{
  "best_metric": 2.38608717918396,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.14106859460412627,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00035267148651031563,
      "eval_loss": 3.0103461742401123,
      "eval_runtime": 25.7577,
      "eval_samples_per_second": 46.355,
      "eval_steps_per_second": 11.608,
      "step": 1
    },
    {
      "epoch": 0.0035267148651031564,
      "grad_norm": 1.8814945220947266,
      "learning_rate": 4.02e-05,
      "loss": 1.7486,
      "step": 10
    },
    {
      "epoch": 0.007053429730206313,
      "grad_norm": 3.284661054611206,
      "learning_rate": 8.04e-05,
      "loss": 2.104,
      "step": 20
    },
    {
      "epoch": 0.01058014459530947,
      "grad_norm": 4.527420520782471,
      "learning_rate": 0.0001206,
      "loss": 2.6147,
      "step": 30
    },
    {
      "epoch": 0.014106859460412626,
      "grad_norm": 8.724098205566406,
      "learning_rate": 0.0001608,
      "loss": 2.973,
      "step": 40
    },
    {
      "epoch": 0.017633574325515784,
      "grad_norm": 15.409860610961914,
      "learning_rate": 0.000201,
      "loss": 3.0979,
      "step": 50
    },
    {
      "epoch": 0.017633574325515784,
      "eval_loss": 2.7572579383850098,
      "eval_runtime": 25.7728,
      "eval_samples_per_second": 46.328,
      "eval_steps_per_second": 11.601,
      "step": 50
    },
    {
      "epoch": 0.02116028919061894,
      "grad_norm": 2.0140380859375,
      "learning_rate": 0.00020075518705111234,
      "loss": 1.6315,
      "step": 60
    },
    {
      "epoch": 0.024687004055722096,
      "grad_norm": 2.247471332550049,
      "learning_rate": 0.00020002194090852784,
      "loss": 2.1592,
      "step": 70
    },
    {
      "epoch": 0.02821371892082525,
      "grad_norm": 5.211777210235596,
      "learning_rate": 0.00019880383387374748,
      "loss": 2.7279,
      "step": 80
    },
    {
      "epoch": 0.03174043378592841,
      "grad_norm": 6.06164026260376,
      "learning_rate": 0.00019710680044180106,
      "loss": 2.995,
      "step": 90
    },
    {
      "epoch": 0.03526714865103157,
      "grad_norm": 12.699899673461914,
      "learning_rate": 0.0001949391083889838,
      "loss": 3.0191,
      "step": 100
    },
    {
      "epoch": 0.03526714865103157,
      "eval_loss": 3.1388041973114014,
      "eval_runtime": 25.4478,
      "eval_samples_per_second": 46.92,
      "eval_steps_per_second": 11.75,
      "step": 100
    },
    {
      "epoch": 0.03879386351613472,
      "grad_norm": 1.716439127922058,
      "learning_rate": 0.00019231131849308138,
      "loss": 1.8341,
      "step": 110
    },
    {
      "epoch": 0.04232057838123788,
      "grad_norm": 2.2980763912200928,
      "learning_rate": 0.00018923623308232218,
      "loss": 2.0825,
      "step": 120
    },
    {
      "epoch": 0.045847293246341035,
      "grad_norm": 3.878023862838745,
      "learning_rate": 0.00018572883366372081,
      "loss": 2.7559,
      "step": 130
    },
    {
      "epoch": 0.04937400811144419,
      "grad_norm": 5.2749786376953125,
      "learning_rate": 0.00018180620793468224,
      "loss": 2.8715,
      "step": 140
    },
    {
      "epoch": 0.05290072297654735,
      "grad_norm": 15.11570930480957,
      "learning_rate": 0.00017748746653345728,
      "loss": 3.1419,
      "step": 150
    },
    {
      "epoch": 0.05290072297654735,
      "eval_loss": 2.7679033279418945,
      "eval_runtime": 25.974,
      "eval_samples_per_second": 45.969,
      "eval_steps_per_second": 11.512,
      "step": 150
    },
    {
      "epoch": 0.0564274378416505,
      "grad_norm": 1.4065930843353271,
      "learning_rate": 0.00017279364993403443,
      "loss": 1.9145,
      "step": 160
    },
    {
      "epoch": 0.05995415270675366,
      "grad_norm": 2.066331624984741,
      "learning_rate": 0.00016774762593906525,
      "loss": 1.9541,
      "step": 170
    },
    {
      "epoch": 0.06348086757185682,
      "grad_norm": 3.5042123794555664,
      "learning_rate": 0.00016237397827022866,
      "loss": 2.4669,
      "step": 180
    },
    {
      "epoch": 0.06700758243695998,
      "grad_norm": 5.192580223083496,
      "learning_rate": 0.00015669888679881007,
      "loss": 2.8639,
      "step": 190
    },
    {
      "epoch": 0.07053429730206313,
      "grad_norm": 13.965015411376953,
      "learning_rate": 0.00015075,
      "loss": 2.7112,
      "step": 200
    },
    {
      "epoch": 0.07053429730206313,
      "eval_loss": 2.5790367126464844,
      "eval_runtime": 25.986,
      "eval_samples_per_second": 45.948,
      "eval_steps_per_second": 11.506,
      "step": 200
    },
    {
      "epoch": 0.07406101216716629,
      "grad_norm": 1.4565879106521606,
      "learning_rate": 0.00014455630025230227,
      "loss": 1.8242,
      "step": 210
    },
    {
      "epoch": 0.07758772703226945,
      "grad_norm": 2.0483245849609375,
      "learning_rate": 0.00013814796263829918,
      "loss": 1.8938,
      "step": 220
    },
    {
      "epoch": 0.0811144418973726,
      "grad_norm": 3.366831064224243,
      "learning_rate": 0.00013155620793468223,
      "loss": 2.5577,
      "step": 230
    },
    {
      "epoch": 0.08464115676247576,
      "grad_norm": 4.877556324005127,
      "learning_rate": 0.0001248131505077666,
      "loss": 2.8751,
      "step": 240
    },
    {
      "epoch": 0.08816787162757891,
      "grad_norm": 7.277644157409668,
      "learning_rate": 0.00011795164185552652,
      "loss": 2.9683,
      "step": 250
    },
    {
      "epoch": 0.08816787162757891,
      "eval_loss": 2.5053224563598633,
      "eval_runtime": 25.9786,
      "eval_samples_per_second": 45.961,
      "eval_steps_per_second": 11.509,
      "step": 250
    },
    {
      "epoch": 0.09169458649268207,
      "grad_norm": 1.3616389036178589,
      "learning_rate": 0.00011100511055839919,
      "loss": 1.7079,
      "step": 260
    },
    {
      "epoch": 0.09522130135778523,
      "grad_norm": 2.048992156982422,
      "learning_rate": 0.00010400739941860137,
      "loss": 1.996,
      "step": 270
    },
    {
      "epoch": 0.09874801622288838,
      "grad_norm": 3.304049491882324,
      "learning_rate": 9.699260058139868e-05,
      "loss": 2.6002,
      "step": 280
    },
    {
      "epoch": 0.10227473108799154,
      "grad_norm": 5.327462196350098,
      "learning_rate": 8.999488944160085e-05,
      "loss": 2.904,
      "step": 290
    },
    {
      "epoch": 0.1058014459530947,
      "grad_norm": 13.41323184967041,
      "learning_rate": 8.30483581444735e-05,
      "loss": 3.0004,
      "step": 300
    },
    {
      "epoch": 0.1058014459530947,
      "eval_loss": 2.461601972579956,
      "eval_runtime": 25.8902,
      "eval_samples_per_second": 46.118,
      "eval_steps_per_second": 11.549,
      "step": 300
    },
    {
      "epoch": 0.10932816081819785,
      "grad_norm": 1.484745979309082,
      "learning_rate": 7.618684949223341e-05,
      "loss": 1.7311,
      "step": 310
    },
    {
      "epoch": 0.112854875683301,
      "grad_norm": 2.000025749206543,
      "learning_rate": 6.94437920653178e-05,
      "loss": 2.2476,
      "step": 320
    },
    {
      "epoch": 0.11638159054840416,
      "grad_norm": 3.111759901046753,
      "learning_rate": 6.285203736170084e-05,
      "loss": 2.6156,
      "step": 330
    },
    {
      "epoch": 0.11990830541350732,
      "grad_norm": 4.285041809082031,
      "learning_rate": 5.6443699747697714e-05,
      "loss": 2.7437,
      "step": 340
    },
    {
      "epoch": 0.12343502027861047,
      "grad_norm": 11.187140464782715,
      "learning_rate": 5.025000000000002e-05,
      "loss": 3.0227,
      "step": 350
    },
    {
      "epoch": 0.12343502027861047,
      "eval_loss": 2.405674695968628,
      "eval_runtime": 25.8716,
      "eval_samples_per_second": 46.151,
      "eval_steps_per_second": 11.557,
      "step": 350
    },
    {
      "epoch": 0.12696173514371364,
      "grad_norm": 1.2822436094284058,
      "learning_rate": 4.430111320118996e-05,
      "loss": 1.6962,
      "step": 360
    },
    {
      "epoch": 0.1304884500088168,
      "grad_norm": 2.262040853500366,
      "learning_rate": 3.862602172977134e-05,
      "loss": 2.0943,
      "step": 370
    },
    {
      "epoch": 0.13401516487391996,
      "grad_norm": 3.736957550048828,
      "learning_rate": 3.325237406093478e-05,
      "loss": 2.6009,
      "step": 380
    },
    {
      "epoch": 0.1375418797390231,
      "grad_norm": 4.0212321281433105,
      "learning_rate": 2.820635006596558e-05,
      "loss": 2.7693,
      "step": 390
    },
    {
      "epoch": 0.14106859460412627,
      "grad_norm": 14.131185531616211,
      "learning_rate": 2.351253346654272e-05,
      "loss": 3.0325,
      "step": 400
    },
    {
      "epoch": 0.14106859460412627,
      "eval_loss": 2.38608717918396,
      "eval_runtime": 25.8049,
      "eval_samples_per_second": 46.27,
      "eval_steps_per_second": 11.587,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 4018810864533504.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}