{
  "best_metric": 3.121091365814209,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.1812825742125538,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036256514842510764,
      "grad_norm": 8.241829872131348,
      "learning_rate": 5e-05,
      "loss": 4.5069,
      "step": 1
    },
    {
      "epoch": 0.0036256514842510764,
      "eval_loss": 5.34570837020874,
      "eval_runtime": 75.8053,
      "eval_samples_per_second": 24.51,
      "eval_steps_per_second": 3.074,
      "step": 1
    },
    {
      "epoch": 0.007251302968502153,
      "grad_norm": 30.456340789794922,
      "learning_rate": 0.0001,
      "loss": 4.6473,
      "step": 2
    },
    {
      "epoch": 0.010876954452753228,
      "grad_norm": 6.858401298522949,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.6742,
      "step": 3
    },
    {
      "epoch": 0.014502605937004306,
      "grad_norm": 13.97120189666748,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.5947,
      "step": 4
    },
    {
      "epoch": 0.018128257421255383,
      "grad_norm": 18.036510467529297,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.3272,
      "step": 5
    },
    {
      "epoch": 0.021753908905506457,
      "grad_norm": 12.143863677978516,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.1179,
      "step": 6
    },
    {
      "epoch": 0.025379560389757534,
      "grad_norm": 3.1463892459869385,
      "learning_rate": 9.73465064747553e-05,
      "loss": 4.0047,
      "step": 7
    },
    {
      "epoch": 0.02900521187400861,
      "grad_norm": 3.756556272506714,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.9971,
      "step": 8
    },
    {
      "epoch": 0.03263086335825969,
      "grad_norm": 2.290227174758911,
      "learning_rate": 9.484363707663442e-05,
      "loss": 4.0485,
      "step": 9
    },
    {
      "epoch": 0.036256514842510766,
      "grad_norm": 2.1480581760406494,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.9855,
      "step": 10
    },
    {
      "epoch": 0.03988216632676184,
      "grad_norm": 2.481700897216797,
      "learning_rate": 9.157348061512727e-05,
      "loss": 3.9623,
      "step": 11
    },
    {
      "epoch": 0.043507817811012914,
      "grad_norm": 3.275925397872925,
      "learning_rate": 8.966766701456177e-05,
      "loss": 4.0405,
      "step": 12
    },
    {
      "epoch": 0.04713346929526399,
      "grad_norm": 4.188512802124023,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.5813,
      "step": 13
    },
    {
      "epoch": 0.05075912077951507,
      "grad_norm": 4.209834098815918,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.533,
      "step": 14
    },
    {
      "epoch": 0.054384772263766146,
      "grad_norm": 3.3487038612365723,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.4657,
      "step": 15
    },
    {
      "epoch": 0.05801042374801722,
      "grad_norm": 4.447124004364014,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.3674,
      "step": 16
    },
    {
      "epoch": 0.0616360752322683,
      "grad_norm": 17.628175735473633,
      "learning_rate": 7.777851165098012e-05,
      "loss": 3.3767,
      "step": 17
    },
    {
      "epoch": 0.06526172671651938,
      "grad_norm": 5.452234745025635,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.3199,
      "step": 18
    },
    {
      "epoch": 0.06888737820077045,
      "grad_norm": 16.761486053466797,
      "learning_rate": 7.211443451095007e-05,
      "loss": 3.2475,
      "step": 19
    },
    {
      "epoch": 0.07251302968502153,
      "grad_norm": 11.818711280822754,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.3671,
      "step": 20
    },
    {
      "epoch": 0.07613868116927261,
      "grad_norm": 10.191901206970215,
      "learning_rate": 6.607197326515808e-05,
      "loss": 3.3358,
      "step": 21
    },
    {
      "epoch": 0.07976433265352369,
      "grad_norm": 7.763014793395996,
      "learning_rate": 6.294095225512603e-05,
      "loss": 3.4395,
      "step": 22
    },
    {
      "epoch": 0.08338998413777475,
      "grad_norm": 6.43538236618042,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.4213,
      "step": 23
    },
    {
      "epoch": 0.08701563562202583,
      "grad_norm": 4.963839530944824,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 3.4948,
      "step": 24
    },
    {
      "epoch": 0.0906412871062769,
      "grad_norm": 9.364582061767578,
      "learning_rate": 5.327015646150716e-05,
      "loss": 3.6978,
      "step": 25
    },
    {
      "epoch": 0.0906412871062769,
      "eval_loss": 3.2366089820861816,
      "eval_runtime": 75.6772,
      "eval_samples_per_second": 24.552,
      "eval_steps_per_second": 3.079,
      "step": 25
    },
    {
      "epoch": 0.09426693859052798,
      "grad_norm": 5.509792327880859,
      "learning_rate": 5e-05,
      "loss": 3.1615,
      "step": 26
    },
    {
      "epoch": 0.09789259007477906,
      "grad_norm": 8.197694778442383,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 3.0753,
      "step": 27
    },
    {
      "epoch": 0.10151824155903014,
      "grad_norm": 1.9906346797943115,
      "learning_rate": 4.347369038899744e-05,
      "loss": 3.0005,
      "step": 28
    },
    {
      "epoch": 0.10514389304328121,
      "grad_norm": 1.6515172719955444,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 3.149,
      "step": 29
    },
    {
      "epoch": 0.10876954452753229,
      "grad_norm": 2.503220558166504,
      "learning_rate": 3.705904774487396e-05,
      "loss": 3.0762,
      "step": 30
    },
    {
      "epoch": 0.11239519601178337,
      "grad_norm": 1.4713380336761475,
      "learning_rate": 3.392802673484193e-05,
      "loss": 3.1036,
      "step": 31
    },
    {
      "epoch": 0.11602084749603445,
      "grad_norm": 1.6807591915130615,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.1145,
      "step": 32
    },
    {
      "epoch": 0.11964649898028552,
      "grad_norm": 2.160545825958252,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 3.0805,
      "step": 33
    },
    {
      "epoch": 0.1232721504645366,
      "grad_norm": 15.812837600708008,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.1181,
      "step": 34
    },
    {
      "epoch": 0.12689780194878766,
      "grad_norm": 2.214811086654663,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 3.0835,
      "step": 35
    },
    {
      "epoch": 0.13052345343303876,
      "grad_norm": 2.4301793575286865,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 3.2651,
      "step": 36
    },
    {
      "epoch": 0.13414910491728982,
      "grad_norm": 3.295548677444458,
      "learning_rate": 1.703270924499656e-05,
      "loss": 3.2649,
      "step": 37
    },
    {
      "epoch": 0.1377747564015409,
      "grad_norm": 2.6664798259735107,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.1903,
      "step": 38
    },
    {
      "epoch": 0.14140040788579197,
      "grad_norm": 1.2872811555862427,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 3.0828,
      "step": 39
    },
    {
      "epoch": 0.14502605937004306,
      "grad_norm": 2.149052858352661,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 3.0371,
      "step": 40
    },
    {
      "epoch": 0.14865171085429413,
      "grad_norm": 2.295020341873169,
      "learning_rate": 8.426519384872733e-06,
      "loss": 3.1058,
      "step": 41
    },
    {
      "epoch": 0.15227736233854522,
      "grad_norm": 1.5253604650497437,
      "learning_rate": 6.698729810778065e-06,
      "loss": 3.099,
      "step": 42
    },
    {
      "epoch": 0.15590301382279628,
      "grad_norm": 1.4826136827468872,
      "learning_rate": 5.156362923365588e-06,
      "loss": 3.0172,
      "step": 43
    },
    {
      "epoch": 0.15952866530704737,
      "grad_norm": 2.7176144123077393,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.217,
      "step": 44
    },
    {
      "epoch": 0.16315431679129844,
      "grad_norm": 1.5273343324661255,
      "learning_rate": 2.653493525244721e-06,
      "loss": 3.0648,
      "step": 45
    },
    {
      "epoch": 0.1667799682755495,
      "grad_norm": 3.0926811695098877,
      "learning_rate": 1.70370868554659e-06,
      "loss": 3.0708,
      "step": 46
    },
    {
      "epoch": 0.1704056197598006,
      "grad_norm": 1.7232677936553955,
      "learning_rate": 9.607359798384785e-07,
      "loss": 3.1711,
      "step": 47
    },
    {
      "epoch": 0.17403127124405166,
      "grad_norm": 2.884068250656128,
      "learning_rate": 4.277569313094809e-07,
      "loss": 3.1643,
      "step": 48
    },
    {
      "epoch": 0.17765692272830275,
      "grad_norm": 3.1874499320983887,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 3.1872,
      "step": 49
    },
    {
      "epoch": 0.1812825742125538,
      "grad_norm": 4.788722991943359,
      "learning_rate": 0.0,
      "loss": 3.4839,
      "step": 50
    },
    {
      "epoch": 0.1812825742125538,
      "eval_loss": 3.121091365814209,
      "eval_runtime": 75.5847,
      "eval_samples_per_second": 24.582,
      "eval_steps_per_second": 3.083,
      "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": 2.229252309123072e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}