{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.997818974918212,
  "eval_steps": 500,
  "global_step": 16500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09087604507451835,
      "grad_norm": 0.4654020667076111,
      "learning_rate": 0.0002,
      "loss": 0.8096,
      "step": 250
    },
    {
      "epoch": 0.1817520901490367,
      "grad_norm": 0.41708114743232727,
      "learning_rate": 0.0002,
      "loss": 0.4755,
      "step": 500
    },
    {
      "epoch": 0.27262813522355506,
      "grad_norm": 0.3150986433029175,
      "learning_rate": 0.0002,
      "loss": 0.3592,
      "step": 750
    },
    {
      "epoch": 0.3635041802980734,
      "grad_norm": 0.47795307636260986,
      "learning_rate": 0.0002,
      "loss": 0.2929,
      "step": 1000
    },
    {
      "epoch": 0.45438022537259176,
      "grad_norm": 0.651059627532959,
      "learning_rate": 0.0002,
      "loss": 0.2592,
      "step": 1250
    },
    {
      "epoch": 0.5452562704471101,
      "grad_norm": 0.5213909149169922,
      "learning_rate": 0.0002,
      "loss": 0.2223,
      "step": 1500
    },
    {
      "epoch": 0.6361323155216285,
      "grad_norm": 0.4708111584186554,
      "learning_rate": 0.0002,
      "loss": 0.2045,
      "step": 1750
    },
    {
      "epoch": 0.7270083605961468,
      "grad_norm": 0.561016857624054,
      "learning_rate": 0.0002,
      "loss": 0.1853,
      "step": 2000
    },
    {
      "epoch": 0.8178844056706652,
      "grad_norm": 0.5329756736755371,
      "learning_rate": 0.0002,
      "loss": 0.1719,
      "step": 2250
    },
    {
      "epoch": 0.9087604507451835,
      "grad_norm": 0.3244706690311432,
      "learning_rate": 0.0002,
      "loss": 0.1642,
      "step": 2500
    },
    {
      "epoch": 0.9996364958197019,
      "grad_norm": 0.2593044340610504,
      "learning_rate": 0.0002,
      "loss": 0.157,
      "step": 2750
    },
    {
      "epoch": 1.0905125408942202,
      "grad_norm": 0.31555283069610596,
      "learning_rate": 0.0002,
      "loss": 0.1464,
      "step": 3000
    },
    {
      "epoch": 1.1813885859687385,
      "grad_norm": 0.25025439262390137,
      "learning_rate": 0.0002,
      "loss": 0.1439,
      "step": 3250
    },
    {
      "epoch": 1.272264631043257,
      "grad_norm": 0.23437458276748657,
      "learning_rate": 0.0002,
      "loss": 0.1438,
      "step": 3500
    },
    {
      "epoch": 1.3631406761177753,
      "grad_norm": 0.21112729609012604,
      "learning_rate": 0.0002,
      "loss": 0.14,
      "step": 3750
    },
    {
      "epoch": 1.4540167211922936,
      "grad_norm": 0.3934556543827057,
      "learning_rate": 0.0002,
      "loss": 0.1368,
      "step": 4000
    },
    {
      "epoch": 1.5448927662668122,
      "grad_norm": 0.14472702145576477,
      "learning_rate": 0.0002,
      "loss": 0.1362,
      "step": 4250
    },
    {
      "epoch": 1.6357688113413305,
      "grad_norm": 0.23997043073177338,
      "learning_rate": 0.0002,
      "loss": 0.1339,
      "step": 4500
    },
    {
      "epoch": 1.7266448564158487,
      "grad_norm": 0.23854462802410126,
      "learning_rate": 0.0002,
      "loss": 0.1336,
      "step": 4750
    },
    {
      "epoch": 1.8175209014903673,
      "grad_norm": 0.5907264351844788,
      "learning_rate": 0.0002,
      "loss": 0.1299,
      "step": 5000
    },
    {
      "epoch": 1.9083969465648853,
      "grad_norm": 0.27979758381843567,
      "learning_rate": 0.0002,
      "loss": 0.1296,
      "step": 5250
    },
    {
      "epoch": 1.9992729916394039,
      "grad_norm": 0.24399316310882568,
      "learning_rate": 0.0002,
      "loss": 0.1287,
      "step": 5500
    },
    {
      "epoch": 2.0901490367139224,
      "grad_norm": 0.21489912271499634,
      "learning_rate": 0.0002,
      "loss": 0.1257,
      "step": 5750
    },
    {
      "epoch": 2.1810250817884405,
      "grad_norm": 0.12766550481319427,
      "learning_rate": 0.0002,
      "loss": 0.1256,
      "step": 6000
    },
    {
      "epoch": 2.271901126862959,
      "grad_norm": 0.14542394876480103,
      "learning_rate": 0.0002,
      "loss": 0.1267,
      "step": 6250
    },
    {
      "epoch": 2.362777171937477,
      "grad_norm": 0.1510189026594162,
      "learning_rate": 0.0002,
      "loss": 0.1245,
      "step": 6500
    },
    {
      "epoch": 2.4536532170119956,
      "grad_norm": 0.12327288836240768,
      "learning_rate": 0.0002,
      "loss": 0.1261,
      "step": 6750
    },
    {
      "epoch": 2.544529262086514,
      "grad_norm": 0.14996737241744995,
      "learning_rate": 0.0002,
      "loss": 0.1263,
      "step": 7000
    },
    {
      "epoch": 2.635405307161032,
      "grad_norm": 0.18016500771045685,
      "learning_rate": 0.0002,
      "loss": 0.123,
      "step": 7250
    },
    {
      "epoch": 2.7262813522355507,
      "grad_norm": 0.16049741208553314,
      "learning_rate": 0.0002,
      "loss": 0.1235,
      "step": 7500
    },
    {
      "epoch": 2.817157397310069,
      "grad_norm": 0.1264464259147644,
      "learning_rate": 0.0002,
      "loss": 0.1232,
      "step": 7750
    },
    {
      "epoch": 2.9080334423845873,
      "grad_norm": 0.12362770736217499,
      "learning_rate": 0.0002,
      "loss": 0.1217,
      "step": 8000
    },
    {
      "epoch": 2.998909487459106,
      "grad_norm": 0.15321820974349976,
      "learning_rate": 0.0002,
      "loss": 0.1198,
      "step": 8250
    },
    {
      "epoch": 3.0897855325336243,
      "grad_norm": 0.10053068399429321,
      "learning_rate": 0.0002,
      "loss": 0.1202,
      "step": 8500
    },
    {
      "epoch": 3.1806615776081424,
      "grad_norm": 0.10968466848134995,
      "learning_rate": 0.0002,
      "loss": 0.1215,
      "step": 8750
    },
    {
      "epoch": 3.271537622682661,
      "grad_norm": 0.1432497352361679,
      "learning_rate": 0.0002,
      "loss": 0.1232,
      "step": 9000
    },
    {
      "epoch": 3.3624136677571794,
      "grad_norm": 0.12788109481334686,
      "learning_rate": 0.0002,
      "loss": 0.1215,
      "step": 9250
    },
    {
      "epoch": 3.4532897128316975,
      "grad_norm": 0.17011073231697083,
      "learning_rate": 0.0002,
      "loss": 0.1201,
      "step": 9500
    },
    {
      "epoch": 3.544165757906216,
      "grad_norm": 0.10264500230550766,
      "learning_rate": 0.0002,
      "loss": 0.1201,
      "step": 9750
    },
    {
      "epoch": 3.6350418029807345,
      "grad_norm": 0.12648449838161469,
      "learning_rate": 0.0002,
      "loss": 0.1196,
      "step": 10000
    },
    {
      "epoch": 3.7259178480552526,
      "grad_norm": 0.1576431840658188,
      "learning_rate": 0.0002,
      "loss": 0.1202,
      "step": 10250
    },
    {
      "epoch": 3.816793893129771,
      "grad_norm": 0.12325482070446014,
      "learning_rate": 0.0002,
      "loss": 0.1191,
      "step": 10500
    },
    {
      "epoch": 3.907669938204289,
      "grad_norm": 0.11772935837507248,
      "learning_rate": 0.0002,
      "loss": 0.1192,
      "step": 10750
    },
    {
      "epoch": 3.9985459832788077,
      "grad_norm": 0.10845024138689041,
      "learning_rate": 0.0002,
      "loss": 0.1196,
      "step": 11000
    },
    {
      "epoch": 4.089422028353326,
      "grad_norm": 0.3801882863044739,
      "learning_rate": 0.0002,
      "loss": 0.1189,
      "step": 11250
    },
    {
      "epoch": 4.180298073427845,
      "grad_norm": 0.07644908130168915,
      "learning_rate": 0.0002,
      "loss": 0.1174,
      "step": 11500
    },
    {
      "epoch": 4.271174118502363,
      "grad_norm": 0.13238635659217834,
      "learning_rate": 0.0002,
      "loss": 0.1183,
      "step": 11750
    },
    {
      "epoch": 4.362050163576881,
      "grad_norm": 0.08820691704750061,
      "learning_rate": 0.0002,
      "loss": 0.1165,
      "step": 12000
    },
    {
      "epoch": 4.4529262086514,
      "grad_norm": 0.17560935020446777,
      "learning_rate": 0.0002,
      "loss": 0.1162,
      "step": 12250
    },
    {
      "epoch": 4.543802253725918,
      "grad_norm": 0.14411073923110962,
      "learning_rate": 0.0002,
      "loss": 0.117,
      "step": 12500
    },
    {
      "epoch": 4.634678298800436,
      "grad_norm": 0.3563734292984009,
      "learning_rate": 0.0002,
      "loss": 0.1187,
      "step": 12750
    },
    {
      "epoch": 4.725554343874954,
      "grad_norm": 0.09806593507528305,
      "learning_rate": 0.0002,
      "loss": 0.12,
      "step": 13000
    },
    {
      "epoch": 4.816430388949473,
      "grad_norm": 0.1437559872865677,
      "learning_rate": 0.0002,
      "loss": 0.1188,
      "step": 13250
    },
    {
      "epoch": 4.907306434023991,
      "grad_norm": 0.12213843315839767,
      "learning_rate": 0.0002,
      "loss": 0.1168,
      "step": 13500
    },
    {
      "epoch": 4.99818247909851,
      "grad_norm": 0.0951525866985321,
      "learning_rate": 0.0002,
      "loss": 0.1168,
      "step": 13750
    },
    {
      "epoch": 5.089058524173028,
      "grad_norm": 0.09333384782075882,
      "learning_rate": 0.0002,
      "loss": 0.1132,
      "step": 14000
    },
    {
      "epoch": 5.179934569247546,
      "grad_norm": 0.07788410037755966,
      "learning_rate": 0.0002,
      "loss": 0.1158,
      "step": 14250
    },
    {
      "epoch": 5.270810614322064,
      "grad_norm": 0.09322191029787064,
      "learning_rate": 0.0002,
      "loss": 0.1151,
      "step": 14500
    },
    {
      "epoch": 5.361686659396583,
      "grad_norm": 0.08279828727245331,
      "learning_rate": 0.0002,
      "loss": 0.1157,
      "step": 14750
    },
    {
      "epoch": 5.452562704471101,
      "grad_norm": 0.0820227861404419,
      "learning_rate": 0.0002,
      "loss": 0.1145,
      "step": 15000
    },
    {
      "epoch": 5.543438749545619,
      "grad_norm": 0.0850677341222763,
      "learning_rate": 0.0002,
      "loss": 0.1164,
      "step": 15250
    },
    {
      "epoch": 5.634314794620138,
      "grad_norm": 0.09393496066331863,
      "learning_rate": 0.0002,
      "loss": 0.1168,
      "step": 15500
    },
    {
      "epoch": 5.7251908396946565,
      "grad_norm": 0.1881243884563446,
      "learning_rate": 0.0002,
      "loss": 0.12,
      "step": 15750
    },
    {
      "epoch": 5.8160668847691745,
      "grad_norm": 0.10050614923238754,
      "learning_rate": 0.0002,
      "loss": 0.1178,
      "step": 16000
    },
    {
      "epoch": 5.9069429298436935,
      "grad_norm": 0.0783284604549408,
      "learning_rate": 0.0002,
      "loss": 0.1156,
      "step": 16250
    },
    {
      "epoch": 5.997818974918212,
      "grad_norm": 0.06173411011695862,
      "learning_rate": 0.0002,
      "loss": 0.1158,
      "step": 16500
    }
  ],
  "logging_steps": 250,
  "max_steps": 16506,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 250,
  "total_flos": 2.0307058697581363e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}