{
  "best_metric": 1.697729229927063,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.0,
  "eval_steps": 25,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 7.020181655883789,
      "learning_rate": 5e-05,
      "loss": 4.6816,
      "step": 1
    },
    {
      "epoch": 0.07142857142857142,
      "eval_loss": 9.965672492980957,
      "eval_runtime": 3.1129,
      "eval_samples_per_second": 30.518,
      "eval_steps_per_second": 3.855,
      "step": 1
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 15.591201782226562,
      "learning_rate": 0.0001,
      "loss": 7.9205,
      "step": 2
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 23.866371154785156,
      "learning_rate": 9.98458666866564e-05,
      "loss": 11.1902,
      "step": 3
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 7.000945091247559,
      "learning_rate": 9.938441702975689e-05,
      "loss": 3.8928,
      "step": 4
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 13.886146545410156,
      "learning_rate": 9.861849601988383e-05,
      "loss": 4.675,
      "step": 5
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 30.203248977661133,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.8457,
      "step": 6
    },
    {
      "epoch": 0.5,
      "grad_norm": 11.34516716003418,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.9694,
      "step": 7
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 15.420345306396484,
      "learning_rate": 9.45503262094184e-05,
      "loss": 2.7578,
      "step": 8
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 17.757953643798828,
      "learning_rate": 9.263200821770461e-05,
      "loss": 2.3079,
      "step": 9
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 2.0385148525238037,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.0236,
      "step": 10
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 4.7338433265686035,
      "learning_rate": 8.802029828000156e-05,
      "loss": 1.9669,
      "step": 11
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 5.90278434753418,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9986,
      "step": 12
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 13.437071800231934,
      "learning_rate": 8.247240241650918e-05,
      "loss": 2.2254,
      "step": 13
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.956202030181885,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.8723,
      "step": 14
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 1.7068158388137817,
      "learning_rate": 7.612492823579745e-05,
      "loss": 1.746,
      "step": 15
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 3.6583316326141357,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.8691,
      "step": 16
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 4.012146472930908,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.9479,
      "step": 17
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 1.376846432685852,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5925,
      "step": 18
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 3.3228981494903564,
      "learning_rate": 6.167226819279528e-05,
      "loss": 1.7874,
      "step": 19
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 2.1668920516967773,
      "learning_rate": 5.782172325201155e-05,
      "loss": 1.8105,
      "step": 20
    },
    {
      "epoch": 1.5,
      "grad_norm": 2.120370626449585,
      "learning_rate": 5.392295478639225e-05,
      "loss": 1.5832,
      "step": 21
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 2.284564971923828,
      "learning_rate": 5e-05,
      "loss": 1.7252,
      "step": 22
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 1.7141883373260498,
      "learning_rate": 4.607704521360776e-05,
      "loss": 1.7305,
      "step": 23
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.3919540643692017,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.579,
      "step": 24
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 1.5577592849731445,
      "learning_rate": 3.832773180720475e-05,
      "loss": 1.651,
      "step": 25
    },
    {
      "epoch": 1.7857142857142856,
      "eval_loss": 1.697729229927063,
      "eval_runtime": 3.1206,
      "eval_samples_per_second": 30.443,
      "eval_steps_per_second": 3.845,
      "step": 25
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 1.2910879850387573,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.6083,
      "step": 26
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 2.372886896133423,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.654,
      "step": 27
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.5181156396865845,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.5466,
      "step": 28
    },
    {
      "epoch": 2.0714285714285716,
      "grad_norm": 0.9630998969078064,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 1.4119,
      "step": 29
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 1.2351303100585938,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.5674,
      "step": 30
    },
    {
      "epoch": 2.2142857142857144,
      "grad_norm": 2.0758800506591797,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 1.5598,
      "step": 31
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 1.076073169708252,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4146,
      "step": 32
    },
    {
      "epoch": 2.357142857142857,
      "grad_norm": 1.3192384243011475,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 1.5492,
      "step": 33
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 1.5484938621520996,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.5209,
      "step": 34
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.984063982963562,
      "learning_rate": 7.367991782295391e-06,
      "loss": 1.3867,
      "step": 35
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 1.18297278881073,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.5152,
      "step": 36
    },
    {
      "epoch": 2.642857142857143,
      "grad_norm": 1.3486729860305786,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.4508,
      "step": 37
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 1.0198802947998047,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.3897,
      "step": 38
    },
    {
      "epoch": 2.7857142857142856,
      "grad_norm": 0.9609850645065308,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 1.4722,
      "step": 39
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 1.0965021848678589,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.4413,
      "step": 40
    },
    {
      "epoch": 2.928571428571429,
      "grad_norm": 1.669950008392334,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 1.4793,
      "step": 41
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8596750497817993,
      "learning_rate": 0.0,
      "loss": 1.4315,
      "step": 42
    }
  ],
  "logging_steps": 1,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5.186562649353093e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}