{
  "best_metric": 3.8060593605041504,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.012839236707377747,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025678473414755495,
      "grad_norm": 9.503480911254883,
      "learning_rate": 5e-05,
      "loss": 5.046,
      "step": 1
    },
    {
      "epoch": 0.00025678473414755495,
      "eval_loss": 6.353982925415039,
      "eval_runtime": 2685.0031,
      "eval_samples_per_second": 9.771,
      "eval_steps_per_second": 1.222,
      "step": 1
    },
    {
      "epoch": 0.0005135694682951099,
      "grad_norm": 8.488868713378906,
      "learning_rate": 0.0001,
      "loss": 5.3566,
      "step": 2
    },
    {
      "epoch": 0.0007703542024426647,
      "grad_norm": 6.0592827796936035,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.7974,
      "step": 3
    },
    {
      "epoch": 0.0010271389365902198,
      "grad_norm": 1.7798657417297363,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.3814,
      "step": 4
    },
    {
      "epoch": 0.0012839236707377745,
      "grad_norm": 1.2865231037139893,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.1987,
      "step": 5
    },
    {
      "epoch": 0.0015407084048853295,
      "grad_norm": 1.3466218709945679,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.2718,
      "step": 6
    },
    {
      "epoch": 0.0017974931390328844,
      "grad_norm": 1.229759931564331,
      "learning_rate": 9.73465064747553e-05,
      "loss": 4.1401,
      "step": 7
    },
    {
      "epoch": 0.0020542778731804396,
      "grad_norm": 1.12930166721344,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.1515,
      "step": 8
    },
    {
      "epoch": 0.0023110626073279943,
      "grad_norm": 1.30575692653656,
      "learning_rate": 9.484363707663442e-05,
      "loss": 4.2748,
      "step": 9
    },
    {
      "epoch": 0.002567847341475549,
      "grad_norm": 1.1742302179336548,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.3062,
      "step": 10
    },
    {
      "epoch": 0.0028246320756231042,
      "grad_norm": 1.5008646249771118,
      "learning_rate": 9.157348061512727e-05,
      "loss": 4.4308,
      "step": 11
    },
    {
      "epoch": 0.003081416809770659,
      "grad_norm": 2.1297407150268555,
      "learning_rate": 8.966766701456177e-05,
      "loss": 4.8561,
      "step": 12
    },
    {
      "epoch": 0.003338201543918214,
      "grad_norm": 2.1846420764923096,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.725,
      "step": 13
    },
    {
      "epoch": 0.003594986278065769,
      "grad_norm": 2.437375783920288,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.7061,
      "step": 14
    },
    {
      "epoch": 0.003851771012213324,
      "grad_norm": 1.4832355976104736,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.7094,
      "step": 15
    },
    {
      "epoch": 0.004108555746360879,
      "grad_norm": 0.9080920815467834,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.7777,
      "step": 16
    },
    {
      "epoch": 0.004365340480508434,
      "grad_norm": 0.7947410941123962,
      "learning_rate": 7.777851165098012e-05,
      "loss": 3.8381,
      "step": 17
    },
    {
      "epoch": 0.004622125214655989,
      "grad_norm": 0.9278391003608704,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.9257,
      "step": 18
    },
    {
      "epoch": 0.004878909948803543,
      "grad_norm": 0.9925792217254639,
      "learning_rate": 7.211443451095007e-05,
      "loss": 3.889,
      "step": 19
    },
    {
      "epoch": 0.005135694682951098,
      "grad_norm": 1.056364893913269,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.0978,
      "step": 20
    },
    {
      "epoch": 0.005392479417098654,
      "grad_norm": 1.086922526359558,
      "learning_rate": 6.607197326515808e-05,
      "loss": 4.1079,
      "step": 21
    },
    {
      "epoch": 0.0056492641512462085,
      "grad_norm": 1.101845145225525,
      "learning_rate": 6.294095225512603e-05,
      "loss": 4.108,
      "step": 22
    },
    {
      "epoch": 0.005906048885393763,
      "grad_norm": 1.2063024044036865,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 4.1103,
      "step": 23
    },
    {
      "epoch": 0.006162833619541318,
      "grad_norm": 1.4133981466293335,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 4.3308,
      "step": 24
    },
    {
      "epoch": 0.0064196183536888735,
      "grad_norm": 2.3334479331970215,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.708,
      "step": 25
    },
    {
      "epoch": 0.0064196183536888735,
      "eval_loss": 3.9213130474090576,
      "eval_runtime": 2685.7074,
      "eval_samples_per_second": 9.769,
      "eval_steps_per_second": 1.221,
      "step": 25
    },
    {
      "epoch": 0.006676403087836428,
      "grad_norm": 1.3409721851348877,
      "learning_rate": 5e-05,
      "loss": 3.4359,
      "step": 26
    },
    {
      "epoch": 0.006933187821983983,
      "grad_norm": 1.558974027633667,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 3.5878,
      "step": 27
    },
    {
      "epoch": 0.007189972556131538,
      "grad_norm": 1.5054473876953125,
      "learning_rate": 4.347369038899744e-05,
      "loss": 3.6143,
      "step": 28
    },
    {
      "epoch": 0.007446757290279093,
      "grad_norm": 1.3647345304489136,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 3.7567,
      "step": 29
    },
    {
      "epoch": 0.007703542024426648,
      "grad_norm": 1.1692473888397217,
      "learning_rate": 3.705904774487396e-05,
      "loss": 3.772,
      "step": 30
    },
    {
      "epoch": 0.007960326758574202,
      "grad_norm": 0.9748162031173706,
      "learning_rate": 3.392802673484193e-05,
      "loss": 3.7938,
      "step": 31
    },
    {
      "epoch": 0.008217111492721758,
      "grad_norm": 0.8939160108566284,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.9191,
      "step": 32
    },
    {
      "epoch": 0.008473896226869313,
      "grad_norm": 0.808001697063446,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 3.9843,
      "step": 33
    },
    {
      "epoch": 0.008730680961016868,
      "grad_norm": 0.8469786047935486,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.9302,
      "step": 34
    },
    {
      "epoch": 0.008987465695164423,
      "grad_norm": 0.9428398609161377,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 3.9169,
      "step": 35
    },
    {
      "epoch": 0.009244250429311977,
      "grad_norm": 1.1682770252227783,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 4.044,
      "step": 36
    },
    {
      "epoch": 0.009501035163459532,
      "grad_norm": 1.7911386489868164,
      "learning_rate": 1.703270924499656e-05,
      "loss": 4.1906,
      "step": 37
    },
    {
      "epoch": 0.009757819897607087,
      "grad_norm": 0.841162919998169,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.4853,
      "step": 38
    },
    {
      "epoch": 0.010014604631754642,
      "grad_norm": 0.656592071056366,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 3.4707,
      "step": 39
    },
    {
      "epoch": 0.010271389365902196,
      "grad_norm": 0.6998878717422485,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 3.5523,
      "step": 40
    },
    {
      "epoch": 0.010528174100049753,
      "grad_norm": 0.6899571418762207,
      "learning_rate": 8.426519384872733e-06,
      "loss": 3.6552,
      "step": 41
    },
    {
      "epoch": 0.010784958834197307,
      "grad_norm": 0.6952070593833923,
      "learning_rate": 6.698729810778065e-06,
      "loss": 3.6545,
      "step": 42
    },
    {
      "epoch": 0.011041743568344862,
      "grad_norm": 0.7949510216712952,
      "learning_rate": 5.156362923365588e-06,
      "loss": 3.8045,
      "step": 43
    },
    {
      "epoch": 0.011298528302492417,
      "grad_norm": 0.7673659324645996,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.8022,
      "step": 44
    },
    {
      "epoch": 0.011555313036639972,
      "grad_norm": 0.7975015640258789,
      "learning_rate": 2.653493525244721e-06,
      "loss": 3.8132,
      "step": 45
    },
    {
      "epoch": 0.011812097770787526,
      "grad_norm": 0.8527703285217285,
      "learning_rate": 1.70370868554659e-06,
      "loss": 3.921,
      "step": 46
    },
    {
      "epoch": 0.012068882504935081,
      "grad_norm": 0.9256014227867126,
      "learning_rate": 9.607359798384785e-07,
      "loss": 3.9535,
      "step": 47
    },
    {
      "epoch": 0.012325667239082636,
      "grad_norm": 1.11979079246521,
      "learning_rate": 4.277569313094809e-07,
      "loss": 3.8955,
      "step": 48
    },
    {
      "epoch": 0.012582451973230192,
      "grad_norm": 1.5714532136917114,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 4.1461,
      "step": 49
    },
    {
      "epoch": 0.012839236707377747,
      "grad_norm": 2.802791118621826,
      "learning_rate": 0.0,
      "loss": 4.5027,
      "step": 50
    },
    {
      "epoch": 0.012839236707377747,
      "eval_loss": 3.8060593605041504,
      "eval_runtime": 2685.47,
      "eval_samples_per_second": 9.77,
      "eval_steps_per_second": 1.221,
      "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": 6.631381723512832e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}