{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09976057462090981,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009976057462090981,
      "grad_norm": 0.0038604736328125,
      "learning_rate": 0.00019800000000000002,
      "loss": 0.6617,
      "step": 50
    },
    {
      "epoch": 0.0019952114924181963,
      "grad_norm": 6.3125,
      "learning_rate": 0.000196,
      "loss": 0.4755,
      "step": 100
    },
    {
      "epoch": 0.0029928172386272946,
      "grad_norm": 8.5625,
      "learning_rate": 0.000194,
      "loss": 0.7675,
      "step": 150
    },
    {
      "epoch": 0.0039904229848363925,
      "grad_norm": 2.375,
      "learning_rate": 0.000192,
      "loss": 0.3436,
      "step": 200
    },
    {
      "epoch": 0.004988028731045491,
      "grad_norm": 0.008544921875,
      "learning_rate": 0.00019,
      "loss": 0.3634,
      "step": 250
    },
    {
      "epoch": 0.005985634477254589,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.000188,
      "loss": 0.2994,
      "step": 300
    },
    {
      "epoch": 0.006983240223463687,
      "grad_norm": 0.003570556640625,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.3632,
      "step": 350
    },
    {
      "epoch": 0.007980845969672785,
      "grad_norm": 0.6875,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.4774,
      "step": 400
    },
    {
      "epoch": 0.008978451715881883,
      "grad_norm": 22.875,
      "learning_rate": 0.000182,
      "loss": 0.4284,
      "step": 450
    },
    {
      "epoch": 0.009976057462090982,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00018,
      "loss": 0.2701,
      "step": 500
    },
    {
      "epoch": 0.01097366320830008,
      "grad_norm": 2.640625,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.3871,
      "step": 550
    },
    {
      "epoch": 0.011971268954509178,
      "grad_norm": 0.031982421875,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.4374,
      "step": 600
    },
    {
      "epoch": 0.012968874700718277,
      "grad_norm": 0.369140625,
      "learning_rate": 0.000174,
      "loss": 0.5315,
      "step": 650
    },
    {
      "epoch": 0.013966480446927373,
      "grad_norm": 1.046875,
      "learning_rate": 0.000172,
      "loss": 0.2943,
      "step": 700
    },
    {
      "epoch": 0.014964086193136472,
      "grad_norm": 0.10986328125,
      "learning_rate": 0.00017,
      "loss": 0.4425,
      "step": 750
    },
    {
      "epoch": 0.01596169193934557,
      "grad_norm": 0.0390625,
      "learning_rate": 0.000168,
      "loss": 0.5047,
      "step": 800
    },
    {
      "epoch": 0.01695929768555467,
      "grad_norm": 0.0003719329833984375,
      "learning_rate": 0.000166,
      "loss": 0.5276,
      "step": 850
    },
    {
      "epoch": 0.017956903431763767,
      "grad_norm": 4.71875,
      "learning_rate": 0.000164,
      "loss": 0.4847,
      "step": 900
    },
    {
      "epoch": 0.018954509177972863,
      "grad_norm": 0.0517578125,
      "learning_rate": 0.000162,
      "loss": 0.3319,
      "step": 950
    },
    {
      "epoch": 0.019952114924181964,
      "grad_norm": 2.40625,
      "learning_rate": 0.00016,
      "loss": 0.5723,
      "step": 1000
    },
    {
      "epoch": 0.02094972067039106,
      "grad_norm": 16.25,
      "learning_rate": 0.00015800000000000002,
      "loss": 0.2602,
      "step": 1050
    },
    {
      "epoch": 0.02194732641660016,
      "grad_norm": 8.0625,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.4477,
      "step": 1100
    },
    {
      "epoch": 0.022944932162809257,
      "grad_norm": 23.75,
      "learning_rate": 0.000154,
      "loss": 0.3337,
      "step": 1150
    },
    {
      "epoch": 0.023942537909018357,
      "grad_norm": 0.00189208984375,
      "learning_rate": 0.000152,
      "loss": 0.3281,
      "step": 1200
    },
    {
      "epoch": 0.024940143655227454,
      "grad_norm": 4.96875,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.586,
      "step": 1250
    },
    {
      "epoch": 0.025937749401436554,
      "grad_norm": 0.10595703125,
      "learning_rate": 0.000148,
      "loss": 0.4816,
      "step": 1300
    },
    {
      "epoch": 0.02693535514764565,
      "grad_norm": 0.49609375,
      "learning_rate": 0.000146,
      "loss": 0.2697,
      "step": 1350
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 3.9375,
      "learning_rate": 0.000144,
      "loss": 0.3875,
      "step": 1400
    },
    {
      "epoch": 0.028930566640063847,
      "grad_norm": 0.25390625,
      "learning_rate": 0.000142,
      "loss": 0.4165,
      "step": 1450
    },
    {
      "epoch": 0.029928172386272944,
      "grad_norm": 0.62109375,
      "learning_rate": 0.00014,
      "loss": 0.369,
      "step": 1500
    },
    {
      "epoch": 0.030925778132482044,
      "grad_norm": 4.1875,
      "learning_rate": 0.000138,
      "loss": 0.5041,
      "step": 1550
    },
    {
      "epoch": 0.03192338387869114,
      "grad_norm": 41.75,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.217,
      "step": 1600
    },
    {
      "epoch": 0.03292098962490024,
      "grad_norm": 0.01171875,
      "learning_rate": 0.000134,
      "loss": 0.2277,
      "step": 1650
    },
    {
      "epoch": 0.03391859537110934,
      "grad_norm": 42.25,
      "learning_rate": 0.000132,
      "loss": 0.404,
      "step": 1700
    },
    {
      "epoch": 0.034916201117318434,
      "grad_norm": 3.09375,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.4747,
      "step": 1750
    },
    {
      "epoch": 0.035913806863527534,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.2959,
      "step": 1800
    },
    {
      "epoch": 0.036911412609736634,
      "grad_norm": 0.0250244140625,
      "learning_rate": 0.000126,
      "loss": 0.3211,
      "step": 1850
    },
    {
      "epoch": 0.03790901835594573,
      "grad_norm": 0.043212890625,
      "learning_rate": 0.000124,
      "loss": 0.5209,
      "step": 1900
    },
    {
      "epoch": 0.03890662410215483,
      "grad_norm": 0.02734375,
      "learning_rate": 0.000122,
      "loss": 0.36,
      "step": 1950
    },
    {
      "epoch": 0.03990422984836393,
      "grad_norm": 0.01025390625,
      "learning_rate": 0.00012,
      "loss": 0.4134,
      "step": 2000
    },
    {
      "epoch": 0.04090183559457303,
      "grad_norm": 13.3125,
      "learning_rate": 0.000118,
      "loss": 0.5532,
      "step": 2050
    },
    {
      "epoch": 0.04189944134078212,
      "grad_norm": 0.0072021484375,
      "learning_rate": 0.000116,
      "loss": 0.383,
      "step": 2100
    },
    {
      "epoch": 0.04289704708699122,
      "grad_norm": 0.453125,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.2125,
      "step": 2150
    },
    {
      "epoch": 0.04389465283320032,
      "grad_norm": 0.0068359375,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.4954,
      "step": 2200
    },
    {
      "epoch": 0.04489225857940942,
      "grad_norm": 0.0162353515625,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.505,
      "step": 2250
    },
    {
      "epoch": 0.045889864325618514,
      "grad_norm": 0.0024261474609375,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.6058,
      "step": 2300
    },
    {
      "epoch": 0.046887470071827614,
      "grad_norm": 0.0030059814453125,
      "learning_rate": 0.00010600000000000002,
      "loss": 0.3943,
      "step": 2350
    },
    {
      "epoch": 0.047885075818036714,
      "grad_norm": 10.875,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.3382,
      "step": 2400
    },
    {
      "epoch": 0.04888268156424581,
      "grad_norm": 0.0181884765625,
      "learning_rate": 0.00010200000000000001,
      "loss": 0.3642,
      "step": 2450
    },
    {
      "epoch": 0.04988028731045491,
      "grad_norm": 3.265625,
      "learning_rate": 0.0001,
      "loss": 0.4616,
      "step": 2500
    },
    {
      "epoch": 0.05087789305666401,
      "grad_norm": 7.0,
      "learning_rate": 9.8e-05,
      "loss": 0.3914,
      "step": 2550
    },
    {
      "epoch": 0.05187549880287311,
      "grad_norm": 15.0,
      "learning_rate": 9.6e-05,
      "loss": 0.3353,
      "step": 2600
    },
    {
      "epoch": 0.0528731045490822,
      "grad_norm": 0.0050048828125,
      "learning_rate": 9.4e-05,
      "loss": 0.4456,
      "step": 2650
    },
    {
      "epoch": 0.0538707102952913,
      "grad_norm": 0.006927490234375,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.2634,
      "step": 2700
    },
    {
      "epoch": 0.0548683160415004,
      "grad_norm": 0.002685546875,
      "learning_rate": 9e-05,
      "loss": 0.3685,
      "step": 2750
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 9.0625,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.352,
      "step": 2800
    },
    {
      "epoch": 0.056863527533918594,
      "grad_norm": 0.0137939453125,
      "learning_rate": 8.6e-05,
      "loss": 0.4359,
      "step": 2850
    },
    {
      "epoch": 0.057861133280127694,
      "grad_norm": 0.010009765625,
      "learning_rate": 8.4e-05,
      "loss": 0.3103,
      "step": 2900
    },
    {
      "epoch": 0.058858739026336794,
      "grad_norm": 0.01141357421875,
      "learning_rate": 8.2e-05,
      "loss": 0.4468,
      "step": 2950
    },
    {
      "epoch": 0.05985634477254589,
      "grad_norm": 4.15625,
      "learning_rate": 8e-05,
      "loss": 0.299,
      "step": 3000
    },
    {
      "epoch": 0.06085395051875499,
      "grad_norm": 3.984375,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.3858,
      "step": 3050
    },
    {
      "epoch": 0.06185155626496409,
      "grad_norm": 0.07763671875,
      "learning_rate": 7.6e-05,
      "loss": 0.5305,
      "step": 3100
    },
    {
      "epoch": 0.06284916201117319,
      "grad_norm": 0.018310546875,
      "learning_rate": 7.4e-05,
      "loss": 0.4533,
      "step": 3150
    },
    {
      "epoch": 0.06384676775738228,
      "grad_norm": 36.5,
      "learning_rate": 7.2e-05,
      "loss": 0.4423,
      "step": 3200
    },
    {
      "epoch": 0.06484437350359137,
      "grad_norm": 0.0289306640625,
      "learning_rate": 7e-05,
      "loss": 0.5003,
      "step": 3250
    },
    {
      "epoch": 0.06584197924980048,
      "grad_norm": 4.625,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.527,
      "step": 3300
    },
    {
      "epoch": 0.06683958499600957,
      "grad_norm": 0.20703125,
      "learning_rate": 6.6e-05,
      "loss": 0.2865,
      "step": 3350
    },
    {
      "epoch": 0.06783719074221868,
      "grad_norm": 0.04296875,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.3976,
      "step": 3400
    },
    {
      "epoch": 0.06883479648842777,
      "grad_norm": 0.01275634765625,
      "learning_rate": 6.2e-05,
      "loss": 0.2756,
      "step": 3450
    },
    {
      "epoch": 0.06983240223463687,
      "grad_norm": 8.25,
      "learning_rate": 6e-05,
      "loss": 0.2762,
      "step": 3500
    },
    {
      "epoch": 0.07083000798084597,
      "grad_norm": 6.125,
      "learning_rate": 5.8e-05,
      "loss": 0.4,
      "step": 3550
    },
    {
      "epoch": 0.07182761372705507,
      "grad_norm": 0.00193023681640625,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.4484,
      "step": 3600
    },
    {
      "epoch": 0.07282521947326416,
      "grad_norm": 0.0228271484375,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.1631,
      "step": 3650
    },
    {
      "epoch": 0.07382282521947327,
      "grad_norm": 0.0634765625,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.3579,
      "step": 3700
    },
    {
      "epoch": 0.07482043096568236,
      "grad_norm": 11.4375,
      "learning_rate": 5e-05,
      "loss": 0.2258,
      "step": 3750
    },
    {
      "epoch": 0.07581803671189145,
      "grad_norm": 20.875,
      "learning_rate": 4.8e-05,
      "loss": 0.4282,
      "step": 3800
    },
    {
      "epoch": 0.07681564245810056,
      "grad_norm": 0.046875,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.3967,
      "step": 3850
    },
    {
      "epoch": 0.07781324820430965,
      "grad_norm": 0.0035552978515625,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.3414,
      "step": 3900
    },
    {
      "epoch": 0.07881085395051876,
      "grad_norm": 0.00653076171875,
      "learning_rate": 4.2e-05,
      "loss": 0.3421,
      "step": 3950
    },
    {
      "epoch": 0.07980845969672785,
      "grad_norm": 0.0201416015625,
      "learning_rate": 4e-05,
      "loss": 0.2607,
      "step": 4000
    },
    {
      "epoch": 0.08080606544293695,
      "grad_norm": 0.0027313232421875,
      "learning_rate": 3.8e-05,
      "loss": 0.3414,
      "step": 4050
    },
    {
      "epoch": 0.08180367118914605,
      "grad_norm": 0.010986328125,
      "learning_rate": 3.6e-05,
      "loss": 0.1826,
      "step": 4100
    },
    {
      "epoch": 0.08280127693535515,
      "grad_norm": 34.25,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.374,
      "step": 4150
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 11.75,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.3928,
      "step": 4200
    },
    {
      "epoch": 0.08479648842777335,
      "grad_norm": 2.203125,
      "learning_rate": 3e-05,
      "loss": 0.2718,
      "step": 4250
    },
    {
      "epoch": 0.08579409417398244,
      "grad_norm": 0.004302978515625,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.4629,
      "step": 4300
    },
    {
      "epoch": 0.08679169992019153,
      "grad_norm": 0.04931640625,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.6785,
      "step": 4350
    },
    {
      "epoch": 0.08778930566640064,
      "grad_norm": 2.90625,
      "learning_rate": 2.4e-05,
      "loss": 0.3149,
      "step": 4400
    },
    {
      "epoch": 0.08878691141260973,
      "grad_norm": 15.0,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.1649,
      "step": 4450
    },
    {
      "epoch": 0.08978451715881884,
      "grad_norm": 13.5625,
      "learning_rate": 2e-05,
      "loss": 0.3696,
      "step": 4500
    },
    {
      "epoch": 0.09078212290502793,
      "grad_norm": 4.71875,
      "learning_rate": 1.8e-05,
      "loss": 0.2958,
      "step": 4550
    },
    {
      "epoch": 0.09177972865123703,
      "grad_norm": 0.0091552734375,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.4197,
      "step": 4600
    },
    {
      "epoch": 0.09277733439744613,
      "grad_norm": 1.2578125,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.3516,
      "step": 4650
    },
    {
      "epoch": 0.09377494014365523,
      "grad_norm": 0.0252685546875,
      "learning_rate": 1.2e-05,
      "loss": 0.3903,
      "step": 4700
    },
    {
      "epoch": 0.09477254588986432,
      "grad_norm": 0.001434326171875,
      "learning_rate": 1e-05,
      "loss": 0.4062,
      "step": 4750
    },
    {
      "epoch": 0.09577015163607343,
      "grad_norm": 3.625,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.5118,
      "step": 4800
    },
    {
      "epoch": 0.09676775738228252,
      "grad_norm": 0.001373291015625,
      "learning_rate": 6e-06,
      "loss": 0.3564,
      "step": 4850
    },
    {
      "epoch": 0.09776536312849161,
      "grad_norm": 0.017578125,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.2415,
      "step": 4900
    },
    {
      "epoch": 0.09876296887470072,
      "grad_norm": 5.9375,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.4096,
      "step": 4950
    },
    {
      "epoch": 0.09976057462090981,
      "grad_norm": 0.0230712890625,
      "learning_rate": 0.0,
      "loss": 0.3159,
      "step": 5000
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.937397973909504e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}