{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.5556383771696307,
  "global_step": 120000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 3.5494977460689314e-07,
      "loss": 106.7756,
      "step": 500
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.098995492137863e-07,
      "loss": 55.928,
      "step": 1000
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.0648493238206793e-06,
      "loss": 25.6157,
      "step": 1500
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.4197990984275725e-06,
      "loss": 13.8842,
      "step": 2000
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.7747488730344656e-06,
      "loss": 8.5782,
      "step": 2500
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.1296986476413585e-06,
      "loss": 5.295,
      "step": 3000
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.484648422248252e-06,
      "loss": 4.1387,
      "step": 3500
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.839598196855145e-06,
      "loss": 3.7483,
      "step": 4000
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.1945479714620384e-06,
      "loss": 3.5894,
      "step": 4500
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.5494977460689313e-06,
      "loss": 3.5092,
      "step": 5000
    },
    {
      "epoch": 0.11,
      "eval_loss": 3.413250684738159,
      "eval_runtime": 1854.1371,
      "eval_samples_per_second": 83.756,
      "eval_steps_per_second": 2.617,
      "step": 5000
    },
    {
      "epoch": 0.12,
      "learning_rate": 3.9044475206758246e-06,
      "loss": 3.4366,
      "step": 5500
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.259397295282717e-06,
      "loss": 3.3932,
      "step": 6000
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.614347069889611e-06,
      "loss": 3.3452,
      "step": 6500
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.969296844496504e-06,
      "loss": 3.3191,
      "step": 7000
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.324246619103397e-06,
      "loss": 3.386,
      "step": 7500
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.67919639371029e-06,
      "loss": 3.3067,
      "step": 8000
    },
    {
      "epoch": 0.18,
      "learning_rate": 6.0341461683171835e-06,
      "loss": 3.101,
      "step": 8500
    },
    {
      "epoch": 0.19,
      "learning_rate": 6.389095942924077e-06,
      "loss": 3.0029,
      "step": 9000
    },
    {
      "epoch": 0.2,
      "learning_rate": 6.744045717530969e-06,
      "loss": 2.8389,
      "step": 9500
    },
    {
      "epoch": 0.21,
      "learning_rate": 7.0989954921378625e-06,
      "loss": 2.7564,
      "step": 10000
    },
    {
      "epoch": 0.21,
      "eval_loss": 3.15372633934021,
      "eval_runtime": 1844.2363,
      "eval_samples_per_second": 84.206,
      "eval_steps_per_second": 2.631,
      "step": 10000
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.453945266744757e-06,
      "loss": 2.7356,
      "step": 10500
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.808895041351649e-06,
      "loss": 2.7274,
      "step": 11000
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.163844815958542e-06,
      "loss": 2.6345,
      "step": 11500
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.518794590565434e-06,
      "loss": 2.811,
      "step": 12000
    },
    {
      "epoch": 0.27,
      "learning_rate": 8.873744365172329e-06,
      "loss": 3.1051,
      "step": 12500
    },
    {
      "epoch": 0.28,
      "learning_rate": 9.228694139779222e-06,
      "loss": 3.177,
      "step": 13000
    },
    {
      "epoch": 0.29,
      "learning_rate": 9.583643914386114e-06,
      "loss": 3.1396,
      "step": 13500
    },
    {
      "epoch": 0.3,
      "learning_rate": 9.938593688993007e-06,
      "loss": 3.1375,
      "step": 14000
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.0293543463599902e-05,
      "loss": 3.1084,
      "step": 14500
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.0648493238206794e-05,
      "loss": 3.0979,
      "step": 15000
    },
    {
      "epoch": 0.32,
      "eval_loss": 3.1475002765655518,
      "eval_runtime": 1864.0149,
      "eval_samples_per_second": 83.313,
      "eval_steps_per_second": 2.604,
      "step": 15000
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.1003443012813687e-05,
      "loss": 3.0596,
      "step": 15500
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.135839278742058e-05,
      "loss": 3.0098,
      "step": 16000
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.1713342562027474e-05,
      "loss": 2.9623,
      "step": 16500
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.2068292336634367e-05,
      "loss": 2.9672,
      "step": 17000
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.242324211124126e-05,
      "loss": 2.9116,
      "step": 17500
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.2778191885848154e-05,
      "loss": 2.9084,
      "step": 18000
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.3133141660455045e-05,
      "loss": 2.895,
      "step": 18500
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.3488091435061938e-05,
      "loss": 2.7399,
      "step": 19000
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.3843041209668833e-05,
      "loss": 2.5682,
      "step": 19500
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.4197990984275725e-05,
      "loss": 2.4537,
      "step": 20000
    },
    {
      "epoch": 0.43,
      "eval_loss": 2.9956531524658203,
      "eval_runtime": 1865.9798,
      "eval_samples_per_second": 83.225,
      "eval_steps_per_second": 2.601,
      "step": 20000
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.4552940758882618e-05,
      "loss": 2.4331,
      "step": 20500
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.4907890533489513e-05,
      "loss": 2.4029,
      "step": 21000
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.5262840308096405e-05,
      "loss": 2.3138,
      "step": 21500
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.5617790082703298e-05,
      "loss": 2.228,
      "step": 22000
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.597273985731019e-05,
      "loss": 2.2115,
      "step": 22500
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.6327689631917085e-05,
      "loss": 2.2581,
      "step": 23000
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.6682639406523978e-05,
      "loss": 2.6867,
      "step": 23500
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.7037589181130868e-05,
      "loss": 3.0244,
      "step": 24000
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.7392538955737765e-05,
      "loss": 3.0813,
      "step": 24500
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7747488730344658e-05,
      "loss": 2.9647,
      "step": 25000
    },
    {
      "epoch": 0.53,
      "eval_loss": 2.9123897552490234,
      "eval_runtime": 1873.4567,
      "eval_samples_per_second": 82.893,
      "eval_steps_per_second": 2.59,
      "step": 25000
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.8102438504951548e-05,
      "loss": 2.8759,
      "step": 25500
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.8457388279558445e-05,
      "loss": 2.8097,
      "step": 26000
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.8812338054165338e-05,
      "loss": 2.81,
      "step": 26500
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.9167287828772228e-05,
      "loss": 2.9504,
      "step": 27000
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.9522237603379125e-05,
      "loss": 2.9625,
      "step": 27500
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.9877187377986014e-05,
      "loss": 2.9194,
      "step": 28000
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.0232137152592908e-05,
      "loss": 2.7549,
      "step": 28500
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.0587086927199804e-05,
      "loss": 2.7595,
      "step": 29000
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.0942036701806694e-05,
      "loss": 2.6814,
      "step": 29500
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.1296986476413588e-05,
      "loss": 2.6585,
      "step": 30000
    },
    {
      "epoch": 0.64,
      "eval_loss": 2.933678150177002,
      "eval_runtime": 1864.9329,
      "eval_samples_per_second": 83.272,
      "eval_steps_per_second": 2.602,
      "step": 30000
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.1651936251020484e-05,
      "loss": 2.6016,
      "step": 30500
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.2006886025627374e-05,
      "loss": 2.4808,
      "step": 31000
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.2361835800234267e-05,
      "loss": 2.2513,
      "step": 31500
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.271678557484116e-05,
      "loss": 2.0389,
      "step": 32000
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.3071735349448054e-05,
      "loss": 2.1131,
      "step": 32500
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.3426685124054947e-05,
      "loss": 2.3399,
      "step": 33000
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.378163489866184e-05,
      "loss": 2.2492,
      "step": 33500
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.4136584673268734e-05,
      "loss": 2.0341,
      "step": 34000
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.4491534447875627e-05,
      "loss": 1.9469,
      "step": 34500
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.484648422248252e-05,
      "loss": 1.6619,
      "step": 35000
    },
    {
      "epoch": 0.75,
      "eval_loss": 2.4717917442321777,
      "eval_runtime": 1893.5839,
      "eval_samples_per_second": 82.012,
      "eval_steps_per_second": 2.563,
      "step": 35000
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.5201433997089414e-05,
      "loss": 1.8649,
      "step": 35500
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5556383771696307e-05,
      "loss": 1.9368,
      "step": 36000
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.59113335463032e-05,
      "loss": 1.943,
      "step": 36500
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.626628332091009e-05,
      "loss": 1.8986,
      "step": 37000
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.6621233095516984e-05,
      "loss": 1.9063,
      "step": 37500
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.6976182870123877e-05,
      "loss": 1.9312,
      "step": 38000
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.7331132644730774e-05,
      "loss": 1.9081,
      "step": 38500
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.7686082419337667e-05,
      "loss": 1.9221,
      "step": 39000
    },
    {
      "epoch": 0.84,
      "learning_rate": 2.804103219394456e-05,
      "loss": 1.9273,
      "step": 39500
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.839598196855145e-05,
      "loss": 1.8747,
      "step": 40000
    },
    {
      "epoch": 0.85,
      "eval_loss": 2.6204776763916016,
      "eval_runtime": 1883.3925,
      "eval_samples_per_second": 82.455,
      "eval_steps_per_second": 2.577,
      "step": 40000
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.8750931743158343e-05,
      "loss": 1.8899,
      "step": 40500
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.9105881517765237e-05,
      "loss": 1.8608,
      "step": 41000
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.9460831292372133e-05,
      "loss": 1.8431,
      "step": 41500
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.9815781066979027e-05,
      "loss": 1.8241,
      "step": 42000
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.0170730841585913e-05,
      "loss": 1.7348,
      "step": 42500
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.052568061619281e-05,
      "loss": 1.6507,
      "step": 43000
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.08806303907997e-05,
      "loss": 1.5996,
      "step": 43500
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.1235580165406596e-05,
      "loss": 1.5477,
      "step": 44000
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.159052994001349e-05,
      "loss": 1.5293,
      "step": 44500
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.194547971462038e-05,
      "loss": 1.4987,
      "step": 45000
    },
    {
      "epoch": 0.96,
      "eval_loss": 2.5555038452148438,
      "eval_runtime": 1881.7147,
      "eval_samples_per_second": 82.529,
      "eval_steps_per_second": 2.579,
      "step": 45000
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.2300429489227276e-05,
      "loss": 1.4849,
      "step": 45500
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.265537926383417e-05,
      "loss": 1.4607,
      "step": 46000
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.301032903844106e-05,
      "loss": 1.4327,
      "step": 46500
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.3365278813047956e-05,
      "loss": 1.5583,
      "step": 47000
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.372022858765485e-05,
      "loss": 2.9982,
      "step": 47500
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.4075178362261736e-05,
      "loss": 2.8593,
      "step": 48000
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.4430128136868636e-05,
      "loss": 2.7072,
      "step": 48500
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.478507791147553e-05,
      "loss": 2.6194,
      "step": 49000
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.514002768608242e-05,
      "loss": 2.6802,
      "step": 49500
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.5494977460689316e-05,
      "loss": 2.7354,
      "step": 50000
    },
    {
      "epoch": 1.06,
      "eval_loss": 2.2694995403289795,
      "eval_runtime": 1888.4178,
      "eval_samples_per_second": 82.236,
      "eval_steps_per_second": 2.57,
      "step": 50000
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.58499272352962e-05,
      "loss": 2.7322,
      "step": 50500
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.6204877009903096e-05,
      "loss": 2.5126,
      "step": 51000
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.6559826784509996e-05,
      "loss": 2.4443,
      "step": 51500
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.691477655911689e-05,
      "loss": 2.4459,
      "step": 52000
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.726972633372378e-05,
      "loss": 2.4281,
      "step": 52500
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.7624676108330676e-05,
      "loss": 2.4015,
      "step": 53000
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.797962588293756e-05,
      "loss": 2.3893,
      "step": 53500
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.8334575657544456e-05,
      "loss": 2.3687,
      "step": 54000
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.868952543215135e-05,
      "loss": 2.2275,
      "step": 54500
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.904447520675825e-05,
      "loss": 2.1044,
      "step": 55000
    },
    {
      "epoch": 1.17,
      "eval_loss": 2.3230154514312744,
      "eval_runtime": 1886.2054,
      "eval_samples_per_second": 82.332,
      "eval_steps_per_second": 2.573,
      "step": 55000
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.939942498136514e-05,
      "loss": 1.9299,
      "step": 55500
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.975437475597203e-05,
      "loss": 1.9414,
      "step": 56000
    },
    {
      "epoch": 1.2,
      "learning_rate": 4.010932453057892e-05,
      "loss": 1.915,
      "step": 56500
    },
    {
      "epoch": 1.21,
      "learning_rate": 4.0464274305185815e-05,
      "loss": 1.7593,
      "step": 57000
    },
    {
      "epoch": 1.22,
      "learning_rate": 4.081922407979271e-05,
      "loss": 1.7891,
      "step": 57500
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.117417385439961e-05,
      "loss": 1.8187,
      "step": 58000
    },
    {
      "epoch": 1.25,
      "learning_rate": 4.15291236290065e-05,
      "loss": 1.8112,
      "step": 58500
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.188407340361339e-05,
      "loss": 2.2816,
      "step": 59000
    },
    {
      "epoch": 1.27,
      "learning_rate": 4.223902317822028e-05,
      "loss": 2.6614,
      "step": 59500
    },
    {
      "epoch": 1.28,
      "learning_rate": 4.2593972952827175e-05,
      "loss": 2.7807,
      "step": 60000
    },
    {
      "epoch": 1.28,
      "eval_loss": 2.391098976135254,
      "eval_runtime": 1884.9545,
      "eval_samples_per_second": 82.387,
      "eval_steps_per_second": 2.575,
      "step": 60000
    },
    {
      "epoch": 1.29,
      "learning_rate": 4.294892272743407e-05,
      "loss": 2.7792,
      "step": 60500
    },
    {
      "epoch": 1.3,
      "learning_rate": 4.330387250204097e-05,
      "loss": 2.7677,
      "step": 61000
    },
    {
      "epoch": 1.31,
      "learning_rate": 4.3658822276647855e-05,
      "loss": 2.7702,
      "step": 61500
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.401377205125475e-05,
      "loss": 2.7726,
      "step": 62000
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.436872182586164e-05,
      "loss": 2.7352,
      "step": 62500
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.4723671600468535e-05,
      "loss": 2.6718,
      "step": 63000
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.507862137507543e-05,
      "loss": 2.6335,
      "step": 63500
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.543357114968232e-05,
      "loss": 2.6558,
      "step": 64000
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.5788520924289215e-05,
      "loss": 2.5857,
      "step": 64500
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.614347069889611e-05,
      "loss": 2.6069,
      "step": 65000
    },
    {
      "epoch": 1.38,
      "eval_loss": 2.3972585201263428,
      "eval_runtime": 1888.6438,
      "eval_samples_per_second": 82.226,
      "eval_steps_per_second": 2.57,
      "step": 65000
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.6498420473503e-05,
      "loss": 2.5862,
      "step": 65500
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.6853370248109895e-05,
      "loss": 2.3355,
      "step": 66000
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.720832002271679e-05,
      "loss": 2.1705,
      "step": 66500
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.756326979732368e-05,
      "loss": 2.0997,
      "step": 67000
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.7918219571930575e-05,
      "loss": 2.0904,
      "step": 67500
    },
    {
      "epoch": 1.45,
      "learning_rate": 4.827316934653747e-05,
      "loss": 2.0644,
      "step": 68000
    },
    {
      "epoch": 1.46,
      "learning_rate": 4.862811912114436e-05,
      "loss": 1.9904,
      "step": 68500
    },
    {
      "epoch": 1.47,
      "learning_rate": 4.8983068895751255e-05,
      "loss": 1.9207,
      "step": 69000
    },
    {
      "epoch": 1.48,
      "learning_rate": 4.933801867035815e-05,
      "loss": 1.9133,
      "step": 69500
    },
    {
      "epoch": 1.49,
      "learning_rate": 4.969296844496504e-05,
      "loss": 1.9486,
      "step": 70000
    },
    {
      "epoch": 1.49,
      "eval_loss": 2.2720885276794434,
      "eval_runtime": 1889.9801,
      "eval_samples_per_second": 82.168,
      "eval_steps_per_second": 2.568,
      "step": 70000
    },
    {
      "epoch": 1.5,
      "learning_rate": 5.0047918219571934e-05,
      "loss": 2.3316,
      "step": 70500
    },
    {
      "epoch": 1.51,
      "learning_rate": 5.040286799417883e-05,
      "loss": 2.6124,
      "step": 71000
    },
    {
      "epoch": 1.52,
      "learning_rate": 5.075781776878572e-05,
      "loss": 2.6063,
      "step": 71500
    },
    {
      "epoch": 1.53,
      "learning_rate": 5.1112767543392614e-05,
      "loss": 2.5125,
      "step": 72000
    },
    {
      "epoch": 1.54,
      "learning_rate": 5.146771731799951e-05,
      "loss": 2.575,
      "step": 72500
    },
    {
      "epoch": 1.55,
      "learning_rate": 5.18226670926064e-05,
      "loss": 2.5665,
      "step": 73000
    },
    {
      "epoch": 1.57,
      "learning_rate": 5.2177616867213294e-05,
      "loss": 2.5506,
      "step": 73500
    },
    {
      "epoch": 1.58,
      "learning_rate": 5.253256664182018e-05,
      "loss": 2.5266,
      "step": 74000
    },
    {
      "epoch": 1.59,
      "learning_rate": 5.2887516416427074e-05,
      "loss": 2.4611,
      "step": 74500
    },
    {
      "epoch": 1.6,
      "learning_rate": 5.324246619103397e-05,
      "loss": 2.3811,
      "step": 75000
    },
    {
      "epoch": 1.6,
      "eval_loss": 2.2767999172210693,
      "eval_runtime": 1878.9159,
      "eval_samples_per_second": 82.652,
      "eval_steps_per_second": 2.583,
      "step": 75000
    },
    {
      "epoch": 1.61,
      "learning_rate": 5.359741596564086e-05,
      "loss": 2.3555,
      "step": 75500
    },
    {
      "epoch": 1.62,
      "learning_rate": 5.3952365740247754e-05,
      "loss": 2.4912,
      "step": 76000
    },
    {
      "epoch": 1.63,
      "learning_rate": 5.4307315514854654e-05,
      "loss": 2.4678,
      "step": 76500
    },
    {
      "epoch": 1.64,
      "learning_rate": 5.466226528946155e-05,
      "loss": 2.3853,
      "step": 77000
    },
    {
      "epoch": 1.65,
      "learning_rate": 5.501721506406844e-05,
      "loss": 2.1739,
      "step": 77500
    },
    {
      "epoch": 1.66,
      "learning_rate": 5.5372164838675334e-05,
      "loss": 1.9686,
      "step": 78000
    },
    {
      "epoch": 1.67,
      "learning_rate": 5.572711461328223e-05,
      "loss": 1.7833,
      "step": 78500
    },
    {
      "epoch": 1.68,
      "learning_rate": 5.608206438788912e-05,
      "loss": 1.737,
      "step": 79000
    },
    {
      "epoch": 1.69,
      "learning_rate": 5.643701416249601e-05,
      "loss": 1.7961,
      "step": 79500
    },
    {
      "epoch": 1.7,
      "learning_rate": 5.67919639371029e-05,
      "loss": 1.9018,
      "step": 80000
    },
    {
      "epoch": 1.7,
      "eval_loss": 2.273552417755127,
      "eval_runtime": 1899.1003,
      "eval_samples_per_second": 81.773,
      "eval_steps_per_second": 2.555,
      "step": 80000
    },
    {
      "epoch": 1.71,
      "learning_rate": 5.7146913711709794e-05,
      "loss": 1.7687,
      "step": 80500
    },
    {
      "epoch": 1.73,
      "learning_rate": 5.750186348631669e-05,
      "loss": 1.6724,
      "step": 81000
    },
    {
      "epoch": 1.74,
      "learning_rate": 5.785681326092358e-05,
      "loss": 1.635,
      "step": 81500
    },
    {
      "epoch": 1.75,
      "learning_rate": 5.8211763035530473e-05,
      "loss": 1.431,
      "step": 82000
    },
    {
      "epoch": 1.76,
      "learning_rate": 5.856671281013737e-05,
      "loss": 1.6943,
      "step": 82500
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.892166258474427e-05,
      "loss": 1.7855,
      "step": 83000
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.927661235935116e-05,
      "loss": 1.7722,
      "step": 83500
    },
    {
      "epoch": 1.79,
      "learning_rate": 5.9631562133958053e-05,
      "loss": 1.7553,
      "step": 84000
    },
    {
      "epoch": 1.8,
      "learning_rate": 5.998651190856495e-05,
      "loss": 1.7606,
      "step": 84500
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.0341461683171826e-05,
      "loss": 1.791,
      "step": 85000
    },
    {
      "epoch": 1.81,
      "eval_loss": 2.1984245777130127,
      "eval_runtime": 1895.2328,
      "eval_samples_per_second": 81.94,
      "eval_steps_per_second": 2.561,
      "step": 85000
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.0696411457778727e-05,
      "loss": 1.7625,
      "step": 85500
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.105136123238562e-05,
      "loss": 1.7837,
      "step": 86000
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.140631100699251e-05,
      "loss": 1.785,
      "step": 86500
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.17612607815994e-05,
      "loss": 1.7415,
      "step": 87000
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.21162105562063e-05,
      "loss": 1.7665,
      "step": 87500
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.247116033081319e-05,
      "loss": 1.7438,
      "step": 88000
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.282611010542009e-05,
      "loss": 1.7227,
      "step": 88500
    },
    {
      "epoch": 1.9,
      "learning_rate": 6.318105988002698e-05,
      "loss": 1.6778,
      "step": 89000
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.353600965463387e-05,
      "loss": 1.5861,
      "step": 89500
    },
    {
      "epoch": 1.92,
      "learning_rate": 6.389095942924077e-05,
      "loss": 1.5116,
      "step": 90000
    },
    {
      "epoch": 1.92,
      "eval_loss": 2.233893394470215,
      "eval_runtime": 1904.5796,
      "eval_samples_per_second": 81.538,
      "eval_steps_per_second": 2.548,
      "step": 90000
    },
    {
      "epoch": 1.93,
      "learning_rate": 6.424590920384766e-05,
      "loss": 1.4536,
      "step": 90500
    },
    {
      "epoch": 1.94,
      "learning_rate": 6.460085897845455e-05,
      "loss": 1.4093,
      "step": 91000
    },
    {
      "epoch": 1.95,
      "learning_rate": 6.495580875306145e-05,
      "loss": 1.3914,
      "step": 91500
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.531075852766834e-05,
      "loss": 1.3541,
      "step": 92000
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.566570830227523e-05,
      "loss": 1.3558,
      "step": 92500
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.602065807688213e-05,
      "loss": 1.3333,
      "step": 93000
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.637560785148902e-05,
      "loss": 1.3097,
      "step": 93500
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.673055762609591e-05,
      "loss": 1.5111,
      "step": 94000
    },
    {
      "epoch": 2.01,
      "learning_rate": 6.70855074007028e-05,
      "loss": 2.4014,
      "step": 94500
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.74404571753097e-05,
      "loss": 2.4561,
      "step": 95000
    },
    {
      "epoch": 2.02,
      "eval_loss": 2.1256251335144043,
      "eval_runtime": 1859.0929,
      "eval_samples_per_second": 83.533,
      "eval_steps_per_second": 2.61,
      "step": 95000
    },
    {
      "epoch": 2.03,
      "learning_rate": 6.779540694991659e-05,
      "loss": 2.3495,
      "step": 95500
    },
    {
      "epoch": 2.04,
      "learning_rate": 6.815035672452347e-05,
      "loss": 2.3575,
      "step": 96000
    },
    {
      "epoch": 2.06,
      "learning_rate": 6.850530649913038e-05,
      "loss": 2.475,
      "step": 96500
    },
    {
      "epoch": 2.07,
      "learning_rate": 6.886025627373727e-05,
      "loss": 2.5452,
      "step": 97000
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.921520604834417e-05,
      "loss": 2.5702,
      "step": 97500
    },
    {
      "epoch": 2.09,
      "learning_rate": 6.957015582295106e-05,
      "loss": 2.2523,
      "step": 98000
    },
    {
      "epoch": 2.1,
      "learning_rate": 6.992510559755795e-05,
      "loss": 2.206,
      "step": 98500
    },
    {
      "epoch": 2.11,
      "learning_rate": 7.028005537216485e-05,
      "loss": 2.19,
      "step": 99000
    },
    {
      "epoch": 2.12,
      "learning_rate": 7.063500514677174e-05,
      "loss": 2.1882,
      "step": 99500
    },
    {
      "epoch": 2.13,
      "learning_rate": 7.098995492137863e-05,
      "loss": 2.1672,
      "step": 100000
    },
    {
      "epoch": 2.13,
      "eval_loss": 2.124307155609131,
      "eval_runtime": 1857.878,
      "eval_samples_per_second": 83.588,
      "eval_steps_per_second": 2.612,
      "step": 100000
    },
    {
      "epoch": 2.14,
      "learning_rate": 7.134490469598553e-05,
      "loss": 2.1818,
      "step": 100500
    },
    {
      "epoch": 2.15,
      "learning_rate": 7.16998544705924e-05,
      "loss": 2.113,
      "step": 101000
    },
    {
      "epoch": 2.16,
      "learning_rate": 7.20548042451993e-05,
      "loss": 1.9473,
      "step": 101500
    },
    {
      "epoch": 2.17,
      "learning_rate": 7.240975401980619e-05,
      "loss": 1.8507,
      "step": 102000
    },
    {
      "epoch": 2.18,
      "learning_rate": 7.276470379441309e-05,
      "loss": 1.7292,
      "step": 102500
    },
    {
      "epoch": 2.19,
      "learning_rate": 7.311965356901999e-05,
      "loss": 1.7521,
      "step": 103000
    },
    {
      "epoch": 2.2,
      "learning_rate": 7.347460334362689e-05,
      "loss": 1.7079,
      "step": 103500
    },
    {
      "epoch": 2.21,
      "learning_rate": 7.382955311823378e-05,
      "loss": 1.5634,
      "step": 104000
    },
    {
      "epoch": 2.23,
      "learning_rate": 7.418450289284067e-05,
      "loss": 1.5756,
      "step": 104500
    },
    {
      "epoch": 2.24,
      "learning_rate": 7.453945266744757e-05,
      "loss": 1.5846,
      "step": 105000
    },
    {
      "epoch": 2.24,
      "eval_loss": 2.1730854511260986,
      "eval_runtime": 1854.6465,
      "eval_samples_per_second": 83.733,
      "eval_steps_per_second": 2.617,
      "step": 105000
    },
    {
      "epoch": 2.25,
      "learning_rate": 7.489440244205446e-05,
      "loss": 1.6139,
      "step": 105500
    },
    {
      "epoch": 2.26,
      "learning_rate": 7.524935221666135e-05,
      "loss": 2.1333,
      "step": 106000
    },
    {
      "epoch": 2.27,
      "learning_rate": 7.560430199126823e-05,
      "loss": 2.4937,
      "step": 106500
    },
    {
      "epoch": 2.28,
      "learning_rate": 7.595925176587512e-05,
      "loss": 2.612,
      "step": 107000
    },
    {
      "epoch": 2.29,
      "learning_rate": 7.631420154048202e-05,
      "loss": 2.6089,
      "step": 107500
    },
    {
      "epoch": 2.3,
      "learning_rate": 7.666915131508891e-05,
      "loss": 2.6114,
      "step": 108000
    },
    {
      "epoch": 2.31,
      "learning_rate": 7.70241010896958e-05,
      "loss": 2.6378,
      "step": 108500
    },
    {
      "epoch": 2.32,
      "learning_rate": 7.73790508643027e-05,
      "loss": 2.6115,
      "step": 109000
    },
    {
      "epoch": 2.33,
      "learning_rate": 7.77340006389096e-05,
      "loss": 2.592,
      "step": 109500
    },
    {
      "epoch": 2.34,
      "learning_rate": 7.80889504135165e-05,
      "loss": 2.5257,
      "step": 110000
    },
    {
      "epoch": 2.34,
      "eval_loss": 2.241882085800171,
      "eval_runtime": 1857.7205,
      "eval_samples_per_second": 83.595,
      "eval_steps_per_second": 2.612,
      "step": 110000
    },
    {
      "epoch": 2.35,
      "learning_rate": 7.844390018812339e-05,
      "loss": 2.5092,
      "step": 110500
    },
    {
      "epoch": 2.36,
      "learning_rate": 7.879884996273028e-05,
      "loss": 2.5269,
      "step": 111000
    },
    {
      "epoch": 2.37,
      "learning_rate": 7.915379973733718e-05,
      "loss": 2.4593,
      "step": 111500
    },
    {
      "epoch": 2.39,
      "learning_rate": 7.950874951194406e-05,
      "loss": 2.4574,
      "step": 112000
    },
    {
      "epoch": 2.4,
      "learning_rate": 7.986369928655095e-05,
      "loss": 2.4325,
      "step": 112500
    },
    {
      "epoch": 2.41,
      "learning_rate": 8.021864906115784e-05,
      "loss": 2.1543,
      "step": 113000
    },
    {
      "epoch": 2.42,
      "learning_rate": 8.057359883576474e-05,
      "loss": 2.0012,
      "step": 113500
    },
    {
      "epoch": 2.43,
      "learning_rate": 8.092854861037163e-05,
      "loss": 1.9504,
      "step": 114000
    },
    {
      "epoch": 2.44,
      "learning_rate": 8.128349838497852e-05,
      "loss": 1.9455,
      "step": 114500
    },
    {
      "epoch": 2.45,
      "learning_rate": 8.163844815958542e-05,
      "loss": 1.9144,
      "step": 115000
    },
    {
      "epoch": 2.45,
      "eval_loss": 2.2165353298187256,
      "eval_runtime": 1870.5345,
      "eval_samples_per_second": 83.022,
      "eval_steps_per_second": 2.594,
      "step": 115000
    },
    {
      "epoch": 2.46,
      "learning_rate": 8.199339793419232e-05,
      "loss": 1.8364,
      "step": 115500
    },
    {
      "epoch": 2.47,
      "learning_rate": 8.234834770879922e-05,
      "loss": 1.7797,
      "step": 116000
    },
    {
      "epoch": 2.48,
      "learning_rate": 8.270329748340611e-05,
      "loss": 1.7642,
      "step": 116500
    },
    {
      "epoch": 2.49,
      "learning_rate": 8.3058247258013e-05,
      "loss": 1.7883,
      "step": 117000
    },
    {
      "epoch": 2.5,
      "learning_rate": 8.341319703261988e-05,
      "loss": 2.0817,
      "step": 117500
    },
    {
      "epoch": 2.51,
      "learning_rate": 8.376814680722678e-05,
      "loss": 2.2653,
      "step": 118000
    },
    {
      "epoch": 2.52,
      "learning_rate": 8.412309658183367e-05,
      "loss": 2.2728,
      "step": 118500
    },
    {
      "epoch": 2.53,
      "learning_rate": 8.447804635644056e-05,
      "loss": 2.2776,
      "step": 119000
    },
    {
      "epoch": 2.54,
      "learning_rate": 8.483299613104746e-05,
      "loss": 2.4327,
      "step": 119500
    },
    {
      "epoch": 2.56,
      "learning_rate": 8.518794590565435e-05,
      "loss": 2.4218,
      "step": 120000
    },
    {
      "epoch": 2.56,
      "eval_loss": 2.091143846511841,
      "eval_runtime": 1858.0529,
      "eval_samples_per_second": 83.58,
      "eval_steps_per_second": 2.612,
      "step": 120000
    }
  ],
  "max_steps": 1408650,
  "num_train_epochs": 30,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}