{
  "best_metric": 0.36690789461135864,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.2631578947368421,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 1.0870928764343262,
      "learning_rate": 2e-05,
      "loss": 3.4612,
      "step": 1
    },
    {
      "epoch": 0.010526315789473684,
      "eval_loss": 0.7197428941726685,
      "eval_runtime": 3.9729,
      "eval_samples_per_second": 10.068,
      "eval_steps_per_second": 5.034,
      "step": 1
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 0.9755366444587708,
      "learning_rate": 4e-05,
      "loss": 3.104,
      "step": 2
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 0.7761987447738647,
      "learning_rate": 6e-05,
      "loss": 2.4196,
      "step": 3
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.8784200549125671,
      "learning_rate": 8e-05,
      "loss": 2.902,
      "step": 4
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.8273226618766785,
      "learning_rate": 0.0001,
      "loss": 2.5755,
      "step": 5
    },
    {
      "epoch": 0.05263157894736842,
      "eval_loss": 0.6998571157455444,
      "eval_runtime": 3.9846,
      "eval_samples_per_second": 10.039,
      "eval_steps_per_second": 5.019,
      "step": 5
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 0.9461911916732788,
      "learning_rate": 0.00012,
      "loss": 2.7621,
      "step": 6
    },
    {
      "epoch": 0.07368421052631578,
      "grad_norm": 0.9055727124214172,
      "learning_rate": 0.00014,
      "loss": 2.6826,
      "step": 7
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 1.1680424213409424,
      "learning_rate": 0.00016,
      "loss": 3.0118,
      "step": 8
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": 1.1653456687927246,
      "learning_rate": 0.00018,
      "loss": 2.7572,
      "step": 9
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 1.1418049335479736,
      "learning_rate": 0.0002,
      "loss": 2.3654,
      "step": 10
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 0.6033050417900085,
      "eval_runtime": 3.998,
      "eval_samples_per_second": 10.005,
      "eval_steps_per_second": 5.003,
      "step": 10
    },
    {
      "epoch": 0.11578947368421053,
      "grad_norm": 1.2643702030181885,
      "learning_rate": 0.00019781476007338058,
      "loss": 2.2008,
      "step": 11
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 1.4370661973953247,
      "learning_rate": 0.0001913545457642601,
      "loss": 2.2978,
      "step": 12
    },
    {
      "epoch": 0.1368421052631579,
      "grad_norm": 1.1910825967788696,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.0416,
      "step": 13
    },
    {
      "epoch": 0.14736842105263157,
      "grad_norm": 1.0816625356674194,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.6082,
      "step": 14
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.365301489830017,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.8904,
      "step": 15
    },
    {
      "epoch": 0.15789473684210525,
      "eval_loss": 0.45089927315711975,
      "eval_runtime": 4.025,
      "eval_samples_per_second": 9.938,
      "eval_steps_per_second": 4.969,
      "step": 15
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 1.49168062210083,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.9989,
      "step": 16
    },
    {
      "epoch": 0.17894736842105263,
      "grad_norm": 1.6018949747085571,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.7835,
      "step": 17
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 1.7904855012893677,
      "learning_rate": 8.954715367323468e-05,
      "loss": 2.0032,
      "step": 18
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.5119364261627197,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.6474,
      "step": 19
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.9528592824935913,
      "learning_rate": 5.000000000000002e-05,
      "loss": 2.0977,
      "step": 20
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 0.3827160894870758,
      "eval_runtime": 3.9865,
      "eval_samples_per_second": 10.034,
      "eval_steps_per_second": 5.017,
      "step": 20
    },
    {
      "epoch": 0.22105263157894736,
      "grad_norm": 1.524560809135437,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.3287,
      "step": 21
    },
    {
      "epoch": 0.23157894736842105,
      "grad_norm": 1.800046682357788,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.7179,
      "step": 22
    },
    {
      "epoch": 0.24210526315789474,
      "grad_norm": 1.430746078491211,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.2868,
      "step": 23
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 1.7906553745269775,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.5813,
      "step": 24
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 1.4507813453674316,
      "learning_rate": 0.0,
      "loss": 1.409,
      "step": 25
    },
    {
      "epoch": 0.2631578947368421,
      "eval_loss": 0.36690789461135864,
      "eval_runtime": 3.9921,
      "eval_samples_per_second": 10.02,
      "eval_steps_per_second": 5.01,
      "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": 746823509606400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}