{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 169,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029585798816568046,
      "grad_norm": 2.943749189376831,
      "learning_rate": 0.0002,
      "loss": 0.9772,
      "step": 5
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 0.8338298797607422,
      "learning_rate": 0.0002,
      "loss": 0.4778,
      "step": 10
    },
    {
      "epoch": 0.08875739644970414,
      "grad_norm": 2.0171148777008057,
      "learning_rate": 0.0002,
      "loss": 0.4373,
      "step": 15
    },
    {
      "epoch": 0.11834319526627218,
      "grad_norm": 0.5850780010223389,
      "learning_rate": 0.0002,
      "loss": 0.3965,
      "step": 20
    },
    {
      "epoch": 0.14792899408284024,
      "grad_norm": 0.5566039681434631,
      "learning_rate": 0.0002,
      "loss": 0.3451,
      "step": 25
    },
    {
      "epoch": 0.17751479289940827,
      "grad_norm": 0.5998756289482117,
      "learning_rate": 0.0002,
      "loss": 0.3684,
      "step": 30
    },
    {
      "epoch": 0.20710059171597633,
      "grad_norm": 0.8541339039802551,
      "learning_rate": 0.0002,
      "loss": 0.3338,
      "step": 35
    },
    {
      "epoch": 0.23668639053254437,
      "grad_norm": 0.5334424376487732,
      "learning_rate": 0.0002,
      "loss": 0.3632,
      "step": 40
    },
    {
      "epoch": 0.26627218934911245,
      "grad_norm": 1.0356687307357788,
      "learning_rate": 0.0002,
      "loss": 0.3562,
      "step": 45
    },
    {
      "epoch": 0.2958579881656805,
      "grad_norm": 1.7772154808044434,
      "learning_rate": 0.0002,
      "loss": 0.3509,
      "step": 50
    },
    {
      "epoch": 0.3254437869822485,
      "grad_norm": 0.49876442551612854,
      "learning_rate": 0.0002,
      "loss": 0.3402,
      "step": 55
    },
    {
      "epoch": 0.35502958579881655,
      "grad_norm": 0.5085716247558594,
      "learning_rate": 0.0002,
      "loss": 0.3174,
      "step": 60
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.49447423219680786,
      "learning_rate": 0.0002,
      "loss": 0.3389,
      "step": 65
    },
    {
      "epoch": 0.41420118343195267,
      "grad_norm": 14.360894203186035,
      "learning_rate": 0.0002,
      "loss": 0.3302,
      "step": 70
    },
    {
      "epoch": 0.4437869822485207,
      "grad_norm": 0.4983256161212921,
      "learning_rate": 0.0002,
      "loss": 0.3126,
      "step": 75
    },
    {
      "epoch": 0.47337278106508873,
      "grad_norm": 0.43373844027519226,
      "learning_rate": 0.0002,
      "loss": 0.3228,
      "step": 80
    },
    {
      "epoch": 0.5029585798816568,
      "grad_norm": 0.4059043228626251,
      "learning_rate": 0.0002,
      "loss": 0.3026,
      "step": 85
    },
    {
      "epoch": 0.5325443786982249,
      "grad_norm": 0.4355526268482208,
      "learning_rate": 0.0002,
      "loss": 0.3253,
      "step": 90
    },
    {
      "epoch": 0.5621301775147929,
      "grad_norm": 0.38534995913505554,
      "learning_rate": 0.0002,
      "loss": 0.32,
      "step": 95
    },
    {
      "epoch": 0.591715976331361,
      "grad_norm": 0.392378032207489,
      "learning_rate": 0.0002,
      "loss": 0.3199,
      "step": 100
    },
    {
      "epoch": 0.621301775147929,
      "grad_norm": 0.7453891038894653,
      "learning_rate": 0.0002,
      "loss": 0.3227,
      "step": 105
    },
    {
      "epoch": 0.650887573964497,
      "grad_norm": 0.5021527409553528,
      "learning_rate": 0.0002,
      "loss": 0.3283,
      "step": 110
    },
    {
      "epoch": 0.6804733727810651,
      "grad_norm": 0.35293397307395935,
      "learning_rate": 0.0002,
      "loss": 0.292,
      "step": 115
    },
    {
      "epoch": 0.7100591715976331,
      "grad_norm": 0.9166481494903564,
      "learning_rate": 0.0002,
      "loss": 0.2956,
      "step": 120
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.38071614503860474,
      "learning_rate": 0.0002,
      "loss": 0.3193,
      "step": 125
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.4610137939453125,
      "learning_rate": 0.0002,
      "loss": 0.3024,
      "step": 130
    },
    {
      "epoch": 0.7988165680473372,
      "grad_norm": 0.5271707773208618,
      "learning_rate": 0.0002,
      "loss": 0.3137,
      "step": 135
    },
    {
      "epoch": 0.8284023668639053,
      "grad_norm": 0.3226008117198944,
      "learning_rate": 0.0002,
      "loss": 0.2887,
      "step": 140
    },
    {
      "epoch": 0.8579881656804734,
      "grad_norm": 0.4498213827610016,
      "learning_rate": 0.0002,
      "loss": 0.2873,
      "step": 145
    },
    {
      "epoch": 0.8875739644970414,
      "grad_norm": 0.3456571102142334,
      "learning_rate": 0.0002,
      "loss": 0.2863,
      "step": 150
    },
    {
      "epoch": 0.9171597633136095,
      "grad_norm": 0.35808348655700684,
      "learning_rate": 0.0002,
      "loss": 0.2804,
      "step": 155
    },
    {
      "epoch": 0.9467455621301775,
      "grad_norm": 0.35377588868141174,
      "learning_rate": 0.0002,
      "loss": 0.2883,
      "step": 160
    },
    {
      "epoch": 0.9763313609467456,
      "grad_norm": 0.36346396803855896,
      "learning_rate": 0.0002,
      "loss": 0.2964,
      "step": 165
    },
    {
      "epoch": 1.0,
      "step": 169,
      "total_flos": 1.3380899124648346e+17,
      "train_loss": 0.34797883668594815,
      "train_runtime": 1712.5179,
      "train_samples_per_second": 1.575,
      "train_steps_per_second": 0.099
    }
  ],
  "logging_steps": 5,
  "max_steps": 169,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3380899124648346e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}