{
  "best_metric": 1.0403923988342285,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.847457627118644,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01694915254237288,
      "grad_norm": 0.9787123203277588,
      "learning_rate": 1e-05,
      "loss": 3.0209,
      "step": 1
    },
    {
      "epoch": 0.01694915254237288,
      "eval_loss": 4.1999897956848145,
      "eval_runtime": 1.4503,
      "eval_samples_per_second": 68.951,
      "eval_steps_per_second": 17.238,
      "step": 1
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 2.4502038955688477,
      "learning_rate": 2e-05,
      "loss": 4.4497,
      "step": 2
    },
    {
      "epoch": 0.05084745762711865,
      "grad_norm": 2.665430784225464,
      "learning_rate": 3e-05,
      "loss": 4.639,
      "step": 3
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 2.4935710430145264,
      "learning_rate": 4e-05,
      "loss": 4.4997,
      "step": 4
    },
    {
      "epoch": 0.0847457627118644,
      "grad_norm": 2.3885178565979004,
      "learning_rate": 5e-05,
      "loss": 4.3788,
      "step": 5
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 2.521230459213257,
      "learning_rate": 6e-05,
      "loss": 4.4601,
      "step": 6
    },
    {
      "epoch": 0.11864406779661017,
      "grad_norm": 2.408069133758545,
      "learning_rate": 7e-05,
      "loss": 4.3255,
      "step": 7
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 1.1387848854064941,
      "learning_rate": 8e-05,
      "loss": 3.355,
      "step": 8
    },
    {
      "epoch": 0.15254237288135594,
      "grad_norm": 1.0923254489898682,
      "learning_rate": 9e-05,
      "loss": 3.0777,
      "step": 9
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 1.489324688911438,
      "learning_rate": 0.0001,
      "loss": 3.4978,
      "step": 10
    },
    {
      "epoch": 0.1864406779661017,
      "grad_norm": 1.415766716003418,
      "learning_rate": 9.999115304121457e-05,
      "loss": 3.4619,
      "step": 11
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 1.4508241415023804,
      "learning_rate": 9.996461529560553e-05,
      "loss": 3.2672,
      "step": 12
    },
    {
      "epoch": 0.22033898305084745,
      "grad_norm": 1.6372668743133545,
      "learning_rate": 9.992039615430648e-05,
      "loss": 3.3624,
      "step": 13
    },
    {
      "epoch": 0.23728813559322035,
      "grad_norm": 2.086595296859741,
      "learning_rate": 9.985851126551428e-05,
      "loss": 3.8379,
      "step": 14
    },
    {
      "epoch": 0.2542372881355932,
      "grad_norm": 1.075448751449585,
      "learning_rate": 9.977898252895134e-05,
      "loss": 2.6479,
      "step": 15
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 2.2425975799560547,
      "learning_rate": 9.968183808811586e-05,
      "loss": 2.9848,
      "step": 16
    },
    {
      "epoch": 0.288135593220339,
      "grad_norm": 2.2366819381713867,
      "learning_rate": 9.95671123203224e-05,
      "loss": 2.818,
      "step": 17
    },
    {
      "epoch": 0.3050847457627119,
      "grad_norm": 2.1117076873779297,
      "learning_rate": 9.943484582453653e-05,
      "loss": 2.6075,
      "step": 18
    },
    {
      "epoch": 0.3220338983050847,
      "grad_norm": 2.0897672176361084,
      "learning_rate": 9.928508540700774e-05,
      "loss": 2.5123,
      "step": 19
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 1.8737945556640625,
      "learning_rate": 9.911788406470569e-05,
      "loss": 2.3475,
      "step": 20
    },
    {
      "epoch": 0.3559322033898305,
      "grad_norm": 1.7135223150253296,
      "learning_rate": 9.893330096656574e-05,
      "loss": 2.2067,
      "step": 21
    },
    {
      "epoch": 0.3728813559322034,
      "grad_norm": 0.705153226852417,
      "learning_rate": 9.873140143255036e-05,
      "loss": 2.1873,
      "step": 22
    },
    {
      "epoch": 0.3898305084745763,
      "grad_norm": 0.7329670190811157,
      "learning_rate": 9.85122569105338e-05,
      "loss": 2.6215,
      "step": 23
    },
    {
      "epoch": 0.4067796610169492,
      "grad_norm": 1.136795163154602,
      "learning_rate": 9.827594495101823e-05,
      "loss": 2.8488,
      "step": 24
    },
    {
      "epoch": 0.423728813559322,
      "grad_norm": 1.0769141912460327,
      "learning_rate": 9.802254917969032e-05,
      "loss": 2.8395,
      "step": 25
    },
    {
      "epoch": 0.4406779661016949,
      "grad_norm": 1.4403115510940552,
      "learning_rate": 9.775215926782788e-05,
      "loss": 2.6802,
      "step": 26
    },
    {
      "epoch": 0.4576271186440678,
      "grad_norm": 1.4279862642288208,
      "learning_rate": 9.746487090056713e-05,
      "loss": 2.7192,
      "step": 27
    },
    {
      "epoch": 0.4745762711864407,
      "grad_norm": 1.699432611465454,
      "learning_rate": 9.716078574304189e-05,
      "loss": 2.8853,
      "step": 28
    },
    {
      "epoch": 0.4915254237288136,
      "grad_norm": 1.4521034955978394,
      "learning_rate": 9.684001140440639e-05,
      "loss": 1.9164,
      "step": 29
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 2.434119939804077,
      "learning_rate": 9.650266139975474e-05,
      "loss": 1.3542,
      "step": 30
    },
    {
      "epoch": 0.5254237288135594,
      "grad_norm": 1.6792948246002197,
      "learning_rate": 9.614885510995047e-05,
      "loss": 1.3436,
      "step": 31
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 1.6474392414093018,
      "learning_rate": 9.577871773938011e-05,
      "loss": 1.1094,
      "step": 32
    },
    {
      "epoch": 0.559322033898305,
      "grad_norm": 1.6065335273742676,
      "learning_rate": 9.539238027164619e-05,
      "loss": 0.9116,
      "step": 33
    },
    {
      "epoch": 0.576271186440678,
      "grad_norm": 1.514753818511963,
      "learning_rate": 9.498997942321483e-05,
      "loss": 0.8389,
      "step": 34
    },
    {
      "epoch": 0.5932203389830508,
      "grad_norm": 1.2533358335494995,
      "learning_rate": 9.457165759503493e-05,
      "loss": 0.9727,
      "step": 35
    },
    {
      "epoch": 0.6101694915254238,
      "grad_norm": 0.8802417516708374,
      "learning_rate": 9.413756282214537e-05,
      "loss": 1.7009,
      "step": 36
    },
    {
      "epoch": 0.6271186440677966,
      "grad_norm": 1.1750346422195435,
      "learning_rate": 9.368784872128878e-05,
      "loss": 2.5651,
      "step": 37
    },
    {
      "epoch": 0.6440677966101694,
      "grad_norm": 1.331346035003662,
      "learning_rate": 9.322267443654972e-05,
      "loss": 2.5368,
      "step": 38
    },
    {
      "epoch": 0.6610169491525424,
      "grad_norm": 1.1209417581558228,
      "learning_rate": 9.274220458303727e-05,
      "loss": 2.8612,
      "step": 39
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 1.2335385084152222,
      "learning_rate": 9.224660918863104e-05,
      "loss": 2.6824,
      "step": 40
    },
    {
      "epoch": 0.6949152542372882,
      "grad_norm": 1.1797600984573364,
      "learning_rate": 9.173606363381219e-05,
      "loss": 2.4775,
      "step": 41
    },
    {
      "epoch": 0.711864406779661,
      "grad_norm": 1.6770628690719604,
      "learning_rate": 9.121074858959997e-05,
      "loss": 2.7293,
      "step": 42
    },
    {
      "epoch": 0.7288135593220338,
      "grad_norm": 1.0169050693511963,
      "learning_rate": 9.067084995361623e-05,
      "loss": 1.3915,
      "step": 43
    },
    {
      "epoch": 0.7457627118644068,
      "grad_norm": 1.1066895723342896,
      "learning_rate": 9.011655878430019e-05,
      "loss": 0.5636,
      "step": 44
    },
    {
      "epoch": 0.7627118644067796,
      "grad_norm": 0.9063847661018372,
      "learning_rate": 8.954807123329704e-05,
      "loss": 0.1767,
      "step": 45
    },
    {
      "epoch": 0.7796610169491526,
      "grad_norm": 0.5006846189498901,
      "learning_rate": 8.896558847604414e-05,
      "loss": 0.3629,
      "step": 46
    },
    {
      "epoch": 0.7966101694915254,
      "grad_norm": 0.42200618982315063,
      "learning_rate": 8.836931664057935e-05,
      "loss": 0.2745,
      "step": 47
    },
    {
      "epoch": 0.8135593220338984,
      "grad_norm": 0.3802186846733093,
      "learning_rate": 8.775946673459681e-05,
      "loss": 0.1882,
      "step": 48
    },
    {
      "epoch": 0.8305084745762712,
      "grad_norm": 0.3861039876937866,
      "learning_rate": 8.713625457077585e-05,
      "loss": 0.4487,
      "step": 49
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 0.9502959847450256,
      "learning_rate": 8.649990069040961e-05,
      "loss": 2.1698,
      "step": 50
    },
    {
      "epoch": 0.847457627118644,
      "eval_loss": 1.0403923988342285,
      "eval_runtime": 1.442,
      "eval_samples_per_second": 69.349,
      "eval_steps_per_second": 17.337,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 177,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1236088022630400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}