{
  "best_metric": 0.6643534302711487,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.09149130832570906,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036596523330283625,
      "grad_norm": 13.533607482910156,
      "learning_rate": 2e-05,
      "loss": 6.7335,
      "step": 1
    },
    {
      "epoch": 0.0036596523330283625,
      "eval_loss": 6.834547519683838,
      "eval_runtime": 23.2408,
      "eval_samples_per_second": 4.948,
      "eval_steps_per_second": 2.496,
      "step": 1
    },
    {
      "epoch": 0.007319304666056725,
      "grad_norm": 12.062910079956055,
      "learning_rate": 4e-05,
      "loss": 6.7457,
      "step": 2
    },
    {
      "epoch": 0.010978956999085087,
      "grad_norm": 16.1341609954834,
      "learning_rate": 6e-05,
      "loss": 6.9881,
      "step": 3
    },
    {
      "epoch": 0.01463860933211345,
      "grad_norm": 13.509819984436035,
      "learning_rate": 8e-05,
      "loss": 6.7524,
      "step": 4
    },
    {
      "epoch": 0.018298261665141813,
      "grad_norm": 18.751502990722656,
      "learning_rate": 0.0001,
      "loss": 6.2044,
      "step": 5
    },
    {
      "epoch": 0.018298261665141813,
      "eval_loss": 4.836963653564453,
      "eval_runtime": 21.6674,
      "eval_samples_per_second": 5.308,
      "eval_steps_per_second": 2.677,
      "step": 5
    },
    {
      "epoch": 0.021957913998170174,
      "grad_norm": 25.451454162597656,
      "learning_rate": 0.00012,
      "loss": 4.9829,
      "step": 6
    },
    {
      "epoch": 0.025617566331198535,
      "grad_norm": 12.474746704101562,
      "learning_rate": 0.00014,
      "loss": 3.1686,
      "step": 7
    },
    {
      "epoch": 0.0292772186642269,
      "grad_norm": 7.643014430999756,
      "learning_rate": 0.00016,
      "loss": 1.7034,
      "step": 8
    },
    {
      "epoch": 0.03293687099725526,
      "grad_norm": 3.978961229324341,
      "learning_rate": 0.00018,
      "loss": 1.0381,
      "step": 9
    },
    {
      "epoch": 0.036596523330283626,
      "grad_norm": 2.8465516567230225,
      "learning_rate": 0.0002,
      "loss": 0.6045,
      "step": 10
    },
    {
      "epoch": 0.036596523330283626,
      "eval_loss": 0.8111163377761841,
      "eval_runtime": 21.6419,
      "eval_samples_per_second": 5.314,
      "eval_steps_per_second": 2.68,
      "step": 10
    },
    {
      "epoch": 0.04025617566331199,
      "grad_norm": 3.543696880340576,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.7904,
      "step": 11
    },
    {
      "epoch": 0.04391582799634035,
      "grad_norm": 4.152765274047852,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.9458,
      "step": 12
    },
    {
      "epoch": 0.04757548032936871,
      "grad_norm": 1.8694536685943604,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.7648,
      "step": 13
    },
    {
      "epoch": 0.05123513266239707,
      "grad_norm": 0.97343909740448,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.717,
      "step": 14
    },
    {
      "epoch": 0.05489478499542543,
      "grad_norm": 1.5022720098495483,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.6217,
      "step": 15
    },
    {
      "epoch": 0.05489478499542543,
      "eval_loss": 0.6803416609764099,
      "eval_runtime": 21.8205,
      "eval_samples_per_second": 5.27,
      "eval_steps_per_second": 2.658,
      "step": 15
    },
    {
      "epoch": 0.0585544373284538,
      "grad_norm": 1.3618319034576416,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.7226,
      "step": 16
    },
    {
      "epoch": 0.06221408966148216,
      "grad_norm": 1.1633155345916748,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.6087,
      "step": 17
    },
    {
      "epoch": 0.06587374199451052,
      "grad_norm": 0.8884003162384033,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.6443,
      "step": 18
    },
    {
      "epoch": 0.06953339432753888,
      "grad_norm": 2.3892009258270264,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.8875,
      "step": 19
    },
    {
      "epoch": 0.07319304666056725,
      "grad_norm": 0.9246272444725037,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.536,
      "step": 20
    },
    {
      "epoch": 0.07319304666056725,
      "eval_loss": 0.6643534302711487,
      "eval_runtime": 21.768,
      "eval_samples_per_second": 5.283,
      "eval_steps_per_second": 2.664,
      "step": 20
    },
    {
      "epoch": 0.0768526989935956,
      "grad_norm": 1.0972665548324585,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.7126,
      "step": 21
    },
    {
      "epoch": 0.08051235132662397,
      "grad_norm": 0.5327695608139038,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.606,
      "step": 22
    },
    {
      "epoch": 0.08417200365965233,
      "grad_norm": 1.9314485788345337,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.8752,
      "step": 23
    },
    {
      "epoch": 0.0878316559926807,
      "grad_norm": 1.509268045425415,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.7843,
      "step": 24
    },
    {
      "epoch": 0.09149130832570906,
      "grad_norm": 0.6228687763214111,
      "learning_rate": 0.0,
      "loss": 0.5933,
      "step": 25
    },
    {
      "epoch": 0.09149130832570906,
      "eval_loss": 0.676060140132904,
      "eval_runtime": 21.8701,
      "eval_samples_per_second": 5.258,
      "eval_steps_per_second": 2.652,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4119557308416000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}