{
  "best_metric": 0.7201225757598877,
  "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": 17.753982543945312,
      "learning_rate": 5e-05,
      "loss": 9.8595,
      "step": 1
    },
    {
      "epoch": 0.1032258064516129,
      "eval_loss": 9.912254333496094,
      "eval_runtime": 2.9272,
      "eval_samples_per_second": 22.206,
      "eval_steps_per_second": 3.075,
      "step": 1
    },
    {
      "epoch": 0.2064516129032258,
      "grad_norm": 19.67975425720215,
      "learning_rate": 0.0001,
      "loss": 10.1359,
      "step": 2
    },
    {
      "epoch": 0.3096774193548387,
      "grad_norm": 17.82916259765625,
      "learning_rate": 9.966191788709716e-05,
      "loss": 9.4063,
      "step": 3
    },
    {
      "epoch": 0.4129032258064516,
      "grad_norm": 17.113759994506836,
      "learning_rate": 9.865224352899119e-05,
      "loss": 6.6867,
      "step": 4
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 16.286911010742188,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.4957,
      "step": 5
    },
    {
      "epoch": 0.6193548387096774,
      "grad_norm": 11.957173347473145,
      "learning_rate": 9.468163201617062e-05,
      "loss": 2.6428,
      "step": 6
    },
    {
      "epoch": 0.7225806451612903,
      "grad_norm": 7.334842681884766,
      "learning_rate": 9.177439057064683e-05,
      "loss": 1.7325,
      "step": 7
    },
    {
      "epoch": 0.8258064516129032,
      "grad_norm": 8.276832580566406,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.475,
      "step": 8
    },
    {
      "epoch": 0.9290322580645162,
      "grad_norm": 3.768533229827881,
      "learning_rate": 8.43120818934367e-05,
      "loss": 0.8936,
      "step": 9
    },
    {
      "epoch": 1.096774193548387,
      "grad_norm": 4.0367350578308105,
      "learning_rate": 7.985792958513931e-05,
      "loss": 1.5403,
      "step": 10
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.893155574798584,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8142,
      "step": 11
    },
    {
      "epoch": 1.303225806451613,
      "grad_norm": 2.1027603149414062,
      "learning_rate": 6.980398830195785e-05,
      "loss": 0.7576,
      "step": 12
    },
    {
      "epoch": 1.4064516129032258,
      "grad_norm": 2.0021579265594482,
      "learning_rate": 6.434016163555452e-05,
      "loss": 0.8329,
      "step": 13
    },
    {
      "epoch": 1.5096774193548388,
      "grad_norm": 3.544898509979248,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7915,
      "step": 14
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 1.8699073791503906,
      "learning_rate": 5.290724144552379e-05,
      "loss": 0.8044,
      "step": 15
    },
    {
      "epoch": 1.7161290322580647,
      "grad_norm": 2.309307098388672,
      "learning_rate": 4.709275855447621e-05,
      "loss": 0.7962,
      "step": 16
    },
    {
      "epoch": 1.8193548387096774,
      "grad_norm": 1.51576828956604,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.782,
      "step": 17
    },
    {
      "epoch": 1.9225806451612903,
      "grad_norm": 1.7283101081848145,
      "learning_rate": 3.5659838364445505e-05,
      "loss": 0.7452,
      "step": 18
    },
    {
      "epoch": 2.0903225806451613,
      "grad_norm": 3.430619716644287,
      "learning_rate": 3.019601169804216e-05,
      "loss": 1.3359,
      "step": 19
    },
    {
      "epoch": 2.193548387096774,
      "grad_norm": 1.290723204612732,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7537,
      "step": 20
    },
    {
      "epoch": 2.296774193548387,
      "grad_norm": 1.7700577974319458,
      "learning_rate": 2.0142070414860704e-05,
      "loss": 0.7423,
      "step": 21
    },
    {
      "epoch": 2.4,
      "grad_norm": 2.509115695953369,
      "learning_rate": 1.5687918106563326e-05,
      "loss": 0.789,
      "step": 22
    },
    {
      "epoch": 2.5032258064516126,
      "grad_norm": 0.7740902900695801,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.7628,
      "step": 23
    },
    {
      "epoch": 2.606451612903226,
      "grad_norm": 2.726773500442505,
      "learning_rate": 8.225609429353187e-06,
      "loss": 0.8262,
      "step": 24
    },
    {
      "epoch": 2.709677419354839,
      "grad_norm": 2.366220712661743,
      "learning_rate": 5.318367983829392e-06,
      "loss": 0.808,
      "step": 25
    },
    {
      "epoch": 2.709677419354839,
      "eval_loss": 0.7201225757598877,
      "eval_runtime": 2.9123,
      "eval_samples_per_second": 22.319,
      "eval_steps_per_second": 3.09,
      "step": 25
    },
    {
      "epoch": 2.8129032258064517,
      "grad_norm": 1.8182753324508667,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.7967,
      "step": 26
    },
    {
      "epoch": 2.9161290322580644,
      "grad_norm": 1.4322144985198975,
      "learning_rate": 1.3477564710088098e-06,
      "loss": 0.7748,
      "step": 27
    },
    {
      "epoch": 3.0838709677419356,
      "grad_norm": 3.2206716537475586,
      "learning_rate": 3.380821129028489e-07,
      "loss": 1.3338,
      "step": 28
    },
    {
      "epoch": 3.1870967741935483,
      "grad_norm": 2.47102427482605,
      "learning_rate": 0.0,
      "loss": 0.8182,
      "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
}