{
  "best_metric": 1.583877444267273,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06870491240123669,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013740982480247338,
      "grad_norm": 0.10447467863559723,
      "learning_rate": 1e-05,
      "loss": 0.685,
      "step": 1
    },
    {
      "epoch": 0.0013740982480247338,
      "eval_loss": 3.1940252780914307,
      "eval_runtime": 34.4278,
      "eval_samples_per_second": 35.611,
      "eval_steps_per_second": 8.917,
      "step": 1
    },
    {
      "epoch": 0.0027481964960494676,
      "grad_norm": 0.12629619240760803,
      "learning_rate": 2e-05,
      "loss": 0.8576,
      "step": 2
    },
    {
      "epoch": 0.004122294744074201,
      "grad_norm": 0.12000161409378052,
      "learning_rate": 3e-05,
      "loss": 0.8004,
      "step": 3
    },
    {
      "epoch": 0.005496392992098935,
      "grad_norm": 0.15668775141239166,
      "learning_rate": 4e-05,
      "loss": 0.9421,
      "step": 4
    },
    {
      "epoch": 0.006870491240123669,
      "grad_norm": 0.1253223568201065,
      "learning_rate": 5e-05,
      "loss": 0.91,
      "step": 5
    },
    {
      "epoch": 0.008244589488148402,
      "grad_norm": 0.1712837964296341,
      "learning_rate": 6e-05,
      "loss": 0.853,
      "step": 6
    },
    {
      "epoch": 0.009618687736173137,
      "grad_norm": 0.14983898401260376,
      "learning_rate": 7e-05,
      "loss": 0.9085,
      "step": 7
    },
    {
      "epoch": 0.01099278598419787,
      "grad_norm": 0.1604943573474884,
      "learning_rate": 8e-05,
      "loss": 0.9668,
      "step": 8
    },
    {
      "epoch": 0.012366884232222604,
      "grad_norm": 0.1646648794412613,
      "learning_rate": 9e-05,
      "loss": 0.9474,
      "step": 9
    },
    {
      "epoch": 0.013740982480247337,
      "grad_norm": 0.14233022928237915,
      "learning_rate": 0.0001,
      "loss": 0.9307,
      "step": 10
    },
    {
      "epoch": 0.01511508072827207,
      "grad_norm": 0.14303773641586304,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.0272,
      "step": 11
    },
    {
      "epoch": 0.016489178976296804,
      "grad_norm": 0.13132160902023315,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9655,
      "step": 12
    },
    {
      "epoch": 0.017863277224321537,
      "grad_norm": 0.1405678391456604,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9454,
      "step": 13
    },
    {
      "epoch": 0.019237375472346274,
      "grad_norm": 0.1712307631969452,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.901,
      "step": 14
    },
    {
      "epoch": 0.020611473720371008,
      "grad_norm": 0.17713665962219238,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1299,
      "step": 15
    },
    {
      "epoch": 0.02198557196839574,
      "grad_norm": 0.1875886619091034,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.03,
      "step": 16
    },
    {
      "epoch": 0.023359670216420474,
      "grad_norm": 0.16109849512577057,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9476,
      "step": 17
    },
    {
      "epoch": 0.024733768464445208,
      "grad_norm": 0.1598743498325348,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9316,
      "step": 18
    },
    {
      "epoch": 0.02610786671246994,
      "grad_norm": 0.15691572427749634,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.9573,
      "step": 19
    },
    {
      "epoch": 0.027481964960494674,
      "grad_norm": 0.1694604903459549,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9552,
      "step": 20
    },
    {
      "epoch": 0.028856063208519408,
      "grad_norm": 0.16706468164920807,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0703,
      "step": 21
    },
    {
      "epoch": 0.03023016145654414,
      "grad_norm": 0.16619545221328735,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.1266,
      "step": 22
    },
    {
      "epoch": 0.03160425970456888,
      "grad_norm": 0.17776361107826233,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9576,
      "step": 23
    },
    {
      "epoch": 0.03297835795259361,
      "grad_norm": 0.1760794222354889,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.0205,
      "step": 24
    },
    {
      "epoch": 0.034352456200618345,
      "grad_norm": 0.1899178922176361,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0423,
      "step": 25
    },
    {
      "epoch": 0.035726554448643075,
      "grad_norm": 0.20989012718200684,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.0949,
      "step": 26
    },
    {
      "epoch": 0.03710065269666781,
      "grad_norm": 0.22795264422893524,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.0732,
      "step": 27
    },
    {
      "epoch": 0.03847475094469255,
      "grad_norm": 0.24893148243427277,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.1178,
      "step": 28
    },
    {
      "epoch": 0.03984884919271728,
      "grad_norm": 0.3269492983818054,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2364,
      "step": 29
    },
    {
      "epoch": 0.041222947440742015,
      "grad_norm": 0.2281530201435089,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1341,
      "step": 30
    },
    {
      "epoch": 0.042597045688766745,
      "grad_norm": 0.2597139775753021,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.1221,
      "step": 31
    },
    {
      "epoch": 0.04397114393679148,
      "grad_norm": 0.9067723751068115,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.9614,
      "step": 32
    },
    {
      "epoch": 0.04534524218481621,
      "grad_norm": 4.838332176208496,
      "learning_rate": 9.642770192448536e-05,
      "loss": 6.601,
      "step": 33
    },
    {
      "epoch": 0.04671934043284095,
      "grad_norm": 9.844199180603027,
      "learning_rate": 9.611448774886924e-05,
      "loss": 10.6881,
      "step": 34
    },
    {
      "epoch": 0.04809343868086568,
      "grad_norm": 10.059837341308594,
      "learning_rate": 9.578866633275288e-05,
      "loss": 9.3037,
      "step": 35
    },
    {
      "epoch": 0.049467536928890415,
      "grad_norm": 8.158489227294922,
      "learning_rate": 9.545032675245813e-05,
      "loss": 7.7695,
      "step": 36
    },
    {
      "epoch": 0.05084163517691515,
      "grad_norm": 8.049012184143066,
      "learning_rate": 9.509956150664796e-05,
      "loss": 7.3775,
      "step": 37
    },
    {
      "epoch": 0.05221573342493988,
      "grad_norm": 8.838970184326172,
      "learning_rate": 9.473646649103818e-05,
      "loss": 7.0543,
      "step": 38
    },
    {
      "epoch": 0.05358983167296462,
      "grad_norm": 11.280040740966797,
      "learning_rate": 9.43611409721806e-05,
      "loss": 6.6935,
      "step": 39
    },
    {
      "epoch": 0.05496392992098935,
      "grad_norm": 10.341362953186035,
      "learning_rate": 9.397368756032445e-05,
      "loss": 5.954,
      "step": 40
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 2.2097039222717285,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.2857,
      "step": 41
    },
    {
      "epoch": 0.057712126417038816,
      "grad_norm": 2.333188533782959,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.4563,
      "step": 42
    },
    {
      "epoch": 0.05908622466506355,
      "grad_norm": 2.797895669937134,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.5016,
      "step": 43
    },
    {
      "epoch": 0.06046032291308828,
      "grad_norm": 2.8829591274261475,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.3985,
      "step": 44
    },
    {
      "epoch": 0.06183442116111302,
      "grad_norm": 2.3330905437469482,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.4629,
      "step": 45
    },
    {
      "epoch": 0.06320851940913776,
      "grad_norm": 1.7073644399642944,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.4424,
      "step": 46
    },
    {
      "epoch": 0.06458261765716249,
      "grad_norm": 1.1441912651062012,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.305,
      "step": 47
    },
    {
      "epoch": 0.06595671590518722,
      "grad_norm": 1.0069657564163208,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.547,
      "step": 48
    },
    {
      "epoch": 0.06733081415321196,
      "grad_norm": 0.795106828212738,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.3543,
      "step": 49
    },
    {
      "epoch": 0.06870491240123669,
      "grad_norm": 0.7250723242759705,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.5456,
      "step": 50
    },
    {
      "epoch": 0.06870491240123669,
      "eval_loss": 1.583877444267273,
      "eval_runtime": 34.2929,
      "eval_samples_per_second": 35.751,
      "eval_steps_per_second": 8.952,
      "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": 6250680381603840.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}