{
  "best_metric": 0.719613790512085,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.1870967741935483,
  "eval_steps": 25,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1032258064516129,
      "grad_norm": 17.193058013916016,
      "learning_rate": 5e-05,
      "loss": 9.8595,
      "step": 1
    },
    {
      "epoch": 0.1032258064516129,
      "eval_loss": 9.912254333496094,
      "eval_runtime": 2.8135,
      "eval_samples_per_second": 23.103,
      "eval_steps_per_second": 3.199,
      "step": 1
    },
    {
      "epoch": 0.2064516129032258,
      "grad_norm": 18.80805778503418,
      "learning_rate": 0.0001,
      "loss": 10.1359,
      "step": 2
    },
    {
      "epoch": 0.3096774193548387,
      "grad_norm": 17.248592376708984,
      "learning_rate": 9.966191788709716e-05,
      "loss": 9.4076,
      "step": 3
    },
    {
      "epoch": 0.4129032258064516,
      "grad_norm": 16.575469970703125,
      "learning_rate": 9.865224352899119e-05,
      "loss": 6.6598,
      "step": 4
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 15.255438804626465,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.4599,
      "step": 5
    },
    {
      "epoch": 0.6193548387096774,
      "grad_norm": 11.587812423706055,
      "learning_rate": 9.468163201617062e-05,
      "loss": 2.6178,
      "step": 6
    },
    {
      "epoch": 0.7225806451612903,
      "grad_norm": 7.051799297332764,
      "learning_rate": 9.177439057064683e-05,
      "loss": 1.6899,
      "step": 7
    },
    {
      "epoch": 0.8258064516129032,
      "grad_norm": 7.378282070159912,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.4081,
      "step": 8
    },
    {
      "epoch": 0.9290322580645162,
      "grad_norm": 3.610503673553467,
      "learning_rate": 8.43120818934367e-05,
      "loss": 0.8822,
      "step": 9
    },
    {
      "epoch": 1.096774193548387,
      "grad_norm": 3.9933135509490967,
      "learning_rate": 7.985792958513931e-05,
      "loss": 1.5521,
      "step": 10
    },
    {
      "epoch": 1.2,
      "grad_norm": 2.262838840484619,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8076,
      "step": 11
    },
    {
      "epoch": 1.303225806451613,
      "grad_norm": 1.9050098657608032,
      "learning_rate": 6.980398830195785e-05,
      "loss": 0.7512,
      "step": 12
    },
    {
      "epoch": 1.4064516129032258,
      "grad_norm": 1.8615615367889404,
      "learning_rate": 6.434016163555452e-05,
      "loss": 0.8364,
      "step": 13
    },
    {
      "epoch": 1.5096774193548388,
      "grad_norm": 3.7121288776397705,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7916,
      "step": 14
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 1.259321689605713,
      "learning_rate": 5.290724144552379e-05,
      "loss": 0.7993,
      "step": 15
    },
    {
      "epoch": 1.7161290322580647,
      "grad_norm": 2.167200803756714,
      "learning_rate": 4.709275855447621e-05,
      "loss": 0.7951,
      "step": 16
    },
    {
      "epoch": 1.8193548387096774,
      "grad_norm": 1.593809962272644,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.784,
      "step": 17
    },
    {
      "epoch": 1.9225806451612903,
      "grad_norm": 1.6661827564239502,
      "learning_rate": 3.5659838364445505e-05,
      "loss": 0.7433,
      "step": 18
    },
    {
      "epoch": 2.0903225806451613,
      "grad_norm": 3.160684585571289,
      "learning_rate": 3.019601169804216e-05,
      "loss": 1.34,
      "step": 19
    },
    {
      "epoch": 2.193548387096774,
      "grad_norm": 1.650180459022522,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7564,
      "step": 20
    },
    {
      "epoch": 2.296774193548387,
      "grad_norm": 1.9048398733139038,
      "learning_rate": 2.0142070414860704e-05,
      "loss": 0.746,
      "step": 21
    },
    {
      "epoch": 2.4,
      "grad_norm": 2.8611950874328613,
      "learning_rate": 1.5687918106563326e-05,
      "loss": 0.7922,
      "step": 22
    },
    {
      "epoch": 2.5032258064516126,
      "grad_norm": 0.8405841588973999,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.7664,
      "step": 23
    },
    {
      "epoch": 2.606451612903226,
      "grad_norm": 2.6652488708496094,
      "learning_rate": 8.225609429353187e-06,
      "loss": 0.8275,
      "step": 24
    },
    {
      "epoch": 2.709677419354839,
      "grad_norm": 2.4758827686309814,
      "learning_rate": 5.318367983829392e-06,
      "loss": 0.8093,
      "step": 25
    },
    {
      "epoch": 2.709677419354839,
      "eval_loss": 0.719613790512085,
      "eval_runtime": 1.2962,
      "eval_samples_per_second": 50.145,
      "eval_steps_per_second": 6.943,
      "step": 25
    },
    {
      "epoch": 2.8129032258064517,
      "grad_norm": 1.9881534576416016,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.7991,
      "step": 26
    },
    {
      "epoch": 2.9161290322580644,
      "grad_norm": 1.4184935092926025,
      "learning_rate": 1.3477564710088098e-06,
      "loss": 0.7739,
      "step": 27
    },
    {
      "epoch": 3.0838709677419356,
      "grad_norm": 3.0023298263549805,
      "learning_rate": 3.380821129028489e-07,
      "loss": 1.3348,
      "step": 28
    },
    {
      "epoch": 3.1870967741935483,
      "grad_norm": 2.5828163623809814,
      "learning_rate": 0.0,
      "loss": 0.8249,
      "step": 29
    }
  ],
  "logging_steps": 1,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2929663392913818e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}