{
  "best_metric": 1.3169949054718018,
  "best_model_checkpoint": "miner_id_24/checkpoint-350",
  "epoch": 1.0012453300124533,
  "eval_steps": 50,
  "global_step": 402,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024906600249066002,
      "eval_loss": 2.3575375080108643,
      "eval_runtime": 9.0845,
      "eval_samples_per_second": 18.603,
      "eval_steps_per_second": 4.733,
      "step": 1
    },
    {
      "epoch": 0.024906600249066,
      "grad_norm": 1.6407170295715332,
      "learning_rate": 4.36e-05,
      "loss": 1.6376,
      "step": 10
    },
    {
      "epoch": 0.049813200498132,
      "grad_norm": 2.079932451248169,
      "learning_rate": 8.72e-05,
      "loss": 1.8074,
      "step": 20
    },
    {
      "epoch": 0.074719800747198,
      "grad_norm": 1.752514123916626,
      "learning_rate": 0.0001308,
      "loss": 1.5148,
      "step": 30
    },
    {
      "epoch": 0.099626400996264,
      "grad_norm": 2.3281145095825195,
      "learning_rate": 0.0001744,
      "loss": 1.618,
      "step": 40
    },
    {
      "epoch": 0.12453300124533001,
      "grad_norm": 2.0914270877838135,
      "learning_rate": 0.000218,
      "loss": 1.3761,
      "step": 50
    },
    {
      "epoch": 0.12453300124533001,
      "eval_loss": 1.7705373764038086,
      "eval_runtime": 9.1773,
      "eval_samples_per_second": 18.415,
      "eval_steps_per_second": 4.685,
      "step": 50
    },
    {
      "epoch": 0.149439601494396,
      "grad_norm": 1.1187117099761963,
      "learning_rate": 0.00021756616696447703,
      "loss": 1.6001,
      "step": 60
    },
    {
      "epoch": 0.17434620174346202,
      "grad_norm": 1.864639401435852,
      "learning_rate": 0.00021626812127263666,
      "loss": 1.5317,
      "step": 70
    },
    {
      "epoch": 0.199252801992528,
      "grad_norm": 1.9063708782196045,
      "learning_rate": 0.00021411619567865767,
      "loss": 1.4666,
      "step": 80
    },
    {
      "epoch": 0.22415940224159403,
      "grad_norm": 1.9959717988967896,
      "learning_rate": 0.00021112752002497406,
      "loss": 1.3854,
      "step": 90
    },
    {
      "epoch": 0.24906600249066002,
      "grad_norm": 1.7696688175201416,
      "learning_rate": 0.00020732588488463224,
      "loss": 1.0668,
      "step": 100
    },
    {
      "epoch": 0.24906600249066002,
      "eval_loss": 1.671539306640625,
      "eval_runtime": 9.1879,
      "eval_samples_per_second": 18.394,
      "eval_steps_per_second": 4.68,
      "step": 100
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 1.1212961673736572,
      "learning_rate": 0.00020274155218263936,
      "loss": 1.7123,
      "step": 110
    },
    {
      "epoch": 0.298879202988792,
      "grad_norm": 1.5101659297943115,
      "learning_rate": 0.00019741101430380186,
      "loss": 1.5006,
      "step": 120
    },
    {
      "epoch": 0.32378580323785805,
      "grad_norm": 1.5983831882476807,
      "learning_rate": 0.00019137670360461418,
      "loss": 1.4108,
      "step": 130
    },
    {
      "epoch": 0.34869240348692404,
      "grad_norm": 1.7551649808883667,
      "learning_rate": 0.00018468665464155184,
      "loss": 1.363,
      "step": 140
    },
    {
      "epoch": 0.37359900373599003,
      "grad_norm": 1.9306334257125854,
      "learning_rate": 0.0001773941218045129,
      "loss": 1.0146,
      "step": 150
    },
    {
      "epoch": 0.37359900373599003,
      "eval_loss": 1.5669289827346802,
      "eval_runtime": 9.1037,
      "eval_samples_per_second": 18.564,
      "eval_steps_per_second": 4.723,
      "step": 150
    },
    {
      "epoch": 0.398505603985056,
      "grad_norm": 1.0432745218276978,
      "learning_rate": 0.00016955715539913665,
      "loss": 1.4577,
      "step": 160
    },
    {
      "epoch": 0.42341220423412207,
      "grad_norm": 1.7187490463256836,
      "learning_rate": 0.0001612381395524862,
      "loss": 1.4403,
      "step": 170
    },
    {
      "epoch": 0.44831880448318806,
      "grad_norm": 1.626038908958435,
      "learning_rate": 0.00015250329562047557,
      "loss": 1.2982,
      "step": 180
    },
    {
      "epoch": 0.47322540473225405,
      "grad_norm": 1.8136370182037354,
      "learning_rate": 0.00014342215505003773,
      "loss": 1.4308,
      "step": 190
    },
    {
      "epoch": 0.49813200498132004,
      "grad_norm": 1.1612805128097534,
      "learning_rate": 0.000134067005892176,
      "loss": 0.9796,
      "step": 200
    },
    {
      "epoch": 0.49813200498132004,
      "eval_loss": 1.5291515588760376,
      "eval_runtime": 9.1903,
      "eval_samples_per_second": 18.389,
      "eval_steps_per_second": 4.679,
      "step": 200
    },
    {
      "epoch": 0.523038605230386,
      "grad_norm": 1.3198999166488647,
      "learning_rate": 0.0001245123173717881,
      "loss": 1.8174,
      "step": 210
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 1.404754638671875,
      "learning_rate": 0.00011483414709482405,
      "loss": 1.1952,
      "step": 220
    },
    {
      "epoch": 0.572851805728518,
      "grad_norm": 1.841070532798767,
      "learning_rate": 0.00010510953561155114,
      "loss": 1.2676,
      "step": 230
    },
    {
      "epoch": 0.597758405977584,
      "grad_norm": 1.8930388689041138,
      "learning_rate": 9.541589315534674e-05,
      "loss": 1.3132,
      "step": 240
    },
    {
      "epoch": 0.6226650062266501,
      "grad_norm": 1.8174850940704346,
      "learning_rate": 8.583038343872554e-05,
      "loss": 0.9781,
      "step": 250
    },
    {
      "epoch": 0.6226650062266501,
      "eval_loss": 1.4715014696121216,
      "eval_runtime": 9.1661,
      "eval_samples_per_second": 18.437,
      "eval_steps_per_second": 4.691,
      "step": 250
    },
    {
      "epoch": 0.6475716064757161,
      "grad_norm": 1.1012831926345825,
      "learning_rate": 7.642930941173154e-05,
      "loss": 1.4417,
      "step": 260
    },
    {
      "epoch": 0.6724782067247821,
      "grad_norm": 1.208770990371704,
      "learning_rate": 6.728750587220522e-05,
      "loss": 1.4184,
      "step": 270
    },
    {
      "epoch": 0.6973848069738481,
      "grad_norm": 1.6374764442443848,
      "learning_rate": 5.847774376289351e-05,
      "loss": 1.2979,
      "step": 280
    },
    {
      "epoch": 0.7222914072229141,
      "grad_norm": 1.8867082595825195,
      "learning_rate": 5.0070150897339905e-05,
      "loss": 1.3951,
      "step": 290
    },
    {
      "epoch": 0.7471980074719801,
      "grad_norm": 1.2463188171386719,
      "learning_rate": 4.213165372571504e-05,
      "loss": 0.8543,
      "step": 300
    },
    {
      "epoch": 0.7471980074719801,
      "eval_loss": 1.4179314374923706,
      "eval_runtime": 9.0764,
      "eval_samples_per_second": 18.62,
      "eval_steps_per_second": 4.738,
      "step": 300
    },
    {
      "epoch": 0.772104607721046,
      "grad_norm": 1.0654844045639038,
      "learning_rate": 3.472544458426586e-05,
      "loss": 1.4909,
      "step": 310
    },
    {
      "epoch": 0.797011207970112,
      "grad_norm": 1.1939270496368408,
      "learning_rate": 2.7910478669204397e-05,
      "loss": 1.3609,
      "step": 320
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 1.3185659646987915,
      "learning_rate": 2.174100473924473e-05,
      "loss": 1.4049,
      "step": 330
    },
    {
      "epoch": 0.8468244084682441,
      "grad_norm": 1.7657341957092285,
      "learning_rate": 1.626613328250815e-05,
      "loss": 1.2549,
      "step": 340
    },
    {
      "epoch": 0.8717310087173101,
      "grad_norm": 1.3518775701522827,
      "learning_rate": 1.152944558529147e-05,
      "loss": 1.0009,
      "step": 350
    },
    {
      "epoch": 0.8717310087173101,
      "eval_loss": 1.3169949054718018,
      "eval_runtime": 9.1662,
      "eval_samples_per_second": 18.437,
      "eval_steps_per_second": 4.691,
      "step": 350
    },
    {
      "epoch": 0.8966376089663761,
      "grad_norm": 0.9178294539451599,
      "learning_rate": 7.568646814604021e-06,
      "loss": 1.3807,
      "step": 360
    },
    {
      "epoch": 0.9215442092154421,
      "grad_norm": 1.0393375158309937,
      "learning_rate": 4.4152658760198e-06,
      "loss": 1.2499,
      "step": 370
    },
    {
      "epoch": 0.9464508094645081,
      "grad_norm": 1.3953897953033447,
      "learning_rate": 2.094404436047883e-06,
      "loss": 1.0791,
      "step": 380
    },
    {
      "epoch": 0.9713574097135741,
      "grad_norm": 1.0463335514068604,
      "learning_rate": 6.245371068631892e-07,
      "loss": 1.1939,
      "step": 390
    },
    {
      "epoch": 0.9962640099626401,
      "grad_norm": 1.1366596221923828,
      "learning_rate": 1.736438397464224e-08,
      "loss": 0.9256,
      "step": 400
    },
    {
      "epoch": 0.9962640099626401,
      "eval_loss": 1.3189666271209717,
      "eval_runtime": 9.1794,
      "eval_samples_per_second": 18.411,
      "eval_steps_per_second": 4.684,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 402,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.46090111891669e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}