{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.101449275362319,
  "eval_steps": 25,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2318840579710145,
      "grad_norm": 0.19136838614940643,
      "learning_rate": 9.869238178417235e-05,
      "loss": 0.8409,
      "step": 1
    },
    {
      "epoch": 0.2318840579710145,
      "eval_loss": 1.0124064683914185,
      "eval_runtime": 4.0442,
      "eval_samples_per_second": 12.363,
      "eval_steps_per_second": 3.215,
      "step": 1
    },
    {
      "epoch": 0.463768115942029,
      "grad_norm": 0.1825866848230362,
      "learning_rate": 9.484552115439445e-05,
      "loss": 0.8248,
      "step": 2
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.17050224542617798,
      "learning_rate": 8.868298366769954e-05,
      "loss": 0.8335,
      "step": 3
    },
    {
      "epoch": 0.927536231884058,
      "grad_norm": 0.1381475180387497,
      "learning_rate": 8.056291360290201e-05,
      "loss": 0.8089,
      "step": 4
    },
    {
      "epoch": 1.1884057971014492,
      "grad_norm": 0.263722687959671,
      "learning_rate": 7.095721991691411e-05,
      "loss": 1.4447,
      "step": 5
    },
    {
      "epoch": 1.4202898550724639,
      "grad_norm": 0.12626774609088898,
      "learning_rate": 6.042415061148954e-05,
      "loss": 0.6862,
      "step": 6
    },
    {
      "epoch": 1.6521739130434783,
      "grad_norm": 0.12955999374389648,
      "learning_rate": 4.9575849388510473e-05,
      "loss": 0.7062,
      "step": 7
    },
    {
      "epoch": 1.8840579710144927,
      "grad_norm": 0.10510830581188202,
      "learning_rate": 3.904278008308589e-05,
      "loss": 0.7127,
      "step": 8
    },
    {
      "epoch": 2.1449275362318843,
      "grad_norm": 0.2419198900461197,
      "learning_rate": 2.9437086397097995e-05,
      "loss": 1.3852,
      "step": 9
    },
    {
      "epoch": 2.3768115942028984,
      "grad_norm": 0.09900109469890594,
      "learning_rate": 2.1317016332300447e-05,
      "loss": 0.6807,
      "step": 10
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.09088369458913803,
      "learning_rate": 1.515447884560556e-05,
      "loss": 0.7003,
      "step": 11
    },
    {
      "epoch": 2.8405797101449277,
      "grad_norm": 0.09519483149051666,
      "learning_rate": 1.130761821582766e-05,
      "loss": 0.7133,
      "step": 12
    },
    {
      "epoch": 3.101449275362319,
      "grad_norm": 0.20042948424816132,
      "learning_rate": 1e-05,
      "loss": 1.2335,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "max_steps": 13,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4657700749534822e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}