{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.060175054704595,
  "eval_steps": 8,
  "global_step": 86,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0350109409190372,
      "eval_loss": 10.379219055175781,
      "eval_runtime": 0.7148,
      "eval_samples_per_second": 135.698,
      "eval_steps_per_second": 68.548,
      "step": 1
    },
    {
      "epoch": 0.1050328227571116,
      "grad_norm": 0.10373959690332413,
      "learning_rate": 3e-05,
      "loss": 10.3774,
      "step": 3
    },
    {
      "epoch": 0.2100656455142232,
      "grad_norm": 0.11316292732954025,
      "learning_rate": 6e-05,
      "loss": 10.3758,
      "step": 6
    },
    {
      "epoch": 0.2800875273522976,
      "eval_loss": 10.377415657043457,
      "eval_runtime": 0.7201,
      "eval_samples_per_second": 134.703,
      "eval_steps_per_second": 68.046,
      "step": 8
    },
    {
      "epoch": 0.3150984682713348,
      "grad_norm": 0.10614413022994995,
      "learning_rate": 9e-05,
      "loss": 10.3741,
      "step": 9
    },
    {
      "epoch": 0.4201312910284464,
      "grad_norm": 0.11337128281593323,
      "learning_rate": 0.00012,
      "loss": 10.3761,
      "step": 12
    },
    {
      "epoch": 0.5251641137855579,
      "grad_norm": 0.10311492532491684,
      "learning_rate": 0.00015000000000000001,
      "loss": 10.3712,
      "step": 15
    },
    {
      "epoch": 0.5601750547045952,
      "eval_loss": 10.371430397033691,
      "eval_runtime": 0.7202,
      "eval_samples_per_second": 134.683,
      "eval_steps_per_second": 68.036,
      "step": 16
    },
    {
      "epoch": 0.6301969365426696,
      "grad_norm": 0.12901803851127625,
      "learning_rate": 0.00018,
      "loss": 10.3699,
      "step": 18
    },
    {
      "epoch": 0.7352297592997812,
      "grad_norm": 0.13586793839931488,
      "learning_rate": 0.0001998867339183008,
      "loss": 10.366,
      "step": 21
    },
    {
      "epoch": 0.8402625820568927,
      "grad_norm": 0.18823161721229553,
      "learning_rate": 0.00019819286972627066,
      "loss": 10.3635,
      "step": 24
    },
    {
      "epoch": 0.8402625820568927,
      "eval_loss": 10.358380317687988,
      "eval_runtime": 0.7207,
      "eval_samples_per_second": 134.583,
      "eval_steps_per_second": 67.985,
      "step": 24
    },
    {
      "epoch": 0.9452954048140044,
      "grad_norm": 0.15795904397964478,
      "learning_rate": 0.00019450008187146684,
      "loss": 10.3562,
      "step": 27
    },
    {
      "epoch": 1.0667396061269148,
      "grad_norm": 0.22537720203399658,
      "learning_rate": 0.00018888354486549237,
      "loss": 13.5544,
      "step": 30
    },
    {
      "epoch": 1.136761487964989,
      "eval_loss": 10.337327003479004,
      "eval_runtime": 0.7182,
      "eval_samples_per_second": 135.057,
      "eval_steps_per_second": 68.225,
      "step": 32
    },
    {
      "epoch": 1.1717724288840263,
      "grad_norm": 0.27254220843315125,
      "learning_rate": 0.00018145759520503358,
      "loss": 10.2022,
      "step": 33
    },
    {
      "epoch": 1.276805251641138,
      "grad_norm": 0.2869032025337219,
      "learning_rate": 0.00017237340381050703,
      "loss": 10.3997,
      "step": 36
    },
    {
      "epoch": 1.3818380743982495,
      "grad_norm": 0.2603079676628113,
      "learning_rate": 0.00016181589862206052,
      "loss": 10.2418,
      "step": 39
    },
    {
      "epoch": 1.4168490153172866,
      "eval_loss": 10.31363582611084,
      "eval_runtime": 0.7196,
      "eval_samples_per_second": 134.788,
      "eval_steps_per_second": 68.089,
      "step": 40
    },
    {
      "epoch": 1.486870897155361,
      "grad_norm": 0.1934972107410431,
      "learning_rate": 0.00015000000000000001,
      "loss": 10.3704,
      "step": 42
    },
    {
      "epoch": 1.5919037199124726,
      "grad_norm": 0.19271045923233032,
      "learning_rate": 0.00013716624556603274,
      "loss": 10.3807,
      "step": 45
    },
    {
      "epoch": 1.6969365426695844,
      "grad_norm": 0.14647410809993744,
      "learning_rate": 0.00012357589355094275,
      "loss": 10.2948,
      "step": 48
    },
    {
      "epoch": 1.6969365426695844,
      "eval_loss": 10.299408912658691,
      "eval_runtime": 0.7215,
      "eval_samples_per_second": 134.448,
      "eval_steps_per_second": 67.917,
      "step": 48
    },
    {
      "epoch": 1.8019693654266957,
      "grad_norm": 0.11578352749347687,
      "learning_rate": 0.00010950560433041826,
      "loss": 10.223,
      "step": 51
    },
    {
      "epoch": 1.9070021881838075,
      "grad_norm": 0.10895143449306488,
      "learning_rate": 9.524180841762577e-05,
      "loss": 10.258,
      "step": 54
    },
    {
      "epoch": 1.9770240700218817,
      "eval_loss": 10.293498039245605,
      "eval_runtime": 0.719,
      "eval_samples_per_second": 134.919,
      "eval_steps_per_second": 68.155,
      "step": 56
    },
    {
      "epoch": 2.0284463894967177,
      "grad_norm": 0.2121211737394333,
      "learning_rate": 8.107487556395901e-05,
      "loss": 13.6014,
      "step": 57
    },
    {
      "epoch": 2.1334792122538295,
      "grad_norm": 0.11470862478017807,
      "learning_rate": 6.729320366825784e-05,
      "loss": 10.2428,
      "step": 60
    },
    {
      "epoch": 2.238512035010941,
      "grad_norm": 0.0803636685013771,
      "learning_rate": 5.417734782725896e-05,
      "loss": 10.1202,
      "step": 63
    },
    {
      "epoch": 2.273522975929978,
      "eval_loss": 10.290419578552246,
      "eval_runtime": 0.7218,
      "eval_samples_per_second": 134.394,
      "eval_steps_per_second": 67.89,
      "step": 64
    },
    {
      "epoch": 2.3435448577680527,
      "grad_norm": 0.17679740488529205,
      "learning_rate": 4.19943090428802e-05,
      "loss": 10.6347,
      "step": 66
    },
    {
      "epoch": 2.448577680525164,
      "grad_norm": 0.09998754411935806,
      "learning_rate": 3.099209885178882e-05,
      "loss": 10.2055,
      "step": 69
    },
    {
      "epoch": 2.553610503282276,
      "grad_norm": 0.08292704820632935,
      "learning_rate": 2.139469052572127e-05,
      "loss": 10.3454,
      "step": 72
    },
    {
      "epoch": 2.553610503282276,
      "eval_loss": 10.288853645324707,
      "eval_runtime": 0.7239,
      "eval_samples_per_second": 133.994,
      "eval_steps_per_second": 67.687,
      "step": 72
    },
    {
      "epoch": 2.658643326039387,
      "grad_norm": 0.1350039690732956,
      "learning_rate": 1.339745962155613e-05,
      "loss": 10.279,
      "step": 75
    },
    {
      "epoch": 2.763676148796499,
      "grad_norm": 0.09172733873128891,
      "learning_rate": 7.163206698392744e-06,
      "loss": 10.0236,
      "step": 78
    },
    {
      "epoch": 2.833698030634573,
      "eval_loss": 10.288338661193848,
      "eval_runtime": 0.7231,
      "eval_samples_per_second": 134.151,
      "eval_steps_per_second": 67.767,
      "step": 80
    },
    {
      "epoch": 2.8687089715536107,
      "grad_norm": 0.08289742469787598,
      "learning_rate": 2.818843167645835e-06,
      "loss": 10.2928,
      "step": 81
    },
    {
      "epoch": 2.973741794310722,
      "grad_norm": 0.08898758143186569,
      "learning_rate": 4.5280774269154115e-07,
      "loss": 10.5421,
      "step": 84
    }
  ],
  "logging_steps": 3,
  "max_steps": 86,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 8,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 36914181439488.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}