{
  "best_metric": 1.1518352031707764,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.2947678703021371,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0058953574060427415,
      "grad_norm": 0.7333860993385315,
      "learning_rate": 5e-05,
      "loss": 1.5291,
      "step": 1
    },
    {
      "epoch": 0.0058953574060427415,
      "eval_loss": 1.5804364681243896,
      "eval_runtime": 13.3625,
      "eval_samples_per_second": 85.538,
      "eval_steps_per_second": 10.702,
      "step": 1
    },
    {
      "epoch": 0.011790714812085483,
      "grad_norm": 1.0514726638793945,
      "learning_rate": 0.0001,
      "loss": 1.6328,
      "step": 2
    },
    {
      "epoch": 0.017686072218128224,
      "grad_norm": 0.9634788036346436,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.5343,
      "step": 3
    },
    {
      "epoch": 0.023581429624170966,
      "grad_norm": 0.9008709788322449,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.5294,
      "step": 4
    },
    {
      "epoch": 0.029476787030213707,
      "grad_norm": 0.6989626288414001,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.4912,
      "step": 5
    },
    {
      "epoch": 0.03537214443625645,
      "grad_norm": 0.7588152885437012,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.4778,
      "step": 6
    },
    {
      "epoch": 0.04126750184229919,
      "grad_norm": 0.8170850872993469,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.2548,
      "step": 7
    },
    {
      "epoch": 0.04716285924834193,
      "grad_norm": 0.794342577457428,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1614,
      "step": 8
    },
    {
      "epoch": 0.05305821665438467,
      "grad_norm": 0.7459205389022827,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.1025,
      "step": 9
    },
    {
      "epoch": 0.058953574060427415,
      "grad_norm": 0.6164001822471619,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0585,
      "step": 10
    },
    {
      "epoch": 0.06484893146647015,
      "grad_norm": 0.6428624391555786,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.0682,
      "step": 11
    },
    {
      "epoch": 0.0707442888725129,
      "grad_norm": 0.7521356344223022,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.0957,
      "step": 12
    },
    {
      "epoch": 0.07663964627855564,
      "grad_norm": 0.5672096610069275,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.3186,
      "step": 13
    },
    {
      "epoch": 0.08253500368459837,
      "grad_norm": 0.532937228679657,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.4679,
      "step": 14
    },
    {
      "epoch": 0.08843036109064112,
      "grad_norm": 0.4563632607460022,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.4107,
      "step": 15
    },
    {
      "epoch": 0.09432571849668386,
      "grad_norm": 0.4153241515159607,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.2868,
      "step": 16
    },
    {
      "epoch": 0.10022107590272661,
      "grad_norm": 0.4522489309310913,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.3758,
      "step": 17
    },
    {
      "epoch": 0.10611643330876934,
      "grad_norm": 0.44158637523651123,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2064,
      "step": 18
    },
    {
      "epoch": 0.11201179071481208,
      "grad_norm": 0.6197159290313721,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.2751,
      "step": 19
    },
    {
      "epoch": 0.11790714812085483,
      "grad_norm": 0.5513057112693787,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0396,
      "step": 20
    },
    {
      "epoch": 0.12380250552689757,
      "grad_norm": 0.44052842259407043,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.0566,
      "step": 21
    },
    {
      "epoch": 0.1296978629329403,
      "grad_norm": 0.46214574575424194,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.994,
      "step": 22
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 0.42542994022369385,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.9877,
      "step": 23
    },
    {
      "epoch": 0.1414885777450258,
      "grad_norm": 0.41470226645469666,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.9486,
      "step": 24
    },
    {
      "epoch": 0.14738393515106854,
      "grad_norm": 0.4551374912261963,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.937,
      "step": 25
    },
    {
      "epoch": 0.14738393515106854,
      "eval_loss": 1.1771202087402344,
      "eval_runtime": 13.4859,
      "eval_samples_per_second": 84.755,
      "eval_steps_per_second": 10.604,
      "step": 25
    },
    {
      "epoch": 0.15327929255711129,
      "grad_norm": 0.41432493925094604,
      "learning_rate": 5e-05,
      "loss": 1.3968,
      "step": 26
    },
    {
      "epoch": 0.159174649963154,
      "grad_norm": 0.4302958548069,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.3309,
      "step": 27
    },
    {
      "epoch": 0.16507000736919675,
      "grad_norm": 0.4882798492908478,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.4163,
      "step": 28
    },
    {
      "epoch": 0.1709653647752395,
      "grad_norm": 0.5064733624458313,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.335,
      "step": 29
    },
    {
      "epoch": 0.17686072218128224,
      "grad_norm": 0.4844876229763031,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.2396,
      "step": 30
    },
    {
      "epoch": 0.18275607958732498,
      "grad_norm": 0.47237423062324524,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.1634,
      "step": 31
    },
    {
      "epoch": 0.18865143699336773,
      "grad_norm": 0.5116559863090515,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.15,
      "step": 32
    },
    {
      "epoch": 0.19454679439941047,
      "grad_norm": 0.33985745906829834,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.0385,
      "step": 33
    },
    {
      "epoch": 0.20044215180545322,
      "grad_norm": 0.3580736815929413,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0018,
      "step": 34
    },
    {
      "epoch": 0.20633750921149593,
      "grad_norm": 0.3772769868373871,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.0042,
      "step": 35
    },
    {
      "epoch": 0.21223286661753868,
      "grad_norm": 0.3896821141242981,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.9262,
      "step": 36
    },
    {
      "epoch": 0.21812822402358142,
      "grad_norm": 0.38928064703941345,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.9422,
      "step": 37
    },
    {
      "epoch": 0.22402358142962417,
      "grad_norm": 0.3280961513519287,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.2344,
      "step": 38
    },
    {
      "epoch": 0.22991893883566691,
      "grad_norm": 0.32811683416366577,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.3309,
      "step": 39
    },
    {
      "epoch": 0.23581429624170966,
      "grad_norm": 0.32886970043182373,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.3533,
      "step": 40
    },
    {
      "epoch": 0.2417096536477524,
      "grad_norm": 0.34771019220352173,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.1761,
      "step": 41
    },
    {
      "epoch": 0.24760501105379515,
      "grad_norm": 0.38889893889427185,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.2497,
      "step": 42
    },
    {
      "epoch": 0.25350036845983787,
      "grad_norm": 0.42282721400260925,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.1889,
      "step": 43
    },
    {
      "epoch": 0.2593957258658806,
      "grad_norm": 0.3826811909675598,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.0699,
      "step": 44
    },
    {
      "epoch": 0.26529108327192336,
      "grad_norm": 0.32068920135498047,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.9982,
      "step": 45
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 0.3361916244029999,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.0015,
      "step": 46
    },
    {
      "epoch": 0.27708179808400885,
      "grad_norm": 0.332919716835022,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.9339,
      "step": 47
    },
    {
      "epoch": 0.2829771554900516,
      "grad_norm": 0.3428276479244232,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.9266,
      "step": 48
    },
    {
      "epoch": 0.28887251289609434,
      "grad_norm": 0.3674064874649048,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.9696,
      "step": 49
    },
    {
      "epoch": 0.2947678703021371,
      "grad_norm": 0.42665550112724304,
      "learning_rate": 0.0,
      "loss": 0.9495,
      "step": 50
    },
    {
      "epoch": 0.2947678703021371,
      "eval_loss": 1.1518352031707764,
      "eval_runtime": 13.463,
      "eval_samples_per_second": 84.899,
      "eval_steps_per_second": 10.622,
      "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": 4.556862208029491e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}