{
  "best_metric": 1.9373520612716675,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.010051766597979595,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002010353319595919,
      "grad_norm": 0.7243201732635498,
      "learning_rate": 1e-05,
      "loss": 1.9001,
      "step": 1
    },
    {
      "epoch": 0.0002010353319595919,
      "eval_loss": 2.11344051361084,
      "eval_runtime": 171.9074,
      "eval_samples_per_second": 48.736,
      "eval_steps_per_second": 12.187,
      "step": 1
    },
    {
      "epoch": 0.0004020706639191838,
      "grad_norm": 0.9003947377204895,
      "learning_rate": 2e-05,
      "loss": 1.8396,
      "step": 2
    },
    {
      "epoch": 0.0006031059958787757,
      "grad_norm": 0.9272552728652954,
      "learning_rate": 3e-05,
      "loss": 1.8755,
      "step": 3
    },
    {
      "epoch": 0.0008041413278383676,
      "grad_norm": 1.0478748083114624,
      "learning_rate": 4e-05,
      "loss": 1.7778,
      "step": 4
    },
    {
      "epoch": 0.0010051766597979595,
      "grad_norm": 0.9338437914848328,
      "learning_rate": 5e-05,
      "loss": 1.8533,
      "step": 5
    },
    {
      "epoch": 0.0012062119917575513,
      "grad_norm": 0.9951044321060181,
      "learning_rate": 6e-05,
      "loss": 1.8048,
      "step": 6
    },
    {
      "epoch": 0.0014072473237171433,
      "grad_norm": 0.8657851219177246,
      "learning_rate": 7e-05,
      "loss": 1.8549,
      "step": 7
    },
    {
      "epoch": 0.0016082826556767353,
      "grad_norm": 0.7345765233039856,
      "learning_rate": 8e-05,
      "loss": 1.8697,
      "step": 8
    },
    {
      "epoch": 0.001809317987636327,
      "grad_norm": 0.9524029493331909,
      "learning_rate": 9e-05,
      "loss": 1.8195,
      "step": 9
    },
    {
      "epoch": 0.002010353319595919,
      "grad_norm": 0.9118521809577942,
      "learning_rate": 0.0001,
      "loss": 1.8523,
      "step": 10
    },
    {
      "epoch": 0.002211388651555511,
      "grad_norm": 0.8495756387710571,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.816,
      "step": 11
    },
    {
      "epoch": 0.0024124239835151026,
      "grad_norm": 0.7486765384674072,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.7435,
      "step": 12
    },
    {
      "epoch": 0.002613459315474695,
      "grad_norm": 0.871289849281311,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.8233,
      "step": 13
    },
    {
      "epoch": 0.0028144946474342866,
      "grad_norm": 0.7088490724563599,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7216,
      "step": 14
    },
    {
      "epoch": 0.0030155299793938784,
      "grad_norm": 0.8408116698265076,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.8027,
      "step": 15
    },
    {
      "epoch": 0.0032165653113534706,
      "grad_norm": 0.7949049472808838,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.835,
      "step": 16
    },
    {
      "epoch": 0.0034176006433130623,
      "grad_norm": 0.9442782402038574,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.9566,
      "step": 17
    },
    {
      "epoch": 0.003618635975272654,
      "grad_norm": 0.7910245656967163,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.7318,
      "step": 18
    },
    {
      "epoch": 0.003819671307232246,
      "grad_norm": 0.8084377646446228,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.7165,
      "step": 19
    },
    {
      "epoch": 0.004020706639191838,
      "grad_norm": 0.8121070861816406,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.9654,
      "step": 20
    },
    {
      "epoch": 0.0042217419711514294,
      "grad_norm": 0.9022719264030457,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.8507,
      "step": 21
    },
    {
      "epoch": 0.004422777303111022,
      "grad_norm": 0.7618189454078674,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.7183,
      "step": 22
    },
    {
      "epoch": 0.004623812635070614,
      "grad_norm": 0.6915072202682495,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.8579,
      "step": 23
    },
    {
      "epoch": 0.004824847967030205,
      "grad_norm": 0.7315471768379211,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.8386,
      "step": 24
    },
    {
      "epoch": 0.005025883298989797,
      "grad_norm": 0.7275452017784119,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.772,
      "step": 25
    },
    {
      "epoch": 0.00522691863094939,
      "grad_norm": 0.7768784761428833,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.7954,
      "step": 26
    },
    {
      "epoch": 0.005427953962908981,
      "grad_norm": 0.8576830625534058,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.8411,
      "step": 27
    },
    {
      "epoch": 0.005628989294868573,
      "grad_norm": 0.7678402066230774,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.769,
      "step": 28
    },
    {
      "epoch": 0.005830024626828165,
      "grad_norm": 1.0145021677017212,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0439,
      "step": 29
    },
    {
      "epoch": 0.006031059958787757,
      "grad_norm": 0.9616433382034302,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.8919,
      "step": 30
    },
    {
      "epoch": 0.006232095290747349,
      "grad_norm": 0.7848714590072632,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.8079,
      "step": 31
    },
    {
      "epoch": 0.006433130622706941,
      "grad_norm": 0.8140174150466919,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.7669,
      "step": 32
    },
    {
      "epoch": 0.0066341659546665325,
      "grad_norm": 0.890622615814209,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.6712,
      "step": 33
    },
    {
      "epoch": 0.006835201286626125,
      "grad_norm": 0.872776210308075,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.8183,
      "step": 34
    },
    {
      "epoch": 0.007036236618585716,
      "grad_norm": 0.9921485781669617,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.8694,
      "step": 35
    },
    {
      "epoch": 0.007237271950545308,
      "grad_norm": 1.0803183317184448,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.9187,
      "step": 36
    },
    {
      "epoch": 0.0074383072825049005,
      "grad_norm": 0.9387599229812622,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.9963,
      "step": 37
    },
    {
      "epoch": 0.007639342614464492,
      "grad_norm": 1.0187156200408936,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.7119,
      "step": 38
    },
    {
      "epoch": 0.007840377946424084,
      "grad_norm": 1.048580527305603,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.7683,
      "step": 39
    },
    {
      "epoch": 0.008041413278383676,
      "grad_norm": 0.9831770658493042,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.7932,
      "step": 40
    },
    {
      "epoch": 0.008242448610343268,
      "grad_norm": 1.0285784006118774,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.8248,
      "step": 41
    },
    {
      "epoch": 0.008443483942302859,
      "grad_norm": 1.1290544271469116,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.9735,
      "step": 42
    },
    {
      "epoch": 0.008644519274262451,
      "grad_norm": 1.0321779251098633,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.783,
      "step": 43
    },
    {
      "epoch": 0.008845554606222043,
      "grad_norm": 1.100907802581787,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.7801,
      "step": 44
    },
    {
      "epoch": 0.009046589938181636,
      "grad_norm": 1.203137993812561,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.9669,
      "step": 45
    },
    {
      "epoch": 0.009247625270141228,
      "grad_norm": 1.23589289188385,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.6836,
      "step": 46
    },
    {
      "epoch": 0.00944866060210082,
      "grad_norm": 1.3507293462753296,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.6699,
      "step": 47
    },
    {
      "epoch": 0.00964969593406041,
      "grad_norm": 1.4106907844543457,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7651,
      "step": 48
    },
    {
      "epoch": 0.009850731266020003,
      "grad_norm": 1.957142949104309,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.8771,
      "step": 49
    },
    {
      "epoch": 0.010051766597979595,
      "grad_norm": 2.773338556289673,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.0025,
      "step": 50
    },
    {
      "epoch": 0.010051766597979595,
      "eval_loss": 1.9373520612716675,
      "eval_runtime": 172.4358,
      "eval_samples_per_second": 48.586,
      "eval_steps_per_second": 12.149,
      "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": 1.0825725351297024e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}