{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.128342245989305,
  "eval_steps": 25,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0855614973262032,
      "grad_norm": 0.3136516213417053,
      "learning_rate": 5e-05,
      "loss": 2.3294,
      "step": 1
    },
    {
      "epoch": 0.0855614973262032,
      "eval_loss": NaN,
      "eval_runtime": 0.5577,
      "eval_samples_per_second": 141.657,
      "eval_steps_per_second": 17.931,
      "step": 1
    },
    {
      "epoch": 0.1711229946524064,
      "grad_norm": 0.4243817627429962,
      "learning_rate": 0.0001,
      "loss": 2.4175,
      "step": 2
    },
    {
      "epoch": 0.25668449197860965,
      "grad_norm": 0.35335254669189453,
      "learning_rate": 9.978670881475172e-05,
      "loss": 2.5057,
      "step": 3
    },
    {
      "epoch": 0.3422459893048128,
      "grad_norm": 0.34849148988723755,
      "learning_rate": 9.91486549841951e-05,
      "loss": 2.3986,
      "step": 4
    },
    {
      "epoch": 0.42780748663101603,
      "grad_norm": 0.4511032700538635,
      "learning_rate": 9.809128215864097e-05,
      "loss": 2.3214,
      "step": 5
    },
    {
      "epoch": 0.5133689839572193,
      "grad_norm": 0.32617124915122986,
      "learning_rate": 9.662361147021779e-05,
      "loss": 2.2797,
      "step": 6
    },
    {
      "epoch": 0.5989304812834224,
      "grad_norm": 0.4399779438972473,
      "learning_rate": 9.475816456775313e-05,
      "loss": 2.2683,
      "step": 7
    },
    {
      "epoch": 0.6844919786096256,
      "grad_norm": 0.30387502908706665,
      "learning_rate": 9.251085678648072e-05,
      "loss": 1.3523,
      "step": 8
    },
    {
      "epoch": 0.7700534759358288,
      "grad_norm": 0.3294680118560791,
      "learning_rate": 8.9900861364012e-05,
      "loss": 2.2551,
      "step": 9
    },
    {
      "epoch": 0.8556149732620321,
      "grad_norm": 0.42735546827316284,
      "learning_rate": 8.695044586103296e-05,
      "loss": 2.0628,
      "step": 10
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.0,
      "learning_rate": 8.368478218232787e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 1.0427807486631016,
      "grad_norm": 0.6370770931243896,
      "learning_rate": 8.013173181896283e-05,
      "loss": 3.2772,
      "step": 12
    },
    {
      "epoch": 1.1283422459893049,
      "grad_norm": 0.5347968935966492,
      "learning_rate": 7.63216081438678e-05,
      "loss": 2.3266,
      "step": 13
    },
    {
      "epoch": 1.213903743315508,
      "grad_norm": 0.061232052743434906,
      "learning_rate": 7.228691778882693e-05,
      "loss": 0.2754,
      "step": 14
    },
    {
      "epoch": 1.299465240641711,
      "grad_norm": 0.5249614715576172,
      "learning_rate": 6.806208330935766e-05,
      "loss": 3.6869,
      "step": 15
    },
    {
      "epoch": 1.3850267379679144,
      "grad_norm": 0.6129370331764221,
      "learning_rate": 6.368314950360415e-05,
      "loss": 2.2587,
      "step": 16
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 0.0,
      "learning_rate": 5.918747589082853e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.5561497326203209,
      "grad_norm": 0.475963294506073,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 2.8515,
      "step": 18
    },
    {
      "epoch": 1.641711229946524,
      "grad_norm": 0.17610086500644684,
      "learning_rate": 5e-05,
      "loss": 105.5296,
      "step": 19
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.14969512820243835,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 0.7518,
      "step": 20
    },
    {
      "epoch": 1.8128342245989306,
      "grad_norm": 0.4916137456893921,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 2.0669,
      "step": 21
    },
    {
      "epoch": 1.8983957219251337,
      "grad_norm": 0.9707525372505188,
      "learning_rate": 3.631685049639586e-05,
      "loss": 108.2932,
      "step": 22
    },
    {
      "epoch": 1.9839572192513368,
      "grad_norm": 0.31792283058166504,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 1.6389,
      "step": 23
    },
    {
      "epoch": 2.085561497326203,
      "grad_norm": 0.2978770434856415,
      "learning_rate": 2.771308221117309e-05,
      "loss": 1.7533,
      "step": 24
    },
    {
      "epoch": 2.171122994652406,
      "grad_norm": 0.3738488554954529,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 1.494,
      "step": 25
    },
    {
      "epoch": 2.171122994652406,
      "eval_loss": NaN,
      "eval_runtime": 0.5576,
      "eval_samples_per_second": 141.667,
      "eval_steps_per_second": 17.933,
      "step": 25
    },
    {
      "epoch": 2.2566844919786098,
      "grad_norm": 0.2852610945701599,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 1.9419,
      "step": 26
    },
    {
      "epoch": 2.342245989304813,
      "grad_norm": 0.3041047751903534,
      "learning_rate": 1.631521781767214e-05,
      "loss": 1.6465,
      "step": 27
    },
    {
      "epoch": 2.427807486631016,
      "grad_norm": 0.4177848696708679,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 1.4746,
      "step": 28
    },
    {
      "epoch": 2.5133689839572195,
      "grad_norm": 0.30657851696014404,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 1.7037,
      "step": 29
    },
    {
      "epoch": 2.598930481283422,
      "grad_norm": 0.3365192115306854,
      "learning_rate": 7.489143213519301e-06,
      "loss": 1.484,
      "step": 30
    },
    {
      "epoch": 2.6844919786096257,
      "grad_norm": 0.2342955768108368,
      "learning_rate": 5.241835432246889e-06,
      "loss": 0.6956,
      "step": 31
    },
    {
      "epoch": 2.770053475935829,
      "grad_norm": 0.3052198588848114,
      "learning_rate": 3.376388529782215e-06,
      "loss": 1.6939,
      "step": 32
    },
    {
      "epoch": 2.855614973262032,
      "grad_norm": 0.34793445467948914,
      "learning_rate": 1.908717841359048e-06,
      "loss": 1.4545,
      "step": 33
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.0,
      "learning_rate": 8.513450158049108e-07,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 3.0427807486631018,
      "grad_norm": 0.5034242868423462,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 2.7541,
      "step": 35
    },
    {
      "epoch": 3.128342245989305,
      "grad_norm": 0.4670789837837219,
      "learning_rate": 0.0,
      "loss": 1.8256,
      "step": 36
    }
  ],
  "logging_steps": 1,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.879899736375296e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}