{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2544,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5922580645161291,
      "eval_loss": 0.20889601111412048,
      "eval_runtime": 5.414,
      "eval_samples_per_second": 572.59,
      "eval_steps_per_second": 12.006,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.542173445224762,
      "learning_rate": 1.606918238993711e-05,
      "loss": 0.3345,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8241935483870968,
      "eval_loss": 0.10050595551729202,
      "eval_runtime": 5.7639,
      "eval_samples_per_second": 537.832,
      "eval_steps_per_second": 11.277,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8796774193548387,
      "eval_loss": 0.06686455011367798,
      "eval_runtime": 5.5547,
      "eval_samples_per_second": 558.085,
      "eval_steps_per_second": 11.702,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.4653903543949127,
      "learning_rate": 1.2138364779874214e-05,
      "loss": 0.1167,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8977419354838709,
      "eval_loss": 0.0517834909260273,
      "eval_runtime": 5.5384,
      "eval_samples_per_second": 559.724,
      "eval_steps_per_second": 11.736,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.3185347020626068,
      "learning_rate": 8.207547169811321e-06,
      "loss": 0.0748,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9077419354838709,
      "eval_loss": 0.04287005588412285,
      "eval_runtime": 5.7308,
      "eval_samples_per_second": 540.936,
      "eval_steps_per_second": 11.342,
      "step": 1590
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9093548387096774,
      "eval_loss": 0.038017407059669495,
      "eval_runtime": 5.4241,
      "eval_samples_per_second": 571.523,
      "eval_steps_per_second": 11.984,
      "step": 1908
    },
    {
      "epoch": 6.289308176100629,
      "grad_norm": 0.28105106949806213,
      "learning_rate": 4.276729559748428e-06,
      "loss": 0.0595,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9158064516129032,
      "eval_loss": 0.035654906183481216,
      "eval_runtime": 5.5794,
      "eval_samples_per_second": 555.618,
      "eval_steps_per_second": 11.65,
      "step": 2226
    },
    {
      "epoch": 7.861635220125786,
      "grad_norm": 0.2838191092014313,
      "learning_rate": 3.459119496855346e-07,
      "loss": 0.0534,
      "step": 2500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2544,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 687191447960724.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.2538508748497722,
    "num_train_epochs": 8,
    "temperature": 8
  }
}