{
  "best_metric": 2.9774577617645264,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.055586436909394105,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011117287381878821,
      "grad_norm": 3.354430675506592,
      "learning_rate": 1e-05,
      "loss": 3.5974,
      "step": 1
    },
    {
      "epoch": 0.0011117287381878821,
      "eval_loss": 4.1877617835998535,
      "eval_runtime": 113.634,
      "eval_samples_per_second": 13.332,
      "eval_steps_per_second": 3.335,
      "step": 1
    },
    {
      "epoch": 0.0022234574763757642,
      "grad_norm": 3.5467770099639893,
      "learning_rate": 2e-05,
      "loss": 3.4143,
      "step": 2
    },
    {
      "epoch": 0.0033351862145636463,
      "grad_norm": 2.927022933959961,
      "learning_rate": 3e-05,
      "loss": 3.6115,
      "step": 3
    },
    {
      "epoch": 0.0044469149527515284,
      "grad_norm": 3.4988656044006348,
      "learning_rate": 4e-05,
      "loss": 3.4901,
      "step": 4
    },
    {
      "epoch": 0.005558643690939411,
      "grad_norm": 4.0395894050598145,
      "learning_rate": 5e-05,
      "loss": 3.334,
      "step": 5
    },
    {
      "epoch": 0.006670372429127293,
      "grad_norm": 2.429553270339966,
      "learning_rate": 6e-05,
      "loss": 3.0816,
      "step": 6
    },
    {
      "epoch": 0.007782101167315175,
      "grad_norm": 3.898467540740967,
      "learning_rate": 7e-05,
      "loss": 3.1533,
      "step": 7
    },
    {
      "epoch": 0.008893829905503057,
      "grad_norm": 2.248739004135132,
      "learning_rate": 8e-05,
      "loss": 2.9901,
      "step": 8
    },
    {
      "epoch": 0.010005558643690939,
      "grad_norm": 2.7235913276672363,
      "learning_rate": 9e-05,
      "loss": 2.9727,
      "step": 9
    },
    {
      "epoch": 0.011117287381878822,
      "grad_norm": 4.5654778480529785,
      "learning_rate": 0.0001,
      "loss": 2.7708,
      "step": 10
    },
    {
      "epoch": 0.012229016120066704,
      "grad_norm": 2.844174861907959,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.54,
      "step": 11
    },
    {
      "epoch": 0.013340744858254585,
      "grad_norm": 3.2391204833984375,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.7762,
      "step": 12
    },
    {
      "epoch": 0.014452473596442469,
      "grad_norm": 2.577486515045166,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.63,
      "step": 13
    },
    {
      "epoch": 0.01556420233463035,
      "grad_norm": 2.247913122177124,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.4659,
      "step": 14
    },
    {
      "epoch": 0.016675931072818232,
      "grad_norm": 1.6729823350906372,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.4073,
      "step": 15
    },
    {
      "epoch": 0.017787659811006114,
      "grad_norm": 1.9088224172592163,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.6624,
      "step": 16
    },
    {
      "epoch": 0.018899388549193995,
      "grad_norm": 1.9842281341552734,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.4407,
      "step": 17
    },
    {
      "epoch": 0.020011117287381877,
      "grad_norm": 1.5356720685958862,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.2653,
      "step": 18
    },
    {
      "epoch": 0.021122846025569762,
      "grad_norm": 1.985195517539978,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.4273,
      "step": 19
    },
    {
      "epoch": 0.022234574763757644,
      "grad_norm": 1.7091484069824219,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.5741,
      "step": 20
    },
    {
      "epoch": 0.023346303501945526,
      "grad_norm": 1.6460450887680054,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.3956,
      "step": 21
    },
    {
      "epoch": 0.024458032240133407,
      "grad_norm": 1.9019036293029785,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.3292,
      "step": 22
    },
    {
      "epoch": 0.02556976097832129,
      "grad_norm": 2.058133602142334,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.419,
      "step": 23
    },
    {
      "epoch": 0.02668148971650917,
      "grad_norm": 1.7340707778930664,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.3051,
      "step": 24
    },
    {
      "epoch": 0.027793218454697052,
      "grad_norm": 1.9228554964065552,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.5168,
      "step": 25
    },
    {
      "epoch": 0.028904947192884937,
      "grad_norm": 1.754341959953308,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.4432,
      "step": 26
    },
    {
      "epoch": 0.03001667593107282,
      "grad_norm": 1.7013394832611084,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.2457,
      "step": 27
    },
    {
      "epoch": 0.0311284046692607,
      "grad_norm": 2.271134614944458,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.4197,
      "step": 28
    },
    {
      "epoch": 0.032240133407448586,
      "grad_norm": 1.8764477968215942,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.4092,
      "step": 29
    },
    {
      "epoch": 0.033351862145636464,
      "grad_norm": 2.3360588550567627,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.479,
      "step": 30
    },
    {
      "epoch": 0.03446359088382435,
      "grad_norm": 2.3365495204925537,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.3376,
      "step": 31
    },
    {
      "epoch": 0.03557531962201223,
      "grad_norm": 1.7387199401855469,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.4238,
      "step": 32
    },
    {
      "epoch": 0.03668704836020011,
      "grad_norm": 2.232757091522217,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.2233,
      "step": 33
    },
    {
      "epoch": 0.03779877709838799,
      "grad_norm": 2.0974419116973877,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.4388,
      "step": 34
    },
    {
      "epoch": 0.038910505836575876,
      "grad_norm": 1.7404261827468872,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.4117,
      "step": 35
    },
    {
      "epoch": 0.040022234574763754,
      "grad_norm": 1.9721072912216187,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.5831,
      "step": 36
    },
    {
      "epoch": 0.04113396331295164,
      "grad_norm": 2.2583365440368652,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.1364,
      "step": 37
    },
    {
      "epoch": 0.042245692051139525,
      "grad_norm": 1.8890812397003174,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.258,
      "step": 38
    },
    {
      "epoch": 0.0433574207893274,
      "grad_norm": 1.7999937534332275,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.3508,
      "step": 39
    },
    {
      "epoch": 0.04446914952751529,
      "grad_norm": 1.9692342281341553,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.4641,
      "step": 40
    },
    {
      "epoch": 0.045580878265703166,
      "grad_norm": 2.15486216545105,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.4807,
      "step": 41
    },
    {
      "epoch": 0.04669260700389105,
      "grad_norm": 2.1056225299835205,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.221,
      "step": 42
    },
    {
      "epoch": 0.04780433574207893,
      "grad_norm": 2.421368360519409,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.2285,
      "step": 43
    },
    {
      "epoch": 0.048916064480266815,
      "grad_norm": 2.1402504444122314,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.3976,
      "step": 44
    },
    {
      "epoch": 0.0500277932184547,
      "grad_norm": 1.9907327890396118,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.2016,
      "step": 45
    },
    {
      "epoch": 0.05113952195664258,
      "grad_norm": 3.9180026054382324,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.3729,
      "step": 46
    },
    {
      "epoch": 0.05225125069483046,
      "grad_norm": 2.9096477031707764,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.3403,
      "step": 47
    },
    {
      "epoch": 0.05336297943301834,
      "grad_norm": 2.34836483001709,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.2775,
      "step": 48
    },
    {
      "epoch": 0.054474708171206226,
      "grad_norm": 2.149888038635254,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.1803,
      "step": 49
    },
    {
      "epoch": 0.055586436909394105,
      "grad_norm": 2.810553550720215,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.3257,
      "step": 50
    },
    {
      "epoch": 0.055586436909394105,
      "eval_loss": 2.9774577617645264,
      "eval_runtime": 114.6352,
      "eval_samples_per_second": 13.216,
      "eval_steps_per_second": 3.306,
      "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": 7.54256789372928e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}