{
  "best_metric": 0.7647556662559509,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.13065490772497143,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026130981544994283,
      "grad_norm": 32.21394348144531,
      "learning_rate": 5e-05,
      "loss": 0.7757,
      "step": 1
    },
    {
      "epoch": 0.0026130981544994283,
      "eval_loss": 1.1999441385269165,
      "eval_runtime": 81.1579,
      "eval_samples_per_second": 31.765,
      "eval_steps_per_second": 3.98,
      "step": 1
    },
    {
      "epoch": 0.005226196308998857,
      "grad_norm": 39.36853790283203,
      "learning_rate": 0.0001,
      "loss": 0.9545,
      "step": 2
    },
    {
      "epoch": 0.007839294463498285,
      "grad_norm": 18.13382911682129,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.897,
      "step": 3
    },
    {
      "epoch": 0.010452392617997713,
      "grad_norm": 56.46504211425781,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.0219,
      "step": 4
    },
    {
      "epoch": 0.013065490772497142,
      "grad_norm": 36.28642272949219,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.9692,
      "step": 5
    },
    {
      "epoch": 0.01567858892699657,
      "grad_norm": 22.284128189086914,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.9157,
      "step": 6
    },
    {
      "epoch": 0.018291687081496,
      "grad_norm": 16.324134826660156,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.8129,
      "step": 7
    },
    {
      "epoch": 0.020904785235995427,
      "grad_norm": 15.565814971923828,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.8251,
      "step": 8
    },
    {
      "epoch": 0.023517883390494855,
      "grad_norm": 28.220914840698242,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.89,
      "step": 9
    },
    {
      "epoch": 0.026130981544994283,
      "grad_norm": 33.45243835449219,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9368,
      "step": 10
    },
    {
      "epoch": 0.02874407969949371,
      "grad_norm": 55.80691909790039,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.9962,
      "step": 11
    },
    {
      "epoch": 0.03135717785399314,
      "grad_norm": 54.023651123046875,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.1259,
      "step": 12
    },
    {
      "epoch": 0.03397027600849257,
      "grad_norm": 50.94385528564453,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.0058,
      "step": 13
    },
    {
      "epoch": 0.036583374162992,
      "grad_norm": 28.61728286743164,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7789,
      "step": 14
    },
    {
      "epoch": 0.039196472317491425,
      "grad_norm": 19.02658462524414,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.7883,
      "step": 15
    },
    {
      "epoch": 0.04180957047199085,
      "grad_norm": 12.953407287597656,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8,
      "step": 16
    },
    {
      "epoch": 0.04442266862649028,
      "grad_norm": 10.443005561828613,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.7928,
      "step": 17
    },
    {
      "epoch": 0.04703576678098971,
      "grad_norm": 10.549766540527344,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8224,
      "step": 18
    },
    {
      "epoch": 0.04964886493548914,
      "grad_norm": 11.032112121582031,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.7848,
      "step": 19
    },
    {
      "epoch": 0.05226196308998857,
      "grad_norm": 12.363487243652344,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7763,
      "step": 20
    },
    {
      "epoch": 0.054875061244487995,
      "grad_norm": 12.747096061706543,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.7274,
      "step": 21
    },
    {
      "epoch": 0.05748815939898742,
      "grad_norm": 19.697521209716797,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.832,
      "step": 22
    },
    {
      "epoch": 0.06010125755348685,
      "grad_norm": 29.439302444458008,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.9507,
      "step": 23
    },
    {
      "epoch": 0.06271435570798628,
      "grad_norm": 30.34869384765625,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.0065,
      "step": 24
    },
    {
      "epoch": 0.06532745386248572,
      "grad_norm": 68.95286560058594,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.1147,
      "step": 25
    },
    {
      "epoch": 0.06532745386248572,
      "eval_loss": 0.8179048299789429,
      "eval_runtime": 80.9656,
      "eval_samples_per_second": 31.841,
      "eval_steps_per_second": 3.989,
      "step": 25
    },
    {
      "epoch": 0.06794055201698514,
      "grad_norm": 19.688880920410156,
      "learning_rate": 5e-05,
      "loss": 0.6132,
      "step": 26
    },
    {
      "epoch": 0.07055365017148457,
      "grad_norm": 17.49786376953125,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.727,
      "step": 27
    },
    {
      "epoch": 0.073166748325984,
      "grad_norm": 11.093067169189453,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.7427,
      "step": 28
    },
    {
      "epoch": 0.07577984648048343,
      "grad_norm": 9.140443801879883,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.7637,
      "step": 29
    },
    {
      "epoch": 0.07839294463498285,
      "grad_norm": 8.738513946533203,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.7804,
      "step": 30
    },
    {
      "epoch": 0.08100604278948229,
      "grad_norm": 9.069628715515137,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.7579,
      "step": 31
    },
    {
      "epoch": 0.0836191409439817,
      "grad_norm": 10.622302055358887,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7312,
      "step": 32
    },
    {
      "epoch": 0.08623223909848114,
      "grad_norm": 14.509358406066895,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.7611,
      "step": 33
    },
    {
      "epoch": 0.08884533725298056,
      "grad_norm": 21.554981231689453,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8172,
      "step": 34
    },
    {
      "epoch": 0.09145843540748,
      "grad_norm": 30.103410720825195,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.8458,
      "step": 35
    },
    {
      "epoch": 0.09407153356197942,
      "grad_norm": 27.34261131286621,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.9454,
      "step": 36
    },
    {
      "epoch": 0.09668463171647886,
      "grad_norm": 33.892723083496094,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.9864,
      "step": 37
    },
    {
      "epoch": 0.09929772987097828,
      "grad_norm": 35.015785217285156,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7745,
      "step": 38
    },
    {
      "epoch": 0.10191082802547771,
      "grad_norm": 6.347834587097168,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.6495,
      "step": 39
    },
    {
      "epoch": 0.10452392617997713,
      "grad_norm": 6.344296455383301,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.6931,
      "step": 40
    },
    {
      "epoch": 0.10713702433447657,
      "grad_norm": 6.151936054229736,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.7352,
      "step": 41
    },
    {
      "epoch": 0.10975012248897599,
      "grad_norm": 6.7457661628723145,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.7606,
      "step": 42
    },
    {
      "epoch": 0.11236322064347543,
      "grad_norm": 7.498371124267578,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.7645,
      "step": 43
    },
    {
      "epoch": 0.11497631879797485,
      "grad_norm": 8.821335792541504,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7449,
      "step": 44
    },
    {
      "epoch": 0.11758941695247428,
      "grad_norm": 11.02287483215332,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.722,
      "step": 45
    },
    {
      "epoch": 0.1202025151069737,
      "grad_norm": 15.275715827941895,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.693,
      "step": 46
    },
    {
      "epoch": 0.12281561326147314,
      "grad_norm": 22.680950164794922,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.7993,
      "step": 47
    },
    {
      "epoch": 0.12542871141597256,
      "grad_norm": 31.55802345275879,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.8813,
      "step": 48
    },
    {
      "epoch": 0.12804180957047198,
      "grad_norm": 43.83702850341797,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.8113,
      "step": 49
    },
    {
      "epoch": 0.13065490772497143,
      "grad_norm": 50.75833511352539,
      "learning_rate": 0.0,
      "loss": 1.0654,
      "step": 50
    },
    {
      "epoch": 0.13065490772497143,
      "eval_loss": 0.7647556662559509,
      "eval_runtime": 81.2616,
      "eval_samples_per_second": 31.725,
      "eval_steps_per_second": 3.975,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.727082812528394e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}