{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 2060,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4854368932038835,
      "grad_norm": 0.429694265127182,
      "learning_rate": 8.786407766990292e-05,
      "loss": 0.7853,
      "step": 250
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 0.3274327218532562,
      "learning_rate": 7.572815533980583e-05,
      "loss": 0.395,
      "step": 500
    },
    {
      "epoch": 1.4563106796116505,
      "grad_norm": 0.3228892683982849,
      "learning_rate": 6.359223300970875e-05,
      "loss": 0.3651,
      "step": 750
    },
    {
      "epoch": 1.941747572815534,
      "grad_norm": 0.3434309661388397,
      "learning_rate": 5.145631067961165e-05,
      "loss": 0.3521,
      "step": 1000
    },
    {
      "epoch": 2.4271844660194173,
      "grad_norm": 0.34895673394203186,
      "learning_rate": 3.9320388349514564e-05,
      "loss": 0.3388,
      "step": 1250
    },
    {
      "epoch": 2.912621359223301,
      "grad_norm": 0.39222878217697144,
      "learning_rate": 2.7184466019417475e-05,
      "loss": 0.3261,
      "step": 1500
    },
    {
      "epoch": 3.3980582524271843,
      "grad_norm": 0.4256580173969269,
      "learning_rate": 1.5048543689320387e-05,
      "loss": 0.306,
      "step": 1750
    },
    {
      "epoch": 3.883495145631068,
      "grad_norm": 0.41629472374916077,
      "learning_rate": 2.912621359223301e-06,
      "loss": 0.2938,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "step": 2060,
      "total_flos": 1.4631911156603474e+18,
      "train_loss": 0.39223564203503064,
      "train_runtime": 18749.6172,
      "train_samples_per_second": 28.126,
      "train_steps_per_second": 0.11
    }
  ],
  "logging_steps": 250,
  "max_steps": 2060,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4631911156603474e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}