{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7887323943661971,
  "eval_steps": 500,
  "global_step": 28,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 0.3046221137046814,
      "learning_rate": 1e-08,
      "loss": 0.7936,
      "mean_token_accuracy": 0.8673804849386215,
      "step": 1
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 0.31545570492744446,
      "learning_rate": 2e-08,
      "loss": 0.7759,
      "mean_token_accuracy": 0.8740345686674118,
      "step": 2
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 0.25415748357772827,
      "learning_rate": 3.0000000000000004e-08,
      "loss": 0.6719,
      "mean_token_accuracy": 0.8830722570419312,
      "step": 3
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 0.3462650179862976,
      "learning_rate": 4e-08,
      "loss": 0.8779,
      "mean_token_accuracy": 0.8565912544727325,
      "step": 4
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 0.28566086292266846,
      "learning_rate": 3.98973864678379e-08,
      "loss": 0.7654,
      "mean_token_accuracy": 0.8742299824953079,
      "step": 5
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 0.2303602248430252,
      "learning_rate": 3.959059882504989e-08,
      "loss": 0.6373,
      "mean_token_accuracy": 0.8818237036466599,
      "step": 6
    },
    {
      "epoch": 0.19718309859154928,
      "grad_norm": 0.31892648339271545,
      "learning_rate": 3.908278512800098e-08,
      "loss": 0.8327,
      "mean_token_accuracy": 0.8675516098737717,
      "step": 7
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 0.24556870758533478,
      "learning_rate": 3.837915623240461e-08,
      "loss": 0.6231,
      "mean_token_accuracy": 0.8830387145280838,
      "step": 8
    },
    {
      "epoch": 0.2535211267605634,
      "grad_norm": 0.3155352771282196,
      "learning_rate": 3.748693232289164e-08,
      "loss": 0.8142,
      "mean_token_accuracy": 0.8660248219966888,
      "step": 9
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 0.23740045726299286,
      "learning_rate": 3.6415268824145526e-08,
      "loss": 0.6116,
      "mean_token_accuracy": 0.8935595899820328,
      "step": 10
    },
    {
      "epoch": 0.30985915492957744,
      "grad_norm": 0.2727065682411194,
      "learning_rate": 3.517516245385582e-08,
      "loss": 0.7224,
      "mean_token_accuracy": 0.8836022019386292,
      "step": 11
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": 0.31578633189201355,
      "learning_rate": 3.3779338381513734e-08,
      "loss": 0.8099,
      "mean_token_accuracy": 0.8716088086366653,
      "step": 12
    },
    {
      "epoch": 0.36619718309859156,
      "grad_norm": 0.3671872317790985,
      "learning_rate": 3.224211965095326e-08,
      "loss": 0.9409,
      "mean_token_accuracy": 0.8513100147247314,
      "step": 13
    },
    {
      "epoch": 0.39436619718309857,
      "grad_norm": 0.3061031103134155,
      "learning_rate": 3.0579280206539245e-08,
      "loss": 0.777,
      "mean_token_accuracy": 0.8766786009073257,
      "step": 14
    },
    {
      "epoch": 0.4225352112676056,
      "grad_norm": 0.2184407263994217,
      "learning_rate": 2.880788303115269e-08,
      "loss": 0.5667,
      "mean_token_accuracy": 0.8888842463493347,
      "step": 15
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": 0.2985335886478424,
      "learning_rate": 2.6946105056896403e-08,
      "loss": 0.7663,
      "mean_token_accuracy": 0.8756130933761597,
      "step": 16
    },
    {
      "epoch": 0.4788732394366197,
      "grad_norm": 0.27177271246910095,
      "learning_rate": 2.501305064517441e-08,
      "loss": 0.7015,
      "mean_token_accuracy": 0.8735488653182983,
      "step": 17
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": 0.3162766993045807,
      "learning_rate": 2.3028555550091533e-08,
      "loss": 0.8136,
      "mean_token_accuracy": 0.8720169365406036,
      "step": 18
    },
    {
      "epoch": 0.5352112676056338,
      "grad_norm": 0.31601187586784363,
      "learning_rate": 2.1012983376774256e-08,
      "loss": 0.8157,
      "mean_token_accuracy": 0.8647672235965729,
      "step": 19
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 0.30421891808509827,
      "learning_rate": 1.8987016623225748e-08,
      "loss": 0.7871,
      "mean_token_accuracy": 0.8673246651887894,
      "step": 20
    },
    {
      "epoch": 0.5915492957746479,
      "grad_norm": 0.30133694410324097,
      "learning_rate": 1.6971444449908475e-08,
      "loss": 0.7887,
      "mean_token_accuracy": 0.8707097768783569,
      "step": 21
    },
    {
      "epoch": 0.6197183098591549,
      "grad_norm": 0.2936706244945526,
      "learning_rate": 1.4986949354825586e-08,
      "loss": 0.7546,
      "mean_token_accuracy": 0.8766651749610901,
      "step": 22
    },
    {
      "epoch": 0.647887323943662,
      "grad_norm": 0.24169673025608063,
      "learning_rate": 1.3053894943103596e-08,
      "loss": 0.6154,
      "mean_token_accuracy": 0.8910741060972214,
      "step": 23
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 0.2856695055961609,
      "learning_rate": 1.1192116968847312e-08,
      "loss": 0.7421,
      "mean_token_accuracy": 0.8779312670230865,
      "step": 24
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": 0.26276761293411255,
      "learning_rate": 9.420719793460757e-09,
      "loss": 0.6904,
      "mean_token_accuracy": 0.8801350891590118,
      "step": 25
    },
    {
      "epoch": 0.7323943661971831,
      "grad_norm": 0.30562785267829895,
      "learning_rate": 7.757880349046742e-09,
      "loss": 0.7772,
      "mean_token_accuracy": 0.8724565356969833,
      "step": 26
    },
    {
      "epoch": 0.7605633802816901,
      "grad_norm": 0.3877602219581604,
      "learning_rate": 6.220661618486268e-09,
      "loss": 0.9862,
      "mean_token_accuracy": 0.8512411713600159,
      "step": 27
    },
    {
      "epoch": 0.7887323943661971,
      "grad_norm": 0.2714689075946808,
      "learning_rate": 4.824837546144183e-09,
      "loss": 0.7403,
      "mean_token_accuracy": 0.8708591312170029,
      "step": 28
    }
  ],
  "logging_steps": 1,
  "max_steps": 35,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3612754997035008.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}