{
  "best_metric": 0.3648199141025543,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.073446327683616,
  "eval_steps": 25,
  "global_step": 34,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0903954802259887,
      "grad_norm": 39.80464553833008,
      "learning_rate": 5e-05,
      "loss": 8.2158,
      "step": 1
    },
    {
      "epoch": 0.0903954802259887,
      "eval_loss": 8.382428169250488,
      "eval_runtime": 0.8374,
      "eval_samples_per_second": 59.707,
      "eval_steps_per_second": 15.524,
      "step": 1
    },
    {
      "epoch": 0.1807909604519774,
      "grad_norm": 39.496646881103516,
      "learning_rate": 0.0001,
      "loss": 8.3531,
      "step": 2
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 36.817256927490234,
      "learning_rate": 9.978331270024886e-05,
      "loss": 6.2284,
      "step": 3
    },
    {
      "epoch": 0.3615819209039548,
      "grad_norm": 27.00182342529297,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.5679,
      "step": 4
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 23.09545135498047,
      "learning_rate": 9.80623151079494e-05,
      "loss": 1.3622,
      "step": 5
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 7.017472267150879,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.6531,
      "step": 6
    },
    {
      "epoch": 0.632768361581921,
      "grad_norm": 5.699069023132324,
      "learning_rate": 9.468645689567598e-05,
      "loss": 0.4859,
      "step": 7
    },
    {
      "epoch": 0.7231638418079096,
      "grad_norm": 5.913493633270264,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.4326,
      "step": 8
    },
    {
      "epoch": 0.8135593220338984,
      "grad_norm": 2.080118417739868,
      "learning_rate": 8.978547040132317e-05,
      "loss": 0.3708,
      "step": 9
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 1.318285584449768,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.367,
      "step": 10
    },
    {
      "epoch": 0.9943502824858758,
      "grad_norm": 4.289985656738281,
      "learning_rate": 8.354769778736406e-05,
      "loss": 0.3877,
      "step": 11
    },
    {
      "epoch": 1.0847457627118644,
      "grad_norm": 4.113544940948486,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.7215,
      "step": 12
    },
    {
      "epoch": 1.1751412429378532,
      "grad_norm": 6.731474876403809,
      "learning_rate": 7.62128531571699e-05,
      "loss": 0.3885,
      "step": 13
    },
    {
      "epoch": 1.2655367231638417,
      "grad_norm": 1.0643898248672485,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.341,
      "step": 14
    },
    {
      "epoch": 1.3559322033898304,
      "grad_norm": 2.3805298805236816,
      "learning_rate": 6.80628104764508e-05,
      "loss": 0.3611,
      "step": 15
    },
    {
      "epoch": 1.4463276836158192,
      "grad_norm": 3.9338505268096924,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.3702,
      "step": 16
    },
    {
      "epoch": 1.536723163841808,
      "grad_norm": 2.66167950630188,
      "learning_rate": 5.941077131483025e-05,
      "loss": 0.3573,
      "step": 17
    },
    {
      "epoch": 1.6271186440677967,
      "grad_norm": 0.3380945324897766,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.3487,
      "step": 18
    },
    {
      "epoch": 1.7175141242937855,
      "grad_norm": 2.3317060470581055,
      "learning_rate": 5.058922868516978e-05,
      "loss": 0.3641,
      "step": 19
    },
    {
      "epoch": 1.807909604519774,
      "grad_norm": 1.9171754121780396,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.3631,
      "step": 20
    },
    {
      "epoch": 1.8983050847457628,
      "grad_norm": 1.9694815874099731,
      "learning_rate": 4.19371895235492e-05,
      "loss": 0.348,
      "step": 21
    },
    {
      "epoch": 1.9887005649717513,
      "grad_norm": 0.38023698329925537,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.3436,
      "step": 22
    },
    {
      "epoch": 2.07909604519774,
      "grad_norm": 5.0101704597473145,
      "learning_rate": 3.378714684283011e-05,
      "loss": 0.693,
      "step": 23
    },
    {
      "epoch": 2.169491525423729,
      "grad_norm": 0.6155071258544922,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.3373,
      "step": 24
    },
    {
      "epoch": 2.2598870056497176,
      "grad_norm": 0.9621694087982178,
      "learning_rate": 2.645230221263596e-05,
      "loss": 0.3487,
      "step": 25
    },
    {
      "epoch": 2.2598870056497176,
      "eval_loss": 0.3648199141025543,
      "eval_runtime": 0.8769,
      "eval_samples_per_second": 57.021,
      "eval_steps_per_second": 14.826,
      "step": 25
    },
    {
      "epoch": 2.3502824858757063,
      "grad_norm": 1.5733007192611694,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.3583,
      "step": 26
    },
    {
      "epoch": 2.440677966101695,
      "grad_norm": 0.6812260150909424,
      "learning_rate": 2.0214529598676836e-05,
      "loss": 0.362,
      "step": 27
    },
    {
      "epoch": 2.5310734463276834,
      "grad_norm": 1.1533381938934326,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.3392,
      "step": 28
    },
    {
      "epoch": 2.621468926553672,
      "grad_norm": 0.9058969020843506,
      "learning_rate": 1.531354310432403e-05,
      "loss": 0.3486,
      "step": 29
    },
    {
      "epoch": 2.711864406779661,
      "grad_norm": 1.0298035144805908,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.3511,
      "step": 30
    },
    {
      "epoch": 2.8022598870056497,
      "grad_norm": 0.258158802986145,
      "learning_rate": 1.1937684892050604e-05,
      "loss": 0.339,
      "step": 31
    },
    {
      "epoch": 2.8926553672316384,
      "grad_norm": 0.6644238829612732,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.3545,
      "step": 32
    },
    {
      "epoch": 2.983050847457627,
      "grad_norm": 1.3119802474975586,
      "learning_rate": 1.0216687299751144e-05,
      "loss": 0.3612,
      "step": 33
    },
    {
      "epoch": 3.073446327683616,
      "grad_norm": 1.9420535564422607,
      "learning_rate": 1e-05,
      "loss": 0.6584,
      "step": 34
    }
  ],
  "logging_steps": 1,
  "max_steps": 34,
  "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": 1.0808353705112371e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}