{
  "best_metric": 0.14158989489078522,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.016909029421711193,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006763611768684477,
      "grad_norm": 9.08575439453125,
      "learning_rate": 2e-05,
      "loss": 4.5965,
      "step": 1
    },
    {
      "epoch": 0.0006763611768684477,
      "eval_loss": 4.714530944824219,
      "eval_runtime": 14.2557,
      "eval_samples_per_second": 174.667,
      "eval_steps_per_second": 21.886,
      "step": 1
    },
    {
      "epoch": 0.0013527223537368955,
      "grad_norm": 9.087392807006836,
      "learning_rate": 4e-05,
      "loss": 4.6119,
      "step": 2
    },
    {
      "epoch": 0.002029083530605343,
      "grad_norm": 8.959595680236816,
      "learning_rate": 6e-05,
      "loss": 4.6058,
      "step": 3
    },
    {
      "epoch": 0.002705444707473791,
      "grad_norm": 8.635147094726562,
      "learning_rate": 8e-05,
      "loss": 4.5416,
      "step": 4
    },
    {
      "epoch": 0.0033818058843422386,
      "grad_norm": 9.559680938720703,
      "learning_rate": 0.0001,
      "loss": 4.228,
      "step": 5
    },
    {
      "epoch": 0.0033818058843422386,
      "eval_loss": 3.8396589756011963,
      "eval_runtime": 12.4519,
      "eval_samples_per_second": 199.969,
      "eval_steps_per_second": 25.056,
      "step": 5
    },
    {
      "epoch": 0.004058167061210686,
      "grad_norm": 8.38050365447998,
      "learning_rate": 0.00012,
      "loss": 3.9577,
      "step": 6
    },
    {
      "epoch": 0.0047345282380791345,
      "grad_norm": 9.55387020111084,
      "learning_rate": 0.00014,
      "loss": 3.2044,
      "step": 7
    },
    {
      "epoch": 0.005410889414947582,
      "grad_norm": 9.679418563842773,
      "learning_rate": 0.00016,
      "loss": 2.7643,
      "step": 8
    },
    {
      "epoch": 0.00608725059181603,
      "grad_norm": 10.315975189208984,
      "learning_rate": 0.00018,
      "loss": 2.1942,
      "step": 9
    },
    {
      "epoch": 0.006763611768684477,
      "grad_norm": 9.06428337097168,
      "learning_rate": 0.0002,
      "loss": 1.5751,
      "step": 10
    },
    {
      "epoch": 0.006763611768684477,
      "eval_loss": 1.0617578029632568,
      "eval_runtime": 12.4016,
      "eval_samples_per_second": 200.781,
      "eval_steps_per_second": 25.158,
      "step": 10
    },
    {
      "epoch": 0.0074399729455529254,
      "grad_norm": 6.420353412628174,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.1378,
      "step": 11
    },
    {
      "epoch": 0.008116334122421373,
      "grad_norm": 7.892561912536621,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.8164,
      "step": 12
    },
    {
      "epoch": 0.00879269529928982,
      "grad_norm": 2.6381897926330566,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.2681,
      "step": 13
    },
    {
      "epoch": 0.009469056476158269,
      "grad_norm": 1.4537419080734253,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.38,
      "step": 14
    },
    {
      "epoch": 0.010145417653026716,
      "grad_norm": 2.559450149536133,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.2357,
      "step": 15
    },
    {
      "epoch": 0.010145417653026716,
      "eval_loss": 0.2033427357673645,
      "eval_runtime": 12.442,
      "eval_samples_per_second": 200.128,
      "eval_steps_per_second": 25.076,
      "step": 15
    },
    {
      "epoch": 0.010821778829895164,
      "grad_norm": 2.0941014289855957,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.217,
      "step": 16
    },
    {
      "epoch": 0.011498140006763611,
      "grad_norm": 0.9307464957237244,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0343,
      "step": 17
    },
    {
      "epoch": 0.01217450118363206,
      "grad_norm": 3.1173644065856934,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.2368,
      "step": 18
    },
    {
      "epoch": 0.012850862360500507,
      "grad_norm": 4.499870300292969,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.1805,
      "step": 19
    },
    {
      "epoch": 0.013527223537368955,
      "grad_norm": 2.9719085693359375,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.2002,
      "step": 20
    },
    {
      "epoch": 0.013527223537368955,
      "eval_loss": 0.14818401634693146,
      "eval_runtime": 12.379,
      "eval_samples_per_second": 201.148,
      "eval_steps_per_second": 25.204,
      "step": 20
    },
    {
      "epoch": 0.014203584714237404,
      "grad_norm": 1.814172625541687,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.1932,
      "step": 21
    },
    {
      "epoch": 0.014879945891105851,
      "grad_norm": 1.426396131515503,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0932,
      "step": 22
    },
    {
      "epoch": 0.015556307067974298,
      "grad_norm": 1.169958472251892,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.1249,
      "step": 23
    },
    {
      "epoch": 0.016232668244842745,
      "grad_norm": 1.2674089670181274,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.08,
      "step": 24
    },
    {
      "epoch": 0.016909029421711193,
      "grad_norm": 1.5442484617233276,
      "learning_rate": 0.0,
      "loss": 0.1493,
      "step": 25
    },
    {
      "epoch": 0.016909029421711193,
      "eval_loss": 0.14158989489078522,
      "eval_runtime": 12.4618,
      "eval_samples_per_second": 199.811,
      "eval_steps_per_second": 25.037,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 1079587723280384.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}