{
  "best_metric": 0.5936976671218872,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0013644426251876109,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.457770500750443e-05,
      "grad_norm": 144.50001525878906,
      "learning_rate": 2e-05,
      "loss": 10.3791,
      "step": 1
    },
    {
      "epoch": 5.457770500750443e-05,
      "eval_loss": 2.5071568489074707,
      "eval_runtime": 1638.1983,
      "eval_samples_per_second": 4.709,
      "eval_steps_per_second": 2.355,
      "step": 1
    },
    {
      "epoch": 0.00010915541001500886,
      "grad_norm": 75.3687515258789,
      "learning_rate": 4e-05,
      "loss": 10.9924,
      "step": 2
    },
    {
      "epoch": 0.0001637331150225133,
      "grad_norm": 77.88127899169922,
      "learning_rate": 6e-05,
      "loss": 9.7682,
      "step": 3
    },
    {
      "epoch": 0.00021831082003001773,
      "grad_norm": 75.94482421875,
      "learning_rate": 8e-05,
      "loss": 11.5198,
      "step": 4
    },
    {
      "epoch": 0.0002728885250375222,
      "grad_norm": 90.43827056884766,
      "learning_rate": 0.0001,
      "loss": 8.0485,
      "step": 5
    },
    {
      "epoch": 0.0002728885250375222,
      "eval_loss": 1.7497612237930298,
      "eval_runtime": 1669.5183,
      "eval_samples_per_second": 4.621,
      "eval_steps_per_second": 2.311,
      "step": 5
    },
    {
      "epoch": 0.0003274662300450266,
      "grad_norm": 57.87445831298828,
      "learning_rate": 0.00012,
      "loss": 8.1737,
      "step": 6
    },
    {
      "epoch": 0.00038204393505253105,
      "grad_norm": 43.79530334472656,
      "learning_rate": 0.00014,
      "loss": 4.2036,
      "step": 7
    },
    {
      "epoch": 0.00043662164006003546,
      "grad_norm": 66.7457504272461,
      "learning_rate": 0.00016,
      "loss": 4.739,
      "step": 8
    },
    {
      "epoch": 0.0004911993450675399,
      "grad_norm": 64.27976989746094,
      "learning_rate": 0.00018,
      "loss": 5.9249,
      "step": 9
    },
    {
      "epoch": 0.0005457770500750444,
      "grad_norm": 61.452171325683594,
      "learning_rate": 0.0002,
      "loss": 3.9016,
      "step": 10
    },
    {
      "epoch": 0.0005457770500750444,
      "eval_loss": 0.8490801453590393,
      "eval_runtime": 1654.8317,
      "eval_samples_per_second": 4.662,
      "eval_steps_per_second": 2.331,
      "step": 10
    },
    {
      "epoch": 0.0006003547550825488,
      "grad_norm": 53.36853790283203,
      "learning_rate": 0.00019781476007338058,
      "loss": 3.0506,
      "step": 11
    },
    {
      "epoch": 0.0006549324600900532,
      "grad_norm": 27.169435501098633,
      "learning_rate": 0.0001913545457642601,
      "loss": 2.7678,
      "step": 12
    },
    {
      "epoch": 0.0007095101650975577,
      "grad_norm": 28.606534957885742,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.4129,
      "step": 13
    },
    {
      "epoch": 0.0007640878701050621,
      "grad_norm": 47.180912017822266,
      "learning_rate": 0.00016691306063588583,
      "loss": 4.1726,
      "step": 14
    },
    {
      "epoch": 0.0008186655751125665,
      "grad_norm": 28.278949737548828,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.9509,
      "step": 15
    },
    {
      "epoch": 0.0008186655751125665,
      "eval_loss": 0.6855261325836182,
      "eval_runtime": 1640.8933,
      "eval_samples_per_second": 4.702,
      "eval_steps_per_second": 2.351,
      "step": 15
    },
    {
      "epoch": 0.0008732432801200709,
      "grad_norm": 26.91041374206543,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.1199,
      "step": 16
    },
    {
      "epoch": 0.0009278209851275754,
      "grad_norm": 28.447317123413086,
      "learning_rate": 0.00011045284632676536,
      "loss": 2.8212,
      "step": 17
    },
    {
      "epoch": 0.0009823986901350797,
      "grad_norm": 30.077438354492188,
      "learning_rate": 8.954715367323468e-05,
      "loss": 3.6232,
      "step": 18
    },
    {
      "epoch": 0.0010369763951425842,
      "grad_norm": 26.747535705566406,
      "learning_rate": 6.909830056250527e-05,
      "loss": 3.539,
      "step": 19
    },
    {
      "epoch": 0.0010915541001500887,
      "grad_norm": 39.44731140136719,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.1636,
      "step": 20
    },
    {
      "epoch": 0.0010915541001500887,
      "eval_loss": 0.6109350919723511,
      "eval_runtime": 1648.5256,
      "eval_samples_per_second": 4.68,
      "eval_steps_per_second": 2.34,
      "step": 20
    },
    {
      "epoch": 0.001146131805157593,
      "grad_norm": 21.45176887512207,
      "learning_rate": 3.308693936411421e-05,
      "loss": 2.4128,
      "step": 21
    },
    {
      "epoch": 0.0012007095101650976,
      "grad_norm": 54.497886657714844,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.7321,
      "step": 22
    },
    {
      "epoch": 0.001255287215172602,
      "grad_norm": 25.222110748291016,
      "learning_rate": 8.645454235739903e-06,
      "loss": 2.7975,
      "step": 23
    },
    {
      "epoch": 0.0013098649201801064,
      "grad_norm": 31.24700927734375,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.8001,
      "step": 24
    },
    {
      "epoch": 0.0013644426251876109,
      "grad_norm": 32.96200180053711,
      "learning_rate": 0.0,
      "loss": 2.5787,
      "step": 25
    },
    {
      "epoch": 0.0013644426251876109,
      "eval_loss": 0.5936976671218872,
      "eval_runtime": 1655.1892,
      "eval_samples_per_second": 4.661,
      "eval_steps_per_second": 2.331,
      "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": 4381674464870400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}