{
  "best_metric": 0.600451467268623,
  "best_model_checkpoint": "/home/ubuntu/utah/babylm-24/src/evaluation/results/finetune/DebertaV2-Base-10M_babylm-A/multirc/checkpoint-6812",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 6812,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14679976512037582,
      "grad_norm": 3.0609993934631348,
      "learning_rate": 2.9119201409277748e-05,
      "loss": 0.7038,
      "step": 500
    },
    {
      "epoch": 0.29359953024075164,
      "grad_norm": 1.6316922903060913,
      "learning_rate": 2.823840281855549e-05,
      "loss": 0.6981,
      "step": 1000
    },
    {
      "epoch": 0.44039929536112743,
      "grad_norm": 2.5649499893188477,
      "learning_rate": 2.7357604227833236e-05,
      "loss": 0.6919,
      "step": 1500
    },
    {
      "epoch": 0.5871990604815033,
      "grad_norm": 4.061516284942627,
      "learning_rate": 2.6476805637110984e-05,
      "loss": 0.6644,
      "step": 2000
    },
    {
      "epoch": 0.733998825601879,
      "grad_norm": 2.645333766937256,
      "learning_rate": 2.5596007046388724e-05,
      "loss": 0.6586,
      "step": 2500
    },
    {
      "epoch": 0.8807985907222549,
      "grad_norm": 3.289055347442627,
      "learning_rate": 2.4715208455666472e-05,
      "loss": 0.644,
      "step": 3000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6452144980430603,
      "eval_f1": 0.5682730923694779,
      "eval_loss": 0.6363362073898315,
      "eval_mcc": 0.26813709584707873,
      "eval_runtime": 3.7981,
      "eval_samples_per_second": 638.206,
      "eval_steps_per_second": 79.776,
      "step": 3406
    },
    {
      "epoch": 1.0275983558426307,
      "grad_norm": 5.0068888664245605,
      "learning_rate": 2.383440986494422e-05,
      "loss": 0.6388,
      "step": 3500
    },
    {
      "epoch": 1.1743981209630066,
      "grad_norm": 4.675343036651611,
      "learning_rate": 2.295361127422196e-05,
      "loss": 0.6086,
      "step": 4000
    },
    {
      "epoch": 1.3211978860833824,
      "grad_norm": 3.6214439868927,
      "learning_rate": 2.2072812683499707e-05,
      "loss": 0.603,
      "step": 4500
    },
    {
      "epoch": 1.467997651203758,
      "grad_norm": 13.145421028137207,
      "learning_rate": 2.1192014092777455e-05,
      "loss": 0.6064,
      "step": 5000
    },
    {
      "epoch": 1.6147974163241339,
      "grad_norm": 5.481179714202881,
      "learning_rate": 2.0311215502055195e-05,
      "loss": 0.5854,
      "step": 5500
    },
    {
      "epoch": 1.7615971814445097,
      "grad_norm": 3.6306419372558594,
      "learning_rate": 1.9430416911332943e-05,
      "loss": 0.5898,
      "step": 6000
    },
    {
      "epoch": 1.9083969465648853,
      "grad_norm": 4.952913761138916,
      "learning_rate": 1.8549618320610687e-05,
      "loss": 0.593,
      "step": 6500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6349009871482849,
      "eval_f1": 0.600451467268623,
      "eval_loss": 0.6888149976730347,
      "eval_mcc": 0.2697165007428369,
      "eval_runtime": 3.8279,
      "eval_samples_per_second": 633.242,
      "eval_steps_per_second": 79.155,
      "step": 6812
    }
  ],
  "logging_steps": 500,
  "max_steps": 17030,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "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": 3214550779693056.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}