{
  "best_metric": 1.4445966482162476,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.025196850393700787,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012598425196850393,
      "grad_norm": 1.389225721359253,
      "learning_rate": 2e-05,
      "loss": 1.5322,
      "step": 1
    },
    {
      "epoch": 0.0012598425196850393,
      "eval_loss": 1.47604238986969,
      "eval_runtime": 51.4622,
      "eval_samples_per_second": 6.51,
      "eval_steps_per_second": 3.265,
      "step": 1
    },
    {
      "epoch": 0.0025196850393700786,
      "grad_norm": 1.687314510345459,
      "learning_rate": 4e-05,
      "loss": 1.5691,
      "step": 2
    },
    {
      "epoch": 0.003779527559055118,
      "grad_norm": 1.421244502067566,
      "learning_rate": 6e-05,
      "loss": 1.4222,
      "step": 3
    },
    {
      "epoch": 0.005039370078740157,
      "grad_norm": 1.4597176313400269,
      "learning_rate": 8e-05,
      "loss": 1.5211,
      "step": 4
    },
    {
      "epoch": 0.006299212598425197,
      "grad_norm": 1.670005440711975,
      "learning_rate": 0.0001,
      "loss": 1.5182,
      "step": 5
    },
    {
      "epoch": 0.006299212598425197,
      "eval_loss": 1.4737396240234375,
      "eval_runtime": 50.1519,
      "eval_samples_per_second": 6.68,
      "eval_steps_per_second": 3.35,
      "step": 5
    },
    {
      "epoch": 0.007559055118110236,
      "grad_norm": 1.4321858882904053,
      "learning_rate": 0.00012,
      "loss": 1.5159,
      "step": 6
    },
    {
      "epoch": 0.008818897637795276,
      "grad_norm": 1.5846105813980103,
      "learning_rate": 0.00014,
      "loss": 1.5455,
      "step": 7
    },
    {
      "epoch": 0.010078740157480314,
      "grad_norm": 1.3973721265792847,
      "learning_rate": 0.00016,
      "loss": 1.4616,
      "step": 8
    },
    {
      "epoch": 0.011338582677165355,
      "grad_norm": 1.5478447675704956,
      "learning_rate": 0.00018,
      "loss": 1.4877,
      "step": 9
    },
    {
      "epoch": 0.012598425196850394,
      "grad_norm": 1.6238055229187012,
      "learning_rate": 0.0002,
      "loss": 1.5364,
      "step": 10
    },
    {
      "epoch": 0.012598425196850394,
      "eval_loss": 1.4638172388076782,
      "eval_runtime": 49.4108,
      "eval_samples_per_second": 6.78,
      "eval_steps_per_second": 3.4,
      "step": 10
    },
    {
      "epoch": 0.013858267716535434,
      "grad_norm": 1.5400310754776,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.4818,
      "step": 11
    },
    {
      "epoch": 0.015118110236220473,
      "grad_norm": 1.9725576639175415,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.5816,
      "step": 12
    },
    {
      "epoch": 0.016377952755905513,
      "grad_norm": 1.9127973318099976,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.4193,
      "step": 13
    },
    {
      "epoch": 0.01763779527559055,
      "grad_norm": 2.428370475769043,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.5406,
      "step": 14
    },
    {
      "epoch": 0.01889763779527559,
      "grad_norm": 2.627856492996216,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.548,
      "step": 15
    },
    {
      "epoch": 0.01889763779527559,
      "eval_loss": 1.4514150619506836,
      "eval_runtime": 49.4496,
      "eval_samples_per_second": 6.775,
      "eval_steps_per_second": 3.397,
      "step": 15
    },
    {
      "epoch": 0.02015748031496063,
      "grad_norm": 2.375114679336548,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.3945,
      "step": 16
    },
    {
      "epoch": 0.021417322834645668,
      "grad_norm": 2.3865299224853516,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.4951,
      "step": 17
    },
    {
      "epoch": 0.02267716535433071,
      "grad_norm": 2.61568546295166,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.6419,
      "step": 18
    },
    {
      "epoch": 0.02393700787401575,
      "grad_norm": 2.4963173866271973,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.5219,
      "step": 19
    },
    {
      "epoch": 0.025196850393700787,
      "grad_norm": 2.4020745754241943,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.5499,
      "step": 20
    },
    {
      "epoch": 0.025196850393700787,
      "eval_loss": 1.4445966482162476,
      "eval_runtime": 54.5616,
      "eval_samples_per_second": 6.14,
      "eval_steps_per_second": 3.079,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2598942246174720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}