{
  "best_metric": 0.6072157621383667,
  "best_model_checkpoint": "miner_id_24/checkpoint-350",
  "epoch": 0.013625569354148012,
  "eval_steps": 50,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.8930198154708606e-05,
      "eval_loss": 1.4984747171401978,
      "eval_runtime": 983.3833,
      "eval_samples_per_second": 10.999,
      "eval_steps_per_second": 2.75,
      "step": 1
    },
    {
      "epoch": 0.00038930198154708606,
      "grad_norm": 1.072473168373108,
      "learning_rate": 4.36e-05,
      "loss": 1.3482,
      "step": 10
    },
    {
      "epoch": 0.0007786039630941721,
      "grad_norm": 0.46352726221084595,
      "learning_rate": 8.72e-05,
      "loss": 0.963,
      "step": 20
    },
    {
      "epoch": 0.0011679059446412581,
      "grad_norm": 0.410412460565567,
      "learning_rate": 0.0001308,
      "loss": 0.8434,
      "step": 30
    },
    {
      "epoch": 0.0015572079261883442,
      "grad_norm": 0.5032802224159241,
      "learning_rate": 0.0001744,
      "loss": 0.7283,
      "step": 40
    },
    {
      "epoch": 0.0019465099077354304,
      "grad_norm": 0.4477519989013672,
      "learning_rate": 0.000218,
      "loss": 0.5009,
      "step": 50
    },
    {
      "epoch": 0.0019465099077354304,
      "eval_loss": 0.7281811833381653,
      "eval_runtime": 983.314,
      "eval_samples_per_second": 11.0,
      "eval_steps_per_second": 2.75,
      "step": 50
    },
    {
      "epoch": 0.0023358118892825163,
      "grad_norm": 0.27404654026031494,
      "learning_rate": 0.00021773448147832086,
      "loss": 0.7374,
      "step": 60
    },
    {
      "epoch": 0.0027251138708296024,
      "grad_norm": 0.2829911708831787,
      "learning_rate": 0.0002169392194928312,
      "loss": 0.7182,
      "step": 70
    },
    {
      "epoch": 0.0031144158523766885,
      "grad_norm": 0.32201188802719116,
      "learning_rate": 0.00021561808847998484,
      "loss": 0.7413,
      "step": 80
    },
    {
      "epoch": 0.0035037178339237746,
      "grad_norm": 0.26223206520080566,
      "learning_rate": 0.00021377752485727676,
      "loss": 0.6938,
      "step": 90
    },
    {
      "epoch": 0.0038930198154708607,
      "grad_norm": 0.33605754375457764,
      "learning_rate": 0.00021142649566566402,
      "loss": 0.4976,
      "step": 100
    },
    {
      "epoch": 0.0038930198154708607,
      "eval_loss": 0.6968406438827515,
      "eval_runtime": 985.4328,
      "eval_samples_per_second": 10.976,
      "eval_steps_per_second": 2.744,
      "step": 100
    },
    {
      "epoch": 0.004282321797017947,
      "grad_norm": 0.2566376030445099,
      "learning_rate": 0.0002085764548830435,
      "loss": 0.7146,
      "step": 110
    },
    {
      "epoch": 0.0046716237785650325,
      "grad_norm": 0.26375940442085266,
      "learning_rate": 0.00020524128762162305,
      "loss": 0.7166,
      "step": 120
    },
    {
      "epoch": 0.005060925760112119,
      "grad_norm": 0.3361421525478363,
      "learning_rate": 0.00020143724248105043,
      "loss": 0.7425,
      "step": 130
    },
    {
      "epoch": 0.005450227741659205,
      "grad_norm": 0.2415134310722351,
      "learning_rate": 0.0001971828523868693,
      "loss": 0.6897,
      "step": 140
    },
    {
      "epoch": 0.005839529723206291,
      "grad_norm": 0.31964412331581116,
      "learning_rate": 0.0001924988442999686,
      "loss": 0.4738,
      "step": 150
    },
    {
      "epoch": 0.005839529723206291,
      "eval_loss": 0.6815662384033203,
      "eval_runtime": 985.283,
      "eval_samples_per_second": 10.978,
      "eval_steps_per_second": 2.744,
      "step": 150
    },
    {
      "epoch": 0.006228831704753377,
      "grad_norm": 0.2809494733810425,
      "learning_rate": 0.00018740803823691298,
      "loss": 0.7386,
      "step": 160
    },
    {
      "epoch": 0.0066181336863004635,
      "grad_norm": 0.29278141260147095,
      "learning_rate": 0.00018193523609311556,
      "loss": 0.6875,
      "step": 170
    },
    {
      "epoch": 0.007007435667847549,
      "grad_norm": 0.25264835357666016,
      "learning_rate": 0.00017610710081049675,
      "loss": 0.6877,
      "step": 180
    },
    {
      "epoch": 0.007396737649394636,
      "grad_norm": 0.2684813141822815,
      "learning_rate": 0.00016995202647831142,
      "loss": 0.6176,
      "step": 190
    },
    {
      "epoch": 0.007786039630941721,
      "grad_norm": 0.3800605833530426,
      "learning_rate": 0.00016350000000000002,
      "loss": 0.4925,
      "step": 200
    },
    {
      "epoch": 0.007786039630941721,
      "eval_loss": 0.6556968092918396,
      "eval_runtime": 984.222,
      "eval_samples_per_second": 10.989,
      "eval_steps_per_second": 2.747,
      "step": 200
    },
    {
      "epoch": 0.008175341612488807,
      "grad_norm": 0.30634957551956177,
      "learning_rate": 0.00015678245500000943,
      "loss": 0.7506,
      "step": 210
    },
    {
      "epoch": 0.008564643594035894,
      "grad_norm": 0.2725326418876648,
      "learning_rate": 0.00014983211868233444,
      "loss": 0.7223,
      "step": 220
    },
    {
      "epoch": 0.00895394557558298,
      "grad_norm": 0.24513450264930725,
      "learning_rate": 0.00014268285238686927,
      "loss": 0.6488,
      "step": 230
    },
    {
      "epoch": 0.009343247557130065,
      "grad_norm": 0.2535250782966614,
      "learning_rate": 0.00013536948662036378,
      "loss": 0.6763,
      "step": 240
    },
    {
      "epoch": 0.009732549538677152,
      "grad_norm": 0.33992090821266174,
      "learning_rate": 0.00012792765136569544,
      "loss": 0.4751,
      "step": 250
    },
    {
      "epoch": 0.009732549538677152,
      "eval_loss": 0.6427889466285706,
      "eval_runtime": 985.6091,
      "eval_samples_per_second": 10.974,
      "eval_steps_per_second": 2.743,
      "step": 250
    },
    {
      "epoch": 0.010121851520224238,
      "grad_norm": 0.30529460310935974,
      "learning_rate": 0.00012039360249617425,
      "loss": 0.6539,
      "step": 260
    },
    {
      "epoch": 0.010511153501771325,
      "grad_norm": 0.307180792093277,
      "learning_rate": 0.00011280404514057264,
      "loss": 0.7222,
      "step": 270
    },
    {
      "epoch": 0.01090045548331841,
      "grad_norm": 0.2459094226360321,
      "learning_rate": 0.00010519595485942743,
      "loss": 0.6672,
      "step": 280
    },
    {
      "epoch": 0.011289757464865496,
      "grad_norm": 0.3001365065574646,
      "learning_rate": 9.76063975038258e-05,
      "loss": 0.655,
      "step": 290
    },
    {
      "epoch": 0.011679059446412583,
      "grad_norm": 0.29161515831947327,
      "learning_rate": 9.00723486343046e-05,
      "loss": 0.4496,
      "step": 300
    },
    {
      "epoch": 0.011679059446412583,
      "eval_loss": 0.6232911348342896,
      "eval_runtime": 983.7858,
      "eval_samples_per_second": 10.994,
      "eval_steps_per_second": 2.749,
      "step": 300
    },
    {
      "epoch": 0.012068361427959669,
      "grad_norm": 0.2087341547012329,
      "learning_rate": 8.263051337963623e-05,
      "loss": 0.6382,
      "step": 310
    },
    {
      "epoch": 0.012457663409506754,
      "grad_norm": 0.257894366979599,
      "learning_rate": 7.531714761313074e-05,
      "loss": 0.6506,
      "step": 320
    },
    {
      "epoch": 0.01284696539105384,
      "grad_norm": 0.2307630479335785,
      "learning_rate": 6.816788131766559e-05,
      "loss": 0.6495,
      "step": 330
    },
    {
      "epoch": 0.013236267372600927,
      "grad_norm": 0.25712043046951294,
      "learning_rate": 6.121754499999055e-05,
      "loss": 0.5836,
      "step": 340
    },
    {
      "epoch": 0.013625569354148012,
      "grad_norm": 0.2887607514858246,
      "learning_rate": 5.450000000000003e-05,
      "loss": 0.4547,
      "step": 350
    },
    {
      "epoch": 0.013625569354148012,
      "eval_loss": 0.6072157621383667,
      "eval_runtime": 983.5524,
      "eval_samples_per_second": 10.997,
      "eval_steps_per_second": 2.749,
      "step": 350
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.01689564594176e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}