{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09245562130177515,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009245562130177514,
      "grad_norm": 0.0,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.6901,
      "step": 50
    },
    {
      "epoch": 0.0018491124260355029,
      "grad_norm": 1.09375,
      "learning_rate": 0.000196,
      "loss": 0.4966,
      "step": 100
    },
    {
      "epoch": 0.0027736686390532543,
      "grad_norm": 67.5,
      "learning_rate": 0.000194,
      "loss": 0.8836,
      "step": 150
    },
    {
      "epoch": 0.0036982248520710057,
      "grad_norm": 28.875,
      "learning_rate": 0.000192,
      "loss": 0.6205,
      "step": 200
    },
    {
      "epoch": 0.004622781065088758,
      "grad_norm": 0.023193359375,
      "learning_rate": 0.00019,
      "loss": 0.7316,
      "step": 250
    },
    {
      "epoch": 0.005547337278106509,
      "grad_norm": 0.37109375,
      "learning_rate": 0.000188,
      "loss": 0.7953,
      "step": 300
    },
    {
      "epoch": 0.0064718934911242604,
      "grad_norm": 5.78125,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.5551,
      "step": 350
    },
    {
      "epoch": 0.0073964497041420114,
      "grad_norm": 0.0303955078125,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.8572,
      "step": 400
    },
    {
      "epoch": 0.008321005917159764,
      "grad_norm": 0.0,
      "learning_rate": 0.000182,
      "loss": 0.8262,
      "step": 450
    },
    {
      "epoch": 0.009245562130177515,
      "grad_norm": 0.0,
      "learning_rate": 0.00018,
      "loss": 0.4421,
      "step": 500
    },
    {
      "epoch": 0.010170118343195266,
      "grad_norm": 0.0,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.5296,
      "step": 550
    },
    {
      "epoch": 0.011094674556213017,
      "grad_norm": 0.025146484375,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.5619,
      "step": 600
    },
    {
      "epoch": 0.01201923076923077,
      "grad_norm": 0.0,
      "learning_rate": 0.000174,
      "loss": 0.6676,
      "step": 650
    },
    {
      "epoch": 0.012943786982248521,
      "grad_norm": 0.0,
      "learning_rate": 0.000172,
      "loss": 0.5962,
      "step": 700
    },
    {
      "epoch": 0.013868343195266272,
      "grad_norm": 0.0162353515625,
      "learning_rate": 0.00017,
      "loss": 0.7956,
      "step": 750
    },
    {
      "epoch": 0.014792899408284023,
      "grad_norm": 18.625,
      "learning_rate": 0.000168,
      "loss": 0.84,
      "step": 800
    },
    {
      "epoch": 0.015717455621301776,
      "grad_norm": 27.625,
      "learning_rate": 0.000166,
      "loss": 0.7259,
      "step": 850
    },
    {
      "epoch": 0.01664201183431953,
      "grad_norm": 0.0,
      "learning_rate": 0.000164,
      "loss": 0.5285,
      "step": 900
    },
    {
      "epoch": 0.017566568047337278,
      "grad_norm": 16.125,
      "learning_rate": 0.000162,
      "loss": 0.8432,
      "step": 950
    },
    {
      "epoch": 0.01849112426035503,
      "grad_norm": 0.0,
      "learning_rate": 0.00016,
      "loss": 0.5795,
      "step": 1000
    },
    {
      "epoch": 0.01941568047337278,
      "grad_norm": 3.3125,
      "learning_rate": 0.00015800000000000002,
      "loss": 0.5298,
      "step": 1050
    },
    {
      "epoch": 0.020340236686390532,
      "grad_norm": 3.703125,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.5904,
      "step": 1100
    },
    {
      "epoch": 0.021264792899408285,
      "grad_norm": 0.0,
      "learning_rate": 0.000154,
      "loss": 0.6087,
      "step": 1150
    },
    {
      "epoch": 0.022189349112426034,
      "grad_norm": 0.5859375,
      "learning_rate": 0.000152,
      "loss": 0.729,
      "step": 1200
    },
    {
      "epoch": 0.023113905325443787,
      "grad_norm": 0.0,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.3885,
      "step": 1250
    },
    {
      "epoch": 0.02403846153846154,
      "grad_norm": 0.0,
      "learning_rate": 0.000148,
      "loss": 0.3173,
      "step": 1300
    },
    {
      "epoch": 0.02496301775147929,
      "grad_norm": 0.0,
      "learning_rate": 0.000146,
      "loss": 0.5709,
      "step": 1350
    },
    {
      "epoch": 0.025887573964497042,
      "grad_norm": 0.1884765625,
      "learning_rate": 0.000144,
      "loss": 0.8465,
      "step": 1400
    },
    {
      "epoch": 0.026812130177514795,
      "grad_norm": 0.0,
      "learning_rate": 0.000142,
      "loss": 0.4306,
      "step": 1450
    },
    {
      "epoch": 0.027736686390532544,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00014,
      "loss": 0.549,
      "step": 1500
    },
    {
      "epoch": 0.028661242603550297,
      "grad_norm": 2.9375,
      "learning_rate": 0.000138,
      "loss": 0.3375,
      "step": 1550
    },
    {
      "epoch": 0.029585798816568046,
      "grad_norm": 0.03369140625,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.5455,
      "step": 1600
    },
    {
      "epoch": 0.0305103550295858,
      "grad_norm": 0.09375,
      "learning_rate": 0.000134,
      "loss": 0.5112,
      "step": 1650
    },
    {
      "epoch": 0.03143491124260355,
      "grad_norm": 1.78125,
      "learning_rate": 0.000132,
      "loss": 0.4484,
      "step": 1700
    },
    {
      "epoch": 0.0323594674556213,
      "grad_norm": 0.018310546875,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.5034,
      "step": 1750
    },
    {
      "epoch": 0.03328402366863906,
      "grad_norm": 0.0,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.5168,
      "step": 1800
    },
    {
      "epoch": 0.034208579881656806,
      "grad_norm": 0.018798828125,
      "learning_rate": 0.000126,
      "loss": 0.2794,
      "step": 1850
    },
    {
      "epoch": 0.035133136094674555,
      "grad_norm": 0.0,
      "learning_rate": 0.000124,
      "loss": 0.6018,
      "step": 1900
    },
    {
      "epoch": 0.036057692307692304,
      "grad_norm": 0.0,
      "learning_rate": 0.000122,
      "loss": 0.597,
      "step": 1950
    },
    {
      "epoch": 0.03698224852071006,
      "grad_norm": 0.1044921875,
      "learning_rate": 0.00012,
      "loss": 0.3998,
      "step": 2000
    },
    {
      "epoch": 0.03790680473372781,
      "grad_norm": 0.0252685546875,
      "learning_rate": 0.000118,
      "loss": 0.3998,
      "step": 2050
    },
    {
      "epoch": 0.03883136094674556,
      "grad_norm": 0.0,
      "learning_rate": 0.000116,
      "loss": 0.8371,
      "step": 2100
    },
    {
      "epoch": 0.039755917159763315,
      "grad_norm": 0.10693359375,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.4418,
      "step": 2150
    },
    {
      "epoch": 0.040680473372781065,
      "grad_norm": 0.068359375,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.427,
      "step": 2200
    },
    {
      "epoch": 0.041605029585798814,
      "grad_norm": 0.0,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.5198,
      "step": 2250
    },
    {
      "epoch": 0.04252958579881657,
      "grad_norm": 0.244140625,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.4875,
      "step": 2300
    },
    {
      "epoch": 0.04345414201183432,
      "grad_norm": 3.375,
      "learning_rate": 0.00010600000000000002,
      "loss": 0.4774,
      "step": 2350
    },
    {
      "epoch": 0.04437869822485207,
      "grad_norm": 3.234375,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.4572,
      "step": 2400
    },
    {
      "epoch": 0.045303254437869825,
      "grad_norm": 0.0,
      "learning_rate": 0.00010200000000000001,
      "loss": 0.4148,
      "step": 2450
    },
    {
      "epoch": 0.046227810650887574,
      "grad_norm": 0.1240234375,
      "learning_rate": 0.0001,
      "loss": 0.6811,
      "step": 2500
    },
    {
      "epoch": 0.04715236686390532,
      "grad_norm": 0.0,
      "learning_rate": 9.8e-05,
      "loss": 0.428,
      "step": 2550
    },
    {
      "epoch": 0.04807692307692308,
      "grad_norm": 0.10400390625,
      "learning_rate": 9.6e-05,
      "loss": 0.3754,
      "step": 2600
    },
    {
      "epoch": 0.04900147928994083,
      "grad_norm": 0.0,
      "learning_rate": 9.4e-05,
      "loss": 0.4773,
      "step": 2650
    },
    {
      "epoch": 0.04992603550295858,
      "grad_norm": 3.765625,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.7884,
      "step": 2700
    },
    {
      "epoch": 0.050850591715976334,
      "grad_norm": 0.019775390625,
      "learning_rate": 9e-05,
      "loss": 0.2355,
      "step": 2750
    },
    {
      "epoch": 0.051775147928994084,
      "grad_norm": 0.07421875,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.5385,
      "step": 2800
    },
    {
      "epoch": 0.05269970414201183,
      "grad_norm": 2.625,
      "learning_rate": 8.6e-05,
      "loss": 0.4285,
      "step": 2850
    },
    {
      "epoch": 0.05362426035502959,
      "grad_norm": 4.96875,
      "learning_rate": 8.4e-05,
      "loss": 0.6612,
      "step": 2900
    },
    {
      "epoch": 0.05454881656804734,
      "grad_norm": 0.0198974609375,
      "learning_rate": 8.2e-05,
      "loss": 0.283,
      "step": 2950
    },
    {
      "epoch": 0.05547337278106509,
      "grad_norm": 4.3125,
      "learning_rate": 8e-05,
      "loss": 0.414,
      "step": 3000
    },
    {
      "epoch": 0.05639792899408284,
      "grad_norm": 4.625,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.5375,
      "step": 3050
    },
    {
      "epoch": 0.05732248520710059,
      "grad_norm": 0.0,
      "learning_rate": 7.6e-05,
      "loss": 0.6285,
      "step": 3100
    },
    {
      "epoch": 0.05824704142011834,
      "grad_norm": 0.0118408203125,
      "learning_rate": 7.4e-05,
      "loss": 0.5064,
      "step": 3150
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 0.058837890625,
      "learning_rate": 7.2e-05,
      "loss": 0.4763,
      "step": 3200
    },
    {
      "epoch": 0.06009615384615385,
      "grad_norm": 0.0,
      "learning_rate": 7e-05,
      "loss": 0.5027,
      "step": 3250
    },
    {
      "epoch": 0.0610207100591716,
      "grad_norm": 0.0927734375,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.6967,
      "step": 3300
    },
    {
      "epoch": 0.061945266272189346,
      "grad_norm": 3.328125,
      "learning_rate": 6.6e-05,
      "loss": 0.3514,
      "step": 3350
    },
    {
      "epoch": 0.0628698224852071,
      "grad_norm": 0.0,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.4051,
      "step": 3400
    },
    {
      "epoch": 0.06379437869822485,
      "grad_norm": 0.0,
      "learning_rate": 6.2e-05,
      "loss": 0.4403,
      "step": 3450
    },
    {
      "epoch": 0.0647189349112426,
      "grad_norm": 0.0,
      "learning_rate": 6e-05,
      "loss": 0.4544,
      "step": 3500
    },
    {
      "epoch": 0.06564349112426035,
      "grad_norm": 0.033203125,
      "learning_rate": 5.8e-05,
      "loss": 0.4363,
      "step": 3550
    },
    {
      "epoch": 0.06656804733727811,
      "grad_norm": 0.205078125,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.4371,
      "step": 3600
    },
    {
      "epoch": 0.06749260355029586,
      "grad_norm": 0.07958984375,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.4322,
      "step": 3650
    },
    {
      "epoch": 0.06841715976331361,
      "grad_norm": 0.04736328125,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.4264,
      "step": 3700
    },
    {
      "epoch": 0.06934171597633136,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.4408,
      "step": 3750
    },
    {
      "epoch": 0.07026627218934911,
      "grad_norm": 0.0,
      "learning_rate": 4.8e-05,
      "loss": 0.5493,
      "step": 3800
    },
    {
      "epoch": 0.07119082840236686,
      "grad_norm": 0.0,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.3345,
      "step": 3850
    },
    {
      "epoch": 0.07211538461538461,
      "grad_norm": 0.1044921875,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.319,
      "step": 3900
    },
    {
      "epoch": 0.07303994082840237,
      "grad_norm": 0.041015625,
      "learning_rate": 4.2e-05,
      "loss": 0.6092,
      "step": 3950
    },
    {
      "epoch": 0.07396449704142012,
      "grad_norm": 2.828125,
      "learning_rate": 4e-05,
      "loss": 0.4057,
      "step": 4000
    },
    {
      "epoch": 0.07488905325443787,
      "grad_norm": 0.0281982421875,
      "learning_rate": 3.8e-05,
      "loss": 0.3609,
      "step": 4050
    },
    {
      "epoch": 0.07581360946745562,
      "grad_norm": 0.025390625,
      "learning_rate": 3.6e-05,
      "loss": 0.4486,
      "step": 4100
    },
    {
      "epoch": 0.07673816568047337,
      "grad_norm": 0.034423828125,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.5546,
      "step": 4150
    },
    {
      "epoch": 0.07766272189349112,
      "grad_norm": 0.04443359375,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.4731,
      "step": 4200
    },
    {
      "epoch": 0.07858727810650888,
      "grad_norm": 0.061279296875,
      "learning_rate": 3e-05,
      "loss": 0.4029,
      "step": 4250
    },
    {
      "epoch": 0.07951183431952663,
      "grad_norm": 0.0693359375,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.5766,
      "step": 4300
    },
    {
      "epoch": 0.08043639053254438,
      "grad_norm": 17.875,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.5435,
      "step": 4350
    },
    {
      "epoch": 0.08136094674556213,
      "grad_norm": 0.0,
      "learning_rate": 2.4e-05,
      "loss": 0.4748,
      "step": 4400
    },
    {
      "epoch": 0.08228550295857988,
      "grad_norm": 0.0,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.5257,
      "step": 4450
    },
    {
      "epoch": 0.08321005917159763,
      "grad_norm": 0.0,
      "learning_rate": 2e-05,
      "loss": 0.4337,
      "step": 4500
    },
    {
      "epoch": 0.08413461538461539,
      "grad_norm": 0.048828125,
      "learning_rate": 1.8e-05,
      "loss": 0.5057,
      "step": 4550
    },
    {
      "epoch": 0.08505917159763314,
      "grad_norm": 0.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.5384,
      "step": 4600
    },
    {
      "epoch": 0.08598372781065089,
      "grad_norm": 0.0,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.4339,
      "step": 4650
    },
    {
      "epoch": 0.08690828402366864,
      "grad_norm": 4.25,
      "learning_rate": 1.2e-05,
      "loss": 0.6224,
      "step": 4700
    },
    {
      "epoch": 0.08783284023668639,
      "grad_norm": 0.0191650390625,
      "learning_rate": 1e-05,
      "loss": 0.3908,
      "step": 4750
    },
    {
      "epoch": 0.08875739644970414,
      "grad_norm": 0.08837890625,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.5687,
      "step": 4800
    },
    {
      "epoch": 0.08968195266272189,
      "grad_norm": 0.0,
      "learning_rate": 6e-06,
      "loss": 0.5476,
      "step": 4850
    },
    {
      "epoch": 0.09060650887573965,
      "grad_norm": 0.0145263671875,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.4753,
      "step": 4900
    },
    {
      "epoch": 0.0915310650887574,
      "grad_norm": 0.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.5388,
      "step": 4950
    },
    {
      "epoch": 0.09245562130177515,
      "grad_norm": 4.34375,
      "learning_rate": 0.0,
      "loss": 0.4994,
      "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": 8.979888803807232e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}