{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.999672313792313,
  "eval_steps": 500,
  "global_step": 76290,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 2.980993577139861e-06,
      "loss": 1.8224,
      "step": 500
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.9619871542797224e-06,
      "loss": 1.6774,
      "step": 1000
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.9429807314195834e-06,
      "loss": 1.651,
      "step": 1500
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.9239743085594444e-06,
      "loss": 1.6331,
      "step": 2000
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.9049678856993053e-06,
      "loss": 1.6218,
      "step": 2500
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.8859614628391667e-06,
      "loss": 1.6129,
      "step": 3000
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.8669550399790273e-06,
      "loss": 1.6042,
      "step": 3500
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.8479486171188882e-06,
      "loss": 1.596,
      "step": 4000
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.8289421942587496e-06,
      "loss": 1.5899,
      "step": 4500
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.8099357713986106e-06,
      "loss": 1.5834,
      "step": 5000
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.7909293485384715e-06,
      "loss": 1.5772,
      "step": 5500
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.771922925678333e-06,
      "loss": 1.5719,
      "step": 6000
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.752916502818194e-06,
      "loss": 1.567,
      "step": 6500
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.733910079958055e-06,
      "loss": 1.5625,
      "step": 7000
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.714903657097916e-06,
      "loss": 1.5588,
      "step": 7500
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.544177770614624,
      "eval_runtime": 7.0475,
      "eval_samples_per_second": 139.908,
      "eval_steps_per_second": 0.851,
      "step": 7629
    },
    {
      "epoch": 1.05,
      "learning_rate": 2.695897234237777e-06,
      "loss": 1.5539,
      "step": 8000
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.6768908113776377e-06,
      "loss": 1.5502,
      "step": 8500
    },
    {
      "epoch": 1.18,
      "learning_rate": 2.6578843885174987e-06,
      "loss": 1.5473,
      "step": 9000
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.63887796565736e-06,
      "loss": 1.5443,
      "step": 9500
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.619871542797221e-06,
      "loss": 1.5411,
      "step": 10000
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.600865119937082e-06,
      "loss": 1.5391,
      "step": 10500
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.5818586970769434e-06,
      "loss": 1.5366,
      "step": 11000
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.5628522742168044e-06,
      "loss": 1.5344,
      "step": 11500
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.5438458513566653e-06,
      "loss": 1.532,
      "step": 12000
    },
    {
      "epoch": 1.64,
      "learning_rate": 2.5248394284965263e-06,
      "loss": 1.5295,
      "step": 12500
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.5058330056363877e-06,
      "loss": 1.5286,
      "step": 13000
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.4868265827762487e-06,
      "loss": 1.526,
      "step": 13500
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.4678201599161096e-06,
      "loss": 1.5247,
      "step": 14000
    },
    {
      "epoch": 1.9,
      "learning_rate": 2.448813737055971e-06,
      "loss": 1.5235,
      "step": 14500
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.429807314195832e-06,
      "loss": 1.5219,
      "step": 15000
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.5164680480957031,
      "eval_runtime": 6.9148,
      "eval_samples_per_second": 142.593,
      "eval_steps_per_second": 0.868,
      "step": 15258
    },
    {
      "epoch": 2.03,
      "learning_rate": 2.410800891335693e-06,
      "loss": 1.5194,
      "step": 15500
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.391794468475554e-06,
      "loss": 1.5185,
      "step": 16000
    },
    {
      "epoch": 2.16,
      "learning_rate": 2.372788045615415e-06,
      "loss": 1.5166,
      "step": 16500
    },
    {
      "epoch": 2.23,
      "learning_rate": 2.353781622755276e-06,
      "loss": 1.516,
      "step": 17000
    },
    {
      "epoch": 2.29,
      "learning_rate": 2.334775199895137e-06,
      "loss": 1.5149,
      "step": 17500
    },
    {
      "epoch": 2.36,
      "learning_rate": 2.315768777034998e-06,
      "loss": 1.5137,
      "step": 18000
    },
    {
      "epoch": 2.42,
      "learning_rate": 2.296762354174859e-06,
      "loss": 1.5127,
      "step": 18500
    },
    {
      "epoch": 2.49,
      "learning_rate": 2.27775593131472e-06,
      "loss": 1.5111,
      "step": 19000
    },
    {
      "epoch": 2.56,
      "learning_rate": 2.258749508454581e-06,
      "loss": 1.5103,
      "step": 19500
    },
    {
      "epoch": 2.62,
      "learning_rate": 2.239743085594442e-06,
      "loss": 1.5095,
      "step": 20000
    },
    {
      "epoch": 2.69,
      "learning_rate": 2.220736662734303e-06,
      "loss": 1.5082,
      "step": 20500
    },
    {
      "epoch": 2.75,
      "learning_rate": 2.2017302398741644e-06,
      "loss": 1.5075,
      "step": 21000
    },
    {
      "epoch": 2.82,
      "learning_rate": 2.1827238170140254e-06,
      "loss": 1.5064,
      "step": 21500
    },
    {
      "epoch": 2.88,
      "learning_rate": 2.1637173941538863e-06,
      "loss": 1.5056,
      "step": 22000
    },
    {
      "epoch": 2.95,
      "learning_rate": 2.1447109712937477e-06,
      "loss": 1.5053,
      "step": 22500
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.5032986402511597,
      "eval_runtime": 7.0258,
      "eval_samples_per_second": 140.341,
      "eval_steps_per_second": 0.854,
      "step": 22887
    },
    {
      "epoch": 3.01,
      "learning_rate": 2.1257045484336087e-06,
      "loss": 1.5047,
      "step": 23000
    },
    {
      "epoch": 3.08,
      "learning_rate": 2.1066981255734696e-06,
      "loss": 1.5028,
      "step": 23500
    },
    {
      "epoch": 3.15,
      "learning_rate": 2.0876917027133306e-06,
      "loss": 1.5022,
      "step": 24000
    },
    {
      "epoch": 3.21,
      "learning_rate": 2.068685279853192e-06,
      "loss": 1.5014,
      "step": 24500
    },
    {
      "epoch": 3.28,
      "learning_rate": 2.049678856993053e-06,
      "loss": 1.5005,
      "step": 25000
    },
    {
      "epoch": 3.34,
      "learning_rate": 2.030672434132914e-06,
      "loss": 1.5001,
      "step": 25500
    },
    {
      "epoch": 3.41,
      "learning_rate": 2.011666011272775e-06,
      "loss": 1.4992,
      "step": 26000
    },
    {
      "epoch": 3.47,
      "learning_rate": 1.9926595884126363e-06,
      "loss": 1.4986,
      "step": 26500
    },
    {
      "epoch": 3.54,
      "learning_rate": 1.9736531655524972e-06,
      "loss": 1.498,
      "step": 27000
    },
    {
      "epoch": 3.6,
      "learning_rate": 1.9546467426923586e-06,
      "loss": 1.4974,
      "step": 27500
    },
    {
      "epoch": 3.67,
      "learning_rate": 1.9356403198322196e-06,
      "loss": 1.4969,
      "step": 28000
    },
    {
      "epoch": 3.74,
      "learning_rate": 1.91663389697208e-06,
      "loss": 1.4963,
      "step": 28500
    },
    {
      "epoch": 3.8,
      "learning_rate": 1.8976274741119413e-06,
      "loss": 1.4957,
      "step": 29000
    },
    {
      "epoch": 3.87,
      "learning_rate": 1.8786210512518025e-06,
      "loss": 1.4952,
      "step": 29500
    },
    {
      "epoch": 3.93,
      "learning_rate": 1.8596146283916634e-06,
      "loss": 1.4945,
      "step": 30000
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.8406082055315244e-06,
      "loss": 1.4935,
      "step": 30500
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.4955875873565674,
      "eval_runtime": 6.9086,
      "eval_samples_per_second": 142.721,
      "eval_steps_per_second": 0.868,
      "step": 30517
    },
    {
      "epoch": 4.06,
      "learning_rate": 1.8216017826713858e-06,
      "loss": 1.493,
      "step": 31000
    },
    {
      "epoch": 4.13,
      "learning_rate": 1.8025953598112466e-06,
      "loss": 1.4925,
      "step": 31500
    },
    {
      "epoch": 4.19,
      "learning_rate": 1.7835889369511077e-06,
      "loss": 1.4921,
      "step": 32000
    },
    {
      "epoch": 4.26,
      "learning_rate": 1.764582514090969e-06,
      "loss": 1.4916,
      "step": 32500
    },
    {
      "epoch": 4.33,
      "learning_rate": 1.7455760912308294e-06,
      "loss": 1.4914,
      "step": 33000
    },
    {
      "epoch": 4.39,
      "learning_rate": 1.7265696683706906e-06,
      "loss": 1.4906,
      "step": 33500
    },
    {
      "epoch": 4.46,
      "learning_rate": 1.7075632455105518e-06,
      "loss": 1.4902,
      "step": 34000
    },
    {
      "epoch": 4.52,
      "learning_rate": 1.688556822650413e-06,
      "loss": 1.4898,
      "step": 34500
    },
    {
      "epoch": 4.59,
      "learning_rate": 1.669550399790274e-06,
      "loss": 1.4892,
      "step": 35000
    },
    {
      "epoch": 4.65,
      "learning_rate": 1.650543976930135e-06,
      "loss": 1.4891,
      "step": 35500
    },
    {
      "epoch": 4.72,
      "learning_rate": 1.6315375540699963e-06,
      "loss": 1.4886,
      "step": 36000
    },
    {
      "epoch": 4.78,
      "learning_rate": 1.6125311312098573e-06,
      "loss": 1.4881,
      "step": 36500
    },
    {
      "epoch": 4.85,
      "learning_rate": 1.5935247083497182e-06,
      "loss": 1.4879,
      "step": 37000
    },
    {
      "epoch": 4.92,
      "learning_rate": 1.5745182854895796e-06,
      "loss": 1.4878,
      "step": 37500
    },
    {
      "epoch": 4.98,
      "learning_rate": 1.5555118626294406e-06,
      "loss": 1.4873,
      "step": 38000
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.4904649257659912,
      "eval_runtime": 6.8983,
      "eval_samples_per_second": 142.934,
      "eval_steps_per_second": 0.87,
      "step": 38146
    },
    {
      "epoch": 5.05,
      "learning_rate": 1.5365054397693011e-06,
      "loss": 1.4875,
      "step": 38500
    },
    {
      "epoch": 5.11,
      "learning_rate": 1.5174990169091623e-06,
      "loss": 1.4863,
      "step": 39000
    },
    {
      "epoch": 5.18,
      "learning_rate": 1.4984925940490235e-06,
      "loss": 1.4857,
      "step": 39500
    },
    {
      "epoch": 5.24,
      "learning_rate": 1.4794861711888844e-06,
      "loss": 1.4854,
      "step": 40000
    },
    {
      "epoch": 5.31,
      "learning_rate": 1.4604797483287458e-06,
      "loss": 1.4848,
      "step": 40500
    },
    {
      "epoch": 5.37,
      "learning_rate": 1.4414733254686068e-06,
      "loss": 1.485,
      "step": 41000
    },
    {
      "epoch": 5.44,
      "learning_rate": 1.4224669026084677e-06,
      "loss": 1.4848,
      "step": 41500
    },
    {
      "epoch": 5.51,
      "learning_rate": 1.4034604797483287e-06,
      "loss": 1.4842,
      "step": 42000
    },
    {
      "epoch": 5.57,
      "learning_rate": 1.38445405688819e-06,
      "loss": 1.4839,
      "step": 42500
    },
    {
      "epoch": 5.64,
      "learning_rate": 1.365447634028051e-06,
      "loss": 1.4836,
      "step": 43000
    },
    {
      "epoch": 5.7,
      "learning_rate": 1.346441211167912e-06,
      "loss": 1.4834,
      "step": 43500
    },
    {
      "epoch": 5.77,
      "learning_rate": 1.327434788307773e-06,
      "loss": 1.4831,
      "step": 44000
    },
    {
      "epoch": 5.83,
      "learning_rate": 1.308428365447634e-06,
      "loss": 1.483,
      "step": 44500
    },
    {
      "epoch": 5.9,
      "learning_rate": 1.289421942587495e-06,
      "loss": 1.4827,
      "step": 45000
    },
    {
      "epoch": 5.96,
      "learning_rate": 1.2704155197273563e-06,
      "loss": 1.4826,
      "step": 45500
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.4877293109893799,
      "eval_runtime": 6.98,
      "eval_samples_per_second": 141.261,
      "eval_steps_per_second": 0.86,
      "step": 45775
    },
    {
      "epoch": 6.03,
      "learning_rate": 1.2514090968672173e-06,
      "loss": 1.4818,
      "step": 46000
    },
    {
      "epoch": 6.09,
      "learning_rate": 1.2324026740070782e-06,
      "loss": 1.4819,
      "step": 46500
    },
    {
      "epoch": 6.16,
      "learning_rate": 1.2133962511469392e-06,
      "loss": 1.4815,
      "step": 47000
    },
    {
      "epoch": 6.23,
      "learning_rate": 1.1943898282868006e-06,
      "loss": 1.4814,
      "step": 47500
    },
    {
      "epoch": 6.29,
      "learning_rate": 1.1753834054266616e-06,
      "loss": 1.4809,
      "step": 48000
    },
    {
      "epoch": 6.36,
      "learning_rate": 1.1563769825665225e-06,
      "loss": 1.4803,
      "step": 48500
    },
    {
      "epoch": 6.42,
      "learning_rate": 1.1373705597063835e-06,
      "loss": 1.4808,
      "step": 49000
    },
    {
      "epoch": 6.49,
      "learning_rate": 1.1183641368462449e-06,
      "loss": 1.4806,
      "step": 49500
    },
    {
      "epoch": 6.55,
      "learning_rate": 1.0993577139861058e-06,
      "loss": 1.4803,
      "step": 50000
    },
    {
      "epoch": 6.62,
      "learning_rate": 1.0803512911259668e-06,
      "loss": 1.4801,
      "step": 50500
    },
    {
      "epoch": 6.68,
      "learning_rate": 1.0613448682658278e-06,
      "loss": 1.4797,
      "step": 51000
    },
    {
      "epoch": 6.75,
      "learning_rate": 1.0423384454056887e-06,
      "loss": 1.4796,
      "step": 51500
    },
    {
      "epoch": 6.82,
      "learning_rate": 1.02333202254555e-06,
      "loss": 1.4795,
      "step": 52000
    },
    {
      "epoch": 6.88,
      "learning_rate": 1.004325599685411e-06,
      "loss": 1.4793,
      "step": 52500
    },
    {
      "epoch": 6.95,
      "learning_rate": 9.85319176825272e-07,
      "loss": 1.479,
      "step": 53000
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.4859654903411865,
      "eval_runtime": 7.0683,
      "eval_samples_per_second": 139.495,
      "eval_steps_per_second": 0.849,
      "step": 53404
    },
    {
      "epoch": 7.01,
      "learning_rate": 9.66312753965133e-07,
      "loss": 1.4786,
      "step": 53500
    },
    {
      "epoch": 7.08,
      "learning_rate": 9.473063311049942e-07,
      "loss": 1.4788,
      "step": 54000
    },
    {
      "epoch": 7.14,
      "learning_rate": 9.282999082448553e-07,
      "loss": 1.4785,
      "step": 54500
    },
    {
      "epoch": 7.21,
      "learning_rate": 9.092934853847164e-07,
      "loss": 1.4784,
      "step": 55000
    },
    {
      "epoch": 7.27,
      "learning_rate": 8.902870625245774e-07,
      "loss": 1.4781,
      "step": 55500
    },
    {
      "epoch": 7.34,
      "learning_rate": 8.712806396644386e-07,
      "loss": 1.478,
      "step": 56000
    },
    {
      "epoch": 7.41,
      "learning_rate": 8.522742168042993e-07,
      "loss": 1.4779,
      "step": 56500
    },
    {
      "epoch": 7.47,
      "learning_rate": 8.332677939441605e-07,
      "loss": 1.4779,
      "step": 57000
    },
    {
      "epoch": 7.54,
      "learning_rate": 8.142613710840215e-07,
      "loss": 1.4774,
      "step": 57500
    },
    {
      "epoch": 7.6,
      "learning_rate": 7.952549482238825e-07,
      "loss": 1.4775,
      "step": 58000
    },
    {
      "epoch": 7.67,
      "learning_rate": 7.762485253637437e-07,
      "loss": 1.4772,
      "step": 58500
    },
    {
      "epoch": 7.73,
      "learning_rate": 7.572421025036047e-07,
      "loss": 1.4771,
      "step": 59000
    },
    {
      "epoch": 7.8,
      "learning_rate": 7.382356796434658e-07,
      "loss": 1.4771,
      "step": 59500
    },
    {
      "epoch": 7.86,
      "learning_rate": 7.192292567833268e-07,
      "loss": 1.4769,
      "step": 60000
    },
    {
      "epoch": 7.93,
      "learning_rate": 7.00222833923188e-07,
      "loss": 1.4769,
      "step": 60500
    },
    {
      "epoch": 8.0,
      "learning_rate": 6.812164110630491e-07,
      "loss": 1.4771,
      "step": 61000
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.483931303024292,
      "eval_runtime": 6.9286,
      "eval_samples_per_second": 142.308,
      "eval_steps_per_second": 0.866,
      "step": 61034
    },
    {
      "epoch": 8.06,
      "learning_rate": 6.622099882029101e-07,
      "loss": 1.4775,
      "step": 61500
    },
    {
      "epoch": 8.13,
      "learning_rate": 6.432035653427712e-07,
      "loss": 1.4765,
      "step": 62000
    },
    {
      "epoch": 8.19,
      "learning_rate": 6.24197142482632e-07,
      "loss": 1.4762,
      "step": 62500
    },
    {
      "epoch": 8.26,
      "learning_rate": 6.05190719622493e-07,
      "loss": 1.4764,
      "step": 63000
    },
    {
      "epoch": 8.32,
      "learning_rate": 5.861842967623541e-07,
      "loss": 1.4762,
      "step": 63500
    },
    {
      "epoch": 8.39,
      "learning_rate": 5.671778739022152e-07,
      "loss": 1.4762,
      "step": 64000
    },
    {
      "epoch": 8.45,
      "learning_rate": 5.481714510420763e-07,
      "loss": 1.4761,
      "step": 64500
    },
    {
      "epoch": 8.52,
      "learning_rate": 5.291650281819373e-07,
      "loss": 1.4759,
      "step": 65000
    },
    {
      "epoch": 8.59,
      "learning_rate": 5.101586053217985e-07,
      "loss": 1.4758,
      "step": 65500
    },
    {
      "epoch": 8.65,
      "learning_rate": 4.911521824616596e-07,
      "loss": 1.4755,
      "step": 66000
    },
    {
      "epoch": 8.72,
      "learning_rate": 4.7214575960152063e-07,
      "loss": 1.4754,
      "step": 66500
    },
    {
      "epoch": 8.78,
      "learning_rate": 4.531393367413817e-07,
      "loss": 1.4757,
      "step": 67000
    },
    {
      "epoch": 8.85,
      "learning_rate": 4.341329138812427e-07,
      "loss": 1.4758,
      "step": 67500
    },
    {
      "epoch": 8.91,
      "learning_rate": 4.151264910211035e-07,
      "loss": 1.4754,
      "step": 68000
    },
    {
      "epoch": 8.98,
      "learning_rate": 3.961200681609647e-07,
      "loss": 1.4756,
      "step": 68500
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.4828386306762695,
      "eval_runtime": 6.934,
      "eval_samples_per_second": 142.198,
      "eval_steps_per_second": 0.865,
      "step": 68663
    },
    {
      "epoch": 9.04,
      "learning_rate": 3.771136453008257e-07,
      "loss": 1.4747,
      "step": 69000
    },
    {
      "epoch": 9.11,
      "learning_rate": 3.581072224406868e-07,
      "loss": 1.4753,
      "step": 69500
    },
    {
      "epoch": 9.18,
      "learning_rate": 3.3910079958054786e-07,
      "loss": 1.4752,
      "step": 70000
    },
    {
      "epoch": 9.24,
      "learning_rate": 3.20094376720409e-07,
      "loss": 1.4752,
      "step": 70500
    },
    {
      "epoch": 9.31,
      "learning_rate": 3.0108795386027005e-07,
      "loss": 1.4751,
      "step": 71000
    },
    {
      "epoch": 9.37,
      "learning_rate": 2.820815310001311e-07,
      "loss": 1.4751,
      "step": 71500
    },
    {
      "epoch": 9.44,
      "learning_rate": 2.630751081399922e-07,
      "loss": 1.4749,
      "step": 72000
    },
    {
      "epoch": 9.5,
      "learning_rate": 2.4406868527985326e-07,
      "loss": 1.4748,
      "step": 72500
    },
    {
      "epoch": 9.57,
      "learning_rate": 2.2506226241971439e-07,
      "loss": 1.4751,
      "step": 73000
    },
    {
      "epoch": 9.63,
      "learning_rate": 2.0605583955957543e-07,
      "loss": 1.4747,
      "step": 73500
    },
    {
      "epoch": 9.7,
      "learning_rate": 1.870494166994362e-07,
      "loss": 1.4748,
      "step": 74000
    },
    {
      "epoch": 9.77,
      "learning_rate": 1.6804299383929728e-07,
      "loss": 1.475,
      "step": 74500
    },
    {
      "epoch": 9.83,
      "learning_rate": 1.4903657097915838e-07,
      "loss": 1.4746,
      "step": 75000
    },
    {
      "epoch": 9.9,
      "learning_rate": 1.3003014811901947e-07,
      "loss": 1.4752,
      "step": 75500
    },
    {
      "epoch": 9.96,
      "learning_rate": 1.1102372525888054e-07,
      "loss": 1.4749,
      "step": 76000
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.4823230504989624,
      "eval_runtime": 6.8873,
      "eval_samples_per_second": 143.161,
      "eval_steps_per_second": 0.871,
      "step": 76290
    }
  ],
  "logging_steps": 500,
  "max_steps": 76290,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.609765756918825e+18,
  "trial_name": null,
  "trial_params": null
}