{
  "best_metric": 1.1817097663879395,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 57,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 5.714753150939941,
      "learning_rate": 1e-05,
      "loss": 1.8152,
      "step": 1
    },
    {
      "epoch": 0.05263157894736842,
      "eval_loss": 2.4003829956054688,
      "eval_runtime": 1.4264,
      "eval_samples_per_second": 22.434,
      "eval_steps_per_second": 5.608,
      "step": 1
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 7.170670986175537,
      "learning_rate": 2e-05,
      "loss": 2.2306,
      "step": 2
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 7.550725936889648,
      "learning_rate": 3e-05,
      "loss": 2.4062,
      "step": 3
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 6.948938846588135,
      "learning_rate": 4e-05,
      "loss": 2.2318,
      "step": 4
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 6.083446502685547,
      "learning_rate": 5e-05,
      "loss": 1.2827,
      "step": 5
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 5.913970470428467,
      "learning_rate": 6e-05,
      "loss": 1.371,
      "step": 6
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 5.238213062286377,
      "learning_rate": 7e-05,
      "loss": 1.5717,
      "step": 7
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 5.236299991607666,
      "learning_rate": 8e-05,
      "loss": 1.3621,
      "step": 8
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 2.496065378189087,
      "learning_rate": 9e-05,
      "loss": 1.143,
      "step": 9
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 2.8024847507476807,
      "learning_rate": 0.0001,
      "loss": 1.2504,
      "step": 10
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 3.0046355724334717,
      "learning_rate": 9.988834393115767e-05,
      "loss": 1.2389,
      "step": 11
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 3.0082316398620605,
      "learning_rate": 9.9553874407739e-05,
      "loss": 1.2786,
      "step": 12
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 2.118980646133423,
      "learning_rate": 9.899808525182935e-05,
      "loss": 1.2954,
      "step": 13
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 2.031477689743042,
      "learning_rate": 9.822345875271883e-05,
      "loss": 0.9797,
      "step": 14
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 2.3263585567474365,
      "learning_rate": 9.723345458039594e-05,
      "loss": 1.2429,
      "step": 15
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 2.6109251976013184,
      "learning_rate": 9.603249433382144e-05,
      "loss": 1.2715,
      "step": 16
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 1.9126944541931152,
      "learning_rate": 9.462594179299406e-05,
      "loss": 1.109,
      "step": 17
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 1.9470820426940918,
      "learning_rate": 9.302007896300698e-05,
      "loss": 0.8364,
      "step": 18
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.2464423179626465,
      "learning_rate": 9.122207801708802e-05,
      "loss": 1.1474,
      "step": 19
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 1.3209232091903687,
      "learning_rate": 8.923996926393305e-05,
      "loss": 0.9024,
      "step": 20
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 1.6488995552062988,
      "learning_rate": 8.708260528239788e-05,
      "loss": 0.8782,
      "step": 21
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 1.6716432571411133,
      "learning_rate": 8.475962138373213e-05,
      "loss": 0.8521,
      "step": 22
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 2.1739349365234375,
      "learning_rate": 8.228139257794012e-05,
      "loss": 0.9933,
      "step": 23
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 1.4730769395828247,
      "learning_rate": 7.965898723646776e-05,
      "loss": 0.7727,
      "step": 24
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 1.5656155347824097,
      "learning_rate": 7.690411765816864e-05,
      "loss": 0.8817,
      "step": 25
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": 2.1506686210632324,
      "learning_rate": 7.402908775933419e-05,
      "loss": 1.0105,
      "step": 26
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 2.0018692016601562,
      "learning_rate": 7.104673812141675e-05,
      "loss": 0.7928,
      "step": 27
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 1.695372223854065,
      "learning_rate": 6.797038864187564e-05,
      "loss": 0.8946,
      "step": 28
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 1.8244125843048096,
      "learning_rate": 6.481377904428171e-05,
      "loss": 0.8284,
      "step": 29
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 1.7244329452514648,
      "learning_rate": 6.159100751337642e-05,
      "loss": 0.7186,
      "step": 30
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 2.0243990421295166,
      "learning_rate": 5.831646772915651e-05,
      "loss": 0.8093,
      "step": 31
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 1.6297742128372192,
      "learning_rate": 5.5004784581204927e-05,
      "loss": 0.8709,
      "step": 32
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 1.8952237367630005,
      "learning_rate": 5.167074885038373e-05,
      "loss": 0.8952,
      "step": 33
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": 1.7852932214736938,
      "learning_rate": 4.832925114961629e-05,
      "loss": 0.7839,
      "step": 34
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 2.1525204181671143,
      "learning_rate": 4.4995215418795085e-05,
      "loss": 0.8763,
      "step": 35
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 1.8198322057724,
      "learning_rate": 4.1683532270843504e-05,
      "loss": 0.8486,
      "step": 36
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 1.5310567617416382,
      "learning_rate": 3.840899248662358e-05,
      "loss": 0.5251,
      "step": 37
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.179245710372925,
      "learning_rate": 3.5186220955718306e-05,
      "loss": 0.8381,
      "step": 38
    },
    {
      "epoch": 2.0526315789473686,
      "grad_norm": 1.1245640516281128,
      "learning_rate": 3.202961135812437e-05,
      "loss": 0.6164,
      "step": 39
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 1.41566002368927,
      "learning_rate": 2.895326187858326e-05,
      "loss": 0.6059,
      "step": 40
    },
    {
      "epoch": 2.1578947368421053,
      "grad_norm": 1.5508769750595093,
      "learning_rate": 2.5970912240665813e-05,
      "loss": 0.6455,
      "step": 41
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 1.7090671062469482,
      "learning_rate": 2.3095882341831372e-05,
      "loss": 0.5792,
      "step": 42
    },
    {
      "epoch": 2.263157894736842,
      "grad_norm": 1.374485731124878,
      "learning_rate": 2.0341012763532243e-05,
      "loss": 0.6782,
      "step": 43
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 1.590584397315979,
      "learning_rate": 1.771860742205988e-05,
      "loss": 0.7556,
      "step": 44
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 1.459409236907959,
      "learning_rate": 1.5240378616267886e-05,
      "loss": 0.4689,
      "step": 45
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 1.5467756986618042,
      "learning_rate": 1.2917394717602121e-05,
      "loss": 0.4195,
      "step": 46
    },
    {
      "epoch": 2.473684210526316,
      "grad_norm": 1.3657021522521973,
      "learning_rate": 1.0760030736066951e-05,
      "loss": 0.4721,
      "step": 47
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 1.7539397478103638,
      "learning_rate": 8.777921982911996e-06,
      "loss": 0.5767,
      "step": 48
    },
    {
      "epoch": 2.5789473684210527,
      "grad_norm": 1.5453059673309326,
      "learning_rate": 6.979921036993042e-06,
      "loss": 0.6237,
      "step": 49
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 2.2058823108673096,
      "learning_rate": 5.374058207005944e-06,
      "loss": 0.6392,
      "step": 50
    },
    {
      "epoch": 2.6315789473684212,
      "eval_loss": 1.1817097663879395,
      "eval_runtime": 1.4393,
      "eval_samples_per_second": 22.234,
      "eval_steps_per_second": 5.558,
      "step": 50
    },
    {
      "epoch": 2.6842105263157894,
      "grad_norm": 1.3148783445358276,
      "learning_rate": 3.967505666178556e-06,
      "loss": 0.5752,
      "step": 51
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 1.693260669708252,
      "learning_rate": 2.7665454196040664e-06,
      "loss": 0.5934,
      "step": 52
    },
    {
      "epoch": 2.7894736842105265,
      "grad_norm": 1.6923569440841675,
      "learning_rate": 1.7765412472811771e-06,
      "loss": 0.6168,
      "step": 53
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 1.6930750608444214,
      "learning_rate": 1.0019147481706625e-06,
      "loss": 0.5091,
      "step": 54
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 1.4638423919677734,
      "learning_rate": 4.461255922609986e-07,
      "loss": 0.634,
      "step": 55
    },
    {
      "epoch": 2.9473684210526314,
      "grad_norm": 1.329147219657898,
      "learning_rate": 1.1165606884234181e-07,
      "loss": 0.4201,
      "step": 56
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.8009886741638184,
      "learning_rate": 0.0,
      "loss": 0.5192,
      "step": 57
    }
  ],
  "logging_steps": 1,
  "max_steps": 57,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 2.338589547115315e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}