{
  "best_metric": 1.5392982959747314,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0942951438000943,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001885902876001886,
      "grad_norm": 1.6719341278076172,
      "learning_rate": 1e-05,
      "loss": 1.4085,
      "step": 1
    },
    {
      "epoch": 0.001885902876001886,
      "eval_loss": 1.798437476158142,
      "eval_runtime": 15.88,
      "eval_samples_per_second": 56.234,
      "eval_steps_per_second": 14.106,
      "step": 1
    },
    {
      "epoch": 0.003771805752003772,
      "grad_norm": 1.6418969631195068,
      "learning_rate": 2e-05,
      "loss": 1.4482,
      "step": 2
    },
    {
      "epoch": 0.005657708628005658,
      "grad_norm": 1.6673892736434937,
      "learning_rate": 3e-05,
      "loss": 1.5452,
      "step": 3
    },
    {
      "epoch": 0.007543611504007544,
      "grad_norm": 1.5872431993484497,
      "learning_rate": 4e-05,
      "loss": 1.5037,
      "step": 4
    },
    {
      "epoch": 0.00942951438000943,
      "grad_norm": 1.4873931407928467,
      "learning_rate": 5e-05,
      "loss": 1.362,
      "step": 5
    },
    {
      "epoch": 0.011315417256011316,
      "grad_norm": 1.3264328241348267,
      "learning_rate": 6e-05,
      "loss": 1.385,
      "step": 6
    },
    {
      "epoch": 0.013201320132013201,
      "grad_norm": 1.127667784690857,
      "learning_rate": 7e-05,
      "loss": 1.3468,
      "step": 7
    },
    {
      "epoch": 0.015087223008015087,
      "grad_norm": 1.2904081344604492,
      "learning_rate": 8e-05,
      "loss": 1.3893,
      "step": 8
    },
    {
      "epoch": 0.016973125884016973,
      "grad_norm": 1.4509556293487549,
      "learning_rate": 9e-05,
      "loss": 1.5524,
      "step": 9
    },
    {
      "epoch": 0.01885902876001886,
      "grad_norm": 1.1893857717514038,
      "learning_rate": 0.0001,
      "loss": 1.5371,
      "step": 10
    },
    {
      "epoch": 0.020744931636020744,
      "grad_norm": 1.0708231925964355,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.2872,
      "step": 11
    },
    {
      "epoch": 0.02263083451202263,
      "grad_norm": 1.1538314819335938,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.291,
      "step": 12
    },
    {
      "epoch": 0.024516737388024516,
      "grad_norm": 1.117232084274292,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.4771,
      "step": 13
    },
    {
      "epoch": 0.026402640264026403,
      "grad_norm": 1.038404941558838,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.4339,
      "step": 14
    },
    {
      "epoch": 0.028288543140028287,
      "grad_norm": 1.0554722547531128,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.2713,
      "step": 15
    },
    {
      "epoch": 0.030174446016030174,
      "grad_norm": 0.9968124628067017,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.4743,
      "step": 16
    },
    {
      "epoch": 0.03206034889203206,
      "grad_norm": 1.0715779066085815,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.5222,
      "step": 17
    },
    {
      "epoch": 0.033946251768033946,
      "grad_norm": 1.1179016828536987,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.4405,
      "step": 18
    },
    {
      "epoch": 0.03583215464403583,
      "grad_norm": 0.9977557063102722,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.3601,
      "step": 19
    },
    {
      "epoch": 0.03771805752003772,
      "grad_norm": 1.0840213298797607,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.7028,
      "step": 20
    },
    {
      "epoch": 0.039603960396039604,
      "grad_norm": 1.0020934343338013,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.5547,
      "step": 21
    },
    {
      "epoch": 0.04148986327204149,
      "grad_norm": 1.0338664054870605,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.4547,
      "step": 22
    },
    {
      "epoch": 0.04337576614804337,
      "grad_norm": 1.02623450756073,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.5793,
      "step": 23
    },
    {
      "epoch": 0.04526166902404526,
      "grad_norm": 0.9653357863426208,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.4715,
      "step": 24
    },
    {
      "epoch": 0.04714757190004715,
      "grad_norm": 1.058281421661377,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.5606,
      "step": 25
    },
    {
      "epoch": 0.04903347477604903,
      "grad_norm": 1.0581485033035278,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.3818,
      "step": 26
    },
    {
      "epoch": 0.05091937765205092,
      "grad_norm": 1.0404139757156372,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4896,
      "step": 27
    },
    {
      "epoch": 0.052805280528052806,
      "grad_norm": 0.9869558215141296,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.6065,
      "step": 28
    },
    {
      "epoch": 0.05469118340405469,
      "grad_norm": 1.03351628780365,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4879,
      "step": 29
    },
    {
      "epoch": 0.056577086280056574,
      "grad_norm": 1.1283892393112183,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.6899,
      "step": 30
    },
    {
      "epoch": 0.058462989156058465,
      "grad_norm": 1.1303669214248657,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.7194,
      "step": 31
    },
    {
      "epoch": 0.06034889203206035,
      "grad_norm": 1.136953592300415,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.5471,
      "step": 32
    },
    {
      "epoch": 0.06223479490806223,
      "grad_norm": 1.0339196920394897,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.6283,
      "step": 33
    },
    {
      "epoch": 0.06412069778406412,
      "grad_norm": 1.0422121286392212,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.6243,
      "step": 34
    },
    {
      "epoch": 0.066006600660066,
      "grad_norm": 1.0634968280792236,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.6214,
      "step": 35
    },
    {
      "epoch": 0.06789250353606789,
      "grad_norm": 1.0582144260406494,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.4956,
      "step": 36
    },
    {
      "epoch": 0.06977840641206978,
      "grad_norm": 1.1187388896942139,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.5546,
      "step": 37
    },
    {
      "epoch": 0.07166430928807166,
      "grad_norm": 1.0846741199493408,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.6097,
      "step": 38
    },
    {
      "epoch": 0.07355021216407355,
      "grad_norm": 1.1303223371505737,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.6785,
      "step": 39
    },
    {
      "epoch": 0.07543611504007544,
      "grad_norm": 1.1018422842025757,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.4387,
      "step": 40
    },
    {
      "epoch": 0.07732201791607732,
      "grad_norm": 1.0702595710754395,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.5708,
      "step": 41
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 1.133355975151062,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.5197,
      "step": 42
    },
    {
      "epoch": 0.0810938236680811,
      "grad_norm": 1.1223176717758179,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.5539,
      "step": 43
    },
    {
      "epoch": 0.08297972654408298,
      "grad_norm": 1.097373127937317,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.4639,
      "step": 44
    },
    {
      "epoch": 0.08486562942008487,
      "grad_norm": 1.259489893913269,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.6197,
      "step": 45
    },
    {
      "epoch": 0.08675153229608674,
      "grad_norm": 1.1635847091674805,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.412,
      "step": 46
    },
    {
      "epoch": 0.08863743517208864,
      "grad_norm": 1.3465157747268677,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.6082,
      "step": 47
    },
    {
      "epoch": 0.09052333804809053,
      "grad_norm": 1.2739461660385132,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5323,
      "step": 48
    },
    {
      "epoch": 0.0924092409240924,
      "grad_norm": 1.239130973815918,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.4232,
      "step": 49
    },
    {
      "epoch": 0.0942951438000943,
      "grad_norm": 1.4111778736114502,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.4941,
      "step": 50
    },
    {
      "epoch": 0.0942951438000943,
      "eval_loss": 1.5392982959747314,
      "eval_runtime": 15.8606,
      "eval_samples_per_second": 56.303,
      "eval_steps_per_second": 14.123,
      "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": 3883562421977088.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}