{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1560,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.946100094179943,
      "eval_f1": 0.7340220626860444,
      "eval_loss": 0.14316441118717194,
      "eval_precision": 0.6818477553675992,
      "eval_recall": 0.7948426241941601,
      "eval_runtime": 22.657,
      "eval_samples_per_second": 188.286,
      "eval_steps_per_second": 23.569,
      "step": 312
    },
    {
      "epoch": 1.6025641025641026,
      "grad_norm": 1.601723313331604,
      "learning_rate": 9.69728805152637e-06,
      "loss": 0.2254,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9495906794786515,
      "eval_f1": 0.7751245490465556,
      "eval_loss": 0.13631665706634521,
      "eval_precision": 0.7085427135678392,
      "eval_recall": 0.8555176336746303,
      "eval_runtime": 22.5415,
      "eval_samples_per_second": 189.251,
      "eval_steps_per_second": 23.69,
      "step": 624
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9570789728458807,
      "eval_f1": 0.7985016945121589,
      "eval_loss": 0.1211366131901741,
      "eval_precision": 0.7538167938931297,
      "eval_recall": 0.8488181013778283,
      "eval_runtime": 24.2436,
      "eval_samples_per_second": 175.964,
      "eval_steps_per_second": 22.026,
      "step": 936
    },
    {
      "epoch": 3.2051282051282053,
      "grad_norm": 1.3656506538391113,
      "learning_rate": 5.12309557439129e-06,
      "loss": 0.106,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9592457701350791,
      "eval_f1": 0.8106798983991965,
      "eval_loss": 0.11647596210241318,
      "eval_precision": 0.7609225992459525,
      "eval_recall": 0.8673998230312223,
      "eval_runtime": 22.5547,
      "eval_samples_per_second": 189.14,
      "eval_steps_per_second": 23.676,
      "step": 1248
    },
    {
      "epoch": 4.8076923076923075,
      "grad_norm": 1.5239405632019043,
      "learning_rate": 5.489030972562096e-07,
      "loss": 0.0823,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9592062540750936,
      "eval_f1": 0.8156662914025005,
      "eval_loss": 0.11935316026210785,
      "eval_precision": 0.7676778942672318,
      "eval_recall": 0.8700543546959929,
      "eval_runtime": 24.4196,
      "eval_samples_per_second": 174.696,
      "eval_steps_per_second": 21.868,
      "step": 1560
    }
  ],
  "logging_steps": 500,
  "max_steps": 1560,
  "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": 5358609903377808.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.4271480528661449e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 64,
    "seed": 2
  }
}