{
  "best_metric": 1.7353423833847046,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 0.752164900302887,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 2.2659,
      "step": 1
    },
    {
      "epoch": 0.038461538461538464,
      "eval_loss": 2.211784601211548,
      "eval_runtime": 2.2054,
      "eval_samples_per_second": 157.792,
      "eval_steps_per_second": 4.988,
      "step": 1
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.6016207933425903,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 2.1249,
      "step": 2
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 0.6095423102378845,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 2.1784,
      "step": 3
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.5610781908035278,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 2.1097,
      "step": 4
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 0.4632483422756195,
      "learning_rate": 5.05e-05,
      "loss": 2.0808,
      "step": 5
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.4746914505958557,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 2.1748,
      "step": 6
    },
    {
      "epoch": 0.2692307692307692,
      "grad_norm": 0.5191957354545593,
      "learning_rate": 7.07e-05,
      "loss": 2.1659,
      "step": 7
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.44363823533058167,
      "learning_rate": 8.080000000000001e-05,
      "loss": 2.06,
      "step": 8
    },
    {
      "epoch": 0.34615384615384615,
      "grad_norm": 0.4801614582538605,
      "learning_rate": 9.09e-05,
      "loss": 1.9743,
      "step": 9
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.441130131483078,
      "learning_rate": 0.000101,
      "loss": 1.9754,
      "step": 10
    },
    {
      "epoch": 0.4230769230769231,
      "grad_norm": 0.33599308133125305,
      "learning_rate": 9.951470588235295e-05,
      "loss": 1.9095,
      "step": 11
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3105998933315277,
      "learning_rate": 9.802941176470589e-05,
      "loss": 2.0331,
      "step": 12
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.3804920017719269,
      "learning_rate": 9.654411764705883e-05,
      "loss": 2.0143,
      "step": 13
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.24867188930511475,
      "learning_rate": 9.505882352941176e-05,
      "loss": 1.8873,
      "step": 14
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 0.24112817645072937,
      "learning_rate": 9.35735294117647e-05,
      "loss": 1.8959,
      "step": 15
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.24081434309482574,
      "learning_rate": 9.208823529411765e-05,
      "loss": 1.9147,
      "step": 16
    },
    {
      "epoch": 0.6538461538461539,
      "grad_norm": 0.21563218533992767,
      "learning_rate": 9.060294117647059e-05,
      "loss": 1.8579,
      "step": 17
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.214906245470047,
      "learning_rate": 8.911764705882354e-05,
      "loss": 1.8786,
      "step": 18
    },
    {
      "epoch": 0.7307692307692307,
      "grad_norm": 0.2766111195087433,
      "learning_rate": 8.763235294117648e-05,
      "loss": 2.0301,
      "step": 19
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.1956668496131897,
      "learning_rate": 8.614705882352941e-05,
      "loss": 1.8985,
      "step": 20
    },
    {
      "epoch": 0.8076923076923077,
      "grad_norm": 0.17424818873405457,
      "learning_rate": 8.466176470588235e-05,
      "loss": 1.8675,
      "step": 21
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.17511093616485596,
      "learning_rate": 8.31764705882353e-05,
      "loss": 1.859,
      "step": 22
    },
    {
      "epoch": 0.8846153846153846,
      "grad_norm": 0.19017955660820007,
      "learning_rate": 8.169117647058824e-05,
      "loss": 1.8439,
      "step": 23
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.17834191024303436,
      "learning_rate": 8.020588235294117e-05,
      "loss": 1.8564,
      "step": 24
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 0.23905925452709198,
      "learning_rate": 7.872058823529412e-05,
      "loss": 1.8711,
      "step": 25
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.17136764526367188,
      "learning_rate": 7.723529411764705e-05,
      "loss": 1.8694,
      "step": 26
    },
    {
      "epoch": 1.0384615384615385,
      "grad_norm": 0.1824013590812683,
      "learning_rate": 7.575e-05,
      "loss": 1.8534,
      "step": 27
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.15634748339653015,
      "learning_rate": 7.426470588235294e-05,
      "loss": 1.8498,
      "step": 28
    },
    {
      "epoch": 1.1153846153846154,
      "grad_norm": 0.15968245267868042,
      "learning_rate": 7.277941176470588e-05,
      "loss": 1.7951,
      "step": 29
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.16718855500221252,
      "learning_rate": 7.129411764705883e-05,
      "loss": 1.8043,
      "step": 30
    },
    {
      "epoch": 1.1923076923076923,
      "grad_norm": 0.16687163710594177,
      "learning_rate": 6.980882352941177e-05,
      "loss": 1.7564,
      "step": 31
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.19620829820632935,
      "learning_rate": 6.832352941176471e-05,
      "loss": 1.8006,
      "step": 32
    },
    {
      "epoch": 1.2692307692307692,
      "grad_norm": 0.199501633644104,
      "learning_rate": 6.683823529411764e-05,
      "loss": 1.8423,
      "step": 33
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.1612561047077179,
      "learning_rate": 6.535294117647059e-05,
      "loss": 1.7297,
      "step": 34
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 0.16329838335514069,
      "learning_rate": 6.386764705882353e-05,
      "loss": 1.7766,
      "step": 35
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.16919498145580292,
      "learning_rate": 6.238235294117647e-05,
      "loss": 1.7517,
      "step": 36
    },
    {
      "epoch": 1.4230769230769231,
      "grad_norm": 0.17654262483119965,
      "learning_rate": 6.089705882352941e-05,
      "loss": 1.7398,
      "step": 37
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.17898808419704437,
      "learning_rate": 5.9411764705882355e-05,
      "loss": 1.7625,
      "step": 38
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.20013999938964844,
      "learning_rate": 5.792647058823529e-05,
      "loss": 1.8085,
      "step": 39
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.1709008663892746,
      "learning_rate": 5.6441176470588234e-05,
      "loss": 1.755,
      "step": 40
    },
    {
      "epoch": 1.5769230769230769,
      "grad_norm": 0.16357500851154327,
      "learning_rate": 5.495588235294117e-05,
      "loss": 1.7085,
      "step": 41
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.17873141169548035,
      "learning_rate": 5.347058823529412e-05,
      "loss": 1.73,
      "step": 42
    },
    {
      "epoch": 1.6538461538461537,
      "grad_norm": 0.1770196110010147,
      "learning_rate": 5.198529411764706e-05,
      "loss": 1.7134,
      "step": 43
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.18043147027492523,
      "learning_rate": 5.05e-05,
      "loss": 1.7433,
      "step": 44
    },
    {
      "epoch": 1.7307692307692308,
      "grad_norm": 0.22373785078525543,
      "learning_rate": 4.9014705882352944e-05,
      "loss": 1.8027,
      "step": 45
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.19109472632408142,
      "learning_rate": 4.752941176470588e-05,
      "loss": 1.7714,
      "step": 46
    },
    {
      "epoch": 1.8076923076923077,
      "grad_norm": 0.18167556822299957,
      "learning_rate": 4.6044117647058824e-05,
      "loss": 1.7621,
      "step": 47
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.17304182052612305,
      "learning_rate": 4.455882352941177e-05,
      "loss": 1.6862,
      "step": 48
    },
    {
      "epoch": 1.8846153846153846,
      "grad_norm": 0.18664932250976562,
      "learning_rate": 4.3073529411764704e-05,
      "loss": 1.6783,
      "step": 49
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.18729540705680847,
      "learning_rate": 4.158823529411765e-05,
      "loss": 1.7136,
      "step": 50
    },
    {
      "epoch": 1.9230769230769231,
      "eval_loss": 1.7353423833847046,
      "eval_runtime": 2.3319,
      "eval_samples_per_second": 149.235,
      "eval_steps_per_second": 4.717,
      "step": 50
    },
    {
      "epoch": 1.9615384615384617,
      "grad_norm": 0.2829529047012329,
      "learning_rate": 4.0102941176470584e-05,
      "loss": 1.7164,
      "step": 51
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.17790408432483673,
      "learning_rate": 3.861764705882353e-05,
      "loss": 1.7158,
      "step": 52
    },
    {
      "epoch": 2.0384615384615383,
      "grad_norm": 0.189156174659729,
      "learning_rate": 3.713235294117647e-05,
      "loss": 1.7391,
      "step": 53
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.16967850923538208,
      "learning_rate": 3.5647058823529414e-05,
      "loss": 1.6815,
      "step": 54
    },
    {
      "epoch": 2.1153846153846154,
      "grad_norm": 0.19820086658000946,
      "learning_rate": 3.416176470588236e-05,
      "loss": 1.6854,
      "step": 55
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.18333829939365387,
      "learning_rate": 3.2676470588235294e-05,
      "loss": 1.6754,
      "step": 56
    },
    {
      "epoch": 2.1923076923076925,
      "grad_norm": 0.17899633944034576,
      "learning_rate": 3.119117647058824e-05,
      "loss": 1.6111,
      "step": 57
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.23990844190120697,
      "learning_rate": 2.9705882352941177e-05,
      "loss": 1.6596,
      "step": 58
    },
    {
      "epoch": 2.269230769230769,
      "grad_norm": 0.20980346202850342,
      "learning_rate": 2.8220588235294117e-05,
      "loss": 1.7304,
      "step": 59
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.19088959693908691,
      "learning_rate": 2.673529411764706e-05,
      "loss": 1.7127,
      "step": 60
    },
    {
      "epoch": 2.3461538461538463,
      "grad_norm": 0.19012954831123352,
      "learning_rate": 2.525e-05,
      "loss": 1.669,
      "step": 61
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 0.19641567766666412,
      "learning_rate": 2.376470588235294e-05,
      "loss": 1.6554,
      "step": 62
    },
    {
      "epoch": 2.423076923076923,
      "grad_norm": 0.1937105804681778,
      "learning_rate": 2.2279411764705884e-05,
      "loss": 1.6593,
      "step": 63
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.21003729104995728,
      "learning_rate": 2.0794117647058824e-05,
      "loss": 1.6555,
      "step": 64
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.23616966605186462,
      "learning_rate": 1.9308823529411764e-05,
      "loss": 1.6987,
      "step": 65
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 0.2137942612171173,
      "learning_rate": 1.7823529411764707e-05,
      "loss": 1.7032,
      "step": 66
    },
    {
      "epoch": 2.5769230769230766,
      "grad_norm": 0.19349639117717743,
      "learning_rate": 1.6338235294117647e-05,
      "loss": 1.6375,
      "step": 67
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.2060813009738922,
      "learning_rate": 1.4852941176470589e-05,
      "loss": 1.6618,
      "step": 68
    },
    {
      "epoch": 2.6538461538461537,
      "grad_norm": 0.21163427829742432,
      "learning_rate": 1.336764705882353e-05,
      "loss": 1.5899,
      "step": 69
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.20877523720264435,
      "learning_rate": 1.188235294117647e-05,
      "loss": 1.6251,
      "step": 70
    },
    {
      "epoch": 2.730769230769231,
      "grad_norm": 0.24440649151802063,
      "learning_rate": 1.0397058823529412e-05,
      "loss": 1.6862,
      "step": 71
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.21203215420246124,
      "learning_rate": 8.911764705882354e-06,
      "loss": 1.6578,
      "step": 72
    },
    {
      "epoch": 2.8076923076923075,
      "grad_norm": 0.1981406807899475,
      "learning_rate": 7.426470588235294e-06,
      "loss": 1.6344,
      "step": 73
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.2112911194562912,
      "learning_rate": 5.941176470588235e-06,
      "loss": 1.6169,
      "step": 74
    },
    {
      "epoch": 2.8846153846153846,
      "grad_norm": 0.21944387257099152,
      "learning_rate": 4.455882352941177e-06,
      "loss": 1.6177,
      "step": 75
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.2094384878873825,
      "learning_rate": 2.9705882352941176e-06,
      "loss": 1.6429,
      "step": 76
    },
    {
      "epoch": 2.9615384615384617,
      "grad_norm": 0.2863956093788147,
      "learning_rate": 1.4852941176470588e-06,
      "loss": 1.6306,
      "step": 77
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.18163999915122986,
      "learning_rate": 0.0,
      "loss": 1.6626,
      "step": 78
    }
  ],
  "logging_steps": 1,
  "max_steps": 78,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 4.96732228026368e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}