{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.901960784313726,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_f1": 0.0,
      "eval_f1_sklearn": 0.938717358210703,
      "eval_loss": 0.2602449059486389,
      "eval_precision": 0.0,
      "eval_precision_sklearn": 0.938717358210703,
      "eval_recall": 0.0,
      "eval_recall_sklearn": 0.938717358210703,
      "eval_runtime": 4.1082,
      "eval_samples_per_second": 99.313,
      "eval_steps_per_second": 24.828,
      "step": 306
    },
    {
      "epoch": 1.6339869281045751,
      "grad_norm": 0.6803094744682312,
      "learning_rate": 0.00033660130718954253,
      "loss": 0.2299,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.0,
      "eval_f1_sklearn": 0.938717358210703,
      "eval_loss": 0.26261240243911743,
      "eval_precision": 0.0,
      "eval_precision_sklearn": 0.938717358210703,
      "eval_recall": 0.0,
      "eval_recall_sklearn": 0.938717358210703,
      "eval_runtime": 4.93,
      "eval_samples_per_second": 82.758,
      "eval_steps_per_second": 20.69,
      "step": 612
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.0,
      "eval_f1_sklearn": 0.938717358210703,
      "eval_loss": 0.2532053589820862,
      "eval_precision": 0.0,
      "eval_precision_sklearn": 0.938717358210703,
      "eval_recall": 0.0,
      "eval_recall_sklearn": 0.938717358210703,
      "eval_runtime": 5.1235,
      "eval_samples_per_second": 79.633,
      "eval_steps_per_second": 19.908,
      "step": 918
    },
    {
      "epoch": 3.2679738562091503,
      "grad_norm": 1.0660780668258667,
      "learning_rate": 0.00017320261437908497,
      "loss": 0.2252,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.0,
      "eval_f1_sklearn": 0.938717358210703,
      "eval_loss": 0.2521304190158844,
      "eval_precision": 0.0,
      "eval_precision_sklearn": 0.938717358210703,
      "eval_recall": 0.0,
      "eval_recall_sklearn": 0.938717358210703,
      "eval_runtime": 4.7637,
      "eval_samples_per_second": 85.648,
      "eval_steps_per_second": 21.412,
      "step": 1224
    },
    {
      "epoch": 4.901960784313726,
      "grad_norm": 1.0557869672775269,
      "learning_rate": 9.803921568627451e-06,
      "loss": 0.2172,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1530,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 470773232452584.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "_wandb": {},
    "assignments": {},
    "learning_rate": 0.0005,
    "metric": "eval/loss",
    "per_device_train_batch_size": 4
  }
}