{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9948186528497409,
  "eval_steps": 12,
  "global_step": 48,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02072538860103627,
      "grad_norm": 0.012328565120697021,
      "learning_rate": 4.000000000000001e-06,
      "loss": 12.4632,
      "step": 1
    },
    {
      "epoch": 0.02072538860103627,
      "eval_loss": 12.459209442138672,
      "eval_runtime": 1.4447,
      "eval_samples_per_second": 56.758,
      "eval_steps_per_second": 14.536,
      "step": 1
    },
    {
      "epoch": 0.04145077720207254,
      "grad_norm": 0.01481240801513195,
      "learning_rate": 8.000000000000001e-06,
      "loss": 12.4598,
      "step": 2
    },
    {
      "epoch": 0.06217616580310881,
      "grad_norm": 0.01405641995370388,
      "learning_rate": 1.2e-05,
      "loss": 12.461,
      "step": 3
    },
    {
      "epoch": 0.08290155440414508,
      "grad_norm": 0.012295316904783249,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 12.4607,
      "step": 4
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 0.01401484664529562,
      "learning_rate": 2e-05,
      "loss": 12.4673,
      "step": 5
    },
    {
      "epoch": 0.12435233160621761,
      "grad_norm": 0.015558955259621143,
      "learning_rate": 2.4e-05,
      "loss": 12.4628,
      "step": 6
    },
    {
      "epoch": 0.14507772020725387,
      "grad_norm": 0.013355869799852371,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 12.4672,
      "step": 7
    },
    {
      "epoch": 0.16580310880829016,
      "grad_norm": 0.015484556555747986,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 12.4612,
      "step": 8
    },
    {
      "epoch": 0.18652849740932642,
      "grad_norm": 0.01674036495387554,
      "learning_rate": 3.6e-05,
      "loss": 12.4657,
      "step": 9
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 0.016482409089803696,
      "learning_rate": 4e-05,
      "loss": 12.4615,
      "step": 10
    },
    {
      "epoch": 0.22797927461139897,
      "grad_norm": 0.01787281408905983,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 12.4637,
      "step": 11
    },
    {
      "epoch": 0.24870466321243523,
      "grad_norm": 0.01791117526590824,
      "learning_rate": 4.8e-05,
      "loss": 12.4663,
      "step": 12
    },
    {
      "epoch": 0.24870466321243523,
      "eval_loss": 12.459169387817383,
      "eval_runtime": 1.4466,
      "eval_samples_per_second": 56.684,
      "eval_steps_per_second": 14.517,
      "step": 12
    },
    {
      "epoch": 0.2694300518134715,
      "grad_norm": 0.012630539946258068,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 12.4626,
      "step": 13
    },
    {
      "epoch": 0.29015544041450775,
      "grad_norm": 0.012216604314744473,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 12.4612,
      "step": 14
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 0.01380347739905119,
      "learning_rate": 6e-05,
      "loss": 12.4622,
      "step": 15
    },
    {
      "epoch": 0.3316062176165803,
      "grad_norm": 0.014256793074309826,
      "learning_rate": 6.400000000000001e-05,
      "loss": 12.4618,
      "step": 16
    },
    {
      "epoch": 0.35233160621761656,
      "grad_norm": 0.015153720043599606,
      "learning_rate": 6.800000000000001e-05,
      "loss": 12.4671,
      "step": 17
    },
    {
      "epoch": 0.37305699481865284,
      "grad_norm": 0.013849603943526745,
      "learning_rate": 7.2e-05,
      "loss": 12.4667,
      "step": 18
    },
    {
      "epoch": 0.39378238341968913,
      "grad_norm": 0.013394423760473728,
      "learning_rate": 7.6e-05,
      "loss": 12.4601,
      "step": 19
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 0.015159090980887413,
      "learning_rate": 8e-05,
      "loss": 12.4657,
      "step": 20
    },
    {
      "epoch": 0.43523316062176165,
      "grad_norm": 0.015923170372843742,
      "learning_rate": 8.4e-05,
      "loss": 12.4655,
      "step": 21
    },
    {
      "epoch": 0.45595854922279794,
      "grad_norm": 0.01685705967247486,
      "learning_rate": 8.800000000000001e-05,
      "loss": 12.4621,
      "step": 22
    },
    {
      "epoch": 0.47668393782383417,
      "grad_norm": 0.015810972079634666,
      "learning_rate": 9.200000000000001e-05,
      "loss": 12.465,
      "step": 23
    },
    {
      "epoch": 0.49740932642487046,
      "grad_norm": 0.018734809011220932,
      "learning_rate": 9.6e-05,
      "loss": 12.4651,
      "step": 24
    },
    {
      "epoch": 0.49740932642487046,
      "eval_loss": 12.45895767211914,
      "eval_runtime": 1.4297,
      "eval_samples_per_second": 57.355,
      "eval_steps_per_second": 14.688,
      "step": 24
    },
    {
      "epoch": 0.5181347150259067,
      "grad_norm": 0.01412452757358551,
      "learning_rate": 0.0001,
      "loss": 12.4627,
      "step": 25
    },
    {
      "epoch": 0.538860103626943,
      "grad_norm": 0.01330703403800726,
      "learning_rate": 0.00010400000000000001,
      "loss": 12.4633,
      "step": 26
    },
    {
      "epoch": 0.5595854922279793,
      "grad_norm": 0.01628568395972252,
      "learning_rate": 0.00010800000000000001,
      "loss": 12.4593,
      "step": 27
    },
    {
      "epoch": 0.5803108808290155,
      "grad_norm": 0.013267126865684986,
      "learning_rate": 0.00011200000000000001,
      "loss": 12.4597,
      "step": 28
    },
    {
      "epoch": 0.6010362694300518,
      "grad_norm": 0.01633607968688011,
      "learning_rate": 0.000116,
      "loss": 12.4574,
      "step": 29
    },
    {
      "epoch": 0.6217616580310881,
      "grad_norm": 0.014100078493356705,
      "learning_rate": 0.00012,
      "loss": 12.4624,
      "step": 30
    },
    {
      "epoch": 0.6424870466321243,
      "grad_norm": 0.0167540293186903,
      "learning_rate": 0.000124,
      "loss": 12.4602,
      "step": 31
    },
    {
      "epoch": 0.6632124352331606,
      "grad_norm": 0.015121635980904102,
      "learning_rate": 0.00012800000000000002,
      "loss": 12.4627,
      "step": 32
    },
    {
      "epoch": 0.6839378238341969,
      "grad_norm": 0.015222931280732155,
      "learning_rate": 0.000132,
      "loss": 12.4621,
      "step": 33
    },
    {
      "epoch": 0.7046632124352331,
      "grad_norm": 0.01850767433643341,
      "learning_rate": 0.00013600000000000003,
      "loss": 12.4652,
      "step": 34
    },
    {
      "epoch": 0.7253886010362695,
      "grad_norm": 0.021301083266735077,
      "learning_rate": 0.00014,
      "loss": 12.4616,
      "step": 35
    },
    {
      "epoch": 0.7461139896373057,
      "grad_norm": 0.02175988256931305,
      "learning_rate": 0.000144,
      "loss": 12.4653,
      "step": 36
    },
    {
      "epoch": 0.7461139896373057,
      "eval_loss": 12.458399772644043,
      "eval_runtime": 1.4242,
      "eval_samples_per_second": 57.575,
      "eval_steps_per_second": 14.745,
      "step": 36
    },
    {
      "epoch": 0.7668393782383419,
      "grad_norm": 0.016086047515273094,
      "learning_rate": 0.000148,
      "loss": 12.4601,
      "step": 37
    },
    {
      "epoch": 0.7875647668393783,
      "grad_norm": 0.016342192888259888,
      "learning_rate": 0.000152,
      "loss": 12.46,
      "step": 38
    },
    {
      "epoch": 0.8082901554404145,
      "grad_norm": 0.018003815785050392,
      "learning_rate": 0.00015600000000000002,
      "loss": 12.4616,
      "step": 39
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 0.020604344084858894,
      "learning_rate": 0.00016,
      "loss": 12.4571,
      "step": 40
    },
    {
      "epoch": 0.8497409326424871,
      "grad_norm": 0.01911165565252304,
      "learning_rate": 0.000164,
      "loss": 12.4576,
      "step": 41
    },
    {
      "epoch": 0.8704663212435233,
      "grad_norm": 0.022435059770941734,
      "learning_rate": 0.000168,
      "loss": 12.4594,
      "step": 42
    },
    {
      "epoch": 0.8911917098445595,
      "grad_norm": 0.0239774901419878,
      "learning_rate": 0.000172,
      "loss": 12.4606,
      "step": 43
    },
    {
      "epoch": 0.9119170984455959,
      "grad_norm": 0.02675757370889187,
      "learning_rate": 0.00017600000000000002,
      "loss": 12.4617,
      "step": 44
    },
    {
      "epoch": 0.9326424870466321,
      "grad_norm": 0.028698239475488663,
      "learning_rate": 0.00018,
      "loss": 12.4596,
      "step": 45
    },
    {
      "epoch": 0.9533678756476683,
      "grad_norm": 0.02775721438229084,
      "learning_rate": 0.00018400000000000003,
      "loss": 12.4607,
      "step": 46
    },
    {
      "epoch": 0.9740932642487047,
      "grad_norm": 0.03137590363621712,
      "learning_rate": 0.000188,
      "loss": 12.4636,
      "step": 47
    },
    {
      "epoch": 0.9948186528497409,
      "grad_norm": 0.035989392548799515,
      "learning_rate": 0.000192,
      "loss": 12.4666,
      "step": 48
    },
    {
      "epoch": 0.9948186528497409,
      "eval_loss": 12.45715045928955,
      "eval_runtime": 1.4531,
      "eval_samples_per_second": 56.429,
      "eval_steps_per_second": 14.451,
      "step": 48
    }
  ],
  "logging_steps": 1,
  "max_steps": 48,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 12,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 236760072192.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}