{
  "best_metric": 0.6981587409973145,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.15618898867629832,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031237797735259665,
      "grad_norm": 122.5908203125,
      "learning_rate": 5e-05,
      "loss": 1.3888,
      "step": 1
    },
    {
      "epoch": 0.0031237797735259665,
      "eval_loss": 4.010549068450928,
      "eval_runtime": 62.0145,
      "eval_samples_per_second": 34.782,
      "eval_steps_per_second": 4.354,
      "step": 1
    },
    {
      "epoch": 0.006247559547051933,
      "grad_norm": 195.3430633544922,
      "learning_rate": 0.0001,
      "loss": 1.9557,
      "step": 2
    },
    {
      "epoch": 0.009371339320577899,
      "grad_norm": 181.5518035888672,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.7302,
      "step": 3
    },
    {
      "epoch": 0.012495119094103866,
      "grad_norm": 147.94204711914062,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.1438,
      "step": 4
    },
    {
      "epoch": 0.015618898867629832,
      "grad_norm": 92.91121673583984,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.5056,
      "step": 5
    },
    {
      "epoch": 0.018742678641155797,
      "grad_norm": 69.36351776123047,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.2954,
      "step": 6
    },
    {
      "epoch": 0.021866458414681766,
      "grad_norm": 93.85100555419922,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.1558,
      "step": 7
    },
    {
      "epoch": 0.024990238188207732,
      "grad_norm": 65.72035217285156,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.2143,
      "step": 8
    },
    {
      "epoch": 0.028114017961733698,
      "grad_norm": 52.03777313232422,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.0514,
      "step": 9
    },
    {
      "epoch": 0.031237797735259663,
      "grad_norm": 38.72542953491211,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9671,
      "step": 10
    },
    {
      "epoch": 0.03436157750878563,
      "grad_norm": 33.95488739013672,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.0728,
      "step": 11
    },
    {
      "epoch": 0.037485357282311595,
      "grad_norm": 37.485965728759766,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.0328,
      "step": 12
    },
    {
      "epoch": 0.04060913705583756,
      "grad_norm": 36.62322235107422,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.8906,
      "step": 13
    },
    {
      "epoch": 0.04373291682936353,
      "grad_norm": 27.22071647644043,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.665,
      "step": 14
    },
    {
      "epoch": 0.0468566966028895,
      "grad_norm": 25.39254379272461,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.6345,
      "step": 15
    },
    {
      "epoch": 0.049980476376415464,
      "grad_norm": 26.609024047851562,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.6847,
      "step": 16
    },
    {
      "epoch": 0.05310425614994143,
      "grad_norm": 26.597126007080078,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.7541,
      "step": 17
    },
    {
      "epoch": 0.056228035923467395,
      "grad_norm": 34.9815673828125,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8164,
      "step": 18
    },
    {
      "epoch": 0.05935181569699336,
      "grad_norm": 30.860759735107422,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.8138,
      "step": 19
    },
    {
      "epoch": 0.06247559547051933,
      "grad_norm": 36.81730270385742,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.773,
      "step": 20
    },
    {
      "epoch": 0.0655993752440453,
      "grad_norm": 29.138015747070312,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.7419,
      "step": 21
    },
    {
      "epoch": 0.06872315501757126,
      "grad_norm": 36.97837829589844,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8219,
      "step": 22
    },
    {
      "epoch": 0.07184693479109723,
      "grad_norm": 33.30280303955078,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.7936,
      "step": 23
    },
    {
      "epoch": 0.07497071456462319,
      "grad_norm": 34.63959884643555,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.8485,
      "step": 24
    },
    {
      "epoch": 0.07809449433814916,
      "grad_norm": 31.568161010742188,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.7821,
      "step": 25
    },
    {
      "epoch": 0.07809449433814916,
      "eval_loss": 0.7292673587799072,
      "eval_runtime": 62.1065,
      "eval_samples_per_second": 34.731,
      "eval_steps_per_second": 4.347,
      "step": 25
    },
    {
      "epoch": 0.08121827411167512,
      "grad_norm": 20.802223205566406,
      "learning_rate": 5e-05,
      "loss": 0.614,
      "step": 26
    },
    {
      "epoch": 0.0843420538852011,
      "grad_norm": 25.634445190429688,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.6549,
      "step": 27
    },
    {
      "epoch": 0.08746583365872707,
      "grad_norm": 24.01685905456543,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.7213,
      "step": 28
    },
    {
      "epoch": 0.09058961343225302,
      "grad_norm": 25.094823837280273,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.6263,
      "step": 29
    },
    {
      "epoch": 0.093713393205779,
      "grad_norm": 25.876249313354492,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.679,
      "step": 30
    },
    {
      "epoch": 0.09683717297930496,
      "grad_norm": 21.759727478027344,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.6216,
      "step": 31
    },
    {
      "epoch": 0.09996095275283093,
      "grad_norm": 24.143407821655273,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.636,
      "step": 32
    },
    {
      "epoch": 0.10308473252635689,
      "grad_norm": 25.804513931274414,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.6894,
      "step": 33
    },
    {
      "epoch": 0.10620851229988286,
      "grad_norm": 27.420663833618164,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8195,
      "step": 34
    },
    {
      "epoch": 0.10933229207340882,
      "grad_norm": 29.06009292602539,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.7946,
      "step": 35
    },
    {
      "epoch": 0.11245607184693479,
      "grad_norm": 28.592594146728516,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.786,
      "step": 36
    },
    {
      "epoch": 0.11557985162046076,
      "grad_norm": 32.12931823730469,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.8086,
      "step": 37
    },
    {
      "epoch": 0.11870363139398672,
      "grad_norm": 23.032005310058594,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.69,
      "step": 38
    },
    {
      "epoch": 0.1218274111675127,
      "grad_norm": 16.44974136352539,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.4579,
      "step": 39
    },
    {
      "epoch": 0.12495119094103865,
      "grad_norm": 20.0357666015625,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.5951,
      "step": 40
    },
    {
      "epoch": 0.1280749707145646,
      "grad_norm": 21.83281898498535,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.6761,
      "step": 41
    },
    {
      "epoch": 0.1311987504880906,
      "grad_norm": 24.00539779663086,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.6549,
      "step": 42
    },
    {
      "epoch": 0.13432253026161656,
      "grad_norm": 26.342254638671875,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.6536,
      "step": 43
    },
    {
      "epoch": 0.13744631003514252,
      "grad_norm": 24.765623092651367,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7236,
      "step": 44
    },
    {
      "epoch": 0.1405700898086685,
      "grad_norm": 27.13953399658203,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.7191,
      "step": 45
    },
    {
      "epoch": 0.14369386958219446,
      "grad_norm": 23.938737869262695,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.6521,
      "step": 46
    },
    {
      "epoch": 0.14681764935572042,
      "grad_norm": 41.53923416137695,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.709,
      "step": 47
    },
    {
      "epoch": 0.14994142912924638,
      "grad_norm": 26.58255386352539,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.6992,
      "step": 48
    },
    {
      "epoch": 0.15306520890277237,
      "grad_norm": 29.302122116088867,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.7472,
      "step": 49
    },
    {
      "epoch": 0.15618898867629832,
      "grad_norm": 29.7325496673584,
      "learning_rate": 0.0,
      "loss": 0.85,
      "step": 50
    },
    {
      "epoch": 0.15618898867629832,
      "eval_loss": 0.6981587409973145,
      "eval_runtime": 62.0993,
      "eval_samples_per_second": 34.735,
      "eval_steps_per_second": 4.348,
      "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": 5.658021338284032e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}