{
  "best_metric": 0.6515164971351624,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.000518158877875134,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0726355115005362e-05,
      "grad_norm": 4.606229305267334,
      "learning_rate": 2e-05,
      "loss": 6.4285,
      "step": 1
    },
    {
      "epoch": 2.0726355115005362e-05,
      "eval_loss": 1.386435627937317,
      "eval_runtime": 3680.0393,
      "eval_samples_per_second": 5.52,
      "eval_steps_per_second": 2.76,
      "step": 1
    },
    {
      "epoch": 4.1452710230010724e-05,
      "grad_norm": 3.1252923011779785,
      "learning_rate": 4e-05,
      "loss": 3.6875,
      "step": 2
    },
    {
      "epoch": 6.217906534501609e-05,
      "grad_norm": 5.3452863693237305,
      "learning_rate": 6e-05,
      "loss": 9.747,
      "step": 3
    },
    {
      "epoch": 8.290542046002145e-05,
      "grad_norm": 3.473754644393921,
      "learning_rate": 8e-05,
      "loss": 4.0488,
      "step": 4
    },
    {
      "epoch": 0.00010363177557502682,
      "grad_norm": 5.435574531555176,
      "learning_rate": 0.0001,
      "loss": 6.2278,
      "step": 5
    },
    {
      "epoch": 0.00010363177557502682,
      "eval_loss": 1.3445682525634766,
      "eval_runtime": 3632.6364,
      "eval_samples_per_second": 5.592,
      "eval_steps_per_second": 2.796,
      "step": 5
    },
    {
      "epoch": 0.00012435813069003218,
      "grad_norm": 3.7246408462524414,
      "learning_rate": 0.00012,
      "loss": 3.9211,
      "step": 6
    },
    {
      "epoch": 0.00014508448580503755,
      "grad_norm": 7.678606986999512,
      "learning_rate": 0.00014,
      "loss": 8.467,
      "step": 7
    },
    {
      "epoch": 0.0001658108409200429,
      "grad_norm": 5.895946979522705,
      "learning_rate": 0.00016,
      "loss": 5.3675,
      "step": 8
    },
    {
      "epoch": 0.00018653719603504827,
      "grad_norm": 3.4130988121032715,
      "learning_rate": 0.00018,
      "loss": 2.225,
      "step": 9
    },
    {
      "epoch": 0.00020726355115005364,
      "grad_norm": 2.9022064208984375,
      "learning_rate": 0.0002,
      "loss": 1.891,
      "step": 10
    },
    {
      "epoch": 0.00020726355115005364,
      "eval_loss": 0.9219593405723572,
      "eval_runtime": 3715.7051,
      "eval_samples_per_second": 5.467,
      "eval_steps_per_second": 2.734,
      "step": 10
    },
    {
      "epoch": 0.00022798990626505898,
      "grad_norm": 3.7265615463256836,
      "learning_rate": 0.00019781476007338058,
      "loss": 3.7521,
      "step": 11
    },
    {
      "epoch": 0.00024871626138006436,
      "grad_norm": 3.3085176944732666,
      "learning_rate": 0.0001913545457642601,
      "loss": 3.5305,
      "step": 12
    },
    {
      "epoch": 0.00026944261649506973,
      "grad_norm": 2.6875157356262207,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.4707,
      "step": 13
    },
    {
      "epoch": 0.0002901689716100751,
      "grad_norm": 3.5962133407592773,
      "learning_rate": 0.00016691306063588583,
      "loss": 2.0995,
      "step": 14
    },
    {
      "epoch": 0.0003108953267250804,
      "grad_norm": 6.021538257598877,
      "learning_rate": 0.00015000000000000001,
      "loss": 5.681,
      "step": 15
    },
    {
      "epoch": 0.0003108953267250804,
      "eval_loss": 0.7419989705085754,
      "eval_runtime": 3758.5522,
      "eval_samples_per_second": 5.405,
      "eval_steps_per_second": 2.703,
      "step": 15
    },
    {
      "epoch": 0.0003316216818400858,
      "grad_norm": 3.865921974182129,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.126,
      "step": 16
    },
    {
      "epoch": 0.00035234803695509116,
      "grad_norm": 2.362683057785034,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.2977,
      "step": 17
    },
    {
      "epoch": 0.00037307439207009654,
      "grad_norm": 2.6094250679016113,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.5112,
      "step": 18
    },
    {
      "epoch": 0.0003938007471851019,
      "grad_norm": 6.798496246337891,
      "learning_rate": 6.909830056250527e-05,
      "loss": 3.5821,
      "step": 19
    },
    {
      "epoch": 0.0004145271023001073,
      "grad_norm": 9.604643821716309,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.7374,
      "step": 20
    },
    {
      "epoch": 0.0004145271023001073,
      "eval_loss": 0.673650860786438,
      "eval_runtime": 3842.2195,
      "eval_samples_per_second": 5.287,
      "eval_steps_per_second": 2.644,
      "step": 20
    },
    {
      "epoch": 0.0004352534574151126,
      "grad_norm": 6.2658281326293945,
      "learning_rate": 3.308693936411421e-05,
      "loss": 4.2788,
      "step": 21
    },
    {
      "epoch": 0.00045597981253011797,
      "grad_norm": 2.940730571746826,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.2236,
      "step": 22
    },
    {
      "epoch": 0.00047670616764512334,
      "grad_norm": 6.151371002197266,
      "learning_rate": 8.645454235739903e-06,
      "loss": 2.7089,
      "step": 23
    },
    {
      "epoch": 0.0004974325227601287,
      "grad_norm": 7.25663423538208,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 2.9291,
      "step": 24
    },
    {
      "epoch": 0.000518158877875134,
      "grad_norm": 11.405837059020996,
      "learning_rate": 0.0,
      "loss": 5.4171,
      "step": 25
    },
    {
      "epoch": 0.000518158877875134,
      "eval_loss": 0.6515164971351624,
      "eval_runtime": 3699.6936,
      "eval_samples_per_second": 5.491,
      "eval_steps_per_second": 2.746,
      "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": 4071873105100800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}