{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8583690987124464,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08583690987124463,
      "grad_norm": 0.13883593678474426,
      "learning_rate": 0.0001998960663781063,
      "loss": 0.829,
      "step": 100
    },
    {
      "epoch": 0.17167381974248927,
      "grad_norm": 0.13720104098320007,
      "learning_rate": 0.00019906589321760313,
      "loss": 0.648,
      "step": 200
    },
    {
      "epoch": 0.2575107296137339,
      "grad_norm": 0.1670483946800232,
      "learning_rate": 0.00019741244594178857,
      "loss": 0.587,
      "step": 300
    },
    {
      "epoch": 0.34334763948497854,
      "grad_norm": 0.16993218660354614,
      "learning_rate": 0.00019494946530743566,
      "loss": 0.5547,
      "step": 400
    },
    {
      "epoch": 0.4291845493562232,
      "grad_norm": 0.16408105194568634,
      "learning_rate": 0.00019169741959214142,
      "loss": 0.5319,
      "step": 500
    },
    {
      "epoch": 0.5150214592274678,
      "grad_norm": 0.1872694492340088,
      "learning_rate": 0.0001876833344953899,
      "loss": 0.5147,
      "step": 600
    },
    {
      "epoch": 0.6008583690987125,
      "grad_norm": 0.18225158751010895,
      "learning_rate": 0.0001829405685450202,
      "loss": 0.5009,
      "step": 700
    },
    {
      "epoch": 0.6866952789699571,
      "grad_norm": 0.1850147843360901,
      "learning_rate": 0.00017750853587555535,
      "loss": 0.4866,
      "step": 800
    },
    {
      "epoch": 0.7725321888412017,
      "grad_norm": 0.20939144492149353,
      "learning_rate": 0.00017143237868220553,
      "loss": 0.4721,
      "step": 900
    },
    {
      "epoch": 0.8583690987124464,
      "grad_norm": 0.21306931972503662,
      "learning_rate": 0.00016476259207257407,
      "loss": 0.4626,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 3495,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.6883623051264e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}