{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03145949589903,
  "eval_steps": 42,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014980712332871428,
      "eval_loss": 1.160882592201233,
      "eval_runtime": 311.16,
      "eval_samples_per_second": 36.133,
      "eval_steps_per_second": 4.519,
      "step": 1
    },
    {
      "epoch": 0.00044942136998614283,
      "grad_norm": 0.12129199504852295,
      "learning_rate": 1.5e-05,
      "loss": 1.1193,
      "step": 3
    },
    {
      "epoch": 0.0008988427399722857,
      "grad_norm": 0.11971050500869751,
      "learning_rate": 3e-05,
      "loss": 1.103,
      "step": 6
    },
    {
      "epoch": 0.0013482641099584285,
      "grad_norm": 0.10862895101308823,
      "learning_rate": 4.5e-05,
      "loss": 1.0659,
      "step": 9
    },
    {
      "epoch": 0.0017976854799445713,
      "grad_norm": 0.11977853626012802,
      "learning_rate": 4.9997944716957985e-05,
      "loss": 1.0914,
      "step": 12
    },
    {
      "epoch": 0.0022471068499307144,
      "grad_norm": 0.12554779648780823,
      "learning_rate": 4.99871554050172e-05,
      "loss": 1.1725,
      "step": 15
    },
    {
      "epoch": 0.002696528219916857,
      "grad_norm": 0.13287784159183502,
      "learning_rate": 4.996712222958461e-05,
      "loss": 1.1145,
      "step": 18
    },
    {
      "epoch": 0.003145949589903,
      "grad_norm": 0.1167389452457428,
      "learning_rate": 4.993785260182552e-05,
      "loss": 1.0956,
      "step": 21
    },
    {
      "epoch": 0.0035953709598891426,
      "grad_norm": 0.11548212915658951,
      "learning_rate": 4.989935734988098e-05,
      "loss": 1.12,
      "step": 24
    },
    {
      "epoch": 0.004044792329875285,
      "grad_norm": 0.12251826375722885,
      "learning_rate": 4.9851650714862006e-05,
      "loss": 1.0895,
      "step": 27
    },
    {
      "epoch": 0.004494213699861429,
      "grad_norm": 0.12304849177598953,
      "learning_rate": 4.979475034558115e-05,
      "loss": 1.1302,
      "step": 30
    },
    {
      "epoch": 0.004943635069847571,
      "grad_norm": 0.12594439089298248,
      "learning_rate": 4.9728677292023405e-05,
      "loss": 1.0825,
      "step": 33
    },
    {
      "epoch": 0.005393056439833714,
      "grad_norm": 0.11802031844854355,
      "learning_rate": 4.965345599755887e-05,
      "loss": 1.0949,
      "step": 36
    },
    {
      "epoch": 0.005842477809819857,
      "grad_norm": 0.12052260339260101,
      "learning_rate": 4.95691142899001e-05,
      "loss": 1.2106,
      "step": 39
    },
    {
      "epoch": 0.006291899179806,
      "grad_norm": 0.14151117205619812,
      "learning_rate": 4.9475683370807326e-05,
      "loss": 1.0855,
      "step": 42
    },
    {
      "epoch": 0.006291899179806,
      "eval_loss": 1.1297273635864258,
      "eval_runtime": 313.2801,
      "eval_samples_per_second": 35.888,
      "eval_steps_per_second": 4.488,
      "step": 42
    },
    {
      "epoch": 0.006741320549792143,
      "grad_norm": 0.13759616017341614,
      "learning_rate": 4.937319780454559e-05,
      "loss": 1.1133,
      "step": 45
    },
    {
      "epoch": 0.007190741919778285,
      "grad_norm": 0.14887671172618866,
      "learning_rate": 4.926169550509787e-05,
      "loss": 1.1339,
      "step": 48
    },
    {
      "epoch": 0.007640163289764428,
      "grad_norm": 0.13235358893871307,
      "learning_rate": 4.914121772213898e-05,
      "loss": 1.0057,
      "step": 51
    },
    {
      "epoch": 0.00808958465975057,
      "grad_norm": 0.14951473474502563,
      "learning_rate": 4.9011809025775486e-05,
      "loss": 1.0919,
      "step": 54
    },
    {
      "epoch": 0.008539006029736713,
      "grad_norm": 0.1409119963645935,
      "learning_rate": 4.887351729005726e-05,
      "loss": 1.143,
      "step": 57
    },
    {
      "epoch": 0.008988427399722857,
      "grad_norm": 0.13198496401309967,
      "learning_rate": 4.8726393675266716e-05,
      "loss": 1.0853,
      "step": 60
    },
    {
      "epoch": 0.009437848769709,
      "grad_norm": 0.15319645404815674,
      "learning_rate": 4.8570492608992325e-05,
      "loss": 1.0534,
      "step": 63
    },
    {
      "epoch": 0.009887270139695143,
      "grad_norm": 0.1532219797372818,
      "learning_rate": 4.8405871765993433e-05,
      "loss": 1.1016,
      "step": 66
    },
    {
      "epoch": 0.010336691509681285,
      "grad_norm": 0.14198264479637146,
      "learning_rate": 4.82325920468638e-05,
      "loss": 1.029,
      "step": 69
    },
    {
      "epoch": 0.010786112879667428,
      "grad_norm": 0.12415461987257004,
      "learning_rate": 4.805071755550177e-05,
      "loss": 1.1565,
      "step": 72
    },
    {
      "epoch": 0.01123553424965357,
      "grad_norm": 0.1350441873073578,
      "learning_rate": 4.7860315575395316e-05,
      "loss": 1.1276,
      "step": 75
    },
    {
      "epoch": 0.011684955619639713,
      "grad_norm": 0.12075574696063995,
      "learning_rate": 4.766145654473095e-05,
      "loss": 1.0753,
      "step": 78
    },
    {
      "epoch": 0.012134376989625857,
      "grad_norm": 0.11550460755825043,
      "learning_rate": 4.745421403033548e-05,
      "loss": 1.0078,
      "step": 81
    },
    {
      "epoch": 0.012583798359612,
      "grad_norm": 0.12455905228853226,
      "learning_rate": 4.72386647004603e-05,
      "loss": 1.0373,
      "step": 84
    },
    {
      "epoch": 0.012583798359612,
      "eval_loss": 1.1157194375991821,
      "eval_runtime": 312.8234,
      "eval_samples_per_second": 35.94,
      "eval_steps_per_second": 4.495,
      "step": 84
    },
    {
      "epoch": 0.013033219729598143,
      "grad_norm": 0.12993893027305603,
      "learning_rate": 4.701488829641845e-05,
      "loss": 1.1313,
      "step": 87
    },
    {
      "epoch": 0.013482641099584285,
      "grad_norm": 0.18705669045448303,
      "learning_rate": 4.678296760308474e-05,
      "loss": 1.2752,
      "step": 90
    },
    {
      "epoch": 0.013932062469570428,
      "grad_norm": 0.14135660231113434,
      "learning_rate": 4.6542988418269876e-05,
      "loss": 1.1628,
      "step": 93
    },
    {
      "epoch": 0.01438148383955657,
      "grad_norm": 0.11707276850938797,
      "learning_rate": 4.629503952098011e-05,
      "loss": 1.0801,
      "step": 96
    },
    {
      "epoch": 0.014830905209542713,
      "grad_norm": 0.14167702198028564,
      "learning_rate": 4.6039212638573833e-05,
      "loss": 1.0452,
      "step": 99
    },
    {
      "epoch": 0.015280326579528856,
      "grad_norm": 0.15983764827251434,
      "learning_rate": 4.5775602412827604e-05,
      "loss": 1.1844,
      "step": 102
    },
    {
      "epoch": 0.015729747949515,
      "grad_norm": 0.12750358879566193,
      "learning_rate": 4.55043063649239e-05,
      "loss": 1.0877,
      "step": 105
    },
    {
      "epoch": 0.01617916931950114,
      "grad_norm": 0.1487520933151245,
      "learning_rate": 4.522542485937369e-05,
      "loss": 1.1373,
      "step": 108
    },
    {
      "epoch": 0.016628590689487285,
      "grad_norm": 0.16089919209480286,
      "learning_rate": 4.493906106688712e-05,
      "loss": 1.1806,
      "step": 111
    },
    {
      "epoch": 0.017078012059473426,
      "grad_norm": 0.158865287899971,
      "learning_rate": 4.4645320926206064e-05,
      "loss": 1.0689,
      "step": 114
    },
    {
      "epoch": 0.01752743342945957,
      "grad_norm": 0.16464003920555115,
      "learning_rate": 4.434431310491267e-05,
      "loss": 1.1319,
      "step": 117
    },
    {
      "epoch": 0.017976854799445715,
      "grad_norm": 0.12468679249286652,
      "learning_rate": 4.4036148959228365e-05,
      "loss": 1.0237,
      "step": 120
    },
    {
      "epoch": 0.018426276169431856,
      "grad_norm": 0.14475342631340027,
      "learning_rate": 4.372094249281821e-05,
      "loss": 1.1352,
      "step": 123
    },
    {
      "epoch": 0.018875697539418,
      "grad_norm": 0.1386341154575348,
      "learning_rate": 4.3398810314615876e-05,
      "loss": 1.177,
      "step": 126
    },
    {
      "epoch": 0.018875697539418,
      "eval_loss": 1.1068843603134155,
      "eval_runtime": 312.5635,
      "eval_samples_per_second": 35.97,
      "eval_steps_per_second": 4.498,
      "step": 126
    },
    {
      "epoch": 0.01932511890940414,
      "grad_norm": 0.13838274776935577,
      "learning_rate": 4.306987159568479e-05,
      "loss": 0.9996,
      "step": 129
    },
    {
      "epoch": 0.019774540279390285,
      "grad_norm": 0.14386090636253357,
      "learning_rate": 4.273424802513145e-05,
      "loss": 0.9947,
      "step": 132
    },
    {
      "epoch": 0.020223961649376426,
      "grad_norm": 0.14473505318164825,
      "learning_rate": 4.239206376508717e-05,
      "loss": 1.1779,
      "step": 135
    },
    {
      "epoch": 0.02067338301936257,
      "grad_norm": 0.15975573658943176,
      "learning_rate": 4.204344540477499e-05,
      "loss": 1.2125,
      "step": 138
    },
    {
      "epoch": 0.021122804389348715,
      "grad_norm": 0.12576735019683838,
      "learning_rate": 4.16885219136787e-05,
      "loss": 1.1312,
      "step": 141
    },
    {
      "epoch": 0.021572225759334856,
      "grad_norm": 0.16916967928409576,
      "learning_rate": 4.132742459383122e-05,
      "loss": 1.0823,
      "step": 144
    },
    {
      "epoch": 0.022021647129321,
      "grad_norm": 0.17954471707344055,
      "learning_rate": 4.096028703124014e-05,
      "loss": 1.0728,
      "step": 147
    },
    {
      "epoch": 0.02247106849930714,
      "grad_norm": 0.11972087621688843,
      "learning_rate": 4.058724504646834e-05,
      "loss": 1.0886,
      "step": 150
    },
    {
      "epoch": 0.022920489869293285,
      "grad_norm": 0.14640676975250244,
      "learning_rate": 4.0208436644387834e-05,
      "loss": 1.0472,
      "step": 153
    },
    {
      "epoch": 0.023369911239279426,
      "grad_norm": 0.13775284588336945,
      "learning_rate": 3.982400196312564e-05,
      "loss": 1.0984,
      "step": 156
    },
    {
      "epoch": 0.02381933260926557,
      "grad_norm": 0.14184071123600006,
      "learning_rate": 3.943408322222049e-05,
      "loss": 1.1431,
      "step": 159
    },
    {
      "epoch": 0.024268753979251715,
      "grad_norm": 0.1685701608657837,
      "learning_rate": 3.903882467000937e-05,
      "loss": 1.1531,
      "step": 162
    },
    {
      "epoch": 0.024718175349237856,
      "grad_norm": 0.1468999981880188,
      "learning_rate": 3.8638372530263715e-05,
      "loss": 1.1069,
      "step": 165
    },
    {
      "epoch": 0.025167596719224,
      "grad_norm": 0.13278649747371674,
      "learning_rate": 3.823287494809469e-05,
      "loss": 1.1124,
      "step": 168
    },
    {
      "epoch": 0.025167596719224,
      "eval_loss": 1.1012423038482666,
      "eval_runtime": 312.1008,
      "eval_samples_per_second": 36.024,
      "eval_steps_per_second": 4.505,
      "step": 168
    },
    {
      "epoch": 0.02561701808921014,
      "grad_norm": 0.180728018283844,
      "learning_rate": 3.782248193514766e-05,
      "loss": 1.0867,
      "step": 171
    },
    {
      "epoch": 0.026066439459196285,
      "grad_norm": 0.15069565176963806,
      "learning_rate": 3.740734531410626e-05,
      "loss": 1.0624,
      "step": 174
    },
    {
      "epoch": 0.026515860829182426,
      "grad_norm": 0.13892242312431335,
      "learning_rate": 3.698761866252635e-05,
      "loss": 1.0351,
      "step": 177
    },
    {
      "epoch": 0.02696528219916857,
      "grad_norm": 0.1399199515581131,
      "learning_rate": 3.656345725602089e-05,
      "loss": 1.1609,
      "step": 180
    },
    {
      "epoch": 0.027414703569154715,
      "grad_norm": 0.14930486679077148,
      "learning_rate": 3.6135018010816477e-05,
      "loss": 1.1117,
      "step": 183
    },
    {
      "epoch": 0.027864124939140856,
      "grad_norm": 0.15556196868419647,
      "learning_rate": 3.570245942570315e-05,
      "loss": 1.1169,
      "step": 186
    },
    {
      "epoch": 0.028313546309127,
      "grad_norm": 0.17272590100765228,
      "learning_rate": 3.526594152339845e-05,
      "loss": 1.115,
      "step": 189
    },
    {
      "epoch": 0.02876296767911314,
      "grad_norm": 0.17533355951309204,
      "learning_rate": 3.4825625791348096e-05,
      "loss": 1.1298,
      "step": 192
    },
    {
      "epoch": 0.029212389049099285,
      "grad_norm": 0.14778710901737213,
      "learning_rate": 3.438167512198436e-05,
      "loss": 1.1183,
      "step": 195
    },
    {
      "epoch": 0.029661810419085426,
      "grad_norm": 0.14693984389305115,
      "learning_rate": 3.393425375246503e-05,
      "loss": 1.0647,
      "step": 198
    },
    {
      "epoch": 0.03011123178907157,
      "grad_norm": 0.14994005858898163,
      "learning_rate": 3.348352720391469e-05,
      "loss": 1.0008,
      "step": 201
    },
    {
      "epoch": 0.03056065315905771,
      "grad_norm": 0.1611510068178177,
      "learning_rate": 3.3029662220191144e-05,
      "loss": 1.094,
      "step": 204
    },
    {
      "epoch": 0.031010074529043856,
      "grad_norm": 0.19615799188613892,
      "learning_rate": 3.2572826706199305e-05,
      "loss": 1.051,
      "step": 207
    },
    {
      "epoch": 0.03145949589903,
      "grad_norm": 0.15789468586444855,
      "learning_rate": 3.211318966577581e-05,
      "loss": 1.0302,
      "step": 210
    },
    {
      "epoch": 0.03145949589903,
      "eval_loss": 1.0971506834030151,
      "eval_runtime": 312.684,
      "eval_samples_per_second": 35.956,
      "eval_steps_per_second": 4.497,
      "step": 210
    }
  ],
  "logging_steps": 3,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 42,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.724628513606861e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}