": 0.23968210816383362,
      "learning_rate": 0.0002,
      "loss": 0.1415,
      "step": 5250
    },
    {
      "epoch": 1.9992729916394039,
      "grad_norm": 0.20464320480823517,
      "learning_rate": 0.0002,
      "loss": 0.1392,
      "step": 5500
    },
    {
      "epoch": 2.0901490367139224,
      "grad_norm": 0.23473434150218964,
      "learning_rate": 0.0002,
      "loss": 0.1363,
      "step": 5750
    },
    {
      "epoch": 2.1810250817884405,
      "grad_norm": 0.3769285976886749,
      "learning_rate": 0.0002,
      "loss": 0.1373,
      "step": 6000
    },
    {
      "epoch": 2.271901126862959,
      "grad_norm": 0.11411458998918533,
      "learning_rate": 0.0002,
      "loss": 0.1355,
      "step": 6250
    },
    {
      "epoch": 2.362777171937477,
      "grad_norm": 0.14283251762390137,
      "learning_rate": 0.0002,
      "loss": 0.1351,
      "step": 6500
    },
    {
      "epoch": 2.4536532170119956,
      "grad_norm": 0.1278432458639145,
      "learning_rate": 0.0002,
      "loss": 0.1344,
      "step": 6750
    },
    {
      "epoch": 2.544529262086514,
      "grad_norm": 0.1538127213716507,
      "learning_rate": 0.0002,
      "loss": 0.1351,
      "step": 7000
    },
    {
      "epoch": 2.635405307161032,
      "grad_norm": 0.1636444330215454,
      "learning_rate": 0.0002,
      "loss": 0.1341,
      "step": 7250
    },
    {
      "epoch": 2.7262813522355507,
      "grad_norm": 0.23468904197216034,
      "learning_rate": 0.0002,
      "loss": 0.1343,
      "step": 7500
    },
    {
      "epoch": 2.817157397310069,
      "grad_norm": 0.34467971324920654,
      "learning_rate": 0.0002,
      "loss": 0.1342,
      "step": 7750
    },
    {
      "epoch": 2.9080334423845873,
      "grad_norm": 0.15800316631793976,
      "learning_rate": 0.0002,
      "loss": 0.1331,
      "step": 8000
    },
    {
      "epoch": 2.998909487459106,
      "grad_norm": 0.18056762218475342,
      "learning_rate": 0.0002,
      "loss": 0.1324,
      "step": 8250
    },
    {
      "epoch": 3.0897855325336243,
      "grad_norm": 0.12928904592990875,
      "learning_rate": 0.0002,
      "loss": 0.1301,
      "step": 8500
    },
    {
      "epoch": 3.1806615776081424,
      "grad_norm": 0.10186909139156342,
      "learning_rate": 0.0002,
      "loss": 0.1299,
      "step": 8750
    },
    {
      "epoch": 3.271537622682661,
      "grad_norm": 0.1294797658920288,
      "learning_rate": 0.0002,
      "loss": 0.1311,
      "step": 9000
    },
    {
      "epoch": 3.3624136677571794,
      "grad_norm": 0.96567702293396,
      "learning_rate": 0.0002,
      "loss": 0.1292,
      "step": 9250
    },
    {
      "epoch": 3.4532897128316975,
      "grad_norm": 0.7819355130195618,
      "learning_rate": 0.0002,
      "loss": 0.1289,
      "step": 9500
    },
    {
      "epoch": 3.544165757906216,
      "grad_norm": 0.19112642109394073,
      "learning_rate": 0.0002,
      "loss": 0.1305,
      "step": 9750
    },
    {
      "epoch": 3.6350418029807345,
      "grad_norm": 0.09955710917711258,
      "learning_rate": 0.0002,
      "loss": 0.1298,
      "step": 10000
    },
    {
      "epoch": 3.7259178480552526,
      "grad_norm": 0.13611435890197754,
      "learning_rate": 0.0002,
      "loss": 0.1286,
      "step": 10250
    },
    {
      "epoch": 3.816793893129771,
      "grad_norm": 0.11884398013353348,
      "learning_rate": 0.0002,
      "loss": 0.1307,
      "step": 10500
    },
    {
      "epoch": 3.907669938204289,
      "grad_norm": 0.1615493893623352,
      "learning_rate": 0.0002,
      "loss": 0.1284,
      "step": 10750
    },
    {
      "epoch": 3.9985459832788077,
      "grad_norm": 0.31517332792282104,
      "learning_rate": 0.0002,
      "loss": 0.1291,
      "step": 11000
    },
    {
      "epoch": 4.089422028353326,
      "grad_norm": 0.6462264060974121,
      "learning_rate": 0.0002,
      "loss": 0.1276,
      "step": 11250
    },
    {
      "epoch": 4.180298073427845,
      "grad_norm": 0.09960414469242096,
      "learning_rate": 0.0002,
      "loss": 0.1265,
      "step": 11500
    },
    {
      "epoch": 4.271174118502363,
      "grad_norm": 0.09911854565143585,
      "learning_rate": 0.0002,
      "loss": 0.1286,
      "step": 11750
    },
    {
      "epoch": 4.362050163576881,
      "grad_norm": 0.12108103185892105,
      "learning_rate": 0.0002,
      "loss": 0.1282,
      "step": 12000
    },
    {
      "epoch": 4.4529262086514,
      "grad_norm": 0.09403906762599945,
      "learning_rate": 0.0002,
      "loss": 0.1277,
      "step": 12250
    },
    {
      "epoch": 4.543802253725918,
      "grad_norm": 0.12478747963905334,
      "learning_rate": 0.0002,
      "loss": 0.1294,
      "step": 12500
    },
    {
      "epoch": 4.634678298800436,
      "grad_norm": 0.5839309692382812,
      "learning_rate": 0.0002,
      "loss": 0.128,
      "step": 12750
    },
    {
      "epoch": 4.725554343874954,
      "grad_norm": 0.0925154760479927,
      "learning_rate": 0.0002,
      "loss": 0.1278,
      "step": 13000
    },
    {
      "epoch": 4.816430388949473,
      "grad_norm": 0.09721515327692032,
      "learning_rate": 0.0002,
      "loss": 0.1243,
      "step": 13250
    },
    {
      "epoch": 4.907306434023991,
      "grad_norm": 0.11027718335390091,
      "learning_rate": 0.0002,
      "loss": 0.1264,
      "step": 13500
    },
    {
      "epoch": 4.99818247909851,
      "grad_norm": 0.24596811830997467,
      "learning_rate": 0.0002,
      "loss": 0.1247,
      "step": 13750
    },
    {
      "epoch": 5.089058524173028,
      "grad_norm": 0.3751857876777649,
      "learning_rate": 0.0002,
      "loss": 0.1244,
      "step": 14000
    },
    {
      "epoch": 5.179934569247546,
      "grad_norm": 0.0758715569972992,
      "learning_rate": 0.0002,
      "loss": 0.1235,
      "step": 14250
    },
    {
      "epoch": 5.270810614322064,
      "grad_norm": 0.10280770063400269,
      "learning_rate": 0.0002,
      "loss": 0.1263,
      "step": 14500
    },
    {
      "epoch": 5.361686659396583,
      "grad_norm": 0.10937105864286423,
      "learning_rate": 0.0002,
      "loss": 0.1247,
      "step": 14750
    },
    {
      "epoch": 5.452562704471101,
      "grad_norm": 0.10805700719356537,
      "learning_rate": 0.0002,
      "loss": 0.1257,
      "step": 15000
    },
    {
      "epoch": 5.543438749545619,
      "grad_norm": 0.1117258295416832,
      "learning_rate": 0.0002,
      "loss": 0.1289,
      "step": 15250
    },
    {
      "epoch": 5.634314794620138,
      "grad_norm": 0.08629261702299118,
      "learning_rate": 0.0002,
      "loss": 0.1258,
      "step": 15500
    },
    {
      "epoch": 5.7251908396946565,
      "grad_norm": 0.10845168679952621,
      "learning_rate": 0.0002,
      "loss": 0.1259,
      "step": 15750
    },
    {
      "epoch": 5.8160668847691745,
      "grad_norm": 0.08773403614759445,
      "learning_rate": 0.0002,
      "loss": 0.1255,
      "step": 16000
    },
    {
      "epoch": 5.9069429298436935,
      "grad_norm": 0.08745443820953369,
      "learning_rate": 0.0002,
      "loss": 0.1268,
      "step": 16250
    },
    {
      "epoch": 5.997818974918212,
      "grad_norm": 0.29043182730674744,
      "learning_rate": 0.0002,
      "loss": 0.1253,
      "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": 2.32857340165632e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}