{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009078212290502794,
  "eval_steps": 13,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006983240223463687,
      "grad_norm": 0.35678303241729736,
      "learning_rate": 2e-05,
      "loss": 44.3467,
      "step": 1
    },
    {
      "epoch": 0.0006983240223463687,
      "eval_loss": 11.086202621459961,
      "eval_runtime": 3.101,
      "eval_samples_per_second": 194.453,
      "eval_steps_per_second": 97.388,
      "step": 1
    },
    {
      "epoch": 0.0013966480446927375,
      "grad_norm": 0.3373069763183594,
      "learning_rate": 4e-05,
      "loss": 44.345,
      "step": 2
    },
    {
      "epoch": 0.002094972067039106,
      "grad_norm": 0.3595690131187439,
      "learning_rate": 6e-05,
      "loss": 44.3482,
      "step": 3
    },
    {
      "epoch": 0.002793296089385475,
      "grad_norm": 0.33516058325767517,
      "learning_rate": 8e-05,
      "loss": 44.3481,
      "step": 4
    },
    {
      "epoch": 0.0034916201117318434,
      "grad_norm": 0.35325780510902405,
      "learning_rate": 0.0001,
      "loss": 44.3407,
      "step": 5
    },
    {
      "epoch": 0.004189944134078212,
      "grad_norm": 0.3564867079257965,
      "learning_rate": 0.00012,
      "loss": 44.366,
      "step": 6
    },
    {
      "epoch": 0.004888268156424581,
      "grad_norm": 0.3264864385128021,
      "learning_rate": 0.00014,
      "loss": 44.328,
      "step": 7
    },
    {
      "epoch": 0.00558659217877095,
      "grad_norm": 0.36639204621315,
      "learning_rate": 0.00016,
      "loss": 44.3366,
      "step": 8
    },
    {
      "epoch": 0.006284916201117319,
      "grad_norm": 0.35129833221435547,
      "learning_rate": 0.00018,
      "loss": 44.3348,
      "step": 9
    },
    {
      "epoch": 0.006983240223463687,
      "grad_norm": 0.36253875494003296,
      "learning_rate": 0.0002,
      "loss": 44.3533,
      "step": 10
    },
    {
      "epoch": 0.007681564245810056,
      "grad_norm": 0.348306804895401,
      "learning_rate": 0.0001996917333733128,
      "loss": 44.3446,
      "step": 11
    },
    {
      "epoch": 0.008379888268156424,
      "grad_norm": 0.3863369822502136,
      "learning_rate": 0.00019876883405951377,
      "loss": 44.335,
      "step": 12
    },
    {
      "epoch": 0.009078212290502794,
      "grad_norm": 0.3570167124271393,
      "learning_rate": 0.00019723699203976766,
      "loss": 44.3222,
      "step": 13
    },
    {
      "epoch": 0.009078212290502794,
      "eval_loss": 11.082662582397461,
      "eval_runtime": 1.7965,
      "eval_samples_per_second": 335.65,
      "eval_steps_per_second": 168.103,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 18490982400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}