{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006271558482282847,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006271558482282847,
      "grad_norm": 15.568015098571777,
      "learning_rate": 2e-05,
      "loss": 6.8789,
      "step": 1
    },
    {
      "epoch": 0.0006271558482282847,
      "eval_loss": 6.8197808265686035,
      "eval_runtime": 203.7328,
      "eval_samples_per_second": 3.298,
      "eval_steps_per_second": 1.649,
      "step": 1
    },
    {
      "epoch": 0.0012543116964565694,
      "grad_norm": 12.13495922088623,
      "learning_rate": 4e-05,
      "loss": 6.4394,
      "step": 2
    },
    {
      "epoch": 0.0018814675446848542,
      "grad_norm": 16.08320426940918,
      "learning_rate": 6e-05,
      "loss": 6.5909,
      "step": 3
    },
    {
      "epoch": 0.0018814675446848542,
      "eval_loss": 6.544223785400391,
      "eval_runtime": 203.3356,
      "eval_samples_per_second": 3.305,
      "eval_steps_per_second": 1.652,
      "step": 3
    },
    {
      "epoch": 0.002508623392913139,
      "grad_norm": 12.303736686706543,
      "learning_rate": 8e-05,
      "loss": 6.5434,
      "step": 4
    },
    {
      "epoch": 0.0031357792411414237,
      "grad_norm": 12.68710708618164,
      "learning_rate": 0.0001,
      "loss": 5.6184,
      "step": 5
    },
    {
      "epoch": 0.0037629350893697085,
      "grad_norm": 15.014784812927246,
      "learning_rate": 0.00012,
      "loss": 5.1112,
      "step": 6
    },
    {
      "epoch": 0.0037629350893697085,
      "eval_loss": 2.9595587253570557,
      "eval_runtime": 203.6284,
      "eval_samples_per_second": 3.3,
      "eval_steps_per_second": 1.65,
      "step": 6
    },
    {
      "epoch": 0.004390090937597993,
      "grad_norm": 12.314769744873047,
      "learning_rate": 0.00014,
      "loss": 2.5402,
      "step": 7
    },
    {
      "epoch": 0.005017246785826278,
      "grad_norm": 7.833439350128174,
      "learning_rate": 0.00016,
      "loss": 2.2929,
      "step": 8
    },
    {
      "epoch": 0.005644402634054563,
      "grad_norm": 5.7926926612854,
      "learning_rate": 0.00018,
      "loss": 0.5575,
      "step": 9
    },
    {
      "epoch": 0.005644402634054563,
      "eval_loss": 0.1524699479341507,
      "eval_runtime": 204.3828,
      "eval_samples_per_second": 3.288,
      "eval_steps_per_second": 1.644,
      "step": 9
    },
    {
      "epoch": 0.006271558482282847,
      "grad_norm": 2.323312520980835,
      "learning_rate": 0.0002,
      "loss": 0.0799,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5589685858467840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}