{
  "best_metric": 0.5298166275024414,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.055509297807382736,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011101859561476548,
      "grad_norm": 0.49238985776901245,
      "learning_rate": 5e-05,
      "loss": 0.9256,
      "step": 1
    },
    {
      "epoch": 0.0011101859561476548,
      "eval_loss": 0.9522705674171448,
      "eval_runtime": 177.9742,
      "eval_samples_per_second": 34.095,
      "eval_steps_per_second": 4.265,
      "step": 1
    },
    {
      "epoch": 0.0022203719122953097,
      "grad_norm": 0.29853853583335876,
      "learning_rate": 0.0001,
      "loss": 0.6724,
      "step": 2
    },
    {
      "epoch": 0.0033305578684429643,
      "grad_norm": 0.32347244024276733,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.7226,
      "step": 3
    },
    {
      "epoch": 0.004440743824590619,
      "grad_norm": 0.3456582725048065,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.7107,
      "step": 4
    },
    {
      "epoch": 0.005550929780738274,
      "grad_norm": 0.3627603054046631,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.7059,
      "step": 5
    },
    {
      "epoch": 0.006661115736885929,
      "grad_norm": 0.28934207558631897,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.6369,
      "step": 6
    },
    {
      "epoch": 0.007771301693033583,
      "grad_norm": 0.28893226385116577,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.7046,
      "step": 7
    },
    {
      "epoch": 0.008881487649181239,
      "grad_norm": 0.2778341472148895,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.6706,
      "step": 8
    },
    {
      "epoch": 0.009991673605328892,
      "grad_norm": 0.28240063786506653,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.6869,
      "step": 9
    },
    {
      "epoch": 0.011101859561476548,
      "grad_norm": 0.344245970249176,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6947,
      "step": 10
    },
    {
      "epoch": 0.012212045517624202,
      "grad_norm": 0.39578473567962646,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.7149,
      "step": 11
    },
    {
      "epoch": 0.013322231473771857,
      "grad_norm": 0.556731641292572,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.7269,
      "step": 12
    },
    {
      "epoch": 0.014432417429919511,
      "grad_norm": 0.2186538577079773,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.7062,
      "step": 13
    },
    {
      "epoch": 0.015542603386067166,
      "grad_norm": 0.31430763006210327,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.5135,
      "step": 14
    },
    {
      "epoch": 0.01665278934221482,
      "grad_norm": 0.32725635170936584,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.5891,
      "step": 15
    },
    {
      "epoch": 0.017762975298362477,
      "grad_norm": 0.2934384346008301,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.6241,
      "step": 16
    },
    {
      "epoch": 0.01887316125451013,
      "grad_norm": 0.2427055537700653,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.5553,
      "step": 17
    },
    {
      "epoch": 0.019983347210657785,
      "grad_norm": 0.1847805678844452,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5412,
      "step": 18
    },
    {
      "epoch": 0.02109353316680544,
      "grad_norm": 0.17363831400871277,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.5962,
      "step": 19
    },
    {
      "epoch": 0.022203719122953096,
      "grad_norm": 0.17168928682804108,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.5227,
      "step": 20
    },
    {
      "epoch": 0.02331390507910075,
      "grad_norm": 0.24253211915493011,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.5646,
      "step": 21
    },
    {
      "epoch": 0.024424091035248403,
      "grad_norm": 0.24645404517650604,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.5449,
      "step": 22
    },
    {
      "epoch": 0.025534276991396057,
      "grad_norm": 0.31301403045654297,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.5878,
      "step": 23
    },
    {
      "epoch": 0.026644462947543714,
      "grad_norm": 0.4185570478439331,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.572,
      "step": 24
    },
    {
      "epoch": 0.027754648903691368,
      "grad_norm": 0.80572909116745,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.7955,
      "step": 25
    },
    {
      "epoch": 0.027754648903691368,
      "eval_loss": 0.5439428687095642,
      "eval_runtime": 178.4015,
      "eval_samples_per_second": 34.013,
      "eval_steps_per_second": 4.254,
      "step": 25
    },
    {
      "epoch": 0.028864834859839022,
      "grad_norm": 0.07082349061965942,
      "learning_rate": 5e-05,
      "loss": 0.5417,
      "step": 26
    },
    {
      "epoch": 0.02997502081598668,
      "grad_norm": 0.09529879689216614,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.4697,
      "step": 27
    },
    {
      "epoch": 0.031085206772134333,
      "grad_norm": 0.11979064345359802,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.5269,
      "step": 28
    },
    {
      "epoch": 0.03219539272828199,
      "grad_norm": 0.15223853290081024,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.5231,
      "step": 29
    },
    {
      "epoch": 0.03330557868442964,
      "grad_norm": 0.17808681726455688,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.5009,
      "step": 30
    },
    {
      "epoch": 0.034415764640577294,
      "grad_norm": 0.1959284096956253,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.5218,
      "step": 31
    },
    {
      "epoch": 0.035525950596724955,
      "grad_norm": 0.19149121642112732,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5211,
      "step": 32
    },
    {
      "epoch": 0.03663613655287261,
      "grad_norm": 0.21555660665035248,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.5526,
      "step": 33
    },
    {
      "epoch": 0.03774632250902026,
      "grad_norm": 0.23048672080039978,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.5356,
      "step": 34
    },
    {
      "epoch": 0.038856508465167916,
      "grad_norm": 0.2359524667263031,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.5408,
      "step": 35
    },
    {
      "epoch": 0.03996669442131557,
      "grad_norm": 0.27337896823883057,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.5737,
      "step": 36
    },
    {
      "epoch": 0.041076880377463224,
      "grad_norm": 0.3115023970603943,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.5634,
      "step": 37
    },
    {
      "epoch": 0.04218706633361088,
      "grad_norm": 0.09126698970794678,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.6497,
      "step": 38
    },
    {
      "epoch": 0.04329725228975854,
      "grad_norm": 0.0780349001288414,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.4434,
      "step": 39
    },
    {
      "epoch": 0.04440743824590619,
      "grad_norm": 0.09226205199956894,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.4756,
      "step": 40
    },
    {
      "epoch": 0.045517624202053845,
      "grad_norm": 0.10075278580188751,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.5042,
      "step": 41
    },
    {
      "epoch": 0.0466278101582015,
      "grad_norm": 0.10810760408639908,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.4929,
      "step": 42
    },
    {
      "epoch": 0.04773799611434915,
      "grad_norm": 0.12063668668270111,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.5035,
      "step": 43
    },
    {
      "epoch": 0.04884818207049681,
      "grad_norm": 0.13385652005672455,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.5197,
      "step": 44
    },
    {
      "epoch": 0.04995836802664446,
      "grad_norm": 0.14498774707317352,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.4995,
      "step": 45
    },
    {
      "epoch": 0.051068553982792114,
      "grad_norm": 0.15357857942581177,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.4836,
      "step": 46
    },
    {
      "epoch": 0.052178739938939775,
      "grad_norm": 0.2189844846725464,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.5309,
      "step": 47
    },
    {
      "epoch": 0.05328892589508743,
      "grad_norm": 0.2006743997335434,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.5585,
      "step": 48
    },
    {
      "epoch": 0.05439911185123508,
      "grad_norm": 0.24543078243732452,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.5591,
      "step": 49
    },
    {
      "epoch": 0.055509297807382736,
      "grad_norm": 0.4042859673500061,
      "learning_rate": 0.0,
      "loss": 0.6439,
      "step": 50
    },
    {
      "epoch": 0.055509297807382736,
      "eval_loss": 0.5298166275024414,
      "eval_runtime": 177.5866,
      "eval_samples_per_second": 34.169,
      "eval_steps_per_second": 4.274,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5.2738959989538816e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}