{
  "best_metric": 0.959044873714447,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.04371584699453552,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008743169398907104,
      "grad_norm": 13.654485702514648,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 7.2397,
      "step": 1
    },
    {
      "epoch": 0.0008743169398907104,
      "eval_loss": 2.0816423892974854,
      "eval_runtime": 234.4717,
      "eval_samples_per_second": 32.857,
      "eval_steps_per_second": 4.107,
      "step": 1
    },
    {
      "epoch": 0.0017486338797814208,
      "grad_norm": 16.08323097229004,
      "learning_rate": 6.666666666666667e-06,
      "loss": 7.3886,
      "step": 2
    },
    {
      "epoch": 0.002622950819672131,
      "grad_norm": 16.72583770751953,
      "learning_rate": 1e-05,
      "loss": 7.2155,
      "step": 3
    },
    {
      "epoch": 0.0034972677595628415,
      "grad_norm": 16.019792556762695,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 6.8998,
      "step": 4
    },
    {
      "epoch": 0.004371584699453552,
      "grad_norm": 10.719884872436523,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 6.1133,
      "step": 5
    },
    {
      "epoch": 0.005245901639344262,
      "grad_norm": 99.27400207519531,
      "learning_rate": 2e-05,
      "loss": 10.2652,
      "step": 6
    },
    {
      "epoch": 0.006120218579234973,
      "grad_norm": 85.72102355957031,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 9.529,
      "step": 7
    },
    {
      "epoch": 0.006994535519125683,
      "grad_norm": 15.085773468017578,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 5.6537,
      "step": 8
    },
    {
      "epoch": 0.007868852459016393,
      "grad_norm": 12.465982437133789,
      "learning_rate": 3e-05,
      "loss": 5.3902,
      "step": 9
    },
    {
      "epoch": 0.008743169398907104,
      "grad_norm": 9.44223403930664,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.2389,
      "step": 10
    },
    {
      "epoch": 0.009617486338797814,
      "grad_norm": 7.920454025268555,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 4.7169,
      "step": 11
    },
    {
      "epoch": 0.010491803278688525,
      "grad_norm": 8.882831573486328,
      "learning_rate": 4e-05,
      "loss": 4.4305,
      "step": 12
    },
    {
      "epoch": 0.011366120218579235,
      "grad_norm": 6.801806926727295,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 4.3088,
      "step": 13
    },
    {
      "epoch": 0.012240437158469945,
      "grad_norm": 7.269967555999756,
      "learning_rate": 4.666666666666667e-05,
      "loss": 5.6956,
      "step": 14
    },
    {
      "epoch": 0.013114754098360656,
      "grad_norm": 6.725127220153809,
      "learning_rate": 5e-05,
      "loss": 5.209,
      "step": 15
    },
    {
      "epoch": 0.013989071038251366,
      "grad_norm": 6.431244373321533,
      "learning_rate": 5.333333333333333e-05,
      "loss": 5.1324,
      "step": 16
    },
    {
      "epoch": 0.014863387978142076,
      "grad_norm": 5.522418975830078,
      "learning_rate": 5.666666666666667e-05,
      "loss": 4.8785,
      "step": 17
    },
    {
      "epoch": 0.015737704918032787,
      "grad_norm": 13.761688232421875,
      "learning_rate": 6e-05,
      "loss": 3.9461,
      "step": 18
    },
    {
      "epoch": 0.016612021857923497,
      "grad_norm": 23.60154914855957,
      "learning_rate": 6.333333333333333e-05,
      "loss": 1.3604,
      "step": 19
    },
    {
      "epoch": 0.017486338797814208,
      "grad_norm": 14.374363899230957,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.9006,
      "step": 20
    },
    {
      "epoch": 0.018360655737704918,
      "grad_norm": 8.315186500549316,
      "learning_rate": 7e-05,
      "loss": 4.7994,
      "step": 21
    },
    {
      "epoch": 0.01923497267759563,
      "grad_norm": 6.13319730758667,
      "learning_rate": 7.333333333333333e-05,
      "loss": 4.6416,
      "step": 22
    },
    {
      "epoch": 0.02010928961748634,
      "grad_norm": 5.479979038238525,
      "learning_rate": 7.666666666666667e-05,
      "loss": 4.4633,
      "step": 23
    },
    {
      "epoch": 0.02098360655737705,
      "grad_norm": 6.043623924255371,
      "learning_rate": 8e-05,
      "loss": 4.2832,
      "step": 24
    },
    {
      "epoch": 0.02185792349726776,
      "grad_norm": 6.044895172119141,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.8783,
      "step": 25
    },
    {
      "epoch": 0.02273224043715847,
      "grad_norm": 6.741650104522705,
      "learning_rate": 8.666666666666667e-05,
      "loss": 5.4952,
      "step": 26
    },
    {
      "epoch": 0.02360655737704918,
      "grad_norm": 6.030343532562256,
      "learning_rate": 9e-05,
      "loss": 5.1832,
      "step": 27
    },
    {
      "epoch": 0.02448087431693989,
      "grad_norm": 5.912640571594238,
      "learning_rate": 9.333333333333334e-05,
      "loss": 4.8941,
      "step": 28
    },
    {
      "epoch": 0.0253551912568306,
      "grad_norm": 4.158953666687012,
      "learning_rate": 9.666666666666667e-05,
      "loss": 4.8204,
      "step": 29
    },
    {
      "epoch": 0.02622950819672131,
      "grad_norm": 4.939655303955078,
      "learning_rate": 0.0001,
      "loss": 4.4874,
      "step": 30
    },
    {
      "epoch": 0.027103825136612022,
      "grad_norm": 6.877912521362305,
      "learning_rate": 9.999146252290264e-05,
      "loss": 3.2959,
      "step": 31
    },
    {
      "epoch": 0.027978142076502732,
      "grad_norm": 7.6934590339660645,
      "learning_rate": 9.996585300715116e-05,
      "loss": 1.1399,
      "step": 32
    },
    {
      "epoch": 0.028852459016393443,
      "grad_norm": 5.374224662780762,
      "learning_rate": 9.99231801983717e-05,
      "loss": 4.0316,
      "step": 33
    },
    {
      "epoch": 0.029726775956284153,
      "grad_norm": 4.416872978210449,
      "learning_rate": 9.986345866928941e-05,
      "loss": 4.449,
      "step": 34
    },
    {
      "epoch": 0.030601092896174863,
      "grad_norm": 4.096227645874023,
      "learning_rate": 9.978670881475172e-05,
      "loss": 4.4694,
      "step": 35
    },
    {
      "epoch": 0.031475409836065574,
      "grad_norm": 4.204520225524902,
      "learning_rate": 9.96929568447637e-05,
      "loss": 4.1511,
      "step": 36
    },
    {
      "epoch": 0.03234972677595629,
      "grad_norm": 4.906490802764893,
      "learning_rate": 9.958223477553714e-05,
      "loss": 3.9031,
      "step": 37
    },
    {
      "epoch": 0.033224043715846995,
      "grad_norm": 4.104410171508789,
      "learning_rate": 9.94545804185573e-05,
      "loss": 3.9166,
      "step": 38
    },
    {
      "epoch": 0.03409836065573771,
      "grad_norm": 4.067167282104492,
      "learning_rate": 9.931003736767013e-05,
      "loss": 5.0196,
      "step": 39
    },
    {
      "epoch": 0.034972677595628415,
      "grad_norm": 3.7131476402282715,
      "learning_rate": 9.91486549841951e-05,
      "loss": 4.8069,
      "step": 40
    },
    {
      "epoch": 0.03584699453551913,
      "grad_norm": 3.895036220550537,
      "learning_rate": 9.89704883800683e-05,
      "loss": 4.7326,
      "step": 41
    },
    {
      "epoch": 0.036721311475409836,
      "grad_norm": 3.369447946548462,
      "learning_rate": 9.877559839902184e-05,
      "loss": 4.5296,
      "step": 42
    },
    {
      "epoch": 0.03759562841530055,
      "grad_norm": 3.4959802627563477,
      "learning_rate": 9.85640515958057e-05,
      "loss": 3.6448,
      "step": 43
    },
    {
      "epoch": 0.03846994535519126,
      "grad_norm": 3.181074619293213,
      "learning_rate": 9.833592021345937e-05,
      "loss": 1.2202,
      "step": 44
    },
    {
      "epoch": 0.03934426229508197,
      "grad_norm": 6.853686332702637,
      "learning_rate": 9.809128215864097e-05,
      "loss": 3.2771,
      "step": 45
    },
    {
      "epoch": 0.04021857923497268,
      "grad_norm": 4.203513145446777,
      "learning_rate": 9.783022097502204e-05,
      "loss": 4.3558,
      "step": 46
    },
    {
      "epoch": 0.04109289617486339,
      "grad_norm": 3.710810422897339,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.2005,
      "step": 47
    },
    {
      "epoch": 0.0419672131147541,
      "grad_norm": 4.0080156326293945,
      "learning_rate": 9.725919140804099e-05,
      "loss": 4.1753,
      "step": 48
    },
    {
      "epoch": 0.04284153005464481,
      "grad_norm": 4.323927402496338,
      "learning_rate": 9.694941803075283e-05,
      "loss": 4.033,
      "step": 49
    },
    {
      "epoch": 0.04371584699453552,
      "grad_norm": 5.3773722648620605,
      "learning_rate": 9.662361147021779e-05,
      "loss": 3.0192,
      "step": 50
    },
    {
      "epoch": 0.04371584699453552,
      "eval_loss": 0.959044873714447,
      "eval_runtime": 235.9651,
      "eval_samples_per_second": 32.649,
      "eval_steps_per_second": 4.081,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 4.475451302918226e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}