{
  "best_metric": 1.3839502334594727,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.8475750577367207,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03695150115473441,
      "grad_norm": 1.0628507137298584,
      "learning_rate": 5e-05,
      "loss": 2.134,
      "step": 1
    },
    {
      "epoch": 0.03695150115473441,
      "eval_loss": 2.0157902240753174,
      "eval_runtime": 5.591,
      "eval_samples_per_second": 32.552,
      "eval_steps_per_second": 4.114,
      "step": 1
    },
    {
      "epoch": 0.07390300230946882,
      "grad_norm": 1.1720733642578125,
      "learning_rate": 0.0001,
      "loss": 2.0829,
      "step": 2
    },
    {
      "epoch": 0.11085450346420324,
      "grad_norm": 1.1043386459350586,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.015,
      "step": 3
    },
    {
      "epoch": 0.14780600461893764,
      "grad_norm": 1.0133167505264282,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.8927,
      "step": 4
    },
    {
      "epoch": 0.18475750577367206,
      "grad_norm": 1.1658165454864502,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.7146,
      "step": 5
    },
    {
      "epoch": 0.22170900692840648,
      "grad_norm": 0.944509744644165,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.5414,
      "step": 6
    },
    {
      "epoch": 0.2586605080831409,
      "grad_norm": 0.613703727722168,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.4056,
      "step": 7
    },
    {
      "epoch": 0.2956120092378753,
      "grad_norm": 0.8270657658576965,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6956,
      "step": 8
    },
    {
      "epoch": 0.3325635103926097,
      "grad_norm": 0.49155479669570923,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.6785,
      "step": 9
    },
    {
      "epoch": 0.3695150115473441,
      "grad_norm": 0.48842838406562805,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5975,
      "step": 10
    },
    {
      "epoch": 0.4064665127020785,
      "grad_norm": 0.5849675536155701,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.5599,
      "step": 11
    },
    {
      "epoch": 0.44341801385681295,
      "grad_norm": 0.622815728187561,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.5254,
      "step": 12
    },
    {
      "epoch": 0.48036951501154734,
      "grad_norm": 0.526707112789154,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.3566,
      "step": 13
    },
    {
      "epoch": 0.5173210161662818,
      "grad_norm": 0.3933887481689453,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.4329,
      "step": 14
    },
    {
      "epoch": 0.5542725173210161,
      "grad_norm": 0.5503090620040894,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.5994,
      "step": 15
    },
    {
      "epoch": 0.5912240184757506,
      "grad_norm": 0.5241612195968628,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.5383,
      "step": 16
    },
    {
      "epoch": 0.628175519630485,
      "grad_norm": 0.44455692172050476,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.5573,
      "step": 17
    },
    {
      "epoch": 0.6651270207852193,
      "grad_norm": 0.36662575602531433,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5157,
      "step": 18
    },
    {
      "epoch": 0.7020785219399538,
      "grad_norm": 0.3800973892211914,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.4676,
      "step": 19
    },
    {
      "epoch": 0.7390300230946882,
      "grad_norm": 0.5022615194320679,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3377,
      "step": 20
    },
    {
      "epoch": 0.7759815242494227,
      "grad_norm": 0.33681997656822205,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.3919,
      "step": 21
    },
    {
      "epoch": 0.812933025404157,
      "grad_norm": 0.3332096040248871,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.5652,
      "step": 22
    },
    {
      "epoch": 0.8498845265588915,
      "grad_norm": 0.3324725329875946,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.4968,
      "step": 23
    },
    {
      "epoch": 0.8868360277136259,
      "grad_norm": 0.3355538249015808,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.4671,
      "step": 24
    },
    {
      "epoch": 0.9237875288683602,
      "grad_norm": 0.33890247344970703,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.4538,
      "step": 25
    },
    {
      "epoch": 0.9237875288683602,
      "eval_loss": 1.39730966091156,
      "eval_runtime": 5.5764,
      "eval_samples_per_second": 32.638,
      "eval_steps_per_second": 4.125,
      "step": 25
    },
    {
      "epoch": 0.9607390300230947,
      "grad_norm": 0.3993252217769623,
      "learning_rate": 5e-05,
      "loss": 1.3449,
      "step": 26
    },
    {
      "epoch": 0.9976905311778291,
      "grad_norm": 0.4546384811401367,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.1338,
      "step": 27
    },
    {
      "epoch": 1.0346420323325636,
      "grad_norm": 1.0680946111679077,
      "learning_rate": 4.347369038899744e-05,
      "loss": 3.1549,
      "step": 28
    },
    {
      "epoch": 1.071593533487298,
      "grad_norm": 0.5346181392669678,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.531,
      "step": 29
    },
    {
      "epoch": 1.1085450346420322,
      "grad_norm": 0.5427453517913818,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.4747,
      "step": 30
    },
    {
      "epoch": 1.1454965357967668,
      "grad_norm": 0.558639407157898,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.393,
      "step": 31
    },
    {
      "epoch": 1.1824480369515011,
      "grad_norm": 0.585619330406189,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.3481,
      "step": 32
    },
    {
      "epoch": 1.2193995381062355,
      "grad_norm": 0.6847278475761414,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.3739,
      "step": 33
    },
    {
      "epoch": 1.25635103926097,
      "grad_norm": 0.5396642088890076,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0703,
      "step": 34
    },
    {
      "epoch": 1.2933025404157044,
      "grad_norm": 0.5222858190536499,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.6278,
      "step": 35
    },
    {
      "epoch": 1.3302540415704387,
      "grad_norm": 0.540937066078186,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.4927,
      "step": 36
    },
    {
      "epoch": 1.3672055427251733,
      "grad_norm": 0.55878084897995,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.4581,
      "step": 37
    },
    {
      "epoch": 1.4041570438799076,
      "grad_norm": 0.5840333104133606,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4209,
      "step": 38
    },
    {
      "epoch": 1.4411085450346421,
      "grad_norm": 0.7051689624786377,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.4098,
      "step": 39
    },
    {
      "epoch": 1.4780600461893765,
      "grad_norm": 0.703649640083313,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.2392,
      "step": 40
    },
    {
      "epoch": 1.5150115473441108,
      "grad_norm": 0.5681647658348083,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.2953,
      "step": 41
    },
    {
      "epoch": 1.5519630484988451,
      "grad_norm": 0.5803612470626831,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.5462,
      "step": 42
    },
    {
      "epoch": 1.5889145496535797,
      "grad_norm": 0.5447371602058411,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.5298,
      "step": 43
    },
    {
      "epoch": 1.625866050808314,
      "grad_norm": 0.5576654076576233,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.3899,
      "step": 44
    },
    {
      "epoch": 1.6628175519630486,
      "grad_norm": 0.5950343608856201,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.4301,
      "step": 45
    },
    {
      "epoch": 1.699769053117783,
      "grad_norm": 0.7155903577804565,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.2867,
      "step": 46
    },
    {
      "epoch": 1.7367205542725173,
      "grad_norm": 0.738254964351654,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.2506,
      "step": 47
    },
    {
      "epoch": 1.7736720554272516,
      "grad_norm": 0.5283464789390564,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.3485,
      "step": 48
    },
    {
      "epoch": 1.8106235565819861,
      "grad_norm": 0.5948820114135742,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.4925,
      "step": 49
    },
    {
      "epoch": 1.8475750577367207,
      "grad_norm": 0.5409876704216003,
      "learning_rate": 0.0,
      "loss": 1.3948,
      "step": 50
    },
    {
      "epoch": 1.8475750577367207,
      "eval_loss": 1.3839502334594727,
      "eval_runtime": 5.5701,
      "eval_samples_per_second": 32.674,
      "eval_steps_per_second": 4.129,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.645754911686656e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}