{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.033819488480236734,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001690974424011837,
      "eval_loss": NaN,
      "eval_runtime": 224.3391,
      "eval_samples_per_second": 11.099,
      "eval_steps_per_second": 5.55,
      "step": 1
    },
    {
      "epoch": 0.0016909744240118367,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 100.9861,
      "step": 10
    },
    {
      "epoch": 0.0033819488480236735,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 100.8249,
      "step": 20
    },
    {
      "epoch": 0.0050729232720355105,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 16.6635,
      "step": 30
    },
    {
      "epoch": 0.006763897696047347,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 4.2478,
      "step": 40
    },
    {
      "epoch": 0.008454872120059184,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 9.0062,
      "step": 50
    },
    {
      "epoch": 0.008454872120059184,
      "eval_loss": NaN,
      "eval_runtime": 223.9149,
      "eval_samples_per_second": 11.12,
      "eval_steps_per_second": 5.56,
      "step": 50
    },
    {
      "epoch": 0.010145846544071021,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.3404,
      "step": 60
    },
    {
      "epoch": 0.011836820968082858,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 4.908,
      "step": 70
    },
    {
      "epoch": 0.013527795392094694,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 62.4184,
      "step": 80
    },
    {
      "epoch": 0.015218769816106531,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 75.0879,
      "step": 90
    },
    {
      "epoch": 0.016909744240118367,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 46.0364,
      "step": 100
    },
    {
      "epoch": 0.016909744240118367,
      "eval_loss": NaN,
      "eval_runtime": 223.9595,
      "eval_samples_per_second": 11.118,
      "eval_steps_per_second": 5.559,
      "step": 100
    },
    {
      "epoch": 0.018600718664130204,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 166.2225,
      "step": 110
    },
    {
      "epoch": 0.020291693088142042,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 110.6994,
      "step": 120
    },
    {
      "epoch": 0.02198266751215388,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 5.273,
      "step": 130
    },
    {
      "epoch": 0.023673641936165717,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 203.2636,
      "step": 140
    },
    {
      "epoch": 0.025364616360177554,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 148.0058,
      "step": 150
    },
    {
      "epoch": 0.025364616360177554,
      "eval_loss": NaN,
      "eval_runtime": 224.0057,
      "eval_samples_per_second": 11.116,
      "eval_steps_per_second": 5.558,
      "step": 150
    },
    {
      "epoch": 0.027055590784189388,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 67.0935,
      "step": 160
    },
    {
      "epoch": 0.028746565208201225,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.2994,
      "step": 170
    },
    {
      "epoch": 0.030437539632213063,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 79.1237,
      "step": 180
    },
    {
      "epoch": 0.0321285140562249,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.7457,
      "step": 190
    },
    {
      "epoch": 0.033819488480236734,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 72.2216,
      "step": 200
    },
    {
      "epoch": 0.033819488480236734,
      "eval_loss": NaN,
      "eval_runtime": 224.0523,
      "eval_samples_per_second": 11.113,
      "eval_steps_per_second": 5.557,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.268523024777216e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}