{
  "best_metric": 0.0,
  "best_model_checkpoint": "hf-correlations-production/checkpoint-142",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 142,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07042253521126761,
      "grad_norm": 1.0503793954849243,
      "learning_rate": 7.092198581560285e-07,
      "loss": 0.3579,
      "step": 10
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 1.0229074954986572,
      "learning_rate": 1.418439716312057e-06,
      "loss": 0.3592,
      "step": 20
    },
    {
      "epoch": 0.2112676056338028,
      "grad_norm": 0.9535344839096069,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 0.3448,
      "step": 30
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 0.9227383732795715,
      "learning_rate": 2.836879432624114e-06,
      "loss": 0.3296,
      "step": 40
    },
    {
      "epoch": 0.352112676056338,
      "grad_norm": 0.8965047001838684,
      "learning_rate": 3.5460992907801423e-06,
      "loss": 0.3188,
      "step": 50
    },
    {
      "epoch": 0.4225352112676056,
      "grad_norm": 0.8495097160339355,
      "learning_rate": 4.255319148936171e-06,
      "loss": 0.3095,
      "step": 60
    },
    {
      "epoch": 0.49295774647887325,
      "grad_norm": 0.78713458776474,
      "learning_rate": 4.964539007092199e-06,
      "loss": 0.2932,
      "step": 70
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 0.7738373875617981,
      "learning_rate": 5.673758865248228e-06,
      "loss": 0.2808,
      "step": 80
    },
    {
      "epoch": 0.6338028169014085,
      "grad_norm": 0.7417505383491516,
      "learning_rate": 6.382978723404256e-06,
      "loss": 0.2681,
      "step": 90
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": 0.6810584664344788,
      "learning_rate": 7.092198581560285e-06,
      "loss": 0.2563,
      "step": 100
    },
    {
      "epoch": 0.7746478873239436,
      "grad_norm": 0.666931688785553,
      "learning_rate": 7.801418439716313e-06,
      "loss": 0.2446,
      "step": 110
    },
    {
      "epoch": 0.8450704225352113,
      "grad_norm": 0.6319063305854797,
      "learning_rate": 8.510638297872341e-06,
      "loss": 0.2305,
      "step": 120
    },
    {
      "epoch": 0.9154929577464789,
      "grad_norm": 0.5967487692832947,
      "learning_rate": 9.21985815602837e-06,
      "loss": 0.2176,
      "step": 130
    },
    {
      "epoch": 0.9859154929577465,
      "grad_norm": 0.5726257562637329,
      "learning_rate": 9.929078014184398e-06,
      "loss": 0.209,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0,
      "eval_f1_macro": 0.0,
      "eval_f1_micro": 0.0,
      "eval_hamming_loss": 0.020087739552066497,
      "eval_hamming_score": 0.9799122604479336,
      "eval_loss": 0.19603106379508972,
      "eval_precision": 0.0,
      "eval_precision_macro": 0.0,
      "eval_precision_micro": 0.0,
      "eval_recall": 0.0,
      "eval_recall_macro": 0.0,
      "eval_recall_micro": 0.0,
      "eval_runtime": 78.2019,
      "eval_samples_per_second": 1.816,
      "eval_steps_per_second": 0.46,
      "eval_subset_accuracy": 0.0,
      "step": 142
    }
  ],
  "logging_steps": 10,
  "max_steps": 284,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 148999746250752.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}