{
  "best_metric": 1.3032262325286865,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.1052631578947367,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 3.4167122840881348,
      "learning_rate": 5e-05,
      "loss": 2.316,
      "step": 1
    },
    {
      "epoch": 0.042105263157894736,
      "eval_loss": 2.7811999320983887,
      "eval_runtime": 11.7019,
      "eval_samples_per_second": 13.673,
      "eval_steps_per_second": 1.709,
      "step": 1
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 4.304935455322266,
      "learning_rate": 0.0001,
      "loss": 2.6399,
      "step": 2
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 3.3157570362091064,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.3477,
      "step": 3
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 2.925718069076538,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.1867,
      "step": 4
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 2.5918376445770264,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.9326,
      "step": 5
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 3.061896800994873,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.7646,
      "step": 6
    },
    {
      "epoch": 0.29473684210526313,
      "grad_norm": 2.938070297241211,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.7371,
      "step": 7
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 2.8561928272247314,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6995,
      "step": 8
    },
    {
      "epoch": 0.37894736842105264,
      "grad_norm": 2.5507919788360596,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.5824,
      "step": 9
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 2.578340768814087,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6718,
      "step": 10
    },
    {
      "epoch": 0.4631578947368421,
      "grad_norm": 2.787281036376953,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.59,
      "step": 11
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 2.2704641819000244,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.4823,
      "step": 12
    },
    {
      "epoch": 0.5473684210526316,
      "grad_norm": 1.7357639074325562,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.4888,
      "step": 13
    },
    {
      "epoch": 0.5894736842105263,
      "grad_norm": 1.5730212926864624,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5301,
      "step": 14
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 1.6096115112304688,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.4074,
      "step": 15
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 1.5140055418014526,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.3359,
      "step": 16
    },
    {
      "epoch": 0.7157894736842105,
      "grad_norm": 1.863604187965393,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.4116,
      "step": 17
    },
    {
      "epoch": 0.7578947368421053,
      "grad_norm": 1.4862691164016724,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.406,
      "step": 18
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.457043170928955,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.391,
      "step": 19
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 1.5490152835845947,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.452,
      "step": 20
    },
    {
      "epoch": 0.8842105263157894,
      "grad_norm": 1.6143372058868408,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.3873,
      "step": 21
    },
    {
      "epoch": 0.9263157894736842,
      "grad_norm": 1.7954074144363403,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.3495,
      "step": 22
    },
    {
      "epoch": 0.968421052631579,
      "grad_norm": 1.6617047786712646,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.141,
      "step": 23
    },
    {
      "epoch": 1.0105263157894737,
      "grad_norm": 1.9556751251220703,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.5716,
      "step": 24
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 1.6083061695098877,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.1135,
      "step": 25
    },
    {
      "epoch": 1.0526315789473684,
      "eval_loss": 1.325190544128418,
      "eval_runtime": 11.6789,
      "eval_samples_per_second": 13.7,
      "eval_steps_per_second": 1.712,
      "step": 25
    },
    {
      "epoch": 1.0947368421052632,
      "grad_norm": 1.974260926246643,
      "learning_rate": 5e-05,
      "loss": 1.148,
      "step": 26
    },
    {
      "epoch": 1.1368421052631579,
      "grad_norm": 1.4720616340637207,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.0633,
      "step": 27
    },
    {
      "epoch": 1.1789473684210527,
      "grad_norm": 1.7669459581375122,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.048,
      "step": 28
    },
    {
      "epoch": 1.2210526315789474,
      "grad_norm": 1.6160643100738525,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.9753,
      "step": 29
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 1.6384661197662354,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.1493,
      "step": 30
    },
    {
      "epoch": 1.305263157894737,
      "grad_norm": 2.024684190750122,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.2016,
      "step": 31
    },
    {
      "epoch": 1.3473684210526315,
      "grad_norm": 1.9289146661758423,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.1616,
      "step": 32
    },
    {
      "epoch": 1.3894736842105262,
      "grad_norm": 1.6927998065948486,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.0759,
      "step": 33
    },
    {
      "epoch": 1.431578947368421,
      "grad_norm": 2.006455183029175,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0973,
      "step": 34
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 1.6544878482818604,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.9614,
      "step": 35
    },
    {
      "epoch": 1.5157894736842106,
      "grad_norm": 1.626354455947876,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.1881,
      "step": 36
    },
    {
      "epoch": 1.5578947368421052,
      "grad_norm": 2.013545036315918,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.1426,
      "step": 37
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.9105583429336548,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.0589,
      "step": 38
    },
    {
      "epoch": 1.6421052631578947,
      "grad_norm": 2.017082929611206,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.0208,
      "step": 39
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 1.7792869806289673,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.9717,
      "step": 40
    },
    {
      "epoch": 1.7263157894736842,
      "grad_norm": 1.467813491821289,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.72,
      "step": 41
    },
    {
      "epoch": 1.768421052631579,
      "grad_norm": 1.8371200561523438,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.3269,
      "step": 42
    },
    {
      "epoch": 1.8105263157894735,
      "grad_norm": 2.0505716800689697,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.2772,
      "step": 43
    },
    {
      "epoch": 1.8526315789473684,
      "grad_norm": 1.8300319910049438,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.0593,
      "step": 44
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 1.950974941253662,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.0374,
      "step": 45
    },
    {
      "epoch": 1.936842105263158,
      "grad_norm": 1.9078106880187988,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.9833,
      "step": 46
    },
    {
      "epoch": 1.9789473684210526,
      "grad_norm": 2.3406636714935303,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.2057,
      "step": 47
    },
    {
      "epoch": 2.0210526315789474,
      "grad_norm": 1.7886607646942139,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.1742,
      "step": 48
    },
    {
      "epoch": 2.0631578947368423,
      "grad_norm": 1.9798243045806885,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.0736,
      "step": 49
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 1.969590187072754,
      "learning_rate": 0.0,
      "loss": 0.9799,
      "step": 50
    },
    {
      "epoch": 2.1052631578947367,
      "eval_loss": 1.3032262325286865,
      "eval_runtime": 11.6161,
      "eval_samples_per_second": 13.774,
      "eval_steps_per_second": 1.722,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 6.174479344467968e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}