{
  "best_metric": 1.330055594444275,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.049049662783568364,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002452483139178418,
      "grad_norm": 1.2774654626846313,
      "learning_rate": 2e-05,
      "loss": 2.0027,
      "step": 1
    },
    {
      "epoch": 0.002452483139178418,
      "eval_loss": 1.831758737564087,
      "eval_runtime": 57.2929,
      "eval_samples_per_second": 3.002,
      "eval_steps_per_second": 1.501,
      "step": 1
    },
    {
      "epoch": 0.004904966278356836,
      "grad_norm": 1.1944187879562378,
      "learning_rate": 4e-05,
      "loss": 2.0304,
      "step": 2
    },
    {
      "epoch": 0.007357449417535254,
      "grad_norm": 1.1539106369018555,
      "learning_rate": 6e-05,
      "loss": 1.8825,
      "step": 3
    },
    {
      "epoch": 0.009809932556713672,
      "grad_norm": 0.9850175976753235,
      "learning_rate": 8e-05,
      "loss": 1.933,
      "step": 4
    },
    {
      "epoch": 0.012262415695892091,
      "grad_norm": 1.0971778631210327,
      "learning_rate": 0.0001,
      "loss": 1.6274,
      "step": 5
    },
    {
      "epoch": 0.012262415695892091,
      "eval_loss": 1.81316077709198,
      "eval_runtime": 58.6601,
      "eval_samples_per_second": 2.932,
      "eval_steps_per_second": 1.466,
      "step": 5
    },
    {
      "epoch": 0.014714898835070508,
      "grad_norm": 1.106279969215393,
      "learning_rate": 0.00012,
      "loss": 1.5355,
      "step": 6
    },
    {
      "epoch": 0.017167381974248927,
      "grad_norm": 1.2348371744155884,
      "learning_rate": 0.00014,
      "loss": 1.866,
      "step": 7
    },
    {
      "epoch": 0.019619865113427344,
      "grad_norm": 1.3462843894958496,
      "learning_rate": 0.00016,
      "loss": 1.9333,
      "step": 8
    },
    {
      "epoch": 0.022072348252605765,
      "grad_norm": 1.5873693227767944,
      "learning_rate": 0.00018,
      "loss": 1.7938,
      "step": 9
    },
    {
      "epoch": 0.024524831391784182,
      "grad_norm": 1.4388872385025024,
      "learning_rate": 0.0002,
      "loss": 1.5617,
      "step": 10
    },
    {
      "epoch": 0.024524831391784182,
      "eval_loss": 1.6017259359359741,
      "eval_runtime": 57.6772,
      "eval_samples_per_second": 2.982,
      "eval_steps_per_second": 1.491,
      "step": 10
    },
    {
      "epoch": 0.0269773145309626,
      "grad_norm": 1.1864739656448364,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.6257,
      "step": 11
    },
    {
      "epoch": 0.029429797670141016,
      "grad_norm": 1.2734822034835815,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.3936,
      "step": 12
    },
    {
      "epoch": 0.03188228080931944,
      "grad_norm": 1.3825111389160156,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.5453,
      "step": 13
    },
    {
      "epoch": 0.034334763948497854,
      "grad_norm": 1.420120358467102,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.3915,
      "step": 14
    },
    {
      "epoch": 0.03678724708767627,
      "grad_norm": 1.3357456922531128,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3022,
      "step": 15
    },
    {
      "epoch": 0.03678724708767627,
      "eval_loss": 1.3924585580825806,
      "eval_runtime": 54.1859,
      "eval_samples_per_second": 3.174,
      "eval_steps_per_second": 1.587,
      "step": 15
    },
    {
      "epoch": 0.03923973022685469,
      "grad_norm": 1.8347684144973755,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4377,
      "step": 16
    },
    {
      "epoch": 0.041692213366033105,
      "grad_norm": 1.6689603328704834,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.3391,
      "step": 17
    },
    {
      "epoch": 0.04414469650521153,
      "grad_norm": 1.8359532356262207,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.4132,
      "step": 18
    },
    {
      "epoch": 0.04659717964438995,
      "grad_norm": 1.6253583431243896,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.0545,
      "step": 19
    },
    {
      "epoch": 0.049049662783568364,
      "grad_norm": 1.4194138050079346,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.098,
      "step": 20
    },
    {
      "epoch": 0.049049662783568364,
      "eval_loss": 1.330055594444275,
      "eval_runtime": 55.0506,
      "eval_samples_per_second": 3.124,
      "eval_steps_per_second": 1.562,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6352059230060544.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}