{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 4283,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 7.751937984496126e-06,
      "loss": 2.7409,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.550387596899225e-05,
      "loss": 2.4444,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9998738851504623e-05,
      "loss": 2.2444,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9985587175059564e-05,
      "loss": 2.1017,
      "step": 200
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.995815877254959e-05,
      "loss": 2.0129,
      "step": 250
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.991649285927394e-05,
      "loss": 1.9724,
      "step": 300
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9860649006374456e-05,
      "loss": 1.904,
      "step": 350
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.979070705566478e-05,
      "loss": 1.8862,
      "step": 400
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9706767005477825e-05,
      "loss": 1.8507,
      "step": 450
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.960894886769486e-05,
      "loss": 1.8229,
      "step": 500
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.949739249616051e-05,
      "loss": 1.792,
      "step": 550
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.937225738672908e-05,
      "loss": 1.7843,
      "step": 600
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9233722449228015e-05,
      "loss": 1.7632,
      "step": 650
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9081985751664576e-05,
      "loss": 1.7554,
      "step": 700
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8917264237041433e-05,
      "loss": 1.7359,
      "step": 750
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.873979341318602e-05,
      "loss": 1.7323,
      "step": 800
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8549827016037167e-05,
      "loss": 1.7054,
      "step": 850
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.8347636646870404e-05,
      "loss": 1.7018,
      "step": 900
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.813351138398058e-05,
      "loss": 1.6967,
      "step": 950
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.7907757369376984e-05,
      "loss": 1.6812,
      "step": 1000
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.767069737108199e-05,
      "loss": 1.6623,
      "step": 1050
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.7422670321658813e-05,
      "loss": 1.6476,
      "step": 1100
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.716403083362841e-05,
      "loss": 1.655,
      "step": 1150
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.6895148692468128e-05,
      "loss": 1.6471,
      "step": 1200
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.6616408327917138e-05,
      "loss": 1.6354,
      "step": 1250
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.632820826434442e-05,
      "loss": 1.6324,
      "step": 1300
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.6030960550965252e-05,
      "loss": 1.6249,
      "step": 1350
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.572509017272072e-05,
      "loss": 1.62,
      "step": 1400
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.5411034442662632e-05,
      "loss": 1.6093,
      "step": 1450
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.508924237671248e-05,
      "loss": 1.5981,
      "step": 1500
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.4760174051688485e-05,
      "loss": 1.6053,
      "step": 1550
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.4424299947518423e-05,
      "loss": 1.6095,
      "step": 1600
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.4082100274578854e-05,
      "loss": 1.5971,
      "step": 1650
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.3734064287122381e-05,
      "loss": 1.5827,
      "step": 1700
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.3380689583774554e-05,
      "loss": 1.583,
      "step": 1750
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.3022481396100574e-05,
      "loss": 1.5648,
      "step": 1800
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.265995186625894e-05,
      "loss": 1.5692,
      "step": 1850
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.229361931477474e-05,
      "loss": 1.5601,
      "step": 1900
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.1924007499479602e-05,
      "loss": 1.5657,
      "step": 1950
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.1551644866677654e-05,
      "loss": 1.5641,
      "step": 2000
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.1177063795608305e-05,
      "loss": 1.5558,
      "step": 2050
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.0800799837285943e-05,
      "loss": 1.5645,
      "step": 2100
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.0423390948804808e-05,
      "loss": 1.5462,
      "step": 2150
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.0045376724203873e-05,
      "loss": 1.5484,
      "step": 2200
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.667297622991301e-06,
      "loss": 1.5371,
      "step": 2250
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.289694197431486e-06,
      "loss": 1.5283,
      "step": 2300
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.913106319699537e-06,
      "loss": 1.5323,
      "step": 2350
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.538072410008054e-06,
      "loss": 1.5344,
      "step": 2400
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.16512866680985e-06,
      "loss": 1.5305,
      "step": 2450
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.794808300177196e-06,
      "loss": 1.5403,
      "step": 2500
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.427640769453647e-06,
      "loss": 1.5241,
      "step": 2550
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.064151026268395e-06,
      "loss": 1.5347,
      "step": 2600
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.704858763995493e-06,
      "loss": 1.5308,
      "step": 2650
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.350277674730938e-06,
      "loss": 1.525,
      "step": 2700
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.0009147148499936e-06,
      "loss": 1.5206,
      "step": 2750
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.657269380194827e-06,
      "loss": 1.5029,
      "step": 2800
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.319832991928664e-06,
      "loss": 1.516,
      "step": 2850
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.989087994077596e-06,
      "loss": 1.5273,
      "step": 2900
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.665507263764299e-06,
      "loss": 1.5062,
      "step": 2950
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.349553435119907e-06,
      "loss": 1.5154,
      "step": 3000
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.041678237840601e-06,
      "loss": 1.5018,
      "step": 3050
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.742321851334625e-06,
      "loss": 1.5079,
      "step": 3100
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.4519122753831635e-06,
      "loss": 1.5034,
      "step": 3150
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.170864718214822e-06,
      "loss": 1.4912,
      "step": 3200
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8995810028685947e-06,
      "loss": 1.507,
      "step": 3250
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.638448992694124e-06,
      "loss": 1.5073,
      "step": 3300
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3878420368105706e-06,
      "loss": 1.5077,
      "step": 3350
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.148118436316944e-06,
      "loss": 1.4956,
      "step": 3400
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.9196209320171176e-06,
      "loss": 1.4851,
      "step": 3450
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7026762143919072e-06,
      "loss": 1.5002,
      "step": 3500
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4975944565188094e-06,
      "loss": 1.4939,
      "step": 3550
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3046688706072563e-06,
      "loss": 1.4976,
      "step": 3600
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1241752887833635e-06,
      "loss": 1.4902,
      "step": 3650
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.563717687235586e-07,
      "loss": 1.4959,
      "step": 3700
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.014982247009473e-07,
      "loss": 1.4928,
      "step": 3750
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.597760845718881e-07,
      "loss": 1.4905,
      "step": 3800
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.314079731932398e-07,
      "loss": 1.5015,
      "step": 3850
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.165774227228492e-07,
      "loss": 1.4831,
      "step": 3900
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.1544861021753137e-07,
      "loss": 1.4946,
      "step": 3950
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.2816612290366358e-07,
      "loss": 1.4841,
      "step": 4000
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5485475145602614e-07,
      "loss": 1.5016,
      "step": 4050
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.561931158041937e-08,
      "loss": 1.4967,
      "step": 4100
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.0544494155169155e-08,
      "loss": 1.4907,
      "step": 4150
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.9694744145755117e-08,
      "loss": 1.4911,
      "step": 4200
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.1141684657065573e-09,
      "loss": 1.4964,
      "step": 4250
    },
    {
      "epoch": 1.0,
      "step": 4283,
      "total_flos": 3.7850139050429645e+17,
      "train_loss": 1.628265750483322,
      "train_runtime": 14247.8723,
      "train_samples_per_second": 14.428,
      "train_steps_per_second": 0.301
    }
  ],
  "logging_steps": 50,
  "max_steps": 4283,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 24000,
  "total_flos": 3.7850139050429645e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}