{
  "best_metric": 0.86515212059021,
  "best_model_checkpoint": "miner_id_24/checkpoint-40",
  "epoch": 1.0105263157894737,
  "eval_steps": 5,
  "global_step": 48,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 12.512845993041992,
      "learning_rate": 2e-05,
      "loss": 7.4717,
      "step": 1
    },
    {
      "epoch": 0.021052631578947368,
      "eval_loss": 1.954355239868164,
      "eval_runtime": 4.2032,
      "eval_samples_per_second": 9.754,
      "eval_steps_per_second": 2.617,
      "step": 1
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 10.354580879211426,
      "learning_rate": 4e-05,
      "loss": 6.8175,
      "step": 2
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 11.656296730041504,
      "learning_rate": 6e-05,
      "loss": 8.1518,
      "step": 3
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 11.693573951721191,
      "learning_rate": 8e-05,
      "loss": 7.629,
      "step": 4
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 11.730287551879883,
      "learning_rate": 0.0001,
      "loss": 7.3375,
      "step": 5
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 1.682303786277771,
      "eval_runtime": 2.8204,
      "eval_samples_per_second": 14.537,
      "eval_steps_per_second": 3.9,
      "step": 5
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 12.48170280456543,
      "learning_rate": 9.986661418317759e-05,
      "loss": 6.8087,
      "step": 6
    },
    {
      "epoch": 0.14736842105263157,
      "grad_norm": 12.089566230773926,
      "learning_rate": 9.946716840375551e-05,
      "loss": 5.7787,
      "step": 7
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 11.18914794921875,
      "learning_rate": 9.880379387779637e-05,
      "loss": 5.5973,
      "step": 8
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 9.470130920410156,
      "learning_rate": 9.78800299954203e-05,
      "loss": 5.4701,
      "step": 9
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 8.024460792541504,
      "learning_rate": 9.67008054366274e-05,
      "loss": 5.1077,
      "step": 10
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 1.200667381286621,
      "eval_runtime": 2.854,
      "eval_samples_per_second": 14.366,
      "eval_steps_per_second": 3.854,
      "step": 10
    },
    {
      "epoch": 0.23157894736842105,
      "grad_norm": 8.415675163269043,
      "learning_rate": 9.527241187465734e-05,
      "loss": 4.4046,
      "step": 11
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 8.372798919677734,
      "learning_rate": 9.360247040719039e-05,
      "loss": 3.4925,
      "step": 12
    },
    {
      "epoch": 0.2736842105263158,
      "grad_norm": 8.111793518066406,
      "learning_rate": 9.16998908944939e-05,
      "loss": 4.1938,
      "step": 13
    },
    {
      "epoch": 0.29473684210526313,
      "grad_norm": 9.599529266357422,
      "learning_rate": 8.957482442146272e-05,
      "loss": 4.0516,
      "step": 14
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 8.057506561279297,
      "learning_rate": 8.72386091371891e-05,
      "loss": 3.9201,
      "step": 15
    },
    {
      "epoch": 0.3157894736842105,
      "eval_loss": 1.03438138961792,
      "eval_runtime": 2.8331,
      "eval_samples_per_second": 14.472,
      "eval_steps_per_second": 3.883,
      "step": 15
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 7.639405250549316,
      "learning_rate": 8.47037097610317e-05,
      "loss": 3.8647,
      "step": 16
    },
    {
      "epoch": 0.35789473684210527,
      "grad_norm": 6.69907283782959,
      "learning_rate": 8.198365107794457e-05,
      "loss": 3.623,
      "step": 17
    },
    {
      "epoch": 0.37894736842105264,
      "grad_norm": 9.067964553833008,
      "learning_rate": 7.909294577789766e-05,
      "loss": 4.6993,
      "step": 18
    },
    {
      "epoch": 0.4,
      "grad_norm": 9.761883735656738,
      "learning_rate": 7.604701702439651e-05,
      "loss": 4.3998,
      "step": 19
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 7.566853046417236,
      "learning_rate": 7.286211616523193e-05,
      "loss": 3.5883,
      "step": 20
    },
    {
      "epoch": 0.42105263157894735,
      "eval_loss": 0.9445624947547913,
      "eval_runtime": 2.8124,
      "eval_samples_per_second": 14.579,
      "eval_steps_per_second": 3.911,
      "step": 20
    },
    {
      "epoch": 0.4421052631578947,
      "grad_norm": 7.73464822769165,
      "learning_rate": 6.95552360245078e-05,
      "loss": 3.1841,
      "step": 21
    },
    {
      "epoch": 0.4631578947368421,
      "grad_norm": 7.116307735443115,
      "learning_rate": 6.614402023857232e-05,
      "loss": 3.3875,
      "step": 22
    },
    {
      "epoch": 0.4842105263157895,
      "grad_norm": 8.046398162841797,
      "learning_rate": 6.264666911958404e-05,
      "loss": 3.4647,
      "step": 23
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 10.406704902648926,
      "learning_rate": 5.908184254897182e-05,
      "loss": 4.1152,
      "step": 24
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 7.041645526885986,
      "learning_rate": 5.546856041889373e-05,
      "loss": 3.2048,
      "step": 25
    },
    {
      "epoch": 0.5263157894736842,
      "eval_loss": 0.9079064130783081,
      "eval_runtime": 2.7719,
      "eval_samples_per_second": 14.791,
      "eval_steps_per_second": 3.968,
      "step": 25
    },
    {
      "epoch": 0.5473684210526316,
      "grad_norm": 6.507800579071045,
      "learning_rate": 5.182610115288295e-05,
      "loss": 3.722,
      "step": 26
    },
    {
      "epoch": 0.5684210526315789,
      "grad_norm": 7.869282245635986,
      "learning_rate": 4.817389884711705e-05,
      "loss": 3.7395,
      "step": 27
    },
    {
      "epoch": 0.5894736842105263,
      "grad_norm": 5.191434383392334,
      "learning_rate": 4.4531439581106295e-05,
      "loss": 2.8574,
      "step": 28
    },
    {
      "epoch": 0.6105263157894737,
      "grad_norm": 7.2071638107299805,
      "learning_rate": 4.0918157451028185e-05,
      "loss": 3.1629,
      "step": 29
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 7.546306133270264,
      "learning_rate": 3.735333088041596e-05,
      "loss": 3.1256,
      "step": 30
    },
    {
      "epoch": 0.631578947368421,
      "eval_loss": 0.889201819896698,
      "eval_runtime": 3.0016,
      "eval_samples_per_second": 13.659,
      "eval_steps_per_second": 3.665,
      "step": 30
    },
    {
      "epoch": 0.6526315789473685,
      "grad_norm": 7.491791248321533,
      "learning_rate": 3.38559797614277e-05,
      "loss": 3.8221,
      "step": 31
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 5.98444938659668,
      "learning_rate": 3.0444763975492208e-05,
      "loss": 2.6445,
      "step": 32
    },
    {
      "epoch": 0.6947368421052632,
      "grad_norm": 8.140755653381348,
      "learning_rate": 2.7137883834768073e-05,
      "loss": 2.5701,
      "step": 33
    },
    {
      "epoch": 0.7157894736842105,
      "grad_norm": 7.46447229385376,
      "learning_rate": 2.3952982975603496e-05,
      "loss": 3.3437,
      "step": 34
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 6.9073896408081055,
      "learning_rate": 2.090705422210237e-05,
      "loss": 2.8894,
      "step": 35
    },
    {
      "epoch": 0.7368421052631579,
      "eval_loss": 0.877814769744873,
      "eval_runtime": 2.9383,
      "eval_samples_per_second": 13.954,
      "eval_steps_per_second": 3.744,
      "step": 35
    },
    {
      "epoch": 0.7578947368421053,
      "grad_norm": 7.086733341217041,
      "learning_rate": 1.801634892205545e-05,
      "loss": 2.5717,
      "step": 36
    },
    {
      "epoch": 0.7789473684210526,
      "grad_norm": 6.663997173309326,
      "learning_rate": 1.5296290238968303e-05,
      "loss": 2.7322,
      "step": 37
    },
    {
      "epoch": 0.8,
      "grad_norm": 8.017515182495117,
      "learning_rate": 1.2761390862810907e-05,
      "loss": 3.5404,
      "step": 38
    },
    {
      "epoch": 0.8210526315789474,
      "grad_norm": 7.22490119934082,
      "learning_rate": 1.0425175578537299e-05,
      "loss": 3.4179,
      "step": 39
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 7.395632743835449,
      "learning_rate": 8.30010910550611e-06,
      "loss": 3.8894,
      "step": 40
    },
    {
      "epoch": 0.8421052631578947,
      "eval_loss": 0.86515212059021,
      "eval_runtime": 2.8008,
      "eval_samples_per_second": 14.639,
      "eval_steps_per_second": 3.927,
      "step": 40
    },
    {
      "epoch": 0.8631578947368421,
      "grad_norm": 6.8620100021362305,
      "learning_rate": 6.397529592809614e-06,
      "loss": 3.6803,
      "step": 41
    },
    {
      "epoch": 0.8842105263157894,
      "grad_norm": 8.952465057373047,
      "learning_rate": 4.727588125342669e-06,
      "loss": 3.8928,
      "step": 42
    },
    {
      "epoch": 0.9052631578947369,
      "grad_norm": 7.425169944763184,
      "learning_rate": 3.299194563372604e-06,
      "loss": 3.8333,
      "step": 43
    },
    {
      "epoch": 0.9263157894736842,
      "grad_norm": 6.198794364929199,
      "learning_rate": 2.1199700045797077e-06,
      "loss": 2.8467,
      "step": 44
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 7.5470170974731445,
      "learning_rate": 1.196206122203647e-06,
      "loss": 3.5179,
      "step": 45
    },
    {
      "epoch": 0.9473684210526315,
      "eval_loss": 0.8671186566352844,
      "eval_runtime": 2.7976,
      "eval_samples_per_second": 14.655,
      "eval_steps_per_second": 3.932,
      "step": 45
    },
    {
      "epoch": 0.968421052631579,
      "grad_norm": 6.172430038452148,
      "learning_rate": 5.328315962444874e-07,
      "loss": 2.8701,
      "step": 46
    },
    {
      "epoch": 0.9894736842105263,
      "grad_norm": 6.897263526916504,
      "learning_rate": 1.333858168224178e-07,
      "loss": 3.4665,
      "step": 47
    },
    {
      "epoch": 1.0105263157894737,
      "grad_norm": 7.529054641723633,
      "learning_rate": 0.0,
      "loss": 4.1975,
      "step": 48
    }
  ],
  "logging_steps": 1,
  "max_steps": 48,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5769698004172800.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}