{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00016036820539959748,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6036820539959746e-05,
      "grad_norm": 1.1467933654785156,
      "learning_rate": 2e-05,
      "loss": 5.8615,
      "step": 1
    },
    {
      "epoch": 1.6036820539959746e-05,
      "eval_loss": 5.424288749694824,
      "eval_runtime": 223.8412,
      "eval_samples_per_second": 117.297,
      "eval_steps_per_second": 58.649,
      "step": 1
    },
    {
      "epoch": 3.207364107991949e-05,
      "grad_norm": 1.018737554550171,
      "learning_rate": 4e-05,
      "loss": 5.3043,
      "step": 2
    },
    {
      "epoch": 4.811046161987924e-05,
      "grad_norm": 1.0681533813476562,
      "learning_rate": 6e-05,
      "loss": 5.5607,
      "step": 3
    },
    {
      "epoch": 4.811046161987924e-05,
      "eval_loss": 5.421457767486572,
      "eval_runtime": 225.1597,
      "eval_samples_per_second": 116.611,
      "eval_steps_per_second": 58.305,
      "step": 3
    },
    {
      "epoch": 6.414728215983899e-05,
      "grad_norm": 1.1862788200378418,
      "learning_rate": 8e-05,
      "loss": 5.6201,
      "step": 4
    },
    {
      "epoch": 8.018410269979874e-05,
      "grad_norm": 0.9025683999061584,
      "learning_rate": 0.0001,
      "loss": 4.9861,
      "step": 5
    },
    {
      "epoch": 9.622092323975848e-05,
      "grad_norm": 0.9972540736198425,
      "learning_rate": 0.00012,
      "loss": 5.5805,
      "step": 6
    },
    {
      "epoch": 9.622092323975848e-05,
      "eval_loss": 5.395673751831055,
      "eval_runtime": 225.5647,
      "eval_samples_per_second": 116.401,
      "eval_steps_per_second": 58.201,
      "step": 6
    },
    {
      "epoch": 0.00011225774377971823,
      "grad_norm": 1.0220520496368408,
      "learning_rate": 0.00014,
      "loss": 5.1607,
      "step": 7
    },
    {
      "epoch": 0.00012829456431967797,
      "grad_norm": 1.0660489797592163,
      "learning_rate": 0.00016,
      "loss": 5.2362,
      "step": 8
    },
    {
      "epoch": 0.00014433138485963774,
      "grad_norm": 1.278847098350525,
      "learning_rate": 0.00018,
      "loss": 5.5377,
      "step": 9
    },
    {
      "epoch": 0.00014433138485963774,
      "eval_loss": 5.315821647644043,
      "eval_runtime": 223.6227,
      "eval_samples_per_second": 117.412,
      "eval_steps_per_second": 58.706,
      "step": 9
    },
    {
      "epoch": 0.00016036820539959748,
      "grad_norm": 0.9021779894828796,
      "learning_rate": 0.0002,
      "loss": 4.8007,
      "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": 34292650475520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}