{
  "best_metric": 1.8866443634033203,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.02498126405196103,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009992505620784412,
      "grad_norm": 4.099094867706299,
      "learning_rate": 2e-05,
      "loss": 10.4902,
      "step": 1
    },
    {
      "epoch": 0.0009992505620784412,
      "eval_loss": 2.557201623916626,
      "eval_runtime": 323.173,
      "eval_samples_per_second": 1.306,
      "eval_steps_per_second": 0.653,
      "step": 1
    },
    {
      "epoch": 0.0019985011241568824,
      "grad_norm": 2.5747148990631104,
      "learning_rate": 4e-05,
      "loss": 9.2517,
      "step": 2
    },
    {
      "epoch": 0.0029977516862353237,
      "grad_norm": 3.2455129623413086,
      "learning_rate": 6e-05,
      "loss": 10.2216,
      "step": 3
    },
    {
      "epoch": 0.003997002248313765,
      "grad_norm": 3.005558490753174,
      "learning_rate": 8e-05,
      "loss": 9.0816,
      "step": 4
    },
    {
      "epoch": 0.004996252810392206,
      "grad_norm": 2.0774357318878174,
      "learning_rate": 0.0001,
      "loss": 8.3727,
      "step": 5
    },
    {
      "epoch": 0.004996252810392206,
      "eval_loss": 2.5335335731506348,
      "eval_runtime": 330.9732,
      "eval_samples_per_second": 1.275,
      "eval_steps_per_second": 0.638,
      "step": 5
    },
    {
      "epoch": 0.005995503372470647,
      "grad_norm": 2.6195902824401855,
      "learning_rate": 0.00012,
      "loss": 8.9349,
      "step": 6
    },
    {
      "epoch": 0.0069947539345490885,
      "grad_norm": 3.1677093505859375,
      "learning_rate": 0.00014,
      "loss": 9.5464,
      "step": 7
    },
    {
      "epoch": 0.00799400449662753,
      "grad_norm": 2.5921058654785156,
      "learning_rate": 0.00016,
      "loss": 8.3258,
      "step": 8
    },
    {
      "epoch": 0.008993255058705971,
      "grad_norm": 5.20781946182251,
      "learning_rate": 0.00018,
      "loss": 10.0573,
      "step": 9
    },
    {
      "epoch": 0.009992505620784412,
      "grad_norm": 4.051074981689453,
      "learning_rate": 0.0002,
      "loss": 10.0896,
      "step": 10
    },
    {
      "epoch": 0.009992505620784412,
      "eval_loss": 2.2394750118255615,
      "eval_runtime": 322.8123,
      "eval_samples_per_second": 1.307,
      "eval_steps_per_second": 0.654,
      "step": 10
    },
    {
      "epoch": 0.010991756182862853,
      "grad_norm": 5.933827877044678,
      "learning_rate": 0.00019781476007338058,
      "loss": 9.2207,
      "step": 11
    },
    {
      "epoch": 0.011991006744941295,
      "grad_norm": 4.955999374389648,
      "learning_rate": 0.0001913545457642601,
      "loss": 8.7849,
      "step": 12
    },
    {
      "epoch": 0.012990257307019736,
      "grad_norm": 4.303705215454102,
      "learning_rate": 0.00018090169943749476,
      "loss": 8.5175,
      "step": 13
    },
    {
      "epoch": 0.013989507869098177,
      "grad_norm": 6.266185760498047,
      "learning_rate": 0.00016691306063588583,
      "loss": 8.015,
      "step": 14
    },
    {
      "epoch": 0.014988758431176618,
      "grad_norm": 7.1753740310668945,
      "learning_rate": 0.00015000000000000001,
      "loss": 9.206,
      "step": 15
    },
    {
      "epoch": 0.014988758431176618,
      "eval_loss": 2.0024607181549072,
      "eval_runtime": 320.3497,
      "eval_samples_per_second": 1.317,
      "eval_steps_per_second": 0.659,
      "step": 15
    },
    {
      "epoch": 0.01598800899325506,
      "grad_norm": 6.993997097015381,
      "learning_rate": 0.00013090169943749476,
      "loss": 7.2703,
      "step": 16
    },
    {
      "epoch": 0.0169872595553335,
      "grad_norm": 7.98905086517334,
      "learning_rate": 0.00011045284632676536,
      "loss": 7.1496,
      "step": 17
    },
    {
      "epoch": 0.017986510117411942,
      "grad_norm": 8.894564628601074,
      "learning_rate": 8.954715367323468e-05,
      "loss": 8.2454,
      "step": 18
    },
    {
      "epoch": 0.01898576067949038,
      "grad_norm": 9.84389877319336,
      "learning_rate": 6.909830056250527e-05,
      "loss": 8.3837,
      "step": 19
    },
    {
      "epoch": 0.019985011241568824,
      "grad_norm": 5.84263801574707,
      "learning_rate": 5.000000000000002e-05,
      "loss": 6.4959,
      "step": 20
    },
    {
      "epoch": 0.019985011241568824,
      "eval_loss": 1.903188705444336,
      "eval_runtime": 327.3109,
      "eval_samples_per_second": 1.289,
      "eval_steps_per_second": 0.645,
      "step": 20
    },
    {
      "epoch": 0.020984261803647264,
      "grad_norm": 6.02990198135376,
      "learning_rate": 3.308693936411421e-05,
      "loss": 7.7003,
      "step": 21
    },
    {
      "epoch": 0.021983512365725707,
      "grad_norm": 6.189011096954346,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 8.5614,
      "step": 22
    },
    {
      "epoch": 0.022982762927804146,
      "grad_norm": 7.53192663192749,
      "learning_rate": 8.645454235739903e-06,
      "loss": 8.2399,
      "step": 23
    },
    {
      "epoch": 0.02398201348988259,
      "grad_norm": 11.395584106445312,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 5.7759,
      "step": 24
    },
    {
      "epoch": 0.02498126405196103,
      "grad_norm": 7.061837673187256,
      "learning_rate": 0.0,
      "loss": 6.8975,
      "step": 25
    },
    {
      "epoch": 0.02498126405196103,
      "eval_loss": 1.8866443634033203,
      "eval_runtime": 315.3013,
      "eval_samples_per_second": 1.338,
      "eval_steps_per_second": 0.669,
      "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": 7915560763392000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}