{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 708,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02824858757062147,
      "grad_norm": 5.842401568474987,
      "learning_rate": 5e-06,
      "loss": 2.0396,
      "step": 10
    },
    {
      "epoch": 0.05649717514124294,
      "grad_norm": 3.6388768595262957,
      "learning_rate": 4.997468222143782e-06,
      "loss": 1.7131,
      "step": 20
    },
    {
      "epoch": 0.0847457627118644,
      "grad_norm": 1.8710689080902667,
      "learning_rate": 4.989878016494418e-06,
      "loss": 1.5907,
      "step": 30
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 1.880666572553662,
      "learning_rate": 4.977244756423578e-06,
      "loss": 1.502,
      "step": 40
    },
    {
      "epoch": 0.14124293785310735,
      "grad_norm": 1.6520564729299156,
      "learning_rate": 4.959594029617741e-06,
      "loss": 1.4357,
      "step": 50
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 1.7284626155394651,
      "learning_rate": 4.9369615862523266e-06,
      "loss": 1.3794,
      "step": 60
    },
    {
      "epoch": 0.1977401129943503,
      "grad_norm": 1.7131842535751252,
      "learning_rate": 4.90939326658249e-06,
      "loss": 1.3396,
      "step": 70
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 1.6872621752920653,
      "learning_rate": 4.876944908097249e-06,
      "loss": 1.3119,
      "step": 80
    },
    {
      "epoch": 0.2542372881355932,
      "grad_norm": 1.6781047658941155,
      "learning_rate": 4.8396822324249915e-06,
      "loss": 1.2932,
      "step": 90
    },
    {
      "epoch": 0.2824858757062147,
      "grad_norm": 1.8225514648316858,
      "learning_rate": 4.797680712219421e-06,
      "loss": 1.2533,
      "step": 100
    },
    {
      "epoch": 0.3107344632768362,
      "grad_norm": 1.4304345855914073,
      "learning_rate": 4.751025418295565e-06,
      "loss": 1.2581,
      "step": 110
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 2.489693154849688,
      "learning_rate": 4.699810847325449e-06,
      "loss": 1.2615,
      "step": 120
    },
    {
      "epoch": 0.3672316384180791,
      "grad_norm": 1.497470889635536,
      "learning_rate": 4.644140730442432e-06,
      "loss": 1.2385,
      "step": 130
    },
    {
      "epoch": 0.3954802259887006,
      "grad_norm": 1.4852922561551125,
      "learning_rate": 4.584127823141855e-06,
      "loss": 1.2228,
      "step": 140
    },
    {
      "epoch": 0.423728813559322,
      "grad_norm": 1.4374567982916069,
      "learning_rate": 4.5198936769035504e-06,
      "loss": 1.2254,
      "step": 150
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 1.4496375733325404,
      "learning_rate": 4.451568392998767e-06,
      "loss": 1.2265,
      "step": 160
    },
    {
      "epoch": 0.480225988700565,
      "grad_norm": 1.2754388779607286,
      "learning_rate": 4.3792903589801515e-06,
      "loss": 1.1846,
      "step": 170
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 1.3975405752824914,
      "learning_rate": 4.30320596838852e-06,
      "loss": 1.178,
      "step": 180
    },
    {
      "epoch": 0.536723163841808,
      "grad_norm": 1.3749489429241677,
      "learning_rate": 4.223469324244115e-06,
      "loss": 1.1717,
      "step": 190
    },
    {
      "epoch": 0.5649717514124294,
      "grad_norm": 1.393315372114993,
      "learning_rate": 4.140241926922916e-06,
      "loss": 1.181,
      "step": 200
    },
    {
      "epoch": 0.5932203389830508,
      "grad_norm": 1.505577319035518,
      "learning_rate": 4.0536923470501775e-06,
      "loss": 1.1744,
      "step": 210
    },
    {
      "epoch": 0.6214689265536724,
      "grad_norm": 1.457055249771263,
      "learning_rate": 3.96399588407373e-06,
      "loss": 1.151,
      "step": 220
    },
    {
      "epoch": 0.6497175141242938,
      "grad_norm": 1.3812712992322103,
      "learning_rate": 3.8713342112085685e-06,
      "loss": 1.1787,
      "step": 230
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 1.528224921984006,
      "learning_rate": 3.775895007471876e-06,
      "loss": 1.158,
      "step": 240
    },
    {
      "epoch": 0.7062146892655368,
      "grad_norm": 1.4254969486921814,
      "learning_rate": 3.677871577553763e-06,
      "loss": 1.1662,
      "step": 250
    },
    {
      "epoch": 0.7344632768361582,
      "grad_norm": 1.4029062285962588,
      "learning_rate": 3.5774624602936344e-06,
      "loss": 1.1716,
      "step": 260
    },
    {
      "epoch": 0.7627118644067796,
      "grad_norm": 1.4621797650744357,
      "learning_rate": 3.474871026555204e-06,
      "loss": 1.1523,
      "step": 270
    },
    {
      "epoch": 0.7909604519774012,
      "grad_norm": 1.576846783408568,
      "learning_rate": 3.370305067314612e-06,
      "loss": 1.169,
      "step": 280
    },
    {
      "epoch": 0.8192090395480226,
      "grad_norm": 1.4553855180258597,
      "learning_rate": 3.2639763727959554e-06,
      "loss": 1.1374,
      "step": 290
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 1.3037242619402352,
      "learning_rate": 3.1561003035066435e-06,
      "loss": 1.144,
      "step": 300
    },
    {
      "epoch": 0.8757062146892656,
      "grad_norm": 1.4064392305723843,
      "learning_rate": 3.0468953540414304e-06,
      "loss": 1.1396,
      "step": 310
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 1.2072866070703256,
      "learning_rate": 2.936582710538593e-06,
      "loss": 1.1388,
      "step": 320
    },
    {
      "epoch": 0.9322033898305084,
      "grad_norm": 1.234511949962314,
      "learning_rate": 2.8253858026845958e-06,
      "loss": 1.149,
      "step": 330
    },
    {
      "epoch": 0.96045197740113,
      "grad_norm": 1.3682697011912646,
      "learning_rate": 2.7135298511746276e-06,
      "loss": 1.1463,
      "step": 340
    },
    {
      "epoch": 0.9887005649717514,
      "grad_norm": 1.4595117952046124,
      "learning_rate": 2.6012414115455826e-06,
      "loss": 1.1339,
      "step": 350
    },
    {
      "epoch": 1.0169491525423728,
      "grad_norm": 1.365355679432521,
      "learning_rate": 2.488747915305431e-06,
      "loss": 1.0592,
      "step": 360
    },
    {
      "epoch": 1.0451977401129944,
      "grad_norm": 1.4547925198477407,
      "learning_rate": 2.376277209288372e-06,
      "loss": 1.0288,
      "step": 370
    },
    {
      "epoch": 1.073446327683616,
      "grad_norm": 1.2787445662747539,
      "learning_rate": 2.2640570941687794e-06,
      "loss": 1.022,
      "step": 380
    },
    {
      "epoch": 1.1016949152542372,
      "grad_norm": 1.3427132830957944,
      "learning_rate": 2.1523148630686397e-06,
      "loss": 1.0311,
      "step": 390
    },
    {
      "epoch": 1.1299435028248588,
      "grad_norm": 1.446710010618482,
      "learning_rate": 2.0412768411929948e-06,
      "loss": 1.017,
      "step": 400
    },
    {
      "epoch": 1.1581920903954803,
      "grad_norm": 1.34481917501583,
      "learning_rate": 1.931167927425832e-06,
      "loss": 1.0266,
      "step": 410
    },
    {
      "epoch": 1.1864406779661016,
      "grad_norm": 1.3341116732215694,
      "learning_rate": 1.8222111388148678e-06,
      "loss": 1.0236,
      "step": 420
    },
    {
      "epoch": 1.2146892655367232,
      "grad_norm": 1.345613554920642,
      "learning_rate": 1.714627158867857e-06,
      "loss": 1.0109,
      "step": 430
    },
    {
      "epoch": 1.2429378531073447,
      "grad_norm": 1.2833581931894298,
      "learning_rate": 1.6086338905752883e-06,
      "loss": 0.9996,
      "step": 440
    },
    {
      "epoch": 1.271186440677966,
      "grad_norm": 1.3699670070856527,
      "learning_rate": 1.50444601506482e-06,
      "loss": 1.0128,
      "step": 450
    },
    {
      "epoch": 1.2994350282485876,
      "grad_norm": 1.2610914382885658,
      "learning_rate": 1.4022745567813334e-06,
      "loss": 1.0094,
      "step": 460
    },
    {
      "epoch": 1.327683615819209,
      "grad_norm": 1.2627951088836191,
      "learning_rate": 1.3023264560733268e-06,
      "loss": 1.0206,
      "step": 470
    },
    {
      "epoch": 1.3559322033898304,
      "grad_norm": 1.268968791060816,
      "learning_rate": 1.2048041500513136e-06,
      "loss": 1.0136,
      "step": 480
    },
    {
      "epoch": 1.384180790960452,
      "grad_norm": 1.2875833787086686,
      "learning_rate": 1.1099051625671928e-06,
      "loss": 1.0029,
      "step": 490
    },
    {
      "epoch": 1.4124293785310735,
      "grad_norm": 1.2562663969235288,
      "learning_rate": 1.0178217041450355e-06,
      "loss": 1.012,
      "step": 500
    },
    {
      "epoch": 1.4406779661016949,
      "grad_norm": 1.2156705609077063,
      "learning_rate": 9.287402826736089e-07,
      "loss": 1.0057,
      "step": 510
    },
    {
      "epoch": 1.4689265536723164,
      "grad_norm": 2.005409061506591,
      "learning_rate": 8.428413256491386e-07,
      "loss": 1.0042,
      "step": 520
    },
    {
      "epoch": 1.497175141242938,
      "grad_norm": 1.2904127978163176,
      "learning_rate": 7.602988147334372e-07,
      "loss": 1.0029,
      "step": 530
    },
    {
      "epoch": 1.5254237288135593,
      "grad_norm": 1.2327199709726766,
      "learning_rate": 6.81279933367571e-07,
      "loss": 0.999,
      "step": 540
    },
    {
      "epoch": 1.5536723163841808,
      "grad_norm": 1.3251476089228396,
      "learning_rate": 6.059447281547929e-07,
      "loss": 1.0063,
      "step": 550
    },
    {
      "epoch": 1.5819209039548023,
      "grad_norm": 1.2684033556573027,
      "learning_rate": 5.344457846985837e-07,
      "loss": 1.0041,
      "step": 560
    },
    {
      "epoch": 1.6101694915254239,
      "grad_norm": 1.274213451781422,
      "learning_rate": 4.6692791855237144e-07,
      "loss": 1.0102,
      "step": 570
    },
    {
      "epoch": 1.6384180790960452,
      "grad_norm": 1.2004747141578425,
      "learning_rate": 4.0352788190688245e-07,
      "loss": 0.9986,
      "step": 580
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.2138867752979392,
      "learning_rate": 3.443740866092074e-07,
      "loss": 0.9936,
      "step": 590
    },
    {
      "epoch": 1.694915254237288,
      "grad_norm": 1.3657230357705068,
      "learning_rate": 2.895863440745822e-07,
      "loss": 1.0085,
      "step": 600
    },
    {
      "epoch": 1.7231638418079096,
      "grad_norm": 1.2178452975739655,
      "learning_rate": 2.3927562261768095e-07,
      "loss": 1.0114,
      "step": 610
    },
    {
      "epoch": 1.7514124293785311,
      "grad_norm": 1.201511284318748,
      "learning_rate": 1.935438226949146e-07,
      "loss": 1.011,
      "step": 620
    },
    {
      "epoch": 1.7796610169491527,
      "grad_norm": 1.2103707783122326,
      "learning_rate": 1.5248357051297957e-07,
      "loss": 1.0053,
      "step": 630
    },
    {
      "epoch": 1.807909604519774,
      "grad_norm": 1.206125451520313,
      "learning_rate": 1.1617803042167142e-07,
      "loss": 0.9949,
      "step": 640
    },
    {
      "epoch": 1.8361581920903953,
      "grad_norm": 1.327611608679995,
      "learning_rate": 8.4700736470959e-08,
      "loss": 1.0107,
      "step": 650
    },
    {
      "epoch": 1.8644067796610169,
      "grad_norm": 1.2479460675046632,
      "learning_rate": 5.811544347348097e-08,
      "loss": 0.9932,
      "step": 660
    },
    {
      "epoch": 1.8926553672316384,
      "grad_norm": 1.2150911321344626,
      "learning_rate": 3.647599787412692e-08,
      "loss": 1.0028,
      "step": 670
    },
    {
      "epoch": 1.92090395480226,
      "grad_norm": 1.1712546508255446,
      "learning_rate": 1.9826228688248073e-08,
      "loss": 0.9951,
      "step": 680
    },
    {
      "epoch": 1.9491525423728815,
      "grad_norm": 1.2304982193614624,
      "learning_rate": 8.19985872939355e-09,
      "loss": 0.9928,
      "step": 690
    },
    {
      "epoch": 1.9774011299435028,
      "grad_norm": 1.2367698151490922,
      "learning_rate": 1.6204363063712647e-09,
      "loss": 0.9979,
      "step": 700
    }
  ],
  "logging_steps": 10,
  "max_steps": 708,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 230913547960320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}