{
  "best_metric": 1.2476589679718018,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03395585738539898,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016977928692699492,
      "eval_loss": 1.4329637289047241,
      "eval_runtime": 234.0581,
      "eval_samples_per_second": 5.298,
      "eval_steps_per_second": 1.324,
      "step": 1
    },
    {
      "epoch": 0.001697792869269949,
      "grad_norm": 1.311955213546753,
      "learning_rate": 4.1400000000000003e-05,
      "loss": 1.4203,
      "step": 10
    },
    {
      "epoch": 0.003395585738539898,
      "grad_norm": 0.7833012342453003,
      "learning_rate": 8.280000000000001e-05,
      "loss": 1.338,
      "step": 20
    },
    {
      "epoch": 0.0050933786078098476,
      "grad_norm": 0.7402932047843933,
      "learning_rate": 0.00012419999999999998,
      "loss": 1.2575,
      "step": 30
    },
    {
      "epoch": 0.006791171477079796,
      "grad_norm": 0.7024871110916138,
      "learning_rate": 0.00016560000000000001,
      "loss": 1.2019,
      "step": 40
    },
    {
      "epoch": 0.008488964346349746,
      "grad_norm": 0.804834246635437,
      "learning_rate": 0.000207,
      "loss": 1.2279,
      "step": 50
    },
    {
      "epoch": 0.008488964346349746,
      "eval_loss": 1.2476589679718018,
      "eval_runtime": 235.3963,
      "eval_samples_per_second": 5.268,
      "eval_steps_per_second": 1.317,
      "step": 50
    },
    {
      "epoch": 0.010186757215619695,
      "grad_norm": 0.7924010753631592,
      "learning_rate": 0.00020674787920189178,
      "loss": 1.222,
      "step": 60
    },
    {
      "epoch": 0.011884550084889643,
      "grad_norm": 0.8740193247795105,
      "learning_rate": 0.00020599274511475253,
      "loss": 1.2045,
      "step": 70
    },
    {
      "epoch": 0.013582342954159592,
      "grad_norm": 0.8409563899040222,
      "learning_rate": 0.00020473827667594888,
      "loss": 1.2077,
      "step": 80
    },
    {
      "epoch": 0.015280135823429542,
      "grad_norm": 1.0255435705184937,
      "learning_rate": 0.00020299058552961598,
      "loss": 1.2556,
      "step": 90
    },
    {
      "epoch": 0.01697792869269949,
      "grad_norm": 1.3903775215148926,
      "learning_rate": 0.00020075818625134152,
      "loss": 1.303,
      "step": 100
    },
    {
      "epoch": 0.01697792869269949,
      "eval_loss": 1.3105939626693726,
      "eval_runtime": 235.3286,
      "eval_samples_per_second": 5.269,
      "eval_steps_per_second": 1.317,
      "step": 100
    },
    {
      "epoch": 0.01867572156196944,
      "grad_norm": 0.6778289675712585,
      "learning_rate": 0.00019805195486600916,
      "loss": 1.3131,
      "step": 110
    },
    {
      "epoch": 0.02037351443123939,
      "grad_norm": 0.7167655825614929,
      "learning_rate": 0.00019488507586089894,
      "loss": 1.1878,
      "step": 120
    },
    {
      "epoch": 0.022071307300509338,
      "grad_norm": 0.786454975605011,
      "learning_rate": 0.00019127297795219008,
      "loss": 1.2166,
      "step": 130
    },
    {
      "epoch": 0.023769100169779286,
      "grad_norm": 0.8451493382453918,
      "learning_rate": 0.00018723325891780706,
      "loss": 1.2909,
      "step": 140
    },
    {
      "epoch": 0.025466893039049237,
      "grad_norm": 0.7425501942634583,
      "learning_rate": 0.0001827855998628142,
      "loss": 1.1985,
      "step": 150
    },
    {
      "epoch": 0.025466893039049237,
      "eval_loss": 1.248077630996704,
      "eval_runtime": 235.4875,
      "eval_samples_per_second": 5.266,
      "eval_steps_per_second": 1.316,
      "step": 150
    },
    {
      "epoch": 0.027164685908319185,
      "grad_norm": 0.8560181856155396,
      "learning_rate": 0.0001779516693350504,
      "loss": 1.1788,
      "step": 160
    },
    {
      "epoch": 0.028862478777589132,
      "grad_norm": 0.7847142815589905,
      "learning_rate": 0.00017275501775814182,
      "loss": 1.2282,
      "step": 170
    },
    {
      "epoch": 0.030560271646859084,
      "grad_norm": 0.8509446382522583,
      "learning_rate": 0.00016722096269620562,
      "loss": 1.2029,
      "step": 180
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 0.9557679891586304,
      "learning_rate": 0.00016137646550922228,
      "loss": 1.2601,
      "step": 190
    },
    {
      "epoch": 0.03395585738539898,
      "grad_norm": 1.3051382303237915,
      "learning_rate": 0.00015525,
      "loss": 1.2807,
      "step": 200
    },
    {
      "epoch": 0.03395585738539898,
      "eval_loss": 1.330949306488037,
      "eval_runtime": 236.0189,
      "eval_samples_per_second": 5.254,
      "eval_steps_per_second": 1.313,
      "step": 200
    }
  ],
  "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.387406029088358e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}