{
  "best_metric": 6.8990583419799805,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.11253340835560557,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004501336334224223,
      "grad_norm": 0.2808712124824524,
      "learning_rate": 5e-05,
      "loss": 6.9367,
      "step": 1
    },
    {
      "epoch": 0.004501336334224223,
      "eval_loss": 6.9341044425964355,
      "eval_runtime": 0.1634,
      "eval_samples_per_second": 305.927,
      "eval_steps_per_second": 79.541,
      "step": 1
    },
    {
      "epoch": 0.009002672668448446,
      "grad_norm": 0.26504793763160706,
      "learning_rate": 0.0001,
      "loss": 6.9358,
      "step": 2
    },
    {
      "epoch": 0.013504009002672668,
      "grad_norm": 0.26658204197883606,
      "learning_rate": 9.990365154573717e-05,
      "loss": 6.9353,
      "step": 3
    },
    {
      "epoch": 0.01800534533689689,
      "grad_norm": 0.27592623233795166,
      "learning_rate": 9.961501876182148e-05,
      "loss": 6.9325,
      "step": 4
    },
    {
      "epoch": 0.022506681671121114,
      "grad_norm": 0.26554349064826965,
      "learning_rate": 9.913533761814537e-05,
      "loss": 6.9318,
      "step": 5
    },
    {
      "epoch": 0.027008018005345337,
      "grad_norm": 0.2666162848472595,
      "learning_rate": 9.846666218300807e-05,
      "loss": 6.9288,
      "step": 6
    },
    {
      "epoch": 0.031509354339569556,
      "grad_norm": 0.26951131224632263,
      "learning_rate": 9.761185582727977e-05,
      "loss": 6.9282,
      "step": 7
    },
    {
      "epoch": 0.03601069067379378,
      "grad_norm": 0.26709139347076416,
      "learning_rate": 9.657457896300791e-05,
      "loss": 6.9263,
      "step": 8
    },
    {
      "epoch": 0.040512027008018,
      "grad_norm": 0.2755928039550781,
      "learning_rate": 9.535927336897098e-05,
      "loss": 6.9234,
      "step": 9
    },
    {
      "epoch": 0.04501336334224223,
      "grad_norm": 0.2812337577342987,
      "learning_rate": 9.397114317029975e-05,
      "loss": 6.9213,
      "step": 10
    },
    {
      "epoch": 0.04951469967646645,
      "grad_norm": 0.2759346067905426,
      "learning_rate": 9.241613255361455e-05,
      "loss": 6.9216,
      "step": 11
    },
    {
      "epoch": 0.054016036010690674,
      "grad_norm": 0.3198561370372772,
      "learning_rate": 9.070090031310558e-05,
      "loss": 6.9133,
      "step": 12
    },
    {
      "epoch": 0.05851737234491489,
      "grad_norm": 0.28667303919792175,
      "learning_rate": 8.883279133655399e-05,
      "loss": 6.9182,
      "step": 13
    },
    {
      "epoch": 0.06301870867913911,
      "grad_norm": 0.2683602273464203,
      "learning_rate": 8.681980515339464e-05,
      "loss": 6.9177,
      "step": 14
    },
    {
      "epoch": 0.06752004501336334,
      "grad_norm": 0.2684856951236725,
      "learning_rate": 8.467056167950311e-05,
      "loss": 6.9157,
      "step": 15
    },
    {
      "epoch": 0.07202138134758757,
      "grad_norm": 0.2700405716896057,
      "learning_rate": 8.239426430539243e-05,
      "loss": 6.9151,
      "step": 16
    },
    {
      "epoch": 0.07652271768181179,
      "grad_norm": 0.28459614515304565,
      "learning_rate": 8.000066048588211e-05,
      "loss": 6.9101,
      "step": 17
    },
    {
      "epoch": 0.081024054016036,
      "grad_norm": 0.28437161445617676,
      "learning_rate": 7.75e-05,
      "loss": 6.9089,
      "step": 18
    },
    {
      "epoch": 0.08552539035026023,
      "grad_norm": 0.28443124890327454,
      "learning_rate": 7.490299105985507e-05,
      "loss": 6.9082,
      "step": 19
    },
    {
      "epoch": 0.09002672668448446,
      "grad_norm": 0.2778397500514984,
      "learning_rate": 7.222075445642904e-05,
      "loss": 6.9079,
      "step": 20
    },
    {
      "epoch": 0.09452806301870868,
      "grad_norm": 0.2845655083656311,
      "learning_rate": 6.946477593864228e-05,
      "loss": 6.9051,
      "step": 21
    },
    {
      "epoch": 0.0990293993529329,
      "grad_norm": 0.2921813726425171,
      "learning_rate": 6.664685702961344e-05,
      "loss": 6.9022,
      "step": 22
    },
    {
      "epoch": 0.10353073568715712,
      "grad_norm": 0.28363725543022156,
      "learning_rate": 6.377906449072578e-05,
      "loss": 6.9022,
      "step": 23
    },
    {
      "epoch": 0.10803207202138135,
      "grad_norm": 0.29650917649269104,
      "learning_rate": 6.087367864990233e-05,
      "loss": 6.898,
      "step": 24
    },
    {
      "epoch": 0.11253340835560557,
      "grad_norm": 0.33996957540512085,
      "learning_rate": 5.794314081535644e-05,
      "loss": 6.892,
      "step": 25
    },
    {
      "epoch": 0.11253340835560557,
      "eval_loss": 6.8990583419799805,
      "eval_runtime": 0.1636,
      "eval_samples_per_second": 305.639,
      "eval_steps_per_second": 79.466,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5705957376000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}