{
  "best_metric": 1.6306217908859253,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0006617038875103391,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.6468155500413566e-05,
      "grad_norm": 0.7657692432403564,
      "learning_rate": 2e-05,
      "loss": 2.0834,
      "step": 1
    },
    {
      "epoch": 2.6468155500413566e-05,
      "eval_loss": 2.068314790725708,
      "eval_runtime": 2723.9413,
      "eval_samples_per_second": 5.84,
      "eval_steps_per_second": 2.92,
      "step": 1
    },
    {
      "epoch": 5.293631100082713e-05,
      "grad_norm": 0.5874371528625488,
      "learning_rate": 4e-05,
      "loss": 2.0173,
      "step": 2
    },
    {
      "epoch": 7.94044665012407e-05,
      "grad_norm": 0.3891468048095703,
      "learning_rate": 6e-05,
      "loss": 1.9446,
      "step": 3
    },
    {
      "epoch": 0.00010587262200165426,
      "grad_norm": 0.4081283509731293,
      "learning_rate": 8e-05,
      "loss": 1.7166,
      "step": 4
    },
    {
      "epoch": 0.00013234077750206782,
      "grad_norm": 0.8195931911468506,
      "learning_rate": 0.0001,
      "loss": 2.4331,
      "step": 5
    },
    {
      "epoch": 0.00013234077750206782,
      "eval_loss": 2.049016237258911,
      "eval_runtime": 2676.6145,
      "eval_samples_per_second": 5.943,
      "eval_steps_per_second": 2.972,
      "step": 5
    },
    {
      "epoch": 0.0001588089330024814,
      "grad_norm": 0.5312638282775879,
      "learning_rate": 0.00012,
      "loss": 2.3191,
      "step": 6
    },
    {
      "epoch": 0.00018527708850289495,
      "grad_norm": 0.7682823538780212,
      "learning_rate": 0.00014,
      "loss": 2.1866,
      "step": 7
    },
    {
      "epoch": 0.00021174524400330852,
      "grad_norm": 1.0563321113586426,
      "learning_rate": 0.00016,
      "loss": 1.5494,
      "step": 8
    },
    {
      "epoch": 0.00023821339950372207,
      "grad_norm": 0.5655686855316162,
      "learning_rate": 0.00018,
      "loss": 1.7485,
      "step": 9
    },
    {
      "epoch": 0.00026468155500413565,
      "grad_norm": 0.7823865413665771,
      "learning_rate": 0.0002,
      "loss": 1.5812,
      "step": 10
    },
    {
      "epoch": 0.00026468155500413565,
      "eval_loss": 1.9181112051010132,
      "eval_runtime": 2698.4084,
      "eval_samples_per_second": 5.895,
      "eval_steps_per_second": 2.948,
      "step": 10
    },
    {
      "epoch": 0.0002911497105045492,
      "grad_norm": 0.5579884648323059,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.5377,
      "step": 11
    },
    {
      "epoch": 0.0003176178660049628,
      "grad_norm": 0.6176705360412598,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.5326,
      "step": 12
    },
    {
      "epoch": 0.0003440860215053763,
      "grad_norm": 0.5186173915863037,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.0937,
      "step": 13
    },
    {
      "epoch": 0.0003705541770057899,
      "grad_norm": 0.5176197290420532,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.7742,
      "step": 14
    },
    {
      "epoch": 0.0003970223325062035,
      "grad_norm": 0.7129431962966919,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.3958,
      "step": 15
    },
    {
      "epoch": 0.0003970223325062035,
      "eval_loss": 1.7733643054962158,
      "eval_runtime": 2688.4396,
      "eval_samples_per_second": 5.917,
      "eval_steps_per_second": 2.959,
      "step": 15
    },
    {
      "epoch": 0.00042349048800661705,
      "grad_norm": 0.7876656651496887,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.1834,
      "step": 16
    },
    {
      "epoch": 0.0004499586435070306,
      "grad_norm": 0.5958340764045715,
      "learning_rate": 0.00011045284632676536,
      "loss": 2.2134,
      "step": 17
    },
    {
      "epoch": 0.00047642679900744415,
      "grad_norm": 0.6715534329414368,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.5464,
      "step": 18
    },
    {
      "epoch": 0.0005028949545078578,
      "grad_norm": 0.6080375909805298,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.3784,
      "step": 19
    },
    {
      "epoch": 0.0005293631100082713,
      "grad_norm": 0.6638407111167908,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.5239,
      "step": 20
    },
    {
      "epoch": 0.0005293631100082713,
      "eval_loss": 1.6472125053405762,
      "eval_runtime": 2769.9677,
      "eval_samples_per_second": 5.743,
      "eval_steps_per_second": 2.872,
      "step": 20
    },
    {
      "epoch": 0.0005558312655086848,
      "grad_norm": 0.5349118113517761,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.4145,
      "step": 21
    },
    {
      "epoch": 0.0005822994210090984,
      "grad_norm": 0.6138023734092712,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.8237,
      "step": 22
    },
    {
      "epoch": 0.000608767576509512,
      "grad_norm": 1.1171259880065918,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.9742,
      "step": 23
    },
    {
      "epoch": 0.0006352357320099256,
      "grad_norm": 0.44693124294281006,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.5706,
      "step": 24
    },
    {
      "epoch": 0.0006617038875103391,
      "grad_norm": 0.7649107575416565,
      "learning_rate": 0.0,
      "loss": 1.9905,
      "step": 25
    },
    {
      "epoch": 0.0006617038875103391,
      "eval_loss": 1.6306217908859253,
      "eval_runtime": 2689.3969,
      "eval_samples_per_second": 5.915,
      "eval_steps_per_second": 2.958,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1731156756135936.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}