{
  "best_metric": 0.6230994462966919,
  "best_model_checkpoint": "/content/drive/MyDrive/XLM-RoBERTa/checkpoint-2785",
  "epoch": 5.0,
  "eval_steps": 100,
  "global_step": 2785,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.293243408203125,
      "learning_rate": 4.5e-06,
      "loss": 0.6948,
      "step": 557
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5242805755395683,
      "eval_f1": 0.6641269841269841,
      "eval_loss": 0.690502405166626,
      "eval_precision": 0.5203980099502488,
      "eval_recall": 0.9175438596491228,
      "eval_runtime": 8.9725,
      "eval_samples_per_second": 123.935,
      "eval_steps_per_second": 7.802,
      "step": 557
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.867625713348389,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6886,
      "step": 1114
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5683453237410072,
      "eval_f1": 0.6536796536796536,
      "eval_loss": 0.6837959289550781,
      "eval_precision": 0.5551470588235294,
      "eval_recall": 0.7947368421052632,
      "eval_runtime": 8.6635,
      "eval_samples_per_second": 128.354,
      "eval_steps_per_second": 8.08,
      "step": 1114
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.451358795166016,
      "learning_rate": 3.5e-06,
      "loss": 0.6696,
      "step": 1671
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5926258992805755,
      "eval_f1": 0.6091458153580673,
      "eval_loss": 0.6735815405845642,
      "eval_precision": 0.599320882852292,
      "eval_recall": 0.6192982456140351,
      "eval_runtime": 8.6269,
      "eval_samples_per_second": 128.899,
      "eval_steps_per_second": 8.114,
      "step": 1671
    },
    {
      "epoch": 4.0,
      "grad_norm": 11.778752326965332,
      "learning_rate": 3e-06,
      "loss": 0.6372,
      "step": 2228
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6402877697841727,
      "eval_f1": 0.6683250414593698,
      "eval_loss": 0.6366727352142334,
      "eval_precision": 0.6336477987421384,
      "eval_recall": 0.7070175438596491,
      "eval_runtime": 8.6235,
      "eval_samples_per_second": 128.95,
      "eval_steps_per_second": 8.117,
      "step": 2228
    },
    {
      "epoch": 5.0,
      "grad_norm": 15.772424697875977,
      "learning_rate": 2.5e-06,
      "loss": 0.6001,
      "step": 2785
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6555755395683454,
      "eval_f1": 0.6706792777300086,
      "eval_loss": 0.6230994462966919,
      "eval_precision": 0.657672849915683,
      "eval_recall": 0.6842105263157895,
      "eval_runtime": 8.6356,
      "eval_samples_per_second": 128.77,
      "eval_steps_per_second": 8.106,
      "step": 2785
    }
  ],
  "logging_steps": 100,
  "max_steps": 5570,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 1.17058108529664e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}