{
  "best_metric": 0.6208587338139933,
  "best_model_checkpoint": "students_scores_model/run-2/checkpoint-1126",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1689,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8880994671403197,
      "grad_norm": 7.292171478271484,
      "learning_rate": 3.526354733861817e-05,
      "loss": 1.0895,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.5011171601790574,
      "eval_loss": 1.1365867853164673,
      "eval_runtime": 37.7018,
      "eval_samples_per_second": 59.679,
      "eval_steps_per_second": 7.48,
      "step": 563
    },
    {
      "epoch": 1.7761989342806395,
      "grad_norm": 11.239688873291016,
      "learning_rate": 2.764723041883023e-05,
      "loss": 0.8974,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.6208587338139933,
      "eval_loss": 0.8815694451332092,
      "eval_runtime": 37.5893,
      "eval_samples_per_second": 59.857,
      "eval_steps_per_second": 7.502,
      "step": 1126
    },
    {
      "epoch": 2.664298401420959,
      "grad_norm": 12.65758991241455,
      "learning_rate": 2.003091349904229e-05,
      "loss": 0.7725,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.5950155132637635,
      "eval_loss": 0.9455859661102295,
      "eval_runtime": 37.7615,
      "eval_samples_per_second": 59.585,
      "eval_steps_per_second": 7.468,
      "step": 1689
    }
  ],
  "logging_steps": 500,
  "max_steps": 2815,
  "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": 6310155946881024.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.2879864258406114e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 16,
    "weight_decay": 0.060543241151812754
  }
}