{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 5265,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4748338081671415,
      "grad_norm": 6.814696788787842,
      "learning_rate": 2.715099715099715e-05,
      "loss": 0.3253,
      "step": 500
    },
    {
      "epoch": 0.949667616334283,
      "grad_norm": 4.430999279022217,
      "learning_rate": 2.4301994301994302e-05,
      "loss": 0.2149,
      "step": 1000
    },
    {
      "epoch": 1.4245014245014245,
      "grad_norm": 5.158424377441406,
      "learning_rate": 2.1452991452991456e-05,
      "loss": 0.1399,
      "step": 1500
    },
    {
      "epoch": 1.899335232668566,
      "grad_norm": 2.9704854488372803,
      "learning_rate": 1.8603988603988604e-05,
      "loss": 0.1341,
      "step": 2000
    },
    {
      "epoch": 2.3741690408357075,
      "grad_norm": 5.91994047164917,
      "learning_rate": 1.5754985754985755e-05,
      "loss": 0.0936,
      "step": 2500
    },
    {
      "epoch": 2.849002849002849,
      "grad_norm": 0.2740668058395386,
      "learning_rate": 1.2905982905982905e-05,
      "loss": 0.088,
      "step": 3000
    },
    {
      "epoch": 3.3238366571699904,
      "grad_norm": 0.8711889386177063,
      "learning_rate": 1.0056980056980058e-05,
      "loss": 0.0658,
      "step": 3500
    },
    {
      "epoch": 3.798670465337132,
      "grad_norm": 0.9366008639335632,
      "learning_rate": 7.207977207977209e-06,
      "loss": 0.0585,
      "step": 4000
    },
    {
      "epoch": 4.273504273504273,
      "grad_norm": 0.3185219168663025,
      "learning_rate": 4.358974358974359e-06,
      "loss": 0.0436,
      "step": 4500
    },
    {
      "epoch": 4.748338081671415,
      "grad_norm": 4.371499061584473,
      "learning_rate": 1.50997150997151e-06,
      "loss": 0.0366,
      "step": 5000
    },
    {
      "epoch": 5.0,
      "step": 5265,
      "total_flos": 2.260855007690496e+16,
      "train_loss": 0.1158968044255647,
      "train_runtime": 1593.6448,
      "train_samples_per_second": 211.305,
      "train_steps_per_second": 3.304
    }
  ],
  "logging_steps": 500,
  "max_steps": 5265,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.260855007690496e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}