{
  "best_metric": 0.042669691145420074,
  "best_model_checkpoint": "miner_id_24/checkpoint-1200",
  "epoch": 1.3592599584670568,
  "eval_steps": 200,
  "global_step": 1800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007551444213705871,
      "eval_loss": 0.3643783926963806,
      "eval_runtime": 87.2468,
      "eval_samples_per_second": 12.791,
      "eval_steps_per_second": 3.198,
      "step": 1
    },
    {
      "epoch": 0.037757221068529356,
      "grad_norm": 1.4100414514541626,
      "learning_rate": 5e-05,
      "loss": 0.1364,
      "step": 50
    },
    {
      "epoch": 0.07551444213705871,
      "grad_norm": 0.6465395092964172,
      "learning_rate": 0.0001,
      "loss": 0.0635,
      "step": 100
    },
    {
      "epoch": 0.11327166320558807,
      "grad_norm": 1.6140310764312744,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.047,
      "step": 150
    },
    {
      "epoch": 0.15102888427411743,
      "grad_norm": 2.0268421173095703,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0477,
      "step": 200
    },
    {
      "epoch": 0.15102888427411743,
      "eval_loss": 0.05864099785685539,
      "eval_runtime": 88.7167,
      "eval_samples_per_second": 12.579,
      "eval_steps_per_second": 3.145,
      "step": 200
    },
    {
      "epoch": 0.18878610534264678,
      "grad_norm": 1.6122969388961792,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0468,
      "step": 250
    },
    {
      "epoch": 0.22654332641117614,
      "grad_norm": 0.023569952696561813,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0393,
      "step": 300
    },
    {
      "epoch": 0.2643005474797055,
      "grad_norm": 0.6391419172286987,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.044,
      "step": 350
    },
    {
      "epoch": 0.30205776854823485,
      "grad_norm": 0.2637801766395569,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0349,
      "step": 400
    },
    {
      "epoch": 0.30205776854823485,
      "eval_loss": 0.048699330538511276,
      "eval_runtime": 88.8453,
      "eval_samples_per_second": 12.561,
      "eval_steps_per_second": 3.14,
      "step": 400
    },
    {
      "epoch": 0.3398149896167642,
      "grad_norm": 1.7430977821350098,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0443,
      "step": 450
    },
    {
      "epoch": 0.37757221068529356,
      "grad_norm": 0.3382541835308075,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0392,
      "step": 500
    },
    {
      "epoch": 0.4153294317538229,
      "grad_norm": 1.5577205419540405,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.0361,
      "step": 550
    },
    {
      "epoch": 0.4530866528223523,
      "grad_norm": 0.838959276676178,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0334,
      "step": 600
    },
    {
      "epoch": 0.4530866528223523,
      "eval_loss": 0.05116293579339981,
      "eval_runtime": 88.8487,
      "eval_samples_per_second": 12.561,
      "eval_steps_per_second": 3.14,
      "step": 600
    },
    {
      "epoch": 0.49084387389088163,
      "grad_norm": 1.6610183715820312,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0422,
      "step": 650
    },
    {
      "epoch": 0.528601094959411,
      "grad_norm": 1.1309680938720703,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0348,
      "step": 700
    },
    {
      "epoch": 0.5663583160279403,
      "grad_norm": 0.7380091547966003,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0404,
      "step": 750
    },
    {
      "epoch": 0.6041155370964697,
      "grad_norm": 0.2660733461380005,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0444,
      "step": 800
    },
    {
      "epoch": 0.6041155370964697,
      "eval_loss": 0.04871406406164169,
      "eval_runtime": 88.864,
      "eval_samples_per_second": 12.559,
      "eval_steps_per_second": 3.14,
      "step": 800
    },
    {
      "epoch": 0.641872758164999,
      "grad_norm": 0.5725349187850952,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0347,
      "step": 850
    },
    {
      "epoch": 0.6796299792335284,
      "grad_norm": 0.9907957911491394,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.035,
      "step": 900
    },
    {
      "epoch": 0.7173872003020577,
      "grad_norm": 0.7868975400924683,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0344,
      "step": 950
    },
    {
      "epoch": 0.7551444213705871,
      "grad_norm": 2.8851935863494873,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0365,
      "step": 1000
    },
    {
      "epoch": 0.7551444213705871,
      "eval_loss": 0.0462164580821991,
      "eval_runtime": 88.9886,
      "eval_samples_per_second": 12.541,
      "eval_steps_per_second": 3.135,
      "step": 1000
    },
    {
      "epoch": 0.7929016424391164,
      "grad_norm": 0.26174625754356384,
      "learning_rate": 5e-05,
      "loss": 0.0385,
      "step": 1050
    },
    {
      "epoch": 0.8306588635076458,
      "grad_norm": 0.055037304759025574,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.039,
      "step": 1100
    },
    {
      "epoch": 0.8684160845761751,
      "grad_norm": 0.029556207358837128,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.0302,
      "step": 1150
    },
    {
      "epoch": 0.9061733056447046,
      "grad_norm": 0.44684645533561707,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0365,
      "step": 1200
    },
    {
      "epoch": 0.9061733056447046,
      "eval_loss": 0.042669691145420074,
      "eval_runtime": 88.4572,
      "eval_samples_per_second": 12.616,
      "eval_steps_per_second": 3.154,
      "step": 1200
    },
    {
      "epoch": 0.9439305267132339,
      "grad_norm": 0.031862616539001465,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0312,
      "step": 1250
    },
    {
      "epoch": 0.9816877477817633,
      "grad_norm": 0.028305215761065483,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0333,
      "step": 1300
    },
    {
      "epoch": 1.0194449688502927,
      "grad_norm": 0.16851945221424103,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0341,
      "step": 1350
    },
    {
      "epoch": 1.057202189918822,
      "grad_norm": 0.09734618663787842,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0196,
      "step": 1400
    },
    {
      "epoch": 1.057202189918822,
      "eval_loss": 0.04361049458384514,
      "eval_runtime": 88.6046,
      "eval_samples_per_second": 12.595,
      "eval_steps_per_second": 3.149,
      "step": 1400
    },
    {
      "epoch": 1.0949594109873513,
      "grad_norm": 0.022358063608407974,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.015,
      "step": 1450
    },
    {
      "epoch": 1.1327166320558808,
      "grad_norm": 0.23758022487163544,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0156,
      "step": 1500
    },
    {
      "epoch": 1.17047385312441,
      "grad_norm": 0.011663041077554226,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0158,
      "step": 1550
    },
    {
      "epoch": 1.2082310741929394,
      "grad_norm": 0.0888688713312149,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0192,
      "step": 1600
    },
    {
      "epoch": 1.2082310741929394,
      "eval_loss": 0.04343624785542488,
      "eval_runtime": 88.893,
      "eval_samples_per_second": 12.554,
      "eval_steps_per_second": 3.139,
      "step": 1600
    },
    {
      "epoch": 1.2459882952614687,
      "grad_norm": 0.28665322065353394,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0139,
      "step": 1650
    },
    {
      "epoch": 1.283745516329998,
      "grad_norm": 0.026126619428396225,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0178,
      "step": 1700
    },
    {
      "epoch": 1.3215027373985275,
      "grad_norm": 0.12513647973537445,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0157,
      "step": 1750
    },
    {
      "epoch": 1.3592599584670568,
      "grad_norm": 0.0799918845295906,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0138,
      "step": 1800
    },
    {
      "epoch": 1.3592599584670568,
      "eval_loss": 0.043415576219558716,
      "eval_runtime": 88.8821,
      "eval_samples_per_second": 12.556,
      "eval_steps_per_second": 3.139,
      "step": 1800
    }
  ],
  "logging_steps": 50,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2271277242822164e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}