{
  "best_metric": 2.6323885917663574,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.6896551724137931,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.027586206896551724,
      "grad_norm": 20.118276596069336,
      "learning_rate": 5e-05,
      "loss": 3.3958,
      "step": 1
    },
    {
      "epoch": 0.027586206896551724,
      "eval_loss": 4.764584064483643,
      "eval_runtime": 0.86,
      "eval_samples_per_second": 58.14,
      "eval_steps_per_second": 15.117,
      "step": 1
    },
    {
      "epoch": 0.05517241379310345,
      "grad_norm": 22.756877899169922,
      "learning_rate": 0.0001,
      "loss": 3.8102,
      "step": 2
    },
    {
      "epoch": 0.08275862068965517,
      "grad_norm": 8.257845878601074,
      "learning_rate": 9.958086757163489e-05,
      "loss": 3.8339,
      "step": 3
    },
    {
      "epoch": 0.1103448275862069,
      "grad_norm": 6.507199764251709,
      "learning_rate": 9.833127793065098e-05,
      "loss": 3.8676,
      "step": 4
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 7.025789260864258,
      "learning_rate": 9.627450856774539e-05,
      "loss": 3.7813,
      "step": 5
    },
    {
      "epoch": 0.16551724137931034,
      "grad_norm": 5.6326775550842285,
      "learning_rate": 9.3448873204592e-05,
      "loss": 3.751,
      "step": 6
    },
    {
      "epoch": 0.19310344827586207,
      "grad_norm": 5.803754806518555,
      "learning_rate": 8.990700808169889e-05,
      "loss": 3.6913,
      "step": 7
    },
    {
      "epoch": 0.2206896551724138,
      "grad_norm": 6.287716388702393,
      "learning_rate": 8.571489144483944e-05,
      "loss": 3.5955,
      "step": 8
    },
    {
      "epoch": 0.2482758620689655,
      "grad_norm": 5.784319877624512,
      "learning_rate": 8.095061449516903e-05,
      "loss": 2.8626,
      "step": 9
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 2.5855143070220947,
      "learning_rate": 7.570292669790186e-05,
      "loss": 2.2897,
      "step": 10
    },
    {
      "epoch": 0.30344827586206896,
      "grad_norm": 4.213158130645752,
      "learning_rate": 7.006958254769438e-05,
      "loss": 2.6085,
      "step": 11
    },
    {
      "epoch": 0.3310344827586207,
      "grad_norm": 4.293095111846924,
      "learning_rate": 6.415552058736854e-05,
      "loss": 2.9261,
      "step": 12
    },
    {
      "epoch": 0.3586206896551724,
      "grad_norm": 3.2849106788635254,
      "learning_rate": 5.80709086014102e-05,
      "loss": 2.8206,
      "step": 13
    },
    {
      "epoch": 0.38620689655172413,
      "grad_norm": 3.5932793617248535,
      "learning_rate": 5.192909139858981e-05,
      "loss": 2.7967,
      "step": 14
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 3.160494327545166,
      "learning_rate": 4.584447941263149e-05,
      "loss": 2.8523,
      "step": 15
    },
    {
      "epoch": 0.4413793103448276,
      "grad_norm": 3.3011345863342285,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 2.7635,
      "step": 16
    },
    {
      "epoch": 0.4689655172413793,
      "grad_norm": 3.8994264602661133,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 2.749,
      "step": 17
    },
    {
      "epoch": 0.496551724137931,
      "grad_norm": 4.317175388336182,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 2.3955,
      "step": 18
    },
    {
      "epoch": 0.5241379310344828,
      "grad_norm": 1.8858942985534668,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 1.9815,
      "step": 19
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 1.9497085809707642,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 2.3041,
      "step": 20
    },
    {
      "epoch": 0.5793103448275863,
      "grad_norm": 2.7413644790649414,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 2.6939,
      "step": 21
    },
    {
      "epoch": 0.6068965517241379,
      "grad_norm": 2.6382477283477783,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 2.5998,
      "step": 22
    },
    {
      "epoch": 0.6344827586206897,
      "grad_norm": 3.448988676071167,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 2.5204,
      "step": 23
    },
    {
      "epoch": 0.6620689655172414,
      "grad_norm": 3.105468511581421,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 2.3369,
      "step": 24
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 2.9059195518493652,
      "learning_rate": 1e-05,
      "loss": 2.3646,
      "step": 25
    },
    {
      "epoch": 0.6896551724137931,
      "eval_loss": 2.6323885917663574,
      "eval_runtime": 0.8746,
      "eval_samples_per_second": 57.168,
      "eval_steps_per_second": 14.864,
      "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": 4.16708196040704e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}