{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011036512462061988,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036788374873539964,
      "eval_loss": 2.3351593017578125,
      "eval_runtime": 111.1483,
      "eval_samples_per_second": 10.302,
      "eval_steps_per_second": 5.155,
      "step": 1
    },
    {
      "epoch": 0.0011036512462061989,
      "grad_norm": 136.164794921875,
      "learning_rate": 6e-05,
      "loss": 8.9828,
      "step": 3
    },
    {
      "epoch": 0.0022073024924123977,
      "grad_norm": 294.3015441894531,
      "learning_rate": 0.00012,
      "loss": 9.4817,
      "step": 6
    },
    {
      "epoch": 0.002943069989883197,
      "eval_loss": 2.3058969974517822,
      "eval_runtime": 112.4921,
      "eval_samples_per_second": 10.178,
      "eval_steps_per_second": 5.094,
      "step": 8
    },
    {
      "epoch": 0.0033109537386185966,
      "grad_norm": 449.0517883300781,
      "learning_rate": 0.00018,
      "loss": 9.1418,
      "step": 9
    },
    {
      "epoch": 0.004414604984824795,
      "grad_norm": 1.915037989616394,
      "learning_rate": 0.00019510565162951537,
      "loss": 8.9134,
      "step": 12
    },
    {
      "epoch": 0.005518256231030994,
      "grad_norm": 2.2603423595428467,
      "learning_rate": 0.00017071067811865476,
      "loss": 8.7408,
      "step": 15
    },
    {
      "epoch": 0.005886139979766394,
      "eval_loss": 1.9156038761138916,
      "eval_runtime": 112.5647,
      "eval_samples_per_second": 10.172,
      "eval_steps_per_second": 5.09,
      "step": 16
    },
    {
      "epoch": 0.006621907477237193,
      "grad_norm": 2.1589083671569824,
      "learning_rate": 0.00013090169943749476,
      "loss": 7.634,
      "step": 18
    },
    {
      "epoch": 0.0077255587234433916,
      "grad_norm": 2.283200263977051,
      "learning_rate": 8.435655349597689e-05,
      "loss": 6.9598,
      "step": 21
    },
    {
      "epoch": 0.00882920996964959,
      "grad_norm": 2.059357166290283,
      "learning_rate": 4.12214747707527e-05,
      "loss": 6.8391,
      "step": 24
    },
    {
      "epoch": 0.00882920996964959,
      "eval_loss": 1.6812446117401123,
      "eval_runtime": 112.5995,
      "eval_samples_per_second": 10.169,
      "eval_steps_per_second": 5.089,
      "step": 24
    },
    {
      "epoch": 0.00993286121585579,
      "grad_norm": 2.2149431705474854,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 6.698,
      "step": 27
    },
    {
      "epoch": 0.011036512462061988,
      "grad_norm": 2.14638614654541,
      "learning_rate": 0.0,
      "loss": 6.6779,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9801969665310720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}