{
  "best_metric": 1.136946678161621,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.38910505836575876,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01556420233463035,
      "grad_norm": 1.466719150543213,
      "learning_rate": 2e-05,
      "loss": 1.7502,
      "step": 1
    },
    {
      "epoch": 0.01556420233463035,
      "eval_loss": 1.9832535982131958,
      "eval_runtime": 6.7392,
      "eval_samples_per_second": 4.006,
      "eval_steps_per_second": 2.077,
      "step": 1
    },
    {
      "epoch": 0.0311284046692607,
      "grad_norm": 1.7232543230056763,
      "learning_rate": 4e-05,
      "loss": 1.7618,
      "step": 2
    },
    {
      "epoch": 0.04669260700389105,
      "grad_norm": 1.608876347541809,
      "learning_rate": 6e-05,
      "loss": 1.954,
      "step": 3
    },
    {
      "epoch": 0.0622568093385214,
      "grad_norm": 1.407583236694336,
      "learning_rate": 8e-05,
      "loss": 1.6882,
      "step": 4
    },
    {
      "epoch": 0.07782101167315175,
      "grad_norm": 1.7650903463363647,
      "learning_rate": 0.0001,
      "loss": 1.767,
      "step": 5
    },
    {
      "epoch": 0.07782101167315175,
      "eval_loss": 1.781813144683838,
      "eval_runtime": 6.8446,
      "eval_samples_per_second": 3.945,
      "eval_steps_per_second": 2.045,
      "step": 5
    },
    {
      "epoch": 0.0933852140077821,
      "grad_norm": 1.3719593286514282,
      "learning_rate": 0.00012,
      "loss": 1.6271,
      "step": 6
    },
    {
      "epoch": 0.10894941634241245,
      "grad_norm": 1.2649123668670654,
      "learning_rate": 0.00014,
      "loss": 1.343,
      "step": 7
    },
    {
      "epoch": 0.1245136186770428,
      "grad_norm": 1.508124589920044,
      "learning_rate": 0.00016,
      "loss": 1.3411,
      "step": 8
    },
    {
      "epoch": 0.14007782101167315,
      "grad_norm": 1.4141943454742432,
      "learning_rate": 0.00018,
      "loss": 1.351,
      "step": 9
    },
    {
      "epoch": 0.1556420233463035,
      "grad_norm": 1.5902554988861084,
      "learning_rate": 0.0002,
      "loss": 1.3537,
      "step": 10
    },
    {
      "epoch": 0.1556420233463035,
      "eval_loss": 1.289820671081543,
      "eval_runtime": 6.5835,
      "eval_samples_per_second": 4.101,
      "eval_steps_per_second": 2.127,
      "step": 10
    },
    {
      "epoch": 0.17120622568093385,
      "grad_norm": 1.4727530479431152,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.9046,
      "step": 11
    },
    {
      "epoch": 0.1867704280155642,
      "grad_norm": 1.3481428623199463,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.0033,
      "step": 12
    },
    {
      "epoch": 0.20233463035019456,
      "grad_norm": 1.3196734189987183,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.0534,
      "step": 13
    },
    {
      "epoch": 0.2178988326848249,
      "grad_norm": 1.399394154548645,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.1459,
      "step": 14
    },
    {
      "epoch": 0.23346303501945526,
      "grad_norm": 1.5871318578720093,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.1591,
      "step": 15
    },
    {
      "epoch": 0.23346303501945526,
      "eval_loss": 1.201937198638916,
      "eval_runtime": 6.665,
      "eval_samples_per_second": 4.051,
      "eval_steps_per_second": 2.101,
      "step": 15
    },
    {
      "epoch": 0.2490272373540856,
      "grad_norm": 1.4517755508422852,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1058,
      "step": 16
    },
    {
      "epoch": 0.26459143968871596,
      "grad_norm": 1.422951102256775,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.0128,
      "step": 17
    },
    {
      "epoch": 0.2801556420233463,
      "grad_norm": 1.248138189315796,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.9126,
      "step": 18
    },
    {
      "epoch": 0.29571984435797666,
      "grad_norm": 1.289448857307434,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.134,
      "step": 19
    },
    {
      "epoch": 0.311284046692607,
      "grad_norm": 1.217300295829773,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.2286,
      "step": 20
    },
    {
      "epoch": 0.311284046692607,
      "eval_loss": 1.146728754043579,
      "eval_runtime": 6.5182,
      "eval_samples_per_second": 4.142,
      "eval_steps_per_second": 2.148,
      "step": 20
    },
    {
      "epoch": 0.32684824902723736,
      "grad_norm": 0.803828775882721,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.9064,
      "step": 21
    },
    {
      "epoch": 0.3424124513618677,
      "grad_norm": 1.1670228242874146,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.9652,
      "step": 22
    },
    {
      "epoch": 0.35797665369649806,
      "grad_norm": 1.113417387008667,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.8614,
      "step": 23
    },
    {
      "epoch": 0.3735408560311284,
      "grad_norm": 1.2294334173202515,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.0798,
      "step": 24
    },
    {
      "epoch": 0.38910505836575876,
      "grad_norm": 1.2414882183074951,
      "learning_rate": 0.0,
      "loss": 1.1288,
      "step": 25
    },
    {
      "epoch": 0.38910505836575876,
      "eval_loss": 1.136946678161621,
      "eval_runtime": 6.4836,
      "eval_samples_per_second": 4.164,
      "eval_steps_per_second": 2.159,
      "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": 5130984043315200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}