{
  "best_metric": 0.737312912940979,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0032907185283906743,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.581437056781349e-05,
      "grad_norm": 1.0699650049209595,
      "learning_rate": 1e-05,
      "loss": 0.637,
      "step": 1
    },
    {
      "epoch": 6.581437056781349e-05,
      "eval_loss": 1.0002368688583374,
      "eval_runtime": 551.1643,
      "eval_samples_per_second": 46.429,
      "eval_steps_per_second": 11.608,
      "step": 1
    },
    {
      "epoch": 0.00013162874113562697,
      "grad_norm": 2.1881673336029053,
      "learning_rate": 2e-05,
      "loss": 0.9542,
      "step": 2
    },
    {
      "epoch": 0.00019744311170344044,
      "grad_norm": 2.023360013961792,
      "learning_rate": 3e-05,
      "loss": 0.9932,
      "step": 3
    },
    {
      "epoch": 0.00026325748227125394,
      "grad_norm": 0.9622493982315063,
      "learning_rate": 4e-05,
      "loss": 0.7212,
      "step": 4
    },
    {
      "epoch": 0.0003290718528390674,
      "grad_norm": 0.841331422328949,
      "learning_rate": 5e-05,
      "loss": 0.6929,
      "step": 5
    },
    {
      "epoch": 0.0003948862234068809,
      "grad_norm": 0.6500568985939026,
      "learning_rate": 6e-05,
      "loss": 0.8744,
      "step": 6
    },
    {
      "epoch": 0.0004607005939746944,
      "grad_norm": 0.5632097721099854,
      "learning_rate": 7e-05,
      "loss": 0.8446,
      "step": 7
    },
    {
      "epoch": 0.0005265149645425079,
      "grad_norm": 0.6277199387550354,
      "learning_rate": 8e-05,
      "loss": 0.8581,
      "step": 8
    },
    {
      "epoch": 0.0005923293351103214,
      "grad_norm": 0.6068065762519836,
      "learning_rate": 9e-05,
      "loss": 0.7305,
      "step": 9
    },
    {
      "epoch": 0.0006581437056781348,
      "grad_norm": 0.5233731865882874,
      "learning_rate": 0.0001,
      "loss": 0.7564,
      "step": 10
    },
    {
      "epoch": 0.0007239580762459483,
      "grad_norm": 0.6165419220924377,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7751,
      "step": 11
    },
    {
      "epoch": 0.0007897724468137618,
      "grad_norm": 0.6531275510787964,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8675,
      "step": 12
    },
    {
      "epoch": 0.0008555868173815753,
      "grad_norm": 0.9979423880577087,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.901,
      "step": 13
    },
    {
      "epoch": 0.0009214011879493888,
      "grad_norm": 0.6355984210968018,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7066,
      "step": 14
    },
    {
      "epoch": 0.0009872155585172022,
      "grad_norm": 0.6977342963218689,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7965,
      "step": 15
    },
    {
      "epoch": 0.0010530299290850158,
      "grad_norm": 0.7177662253379822,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.797,
      "step": 16
    },
    {
      "epoch": 0.0011188442996528292,
      "grad_norm": 0.7751869559288025,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8976,
      "step": 17
    },
    {
      "epoch": 0.0011846586702206428,
      "grad_norm": 0.5987713932991028,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7623,
      "step": 18
    },
    {
      "epoch": 0.0012504730407884562,
      "grad_norm": 0.6170699000358582,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6535,
      "step": 19
    },
    {
      "epoch": 0.0013162874113562695,
      "grad_norm": 0.6360906362533569,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.7772,
      "step": 20
    },
    {
      "epoch": 0.0013821017819240832,
      "grad_norm": 0.6145769357681274,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6495,
      "step": 21
    },
    {
      "epoch": 0.0014479161524918965,
      "grad_norm": 0.6427063941955566,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.704,
      "step": 22
    },
    {
      "epoch": 0.0015137305230597102,
      "grad_norm": 0.6871214509010315,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8987,
      "step": 23
    },
    {
      "epoch": 0.0015795448936275235,
      "grad_norm": 0.5951144695281982,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.6902,
      "step": 24
    },
    {
      "epoch": 0.0016453592641953371,
      "grad_norm": 0.6500367522239685,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7799,
      "step": 25
    },
    {
      "epoch": 0.0017111736347631505,
      "grad_norm": 0.6611123085021973,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.797,
      "step": 26
    },
    {
      "epoch": 0.001776988005330964,
      "grad_norm": 0.7094174027442932,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7681,
      "step": 27
    },
    {
      "epoch": 0.0018428023758987775,
      "grad_norm": 0.6624967455863953,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7345,
      "step": 28
    },
    {
      "epoch": 0.001908616746466591,
      "grad_norm": 0.7387915253639221,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8583,
      "step": 29
    },
    {
      "epoch": 0.0019744311170344043,
      "grad_norm": 0.6667190194129944,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7071,
      "step": 30
    },
    {
      "epoch": 0.002040245487602218,
      "grad_norm": 0.9777696132659912,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8538,
      "step": 31
    },
    {
      "epoch": 0.0021060598581700315,
      "grad_norm": 0.8049740791320801,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8842,
      "step": 32
    },
    {
      "epoch": 0.002171874228737845,
      "grad_norm": 0.7881101369857788,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8156,
      "step": 33
    },
    {
      "epoch": 0.0022376885993056583,
      "grad_norm": 0.7451800107955933,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.915,
      "step": 34
    },
    {
      "epoch": 0.0023035029698734717,
      "grad_norm": 0.7947197556495667,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8311,
      "step": 35
    },
    {
      "epoch": 0.0023693173404412855,
      "grad_norm": 0.7360652089118958,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8241,
      "step": 36
    },
    {
      "epoch": 0.002435131711009099,
      "grad_norm": 0.9908323884010315,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9708,
      "step": 37
    },
    {
      "epoch": 0.0025009460815769123,
      "grad_norm": 0.7604827880859375,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7927,
      "step": 38
    },
    {
      "epoch": 0.0025667604521447257,
      "grad_norm": 0.9196210503578186,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9204,
      "step": 39
    },
    {
      "epoch": 0.002632574822712539,
      "grad_norm": 0.9090496301651001,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8129,
      "step": 40
    },
    {
      "epoch": 0.002698389193280353,
      "grad_norm": 0.9374238848686218,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8409,
      "step": 41
    },
    {
      "epoch": 0.0027642035638481663,
      "grad_norm": 1.0455806255340576,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9103,
      "step": 42
    },
    {
      "epoch": 0.0028300179344159797,
      "grad_norm": 0.8809170722961426,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7275,
      "step": 43
    },
    {
      "epoch": 0.002895832304983793,
      "grad_norm": 1.0520704984664917,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7394,
      "step": 44
    },
    {
      "epoch": 0.0029616466755516065,
      "grad_norm": 1.284458875656128,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7696,
      "step": 45
    },
    {
      "epoch": 0.0030274610461194203,
      "grad_norm": 1.0618311166763306,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7598,
      "step": 46
    },
    {
      "epoch": 0.0030932754166872337,
      "grad_norm": 1.1072180271148682,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6633,
      "step": 47
    },
    {
      "epoch": 0.003159089787255047,
      "grad_norm": 1.2657697200775146,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8497,
      "step": 48
    },
    {
      "epoch": 0.0032249041578228605,
      "grad_norm": 1.1808794736862183,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6705,
      "step": 49
    },
    {
      "epoch": 0.0032907185283906743,
      "grad_norm": 1.749930739402771,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7677,
      "step": 50
    },
    {
      "epoch": 0.0032907185283906743,
      "eval_loss": 0.737312912940979,
      "eval_runtime": 553.3987,
      "eval_samples_per_second": 46.242,
      "eval_steps_per_second": 11.561,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.020984928763904e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}