{
  "best_metric": 0.7528109550476074,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.008306337735692334,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033225350942769335,
      "grad_norm": 1.0169950723648071,
      "learning_rate": 2e-05,
      "loss": 1.3259,
      "step": 1
    },
    {
      "epoch": 0.00033225350942769335,
      "eval_loss": 1.3606626987457275,
      "eval_runtime": 228.2749,
      "eval_samples_per_second": 5.555,
      "eval_steps_per_second": 2.777,
      "step": 1
    },
    {
      "epoch": 0.0006645070188553867,
      "grad_norm": 1.0040243864059448,
      "learning_rate": 4e-05,
      "loss": 1.2554,
      "step": 2
    },
    {
      "epoch": 0.00099676052828308,
      "grad_norm": 1.0681229829788208,
      "learning_rate": 6e-05,
      "loss": 1.2984,
      "step": 3
    },
    {
      "epoch": 0.0013290140377107734,
      "grad_norm": 0.9195343255996704,
      "learning_rate": 8e-05,
      "loss": 1.1735,
      "step": 4
    },
    {
      "epoch": 0.0016612675471384666,
      "grad_norm": 1.0504077672958374,
      "learning_rate": 0.0001,
      "loss": 1.2825,
      "step": 5
    },
    {
      "epoch": 0.0016612675471384666,
      "eval_loss": 1.2597624063491821,
      "eval_runtime": 223.9882,
      "eval_samples_per_second": 5.661,
      "eval_steps_per_second": 2.831,
      "step": 5
    },
    {
      "epoch": 0.00199352105656616,
      "grad_norm": 1.0373380184173584,
      "learning_rate": 0.00012,
      "loss": 1.2688,
      "step": 6
    },
    {
      "epoch": 0.0023257745659938534,
      "grad_norm": 0.9662240147590637,
      "learning_rate": 0.00014,
      "loss": 1.1485,
      "step": 7
    },
    {
      "epoch": 0.002658028075421547,
      "grad_norm": 0.9418009519577026,
      "learning_rate": 0.00016,
      "loss": 1.0905,
      "step": 8
    },
    {
      "epoch": 0.00299028158484924,
      "grad_norm": 1.0762710571289062,
      "learning_rate": 0.00018,
      "loss": 1.1529,
      "step": 9
    },
    {
      "epoch": 0.003322535094276933,
      "grad_norm": 1.0235474109649658,
      "learning_rate": 0.0002,
      "loss": 0.9448,
      "step": 10
    },
    {
      "epoch": 0.003322535094276933,
      "eval_loss": 0.9713111519813538,
      "eval_runtime": 224.1187,
      "eval_samples_per_second": 5.658,
      "eval_steps_per_second": 2.829,
      "step": 10
    },
    {
      "epoch": 0.0036547886037046266,
      "grad_norm": 1.2232210636138916,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.0116,
      "step": 11
    },
    {
      "epoch": 0.00398704211313232,
      "grad_norm": 1.3449325561523438,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.901,
      "step": 12
    },
    {
      "epoch": 0.004319295622560013,
      "grad_norm": 1.398583173751831,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.8434,
      "step": 13
    },
    {
      "epoch": 0.004651549131987707,
      "grad_norm": 1.3255641460418701,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.931,
      "step": 14
    },
    {
      "epoch": 0.0049838026414154,
      "grad_norm": 0.9998956322669983,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.7513,
      "step": 15
    },
    {
      "epoch": 0.0049838026414154,
      "eval_loss": 0.8030931353569031,
      "eval_runtime": 224.8241,
      "eval_samples_per_second": 5.64,
      "eval_steps_per_second": 2.82,
      "step": 15
    },
    {
      "epoch": 0.005316056150843094,
      "grad_norm": 0.9725546836853027,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.8373,
      "step": 16
    },
    {
      "epoch": 0.005648309660270787,
      "grad_norm": 0.9956027269363403,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.7647,
      "step": 17
    },
    {
      "epoch": 0.00598056316969848,
      "grad_norm": 0.991544783115387,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.8184,
      "step": 18
    },
    {
      "epoch": 0.0063128166791261734,
      "grad_norm": 0.7912893891334534,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.6974,
      "step": 19
    },
    {
      "epoch": 0.006645070188553866,
      "grad_norm": 0.9309248924255371,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.7878,
      "step": 20
    },
    {
      "epoch": 0.006645070188553866,
      "eval_loss": 0.7618138790130615,
      "eval_runtime": 229.0859,
      "eval_samples_per_second": 5.535,
      "eval_steps_per_second": 2.768,
      "step": 20
    },
    {
      "epoch": 0.00697732369798156,
      "grad_norm": 1.050058364868164,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.7947,
      "step": 21
    },
    {
      "epoch": 0.007309577207409253,
      "grad_norm": 1.0226415395736694,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.7742,
      "step": 22
    },
    {
      "epoch": 0.007641830716836946,
      "grad_norm": 0.9001511931419373,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.8417,
      "step": 23
    },
    {
      "epoch": 0.00797408422626464,
      "grad_norm": 0.8601190447807312,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.7344,
      "step": 24
    },
    {
      "epoch": 0.008306337735692334,
      "grad_norm": 0.9433331489562988,
      "learning_rate": 0.0,
      "loss": 0.8423,
      "step": 25
    },
    {
      "epoch": 0.008306337735692334,
      "eval_loss": 0.7528109550476074,
      "eval_runtime": 226.3904,
      "eval_samples_per_second": 5.601,
      "eval_steps_per_second": 2.8,
      "step": 25
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1250243326771200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}