{
  "best_metric": 1.781501293182373,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.25477707006369427,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005095541401273885,
      "grad_norm": 1.6865113973617554,
      "learning_rate": 1e-05,
      "loss": 1.7303,
      "step": 1
    },
    {
      "epoch": 0.005095541401273885,
      "eval_loss": 3.259193181991577,
      "eval_runtime": 24.0921,
      "eval_samples_per_second": 13.739,
      "eval_steps_per_second": 3.445,
      "step": 1
    },
    {
      "epoch": 0.01019108280254777,
      "grad_norm": 1.5365358591079712,
      "learning_rate": 2e-05,
      "loss": 1.9211,
      "step": 2
    },
    {
      "epoch": 0.015286624203821656,
      "grad_norm": 1.6096848249435425,
      "learning_rate": 3e-05,
      "loss": 1.8868,
      "step": 3
    },
    {
      "epoch": 0.02038216560509554,
      "grad_norm": 1.564287781715393,
      "learning_rate": 4e-05,
      "loss": 2.0186,
      "step": 4
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 1.5923267602920532,
      "learning_rate": 5e-05,
      "loss": 2.1118,
      "step": 5
    },
    {
      "epoch": 0.030573248407643312,
      "grad_norm": 1.6752326488494873,
      "learning_rate": 6e-05,
      "loss": 2.0342,
      "step": 6
    },
    {
      "epoch": 0.035668789808917196,
      "grad_norm": 1.8032734394073486,
      "learning_rate": 7e-05,
      "loss": 2.1314,
      "step": 7
    },
    {
      "epoch": 0.04076433121019108,
      "grad_norm": 1.8827780485153198,
      "learning_rate": 8e-05,
      "loss": 2.0909,
      "step": 8
    },
    {
      "epoch": 0.045859872611464965,
      "grad_norm": 1.659525990486145,
      "learning_rate": 9e-05,
      "loss": 1.9336,
      "step": 9
    },
    {
      "epoch": 0.050955414012738856,
      "grad_norm": 2.1119885444641113,
      "learning_rate": 0.0001,
      "loss": 1.8145,
      "step": 10
    },
    {
      "epoch": 0.05605095541401274,
      "grad_norm": 1.7493677139282227,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.625,
      "step": 11
    },
    {
      "epoch": 0.061146496815286625,
      "grad_norm": 2.1680750846862793,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.5844,
      "step": 12
    },
    {
      "epoch": 0.06624203821656051,
      "grad_norm": 1.9492312669754028,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.5817,
      "step": 13
    },
    {
      "epoch": 0.07133757961783439,
      "grad_norm": 1.6355711221694946,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.5197,
      "step": 14
    },
    {
      "epoch": 0.07643312101910828,
      "grad_norm": 1.529719591140747,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.5543,
      "step": 15
    },
    {
      "epoch": 0.08152866242038216,
      "grad_norm": 1.396162509918213,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.5315,
      "step": 16
    },
    {
      "epoch": 0.08662420382165605,
      "grad_norm": 1.388858675956726,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.5826,
      "step": 17
    },
    {
      "epoch": 0.09171974522292993,
      "grad_norm": 1.3095834255218506,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.518,
      "step": 18
    },
    {
      "epoch": 0.09681528662420383,
      "grad_norm": 1.4588730335235596,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.5464,
      "step": 19
    },
    {
      "epoch": 0.10191082802547771,
      "grad_norm": 1.393801212310791,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5825,
      "step": 20
    },
    {
      "epoch": 0.1070063694267516,
      "grad_norm": 1.3014535903930664,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.4673,
      "step": 21
    },
    {
      "epoch": 0.11210191082802548,
      "grad_norm": 1.2713675498962402,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.4179,
      "step": 22
    },
    {
      "epoch": 0.11719745222929936,
      "grad_norm": 1.3339929580688477,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.4382,
      "step": 23
    },
    {
      "epoch": 0.12229299363057325,
      "grad_norm": 1.496106505393982,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.4899,
      "step": 24
    },
    {
      "epoch": 0.12738853503184713,
      "grad_norm": 1.4896008968353271,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.5836,
      "step": 25
    },
    {
      "epoch": 0.13248407643312102,
      "grad_norm": 1.593266248703003,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.5117,
      "step": 26
    },
    {
      "epoch": 0.1375796178343949,
      "grad_norm": 1.4740333557128906,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4523,
      "step": 27
    },
    {
      "epoch": 0.14267515923566879,
      "grad_norm": 1.578808069229126,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.4339,
      "step": 28
    },
    {
      "epoch": 0.14777070063694267,
      "grad_norm": 1.60964035987854,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4432,
      "step": 29
    },
    {
      "epoch": 0.15286624203821655,
      "grad_norm": 1.485573649406433,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.3853,
      "step": 30
    },
    {
      "epoch": 0.15796178343949044,
      "grad_norm": 1.4289450645446777,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.4828,
      "step": 31
    },
    {
      "epoch": 0.16305732484076432,
      "grad_norm": 1.4461684226989746,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.5164,
      "step": 32
    },
    {
      "epoch": 0.1681528662420382,
      "grad_norm": 1.5229640007019043,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.5432,
      "step": 33
    },
    {
      "epoch": 0.1732484076433121,
      "grad_norm": 1.5570660829544067,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.6238,
      "step": 34
    },
    {
      "epoch": 0.17834394904458598,
      "grad_norm": 1.4717493057250977,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.457,
      "step": 35
    },
    {
      "epoch": 0.18343949044585986,
      "grad_norm": 1.5823116302490234,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.5628,
      "step": 36
    },
    {
      "epoch": 0.18853503184713377,
      "grad_norm": 1.481979250907898,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.4876,
      "step": 37
    },
    {
      "epoch": 0.19363057324840766,
      "grad_norm": 1.7308721542358398,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.5297,
      "step": 38
    },
    {
      "epoch": 0.19872611464968154,
      "grad_norm": 1.5279890298843384,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.5549,
      "step": 39
    },
    {
      "epoch": 0.20382165605095542,
      "grad_norm": 1.7055156230926514,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.5352,
      "step": 40
    },
    {
      "epoch": 0.2089171974522293,
      "grad_norm": 1.6564401388168335,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.4483,
      "step": 41
    },
    {
      "epoch": 0.2140127388535032,
      "grad_norm": 1.6355057954788208,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.5618,
      "step": 42
    },
    {
      "epoch": 0.21910828025477708,
      "grad_norm": 2.4172537326812744,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.5843,
      "step": 43
    },
    {
      "epoch": 0.22420382165605096,
      "grad_norm": 1.8143280744552612,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.5248,
      "step": 44
    },
    {
      "epoch": 0.22929936305732485,
      "grad_norm": 1.6940934658050537,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.558,
      "step": 45
    },
    {
      "epoch": 0.23439490445859873,
      "grad_norm": 1.8457539081573486,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.4784,
      "step": 46
    },
    {
      "epoch": 0.2394904458598726,
      "grad_norm": 1.8089879751205444,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.568,
      "step": 47
    },
    {
      "epoch": 0.2445859872611465,
      "grad_norm": 2.5819547176361084,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5019,
      "step": 48
    },
    {
      "epoch": 0.24968152866242038,
      "grad_norm": 4.068037033081055,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.5797,
      "step": 49
    },
    {
      "epoch": 0.25477707006369427,
      "grad_norm": 2.636991262435913,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.6978,
      "step": 50
    },
    {
      "epoch": 0.25477707006369427,
      "eval_loss": 1.781501293182373,
      "eval_runtime": 24.7562,
      "eval_samples_per_second": 13.37,
      "eval_steps_per_second": 3.353,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.54256789372928e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}