{
  "best_metric": 0.6037781834602356,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0035234529839242457,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001761726491962123,
      "grad_norm": 2.280508041381836,
      "learning_rate": 2e-05,
      "loss": 5.4485,
      "step": 1
    },
    {
      "epoch": 0.0001761726491962123,
      "eval_loss": 1.4438605308532715,
      "eval_runtime": 556.2546,
      "eval_samples_per_second": 4.298,
      "eval_steps_per_second": 2.15,
      "step": 1
    },
    {
      "epoch": 0.0003523452983924246,
      "grad_norm": 2.090851068496704,
      "learning_rate": 4e-05,
      "loss": 5.9403,
      "step": 2
    },
    {
      "epoch": 0.0005285179475886368,
      "grad_norm": 1.839387059211731,
      "learning_rate": 6e-05,
      "loss": 5.8835,
      "step": 3
    },
    {
      "epoch": 0.0007046905967848492,
      "grad_norm": 3.055464744567871,
      "learning_rate": 8e-05,
      "loss": 6.149,
      "step": 4
    },
    {
      "epoch": 0.0008808632459810614,
      "grad_norm": 4.452210426330566,
      "learning_rate": 0.0001,
      "loss": 6.1922,
      "step": 5
    },
    {
      "epoch": 0.0008808632459810614,
      "eval_loss": 1.3926005363464355,
      "eval_runtime": 552.5067,
      "eval_samples_per_second": 4.328,
      "eval_steps_per_second": 2.165,
      "step": 5
    },
    {
      "epoch": 0.0010570358951772737,
      "grad_norm": 2.274397134780884,
      "learning_rate": 0.00012,
      "loss": 5.7608,
      "step": 6
    },
    {
      "epoch": 0.001233208544373486,
      "grad_norm": 2.994110584259033,
      "learning_rate": 0.00014,
      "loss": 5.2759,
      "step": 7
    },
    {
      "epoch": 0.0014093811935696984,
      "grad_norm": 3.168740749359131,
      "learning_rate": 0.00016,
      "loss": 5.2186,
      "step": 8
    },
    {
      "epoch": 0.0015855538427659106,
      "grad_norm": 2.3188719749450684,
      "learning_rate": 0.00018,
      "loss": 4.6927,
      "step": 9
    },
    {
      "epoch": 0.0017617264919621229,
      "grad_norm": 2.2489876747131348,
      "learning_rate": 0.0002,
      "loss": 4.492,
      "step": 10
    },
    {
      "epoch": 0.0017617264919621229,
      "eval_loss": 1.107193946838379,
      "eval_runtime": 554.1028,
      "eval_samples_per_second": 4.315,
      "eval_steps_per_second": 2.158,
      "step": 10
    },
    {
      "epoch": 0.0019378991411583351,
      "grad_norm": 3.346898317337036,
      "learning_rate": 0.00019781476007338058,
      "loss": 4.6869,
      "step": 11
    },
    {
      "epoch": 0.0021140717903545474,
      "grad_norm": 3.2118544578552246,
      "learning_rate": 0.0001913545457642601,
      "loss": 4.0561,
      "step": 12
    },
    {
      "epoch": 0.00229024443955076,
      "grad_norm": 2.7820489406585693,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.79,
      "step": 13
    },
    {
      "epoch": 0.002466417088746972,
      "grad_norm": 2.8793094158172607,
      "learning_rate": 0.00016691306063588583,
      "loss": 3.2589,
      "step": 14
    },
    {
      "epoch": 0.0026425897379431843,
      "grad_norm": 3.0016520023345947,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.1586,
      "step": 15
    },
    {
      "epoch": 0.0026425897379431843,
      "eval_loss": 0.7481167316436768,
      "eval_runtime": 558.1532,
      "eval_samples_per_second": 4.284,
      "eval_steps_per_second": 2.143,
      "step": 15
    },
    {
      "epoch": 0.0028187623871393968,
      "grad_norm": 2.852313995361328,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.0145,
      "step": 16
    },
    {
      "epoch": 0.002994935036335609,
      "grad_norm": 3.125499725341797,
      "learning_rate": 0.00011045284632676536,
      "loss": 2.7953,
      "step": 17
    },
    {
      "epoch": 0.0031711076855318212,
      "grad_norm": 3.2742762565612793,
      "learning_rate": 8.954715367323468e-05,
      "loss": 2.7007,
      "step": 18
    },
    {
      "epoch": 0.0033472803347280333,
      "grad_norm": 3.3921456336975098,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.5805,
      "step": 19
    },
    {
      "epoch": 0.0035234529839242457,
      "grad_norm": 3.3613152503967285,
      "learning_rate": 5.000000000000002e-05,
      "loss": 2.4456,
      "step": 20
    },
    {
      "epoch": 0.0035234529839242457,
      "eval_loss": 0.6037781834602356,
      "eval_runtime": 553.7732,
      "eval_samples_per_second": 4.318,
      "eval_steps_per_second": 2.16,
      "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": 1.126858116562944e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}