{
  "best_metric": 0.55,
  "best_model_checkpoint": "test\\checkpoint-1500",
  "epoch": 1000.0,
  "eval_steps": 100,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 50.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.264135479927063,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.6603,
      "eval_samples_per_second": 0.429,
      "eval_steps_per_second": 0.215,
      "step": 100
    },
    {
      "epoch": 100.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.3265936374664307,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.6509,
      "eval_samples_per_second": 0.43,
      "eval_steps_per_second": 0.215,
      "step": 200
    },
    {
      "epoch": 150.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.4988499879837036,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.6202,
      "eval_samples_per_second": 0.433,
      "eval_steps_per_second": 0.216,
      "step": 300
    },
    {
      "epoch": 200.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.6139302253723145,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.7737,
      "eval_samples_per_second": 0.419,
      "eval_steps_per_second": 0.209,
      "step": 400
    },
    {
      "epoch": 250.0,
      "grad_norm": 0.14490167796611786,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.3046,
      "step": 500
    },
    {
      "epoch": 250.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.6872639656066895,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.6336,
      "eval_samples_per_second": 0.432,
      "eval_steps_per_second": 0.216,
      "step": 500
    },
    {
      "epoch": 300.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.7239123582839966,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.5649,
      "eval_samples_per_second": 0.438,
      "eval_steps_per_second": 0.219,
      "step": 600
    },
    {
      "epoch": 350.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.7806979417800903,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.4489,
      "eval_samples_per_second": 0.45,
      "eval_steps_per_second": 0.225,
      "step": 700
    },
    {
      "epoch": 400.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.8008891344070435,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.4619,
      "eval_samples_per_second": 0.448,
      "eval_steps_per_second": 0.224,
      "step": 800
    },
    {
      "epoch": 450.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.8712844848632812,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.4231,
      "eval_samples_per_second": 0.452,
      "eval_steps_per_second": 0.226,
      "step": 900
    },
    {
      "epoch": 500.0,
      "grad_norm": 0.03944549337029457,
      "learning_rate": 5e-06,
      "loss": 0.0081,
      "step": 1000
    },
    {
      "epoch": 500.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.9119956493377686,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.9883,
      "eval_samples_per_second": 0.401,
      "eval_steps_per_second": 0.2,
      "step": 1000
    },
    {
      "epoch": 550.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 1.947400450706482,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.9564,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.202,
      "step": 1100
    },
    {
      "epoch": 600.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.939751386642456,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.9517,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.202,
      "step": 1200
    },
    {
      "epoch": 650.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.9685324430465698,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.9434,
      "eval_samples_per_second": 0.405,
      "eval_steps_per_second": 0.202,
      "step": 1300
    },
    {
      "epoch": 700.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.9726978540420532,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 5.0891,
      "eval_samples_per_second": 0.393,
      "eval_steps_per_second": 0.196,
      "step": 1400
    },
    {
      "epoch": 750.0,
      "grad_norm": 0.0346556194126606,
      "learning_rate": 2.5e-06,
      "loss": 0.0044,
      "step": 1500
    },
    {
      "epoch": 750.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 1.9932883977890015,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 5.166,
      "eval_samples_per_second": 0.387,
      "eval_steps_per_second": 0.194,
      "step": 1500
    },
    {
      "epoch": 800.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 2.012096643447876,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 5.144,
      "eval_samples_per_second": 0.389,
      "eval_steps_per_second": 0.194,
      "step": 1600
    },
    {
      "epoch": 850.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 2.0032660961151123,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 5.175,
      "eval_samples_per_second": 0.386,
      "eval_steps_per_second": 0.193,
      "step": 1700
    },
    {
      "epoch": 900.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 2.017909288406372,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.7769,
      "eval_samples_per_second": 0.419,
      "eval_steps_per_second": 0.209,
      "step": 1800
    },
    {
      "epoch": 950.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 2.016812324523926,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.6461,
      "eval_samples_per_second": 0.43,
      "eval_steps_per_second": 0.215,
      "step": 1900
    },
    {
      "epoch": 1000.0,
      "grad_norm": 0.030378883704543114,
      "learning_rate": 0.0,
      "loss": 0.0034,
      "step": 2000
    },
    {
      "epoch": 1000.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 2.0183417797088623,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.7632,
      "eval_samples_per_second": 0.42,
      "eval_steps_per_second": 0.21,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1000,
  "save_steps": 500,
  "total_flos": 796315622400000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}