{
  "best_metric": 0.11683187633752823,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.01592610288262462,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006370441153049849,
      "grad_norm": 0.36896780133247375,
      "learning_rate": 2e-05,
      "loss": 0.3095,
      "step": 1
    },
    {
      "epoch": 0.0006370441153049849,
      "eval_loss": 0.4068775177001953,
      "eval_runtime": 78.4994,
      "eval_samples_per_second": 8.42,
      "eval_steps_per_second": 4.217,
      "step": 1
    },
    {
      "epoch": 0.0012740882306099697,
      "grad_norm": 0.5209144949913025,
      "learning_rate": 4e-05,
      "loss": 0.3803,
      "step": 2
    },
    {
      "epoch": 0.0019111323459149545,
      "grad_norm": 0.3900339603424072,
      "learning_rate": 6e-05,
      "loss": 0.3999,
      "step": 3
    },
    {
      "epoch": 0.0025481764612199395,
      "grad_norm": 0.33980318903923035,
      "learning_rate": 8e-05,
      "loss": 0.3958,
      "step": 4
    },
    {
      "epoch": 0.0031852205765249245,
      "grad_norm": 0.30443429946899414,
      "learning_rate": 0.0001,
      "loss": 0.2916,
      "step": 5
    },
    {
      "epoch": 0.0031852205765249245,
      "eval_loss": 0.3486056625843048,
      "eval_runtime": 77.6187,
      "eval_samples_per_second": 8.516,
      "eval_steps_per_second": 4.264,
      "step": 5
    },
    {
      "epoch": 0.003822264691829909,
      "grad_norm": 0.38940486311912537,
      "learning_rate": 0.00012,
      "loss": 0.2904,
      "step": 6
    },
    {
      "epoch": 0.004459308807134894,
      "grad_norm": 0.4463357627391815,
      "learning_rate": 0.00014,
      "loss": 0.335,
      "step": 7
    },
    {
      "epoch": 0.005096352922439879,
      "grad_norm": 0.36333104968070984,
      "learning_rate": 0.00016,
      "loss": 0.207,
      "step": 8
    },
    {
      "epoch": 0.005733397037744864,
      "grad_norm": 0.47915807366371155,
      "learning_rate": 0.00018,
      "loss": 0.1927,
      "step": 9
    },
    {
      "epoch": 0.006370441153049849,
      "grad_norm": 0.40206965804100037,
      "learning_rate": 0.0002,
      "loss": 0.1337,
      "step": 10
    },
    {
      "epoch": 0.006370441153049849,
      "eval_loss": 0.1668301522731781,
      "eval_runtime": 77.4201,
      "eval_samples_per_second": 8.538,
      "eval_steps_per_second": 4.275,
      "step": 10
    },
    {
      "epoch": 0.007007485268354834,
      "grad_norm": 0.27498698234558105,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.0901,
      "step": 11
    },
    {
      "epoch": 0.007644529383659818,
      "grad_norm": 0.8802281618118286,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.1501,
      "step": 12
    },
    {
      "epoch": 0.008281573498964804,
      "grad_norm": 1.4771318435668945,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.3144,
      "step": 13
    },
    {
      "epoch": 0.008918617614269788,
      "grad_norm": 9.125785827636719,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.3531,
      "step": 14
    },
    {
      "epoch": 0.009555661729574774,
      "grad_norm": 4.068326473236084,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.259,
      "step": 15
    },
    {
      "epoch": 0.009555661729574774,
      "eval_loss": 0.12799595296382904,
      "eval_runtime": 76.8541,
      "eval_samples_per_second": 8.601,
      "eval_steps_per_second": 4.307,
      "step": 15
    },
    {
      "epoch": 0.010192705844879758,
      "grad_norm": 0.6463631391525269,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.11,
      "step": 16
    },
    {
      "epoch": 0.010829749960184742,
      "grad_norm": 0.20193718373775482,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0791,
      "step": 17
    },
    {
      "epoch": 0.011466794075489728,
      "grad_norm": 0.36674124002456665,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.1335,
      "step": 18
    },
    {
      "epoch": 0.012103838190794712,
      "grad_norm": 0.1921597719192505,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.079,
      "step": 19
    },
    {
      "epoch": 0.012740882306099698,
      "grad_norm": 0.11215493083000183,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0738,
      "step": 20
    },
    {
      "epoch": 0.012740882306099698,
      "eval_loss": 0.11883086711168289,
      "eval_runtime": 77.6734,
      "eval_samples_per_second": 8.51,
      "eval_steps_per_second": 4.261,
      "step": 20
    },
    {
      "epoch": 0.013377926421404682,
      "grad_norm": 0.3415384292602539,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.1387,
      "step": 21
    },
    {
      "epoch": 0.014014970536709668,
      "grad_norm": 0.18602176010608673,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0698,
      "step": 22
    },
    {
      "epoch": 0.014652014652014652,
      "grad_norm": 0.18146558105945587,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.0846,
      "step": 23
    },
    {
      "epoch": 0.015289058767319636,
      "grad_norm": 0.3181747496128082,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.1368,
      "step": 24
    },
    {
      "epoch": 0.01592610288262462,
      "grad_norm": 0.18709023296833038,
      "learning_rate": 0.0,
      "loss": 0.0757,
      "step": 25
    },
    {
      "epoch": 0.01592610288262462,
      "eval_loss": 0.11683187633752823,
      "eval_runtime": 76.4223,
      "eval_samples_per_second": 8.649,
      "eval_steps_per_second": 4.331,
      "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": 2275635045335040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}