{
  "best_metric": 2.3451285362243652,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.004653435398683078,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.306870797366156e-05,
      "grad_norm": 1.7735472917556763,
      "learning_rate": 1e-05,
      "loss": 5.8895,
      "step": 1
    },
    {
      "epoch": 9.306870797366156e-05,
      "eval_loss": 6.482426166534424,
      "eval_runtime": 304.4438,
      "eval_samples_per_second": 59.443,
      "eval_steps_per_second": 14.863,
      "step": 1
    },
    {
      "epoch": 0.00018613741594732312,
      "grad_norm": 2.0700442790985107,
      "learning_rate": 2e-05,
      "loss": 6.2705,
      "step": 2
    },
    {
      "epoch": 0.0002792061239209847,
      "grad_norm": 1.9711593389511108,
      "learning_rate": 3e-05,
      "loss": 6.4148,
      "step": 3
    },
    {
      "epoch": 0.00037227483189464623,
      "grad_norm": 1.9225269556045532,
      "learning_rate": 4e-05,
      "loss": 5.9848,
      "step": 4
    },
    {
      "epoch": 0.0004653435398683078,
      "grad_norm": 2.029270887374878,
      "learning_rate": 5e-05,
      "loss": 6.3198,
      "step": 5
    },
    {
      "epoch": 0.0005584122478419694,
      "grad_norm": 1.8473637104034424,
      "learning_rate": 6e-05,
      "loss": 5.9308,
      "step": 6
    },
    {
      "epoch": 0.0006514809558156309,
      "grad_norm": 1.6538199186325073,
      "learning_rate": 7e-05,
      "loss": 5.1228,
      "step": 7
    },
    {
      "epoch": 0.0007445496637892925,
      "grad_norm": 1.8904407024383545,
      "learning_rate": 8e-05,
      "loss": 5.8023,
      "step": 8
    },
    {
      "epoch": 0.000837618371762954,
      "grad_norm": 1.84903085231781,
      "learning_rate": 9e-05,
      "loss": 5.5689,
      "step": 9
    },
    {
      "epoch": 0.0009306870797366156,
      "grad_norm": 2.1736207008361816,
      "learning_rate": 0.0001,
      "loss": 6.1122,
      "step": 10
    },
    {
      "epoch": 0.001023755787710277,
      "grad_norm": 2.170330047607422,
      "learning_rate": 9.999316524962345e-05,
      "loss": 5.9805,
      "step": 11
    },
    {
      "epoch": 0.0011168244956839388,
      "grad_norm": 1.9020719528198242,
      "learning_rate": 9.997266286704631e-05,
      "loss": 5.0548,
      "step": 12
    },
    {
      "epoch": 0.0012098932036576002,
      "grad_norm": 1.9841967821121216,
      "learning_rate": 9.993849845741524e-05,
      "loss": 4.6487,
      "step": 13
    },
    {
      "epoch": 0.0013029619116312618,
      "grad_norm": 1.889742374420166,
      "learning_rate": 9.989068136093873e-05,
      "loss": 4.2314,
      "step": 14
    },
    {
      "epoch": 0.0013960306196049233,
      "grad_norm": 1.9333326816558838,
      "learning_rate": 9.98292246503335e-05,
      "loss": 4.4483,
      "step": 15
    },
    {
      "epoch": 0.001489099327578585,
      "grad_norm": 2.225519895553589,
      "learning_rate": 9.975414512725057e-05,
      "loss": 4.0066,
      "step": 16
    },
    {
      "epoch": 0.0015821680355522464,
      "grad_norm": 2.0410828590393066,
      "learning_rate": 9.966546331768191e-05,
      "loss": 4.3892,
      "step": 17
    },
    {
      "epoch": 0.001675236743525908,
      "grad_norm": 1.9123791456222534,
      "learning_rate": 9.956320346634876e-05,
      "loss": 3.5946,
      "step": 18
    },
    {
      "epoch": 0.0017683054514995695,
      "grad_norm": 1.8343403339385986,
      "learning_rate": 9.944739353007344e-05,
      "loss": 3.5219,
      "step": 19
    },
    {
      "epoch": 0.0018613741594732311,
      "grad_norm": 1.7313987016677856,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.4092,
      "step": 20
    },
    {
      "epoch": 0.0019544428674468928,
      "grad_norm": 1.329962968826294,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.9846,
      "step": 21
    },
    {
      "epoch": 0.002047511575420554,
      "grad_norm": 1.1749334335327148,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.6915,
      "step": 22
    },
    {
      "epoch": 0.0021405802833942156,
      "grad_norm": 1.278825044631958,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.9619,
      "step": 23
    },
    {
      "epoch": 0.0022336489913678775,
      "grad_norm": 1.4575446844100952,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.8164,
      "step": 24
    },
    {
      "epoch": 0.002326717699341539,
      "grad_norm": 1.2176644802093506,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.8337,
      "step": 25
    },
    {
      "epoch": 0.0024197864073152004,
      "grad_norm": 1.6159353256225586,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.9351,
      "step": 26
    },
    {
      "epoch": 0.002512855115288862,
      "grad_norm": 1.5434867143630981,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.4156,
      "step": 27
    },
    {
      "epoch": 0.0026059238232625237,
      "grad_norm": 1.2292698621749878,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.6924,
      "step": 28
    },
    {
      "epoch": 0.002698992531236185,
      "grad_norm": 1.162212610244751,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.8786,
      "step": 29
    },
    {
      "epoch": 0.0027920612392098466,
      "grad_norm": 0.9365395903587341,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.6025,
      "step": 30
    },
    {
      "epoch": 0.0028851299471835084,
      "grad_norm": 0.9078200459480286,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.3615,
      "step": 31
    },
    {
      "epoch": 0.00297819865515717,
      "grad_norm": 0.8768578171730042,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.0822,
      "step": 32
    },
    {
      "epoch": 0.0030712673631308313,
      "grad_norm": 0.9906667470932007,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.4023,
      "step": 33
    },
    {
      "epoch": 0.0031643360711044928,
      "grad_norm": 1.0336462259292603,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.6938,
      "step": 34
    },
    {
      "epoch": 0.0032574047790781546,
      "grad_norm": 0.9745144248008728,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.4473,
      "step": 35
    },
    {
      "epoch": 0.003350473487051816,
      "grad_norm": 1.0437625646591187,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.3341,
      "step": 36
    },
    {
      "epoch": 0.0034435421950254775,
      "grad_norm": 0.9613348245620728,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.3495,
      "step": 37
    },
    {
      "epoch": 0.003536610902999139,
      "grad_norm": 0.9992738366127014,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.7455,
      "step": 38
    },
    {
      "epoch": 0.003629679610972801,
      "grad_norm": 0.8920794129371643,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.3886,
      "step": 39
    },
    {
      "epoch": 0.0037227483189464622,
      "grad_norm": 1.093630075454712,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.3774,
      "step": 40
    },
    {
      "epoch": 0.0038158170269201237,
      "grad_norm": 0.8996030688285828,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.579,
      "step": 41
    },
    {
      "epoch": 0.0039088857348937855,
      "grad_norm": 1.0228679180145264,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.4309,
      "step": 42
    },
    {
      "epoch": 0.004001954442867447,
      "grad_norm": 0.8993352055549622,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.6144,
      "step": 43
    },
    {
      "epoch": 0.004095023150841108,
      "grad_norm": 1.0983102321624756,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.6516,
      "step": 44
    },
    {
      "epoch": 0.00418809185881477,
      "grad_norm": 0.8919628262519836,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.3736,
      "step": 45
    },
    {
      "epoch": 0.004281160566788431,
      "grad_norm": 1.0163989067077637,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.5175,
      "step": 46
    },
    {
      "epoch": 0.004374229274762093,
      "grad_norm": 1.05795419216156,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.6785,
      "step": 47
    },
    {
      "epoch": 0.004467297982735755,
      "grad_norm": 0.9983816146850586,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4914,
      "step": 48
    },
    {
      "epoch": 0.0045603666907094165,
      "grad_norm": 0.9197684526443481,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.0751,
      "step": 49
    },
    {
      "epoch": 0.004653435398683078,
      "grad_norm": 1.136470079421997,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.6757,
      "step": 50
    },
    {
      "epoch": 0.004653435398683078,
      "eval_loss": 2.3451285362243652,
      "eval_runtime": 304.2165,
      "eval_samples_per_second": 59.487,
      "eval_steps_per_second": 14.874,
      "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": 3451611968962560.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}