{
  "best_metric": 7.642526149749756,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.07804878048780488,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031219512195121953,
      "grad_norm": 5.459062099456787,
      "learning_rate": 5e-05,
      "loss": 9.1044,
      "step": 1
    },
    {
      "epoch": 0.0031219512195121953,
      "eval_loss": 8.4755859375,
      "eval_runtime": 0.9418,
      "eval_samples_per_second": 53.09,
      "eval_steps_per_second": 53.09,
      "step": 1
    },
    {
      "epoch": 0.006243902439024391,
      "grad_norm": 5.766212463378906,
      "learning_rate": 0.0001,
      "loss": 8.8885,
      "step": 2
    },
    {
      "epoch": 0.009365853658536585,
      "grad_norm": 5.27004861831665,
      "learning_rate": 9.958086757163489e-05,
      "loss": 8.6246,
      "step": 3
    },
    {
      "epoch": 0.012487804878048781,
      "grad_norm": 5.087274551391602,
      "learning_rate": 9.833127793065098e-05,
      "loss": 8.5958,
      "step": 4
    },
    {
      "epoch": 0.015609756097560976,
      "grad_norm": 5.238975524902344,
      "learning_rate": 9.627450856774539e-05,
      "loss": 8.4973,
      "step": 5
    },
    {
      "epoch": 0.01873170731707317,
      "grad_norm": 4.5957489013671875,
      "learning_rate": 9.3448873204592e-05,
      "loss": 8.1857,
      "step": 6
    },
    {
      "epoch": 0.021853658536585364,
      "grad_norm": 3.9758787155151367,
      "learning_rate": 8.990700808169889e-05,
      "loss": 8.0822,
      "step": 7
    },
    {
      "epoch": 0.024975609756097562,
      "grad_norm": 3.484137773513794,
      "learning_rate": 8.571489144483944e-05,
      "loss": 8.0934,
      "step": 8
    },
    {
      "epoch": 0.028097560975609757,
      "grad_norm": 3.338285207748413,
      "learning_rate": 8.095061449516903e-05,
      "loss": 8.0251,
      "step": 9
    },
    {
      "epoch": 0.03121951219512195,
      "grad_norm": 2.8886618614196777,
      "learning_rate": 7.570292669790186e-05,
      "loss": 7.8113,
      "step": 10
    },
    {
      "epoch": 0.03434146341463415,
      "grad_norm": 2.729102849960327,
      "learning_rate": 7.006958254769438e-05,
      "loss": 7.8799,
      "step": 11
    },
    {
      "epoch": 0.03746341463414634,
      "grad_norm": 2.3049380779266357,
      "learning_rate": 6.415552058736854e-05,
      "loss": 7.7871,
      "step": 12
    },
    {
      "epoch": 0.04058536585365854,
      "grad_norm": 1.9474453926086426,
      "learning_rate": 5.80709086014102e-05,
      "loss": 7.7129,
      "step": 13
    },
    {
      "epoch": 0.04370731707317073,
      "grad_norm": 1.7848256826400757,
      "learning_rate": 5.192909139858981e-05,
      "loss": 7.8224,
      "step": 14
    },
    {
      "epoch": 0.04682926829268293,
      "grad_norm": 1.7634596824645996,
      "learning_rate": 4.584447941263149e-05,
      "loss": 7.8094,
      "step": 15
    },
    {
      "epoch": 0.049951219512195125,
      "grad_norm": 1.7062458992004395,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 7.6345,
      "step": 16
    },
    {
      "epoch": 0.053073170731707316,
      "grad_norm": 1.6087889671325684,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 7.5839,
      "step": 17
    },
    {
      "epoch": 0.056195121951219514,
      "grad_norm": 1.5590335130691528,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 7.6765,
      "step": 18
    },
    {
      "epoch": 0.059317073170731704,
      "grad_norm": 1.6086766719818115,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 7.6771,
      "step": 19
    },
    {
      "epoch": 0.0624390243902439,
      "grad_norm": 1.5486078262329102,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 7.6274,
      "step": 20
    },
    {
      "epoch": 0.0655609756097561,
      "grad_norm": 1.5740314722061157,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 7.6517,
      "step": 21
    },
    {
      "epoch": 0.0686829268292683,
      "grad_norm": 1.5726820230484009,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 7.5514,
      "step": 22
    },
    {
      "epoch": 0.07180487804878048,
      "grad_norm": 1.544975996017456,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 7.613,
      "step": 23
    },
    {
      "epoch": 0.07492682926829268,
      "grad_norm": 1.5659458637237549,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 7.5893,
      "step": 24
    },
    {
      "epoch": 0.07804878048780488,
      "grad_norm": 1.5587267875671387,
      "learning_rate": 1e-05,
      "loss": 7.4812,
      "step": 25
    },
    {
      "epoch": 0.07804878048780488,
      "eval_loss": 7.642526149749756,
      "eval_runtime": 0.971,
      "eval_samples_per_second": 51.495,
      "eval_steps_per_second": 51.495,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 29037976879104.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}