{
  "best_metric": 1.5425931215286255,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.13003901170351106,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002600780234070221,
      "grad_norm": 0.08141548186540604,
      "learning_rate": 5e-05,
      "loss": 1.4806,
      "step": 1
    },
    {
      "epoch": 0.002600780234070221,
      "eval_loss": 1.7399518489837646,
      "eval_runtime": 22.4581,
      "eval_samples_per_second": 115.37,
      "eval_steps_per_second": 14.427,
      "step": 1
    },
    {
      "epoch": 0.005201560468140442,
      "grad_norm": 0.08754484355449677,
      "learning_rate": 0.0001,
      "loss": 1.5087,
      "step": 2
    },
    {
      "epoch": 0.007802340702210663,
      "grad_norm": 0.11383166909217834,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.5678,
      "step": 3
    },
    {
      "epoch": 0.010403120936280884,
      "grad_norm": 0.09885820001363754,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.5686,
      "step": 4
    },
    {
      "epoch": 0.013003901170351105,
      "grad_norm": 0.1233765110373497,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.6442,
      "step": 5
    },
    {
      "epoch": 0.015604681404421327,
      "grad_norm": 0.12786661088466644,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.6532,
      "step": 6
    },
    {
      "epoch": 0.018205461638491547,
      "grad_norm": 0.16046465933322906,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.7213,
      "step": 7
    },
    {
      "epoch": 0.02080624187256177,
      "grad_norm": 0.20578309893608093,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6983,
      "step": 8
    },
    {
      "epoch": 0.02340702210663199,
      "grad_norm": 0.2803490161895752,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.7377,
      "step": 9
    },
    {
      "epoch": 0.02600780234070221,
      "grad_norm": 0.40666747093200684,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8961,
      "step": 10
    },
    {
      "epoch": 0.02860858257477243,
      "grad_norm": 0.5478541254997253,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8006,
      "step": 11
    },
    {
      "epoch": 0.031209362808842653,
      "grad_norm": 0.7642838358879089,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.8276,
      "step": 12
    },
    {
      "epoch": 0.033810143042912875,
      "grad_norm": 0.09872327744960785,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.4478,
      "step": 13
    },
    {
      "epoch": 0.036410923276983094,
      "grad_norm": 0.08637108653783798,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.4842,
      "step": 14
    },
    {
      "epoch": 0.03901170351105332,
      "grad_norm": 0.09273920953273773,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.5139,
      "step": 15
    },
    {
      "epoch": 0.04161248374512354,
      "grad_norm": 0.10740404576063156,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.5607,
      "step": 16
    },
    {
      "epoch": 0.044213263979193757,
      "grad_norm": 0.12133503705263138,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.5293,
      "step": 17
    },
    {
      "epoch": 0.04681404421326398,
      "grad_norm": 0.14166684448719025,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5992,
      "step": 18
    },
    {
      "epoch": 0.0494148244473342,
      "grad_norm": 0.1470976173877716,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.6065,
      "step": 19
    },
    {
      "epoch": 0.05201560468140442,
      "grad_norm": 0.1957826465368271,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5895,
      "step": 20
    },
    {
      "epoch": 0.054616384915474644,
      "grad_norm": 0.2453211396932602,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.57,
      "step": 21
    },
    {
      "epoch": 0.05721716514954486,
      "grad_norm": 0.3172180950641632,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.6455,
      "step": 22
    },
    {
      "epoch": 0.05981794538361508,
      "grad_norm": 0.3927510678768158,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.7744,
      "step": 23
    },
    {
      "epoch": 0.06241872561768531,
      "grad_norm": 0.46858957409858704,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.6495,
      "step": 24
    },
    {
      "epoch": 0.06501950585175553,
      "grad_norm": 0.7443721294403076,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.6001,
      "step": 25
    },
    {
      "epoch": 0.06501950585175553,
      "eval_loss": 1.5651992559432983,
      "eval_runtime": 22.4191,
      "eval_samples_per_second": 115.571,
      "eval_steps_per_second": 14.452,
      "step": 25
    },
    {
      "epoch": 0.06762028608582575,
      "grad_norm": 0.0953252986073494,
      "learning_rate": 5e-05,
      "loss": 1.4085,
      "step": 26
    },
    {
      "epoch": 0.07022106631989597,
      "grad_norm": 0.09956612437963486,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.4664,
      "step": 27
    },
    {
      "epoch": 0.07282184655396619,
      "grad_norm": 0.11147274821996689,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.5273,
      "step": 28
    },
    {
      "epoch": 0.0754226267880364,
      "grad_norm": 0.12826047837734222,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.5368,
      "step": 29
    },
    {
      "epoch": 0.07802340702210664,
      "grad_norm": 0.13391107320785522,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.5507,
      "step": 30
    },
    {
      "epoch": 0.08062418725617686,
      "grad_norm": 0.13899120688438416,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.5767,
      "step": 31
    },
    {
      "epoch": 0.08322496749024708,
      "grad_norm": 0.15416182577610016,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.5633,
      "step": 32
    },
    {
      "epoch": 0.0858257477243173,
      "grad_norm": 0.19598853588104248,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.5447,
      "step": 33
    },
    {
      "epoch": 0.08842652795838751,
      "grad_norm": 0.24805714190006256,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5419,
      "step": 34
    },
    {
      "epoch": 0.09102730819245773,
      "grad_norm": 0.32029539346694946,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.5999,
      "step": 35
    },
    {
      "epoch": 0.09362808842652796,
      "grad_norm": 0.3935973346233368,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.5974,
      "step": 36
    },
    {
      "epoch": 0.09622886866059818,
      "grad_norm": 0.5263167023658752,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.4174,
      "step": 37
    },
    {
      "epoch": 0.0988296488946684,
      "grad_norm": 0.10492201894521713,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.3571,
      "step": 38
    },
    {
      "epoch": 0.10143042912873862,
      "grad_norm": 0.10784497857093811,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.5052,
      "step": 39
    },
    {
      "epoch": 0.10403120936280884,
      "grad_norm": 0.09847010672092438,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.4734,
      "step": 40
    },
    {
      "epoch": 0.10663198959687907,
      "grad_norm": 0.11888845264911652,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.5328,
      "step": 41
    },
    {
      "epoch": 0.10923276983094929,
      "grad_norm": 0.12106700986623764,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.5251,
      "step": 42
    },
    {
      "epoch": 0.11183355006501951,
      "grad_norm": 0.14373373985290527,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.6022,
      "step": 43
    },
    {
      "epoch": 0.11443433029908973,
      "grad_norm": 0.15439628064632416,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.5658,
      "step": 44
    },
    {
      "epoch": 0.11703511053315994,
      "grad_norm": 0.18161892890930176,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.6469,
      "step": 45
    },
    {
      "epoch": 0.11963589076723016,
      "grad_norm": 0.2562808692455292,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.6132,
      "step": 46
    },
    {
      "epoch": 0.1222366710013004,
      "grad_norm": 0.2922062575817108,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.5971,
      "step": 47
    },
    {
      "epoch": 0.12483745123537061,
      "grad_norm": 0.37385690212249756,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.6268,
      "step": 48
    },
    {
      "epoch": 0.12743823146944083,
      "grad_norm": 0.42741650342941284,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.6055,
      "step": 49
    },
    {
      "epoch": 0.13003901170351106,
      "grad_norm": 0.7190040946006775,
      "learning_rate": 0.0,
      "loss": 1.4895,
      "step": 50
    },
    {
      "epoch": 0.13003901170351106,
      "eval_loss": 1.5425931215286255,
      "eval_runtime": 22.4336,
      "eval_samples_per_second": 115.497,
      "eval_steps_per_second": 14.443,
      "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": 8.33416392081408e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}