{
  "best_metric": 0.34462642669677734,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0009974266392706816,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.9897065570827266e-05,
      "grad_norm": 34.571083068847656,
      "learning_rate": 2e-05,
      "loss": 13.0737,
      "step": 1
    },
    {
      "epoch": 3.9897065570827266e-05,
      "eval_loss": 13.415596008300781,
      "eval_runtime": 1769.5683,
      "eval_samples_per_second": 5.964,
      "eval_steps_per_second": 2.982,
      "step": 1
    },
    {
      "epoch": 7.979413114165453e-05,
      "grad_norm": 29.27878761291504,
      "learning_rate": 4e-05,
      "loss": 12.9275,
      "step": 2
    },
    {
      "epoch": 0.0001196911967124818,
      "grad_norm": 32.823585510253906,
      "learning_rate": 6e-05,
      "loss": 13.7609,
      "step": 3
    },
    {
      "epoch": 0.00015958826228330906,
      "grad_norm": 31.356901168823242,
      "learning_rate": 8e-05,
      "loss": 11.9954,
      "step": 4
    },
    {
      "epoch": 0.00019948532785413634,
      "grad_norm": 26.919424057006836,
      "learning_rate": 0.0001,
      "loss": 13.2038,
      "step": 5
    },
    {
      "epoch": 0.00019948532785413634,
      "eval_loss": 9.15496826171875,
      "eval_runtime": 1765.7038,
      "eval_samples_per_second": 5.977,
      "eval_steps_per_second": 2.989,
      "step": 5
    },
    {
      "epoch": 0.0002393823934249636,
      "grad_norm": 29.31121063232422,
      "learning_rate": 0.00012,
      "loss": 9.1004,
      "step": 6
    },
    {
      "epoch": 0.00027927945899579087,
      "grad_norm": 36.97990417480469,
      "learning_rate": 0.00014,
      "loss": 5.5883,
      "step": 7
    },
    {
      "epoch": 0.0003191765245666181,
      "grad_norm": 15.210268020629883,
      "learning_rate": 0.00016,
      "loss": 6.3717,
      "step": 8
    },
    {
      "epoch": 0.0003590735901374454,
      "grad_norm": 8.212323188781738,
      "learning_rate": 0.00018,
      "loss": 3.0233,
      "step": 9
    },
    {
      "epoch": 0.0003989706557082727,
      "grad_norm": 11.827737808227539,
      "learning_rate": 0.0002,
      "loss": 4.0085,
      "step": 10
    },
    {
      "epoch": 0.0003989706557082727,
      "eval_loss": 2.940157890319824,
      "eval_runtime": 1741.7012,
      "eval_samples_per_second": 6.06,
      "eval_steps_per_second": 3.03,
      "step": 10
    },
    {
      "epoch": 0.00043886772127909993,
      "grad_norm": 15.303110122680664,
      "learning_rate": 0.00019781476007338058,
      "loss": 3.1167,
      "step": 11
    },
    {
      "epoch": 0.0004787647868499272,
      "grad_norm": 13.636430740356445,
      "learning_rate": 0.0001913545457642601,
      "loss": 2.3503,
      "step": 12
    },
    {
      "epoch": 0.0005186618524207544,
      "grad_norm": 48.961456298828125,
      "learning_rate": 0.00018090169943749476,
      "loss": 4.2878,
      "step": 13
    },
    {
      "epoch": 0.0005585589179915817,
      "grad_norm": 6.62255859375,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0836,
      "step": 14
    },
    {
      "epoch": 0.0005984559835624089,
      "grad_norm": 19.507169723510742,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.787,
      "step": 15
    },
    {
      "epoch": 0.0005984559835624089,
      "eval_loss": 1.121214747428894,
      "eval_runtime": 1730.8406,
      "eval_samples_per_second": 6.098,
      "eval_steps_per_second": 3.049,
      "step": 15
    },
    {
      "epoch": 0.0006383530491332362,
      "grad_norm": 24.507638931274414,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.627,
      "step": 16
    },
    {
      "epoch": 0.0006782501147040636,
      "grad_norm": 6.47657585144043,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.6762,
      "step": 17
    },
    {
      "epoch": 0.0007181471802748908,
      "grad_norm": 1.4741249084472656,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0164,
      "step": 18
    },
    {
      "epoch": 0.0007580442458457181,
      "grad_norm": 10.461478233337402,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.5178,
      "step": 19
    },
    {
      "epoch": 0.0007979413114165454,
      "grad_norm": 7.646087169647217,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.074,
      "step": 20
    },
    {
      "epoch": 0.0007979413114165454,
      "eval_loss": 0.4543575346469879,
      "eval_runtime": 1731.5884,
      "eval_samples_per_second": 6.095,
      "eval_steps_per_second": 3.047,
      "step": 20
    },
    {
      "epoch": 0.0008378383769873726,
      "grad_norm": 29.23308753967285,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.986,
      "step": 21
    },
    {
      "epoch": 0.0008777354425581999,
      "grad_norm": 3.971245765686035,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.1557,
      "step": 22
    },
    {
      "epoch": 0.0009176325081290271,
      "grad_norm": 0.8797675371170044,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.0135,
      "step": 23
    },
    {
      "epoch": 0.0009575295736998544,
      "grad_norm": 11.720817565917969,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.6844,
      "step": 24
    },
    {
      "epoch": 0.0009974266392706816,
      "grad_norm": 11.88526725769043,
      "learning_rate": 0.0,
      "loss": 0.7534,
      "step": 25
    },
    {
      "epoch": 0.0009974266392706816,
      "eval_loss": 0.34462642669677734,
      "eval_runtime": 1726.2858,
      "eval_samples_per_second": 6.114,
      "eval_steps_per_second": 3.057,
      "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": 6889626824343552.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}