{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004368401892974154,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001456133964324718,
      "eval_loss": 4.835346698760986,
      "eval_runtime": 374.4287,
      "eval_samples_per_second": 7.724,
      "eval_steps_per_second": 3.862,
      "step": 1
    },
    {
      "epoch": 0.0004368401892974154,
      "grad_norm": 4.619075775146484,
      "learning_rate": 6e-05,
      "loss": 5.437,
      "step": 3
    },
    {
      "epoch": 0.0008736803785948308,
      "grad_norm": 2.2696151733398438,
      "learning_rate": 0.00012,
      "loss": 2.4236,
      "step": 6
    },
    {
      "epoch": 0.0011649071714597743,
      "eval_loss": 3.1080992221832275,
      "eval_runtime": 376.915,
      "eval_samples_per_second": 7.673,
      "eval_steps_per_second": 3.836,
      "step": 8
    },
    {
      "epoch": 0.0013105205678922462,
      "grad_norm": 6.686164379119873,
      "learning_rate": 0.00018,
      "loss": 3.9174,
      "step": 9
    },
    {
      "epoch": 0.0017473607571896616,
      "grad_norm": 7.009781360626221,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.0186,
      "step": 12
    },
    {
      "epoch": 0.002184200946487077,
      "grad_norm": 4.845919132232666,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.6153,
      "step": 15
    },
    {
      "epoch": 0.0023298143429195486,
      "eval_loss": 0.6795167326927185,
      "eval_runtime": 376.6236,
      "eval_samples_per_second": 7.679,
      "eval_steps_per_second": 3.839,
      "step": 16
    },
    {
      "epoch": 0.0026210411357844923,
      "grad_norm": 11.320828437805176,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6679,
      "step": 18
    },
    {
      "epoch": 0.0030578813250819077,
      "grad_norm": 13.250831604003906,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.5824,
      "step": 21
    },
    {
      "epoch": 0.003494721514379323,
      "grad_norm": 6.555843353271484,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.4216,
      "step": 24
    },
    {
      "epoch": 0.003494721514379323,
      "eval_loss": 0.5682275295257568,
      "eval_runtime": 376.4911,
      "eval_samples_per_second": 7.681,
      "eval_steps_per_second": 3.841,
      "step": 24
    },
    {
      "epoch": 0.0039315617036767385,
      "grad_norm": 10.028488159179688,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.5132,
      "step": 27
    },
    {
      "epoch": 0.004368401892974154,
      "grad_norm": 4.2849440574646,
      "learning_rate": 0.0,
      "loss": 0.3847,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.109738548887552e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}