{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4287245444801715,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004287245444801715,
      "eval_loss": 1.4249097108840942,
      "eval_runtime": 10.7749,
      "eval_samples_per_second": 36.474,
      "eval_steps_per_second": 4.64,
      "step": 1
    },
    {
      "epoch": 0.012861736334405145,
      "grad_norm": 0.9113896489143372,
      "learning_rate": 3e-05,
      "loss": 1.4703,
      "step": 3
    },
    {
      "epoch": 0.02572347266881029,
      "grad_norm": 0.8911994099617004,
      "learning_rate": 6e-05,
      "loss": 1.4236,
      "step": 6
    },
    {
      "epoch": 0.03858520900321544,
      "grad_norm": 0.7710233330726624,
      "learning_rate": 9e-05,
      "loss": 1.3008,
      "step": 9
    },
    {
      "epoch": 0.03858520900321544,
      "eval_loss": 1.1259669065475464,
      "eval_runtime": 10.753,
      "eval_samples_per_second": 36.548,
      "eval_steps_per_second": 4.65,
      "step": 9
    },
    {
      "epoch": 0.05144694533762058,
      "grad_norm": 0.8508097529411316,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.0518,
      "step": 12
    },
    {
      "epoch": 0.06430868167202572,
      "grad_norm": 0.8443539142608643,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.7249,
      "step": 15
    },
    {
      "epoch": 0.07717041800643087,
      "grad_norm": 1.4097633361816406,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.5457,
      "step": 18
    },
    {
      "epoch": 0.07717041800643087,
      "eval_loss": 0.4698084890842438,
      "eval_runtime": 10.8272,
      "eval_samples_per_second": 36.297,
      "eval_steps_per_second": 4.618,
      "step": 18
    },
    {
      "epoch": 0.09003215434083602,
      "grad_norm": 0.34708932042121887,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.4553,
      "step": 21
    },
    {
      "epoch": 0.10289389067524116,
      "grad_norm": 0.4105893671512604,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.4212,
      "step": 24
    },
    {
      "epoch": 0.1157556270096463,
      "grad_norm": 1.0311174392700195,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.4673,
      "step": 27
    },
    {
      "epoch": 0.1157556270096463,
      "eval_loss": 0.43113449215888977,
      "eval_runtime": 10.8366,
      "eval_samples_per_second": 36.266,
      "eval_steps_per_second": 4.614,
      "step": 27
    },
    {
      "epoch": 0.12861736334405144,
      "grad_norm": 0.4956219792366028,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.4289,
      "step": 30
    },
    {
      "epoch": 0.1414790996784566,
      "grad_norm": 0.4162253141403198,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.4294,
      "step": 33
    },
    {
      "epoch": 0.15434083601286175,
      "grad_norm": 1.1481068134307861,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.4328,
      "step": 36
    },
    {
      "epoch": 0.15434083601286175,
      "eval_loss": 0.41734907031059265,
      "eval_runtime": 10.8711,
      "eval_samples_per_second": 36.151,
      "eval_steps_per_second": 4.599,
      "step": 36
    },
    {
      "epoch": 0.16720257234726688,
      "grad_norm": 0.262054443359375,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.4119,
      "step": 39
    },
    {
      "epoch": 0.18006430868167203,
      "grad_norm": 0.3609679639339447,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.4283,
      "step": 42
    },
    {
      "epoch": 0.19292604501607716,
      "grad_norm": 0.2730075716972351,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.4492,
      "step": 45
    },
    {
      "epoch": 0.19292604501607716,
      "eval_loss": 0.4143539071083069,
      "eval_runtime": 10.8825,
      "eval_samples_per_second": 36.113,
      "eval_steps_per_second": 4.595,
      "step": 45
    },
    {
      "epoch": 0.2057877813504823,
      "grad_norm": 0.30750295519828796,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.4128,
      "step": 48
    },
    {
      "epoch": 0.21864951768488747,
      "grad_norm": 0.45564326643943787,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.3809,
      "step": 51
    },
    {
      "epoch": 0.2315112540192926,
      "grad_norm": 0.34823882579803467,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.4133,
      "step": 54
    },
    {
      "epoch": 0.2315112540192926,
      "eval_loss": 0.407143771648407,
      "eval_runtime": 10.893,
      "eval_samples_per_second": 36.078,
      "eval_steps_per_second": 4.59,
      "step": 54
    },
    {
      "epoch": 0.24437299035369775,
      "grad_norm": 0.5110918283462524,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.4088,
      "step": 57
    },
    {
      "epoch": 0.2572347266881029,
      "grad_norm": 0.32943594455718994,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.4107,
      "step": 60
    },
    {
      "epoch": 0.27009646302250806,
      "grad_norm": 0.4684916138648987,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.3967,
      "step": 63
    },
    {
      "epoch": 0.27009646302250806,
      "eval_loss": 0.40750572085380554,
      "eval_runtime": 10.9324,
      "eval_samples_per_second": 35.948,
      "eval_steps_per_second": 4.574,
      "step": 63
    },
    {
      "epoch": 0.2829581993569132,
      "grad_norm": 0.2500722408294678,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.3752,
      "step": 66
    },
    {
      "epoch": 0.2958199356913183,
      "grad_norm": 0.9661127924919128,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.3869,
      "step": 69
    },
    {
      "epoch": 0.3086816720257235,
      "grad_norm": 0.6735724806785583,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.3793,
      "step": 72
    },
    {
      "epoch": 0.3086816720257235,
      "eval_loss": 0.4086286723613739,
      "eval_runtime": 10.898,
      "eval_samples_per_second": 36.062,
      "eval_steps_per_second": 4.588,
      "step": 72
    },
    {
      "epoch": 0.3215434083601286,
      "grad_norm": 0.6262890696525574,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.4136,
      "step": 75
    },
    {
      "epoch": 0.33440514469453375,
      "grad_norm": 0.7589296698570251,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.4155,
      "step": 78
    },
    {
      "epoch": 0.34726688102893893,
      "grad_norm": 0.6098915338516235,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.4119,
      "step": 81
    },
    {
      "epoch": 0.34726688102893893,
      "eval_loss": 0.40282922983169556,
      "eval_runtime": 10.8945,
      "eval_samples_per_second": 36.073,
      "eval_steps_per_second": 4.589,
      "step": 81
    },
    {
      "epoch": 0.36012861736334406,
      "grad_norm": 0.23373101651668549,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.3801,
      "step": 84
    },
    {
      "epoch": 0.3729903536977492,
      "grad_norm": 0.5538727641105652,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.4045,
      "step": 87
    },
    {
      "epoch": 0.3858520900321543,
      "grad_norm": 0.44058600068092346,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.4008,
      "step": 90
    },
    {
      "epoch": 0.3858520900321543,
      "eval_loss": 0.4011549651622772,
      "eval_runtime": 10.8787,
      "eval_samples_per_second": 36.126,
      "eval_steps_per_second": 4.596,
      "step": 90
    },
    {
      "epoch": 0.3987138263665595,
      "grad_norm": 0.32986781001091003,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.3769,
      "step": 93
    },
    {
      "epoch": 0.4115755627009646,
      "grad_norm": 0.2695184350013733,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.3882,
      "step": 96
    },
    {
      "epoch": 0.42443729903536975,
      "grad_norm": 0.4361032545566559,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.4191,
      "step": 99
    },
    {
      "epoch": 0.42443729903536975,
      "eval_loss": 0.4006556570529938,
      "eval_runtime": 10.8903,
      "eval_samples_per_second": 36.087,
      "eval_steps_per_second": 4.591,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.61253767364608e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}