{
  "best_metric": 1.1075838804244995,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.050200803212851405,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002008032128514056,
      "grad_norm": 0.5316743850708008,
      "learning_rate": 2e-05,
      "loss": 1.2926,
      "step": 1
    },
    {
      "epoch": 0.002008032128514056,
      "eval_loss": 1.366198182106018,
      "eval_runtime": 33.0363,
      "eval_samples_per_second": 6.357,
      "eval_steps_per_second": 3.178,
      "step": 1
    },
    {
      "epoch": 0.004016064257028112,
      "grad_norm": 0.5137491822242737,
      "learning_rate": 4e-05,
      "loss": 1.3676,
      "step": 2
    },
    {
      "epoch": 0.006024096385542169,
      "grad_norm": 0.478731632232666,
      "learning_rate": 6e-05,
      "loss": 1.4289,
      "step": 3
    },
    {
      "epoch": 0.008032128514056224,
      "grad_norm": 0.47497421503067017,
      "learning_rate": 8e-05,
      "loss": 1.3565,
      "step": 4
    },
    {
      "epoch": 0.010040160642570281,
      "grad_norm": 0.5679687857627869,
      "learning_rate": 0.0001,
      "loss": 1.222,
      "step": 5
    },
    {
      "epoch": 0.010040160642570281,
      "eval_loss": 1.346326231956482,
      "eval_runtime": 31.5019,
      "eval_samples_per_second": 6.666,
      "eval_steps_per_second": 3.333,
      "step": 5
    },
    {
      "epoch": 0.012048192771084338,
      "grad_norm": 0.6032833456993103,
      "learning_rate": 0.00012,
      "loss": 1.3786,
      "step": 6
    },
    {
      "epoch": 0.014056224899598393,
      "grad_norm": 0.5019028782844543,
      "learning_rate": 0.00014,
      "loss": 1.0775,
      "step": 7
    },
    {
      "epoch": 0.01606425702811245,
      "grad_norm": 0.5774829983711243,
      "learning_rate": 0.00016,
      "loss": 1.1124,
      "step": 8
    },
    {
      "epoch": 0.018072289156626505,
      "grad_norm": 0.6058626174926758,
      "learning_rate": 0.00018,
      "loss": 0.9779,
      "step": 9
    },
    {
      "epoch": 0.020080321285140562,
      "grad_norm": 0.8557388186454773,
      "learning_rate": 0.0002,
      "loss": 1.1322,
      "step": 10
    },
    {
      "epoch": 0.020080321285140562,
      "eval_loss": 1.2409539222717285,
      "eval_runtime": 31.4916,
      "eval_samples_per_second": 6.668,
      "eval_steps_per_second": 3.334,
      "step": 10
    },
    {
      "epoch": 0.02208835341365462,
      "grad_norm": 0.966452956199646,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.1709,
      "step": 11
    },
    {
      "epoch": 0.024096385542168676,
      "grad_norm": 0.8635215163230896,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.1076,
      "step": 12
    },
    {
      "epoch": 0.02610441767068273,
      "grad_norm": 0.9673819541931152,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.1629,
      "step": 13
    },
    {
      "epoch": 0.028112449799196786,
      "grad_norm": 0.8269699215888977,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.1716,
      "step": 14
    },
    {
      "epoch": 0.030120481927710843,
      "grad_norm": 0.8637534976005554,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3285,
      "step": 15
    },
    {
      "epoch": 0.030120481927710843,
      "eval_loss": 1.159950852394104,
      "eval_runtime": 31.8128,
      "eval_samples_per_second": 6.601,
      "eval_steps_per_second": 3.301,
      "step": 15
    },
    {
      "epoch": 0.0321285140562249,
      "grad_norm": 0.7454081177711487,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1845,
      "step": 16
    },
    {
      "epoch": 0.03413654618473896,
      "grad_norm": 0.8901392817497253,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.015,
      "step": 17
    },
    {
      "epoch": 0.03614457831325301,
      "grad_norm": 0.875340461730957,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.0394,
      "step": 18
    },
    {
      "epoch": 0.03815261044176707,
      "grad_norm": 1.2102932929992676,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.4032,
      "step": 19
    },
    {
      "epoch": 0.040160642570281124,
      "grad_norm": 0.7349887490272522,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.1259,
      "step": 20
    },
    {
      "epoch": 0.040160642570281124,
      "eval_loss": 1.1177598237991333,
      "eval_runtime": 31.8229,
      "eval_samples_per_second": 6.599,
      "eval_steps_per_second": 3.3,
      "step": 20
    },
    {
      "epoch": 0.04216867469879518,
      "grad_norm": 0.7470746040344238,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.1402,
      "step": 21
    },
    {
      "epoch": 0.04417670682730924,
      "grad_norm": 0.8043966293334961,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.0708,
      "step": 22
    },
    {
      "epoch": 0.04618473895582329,
      "grad_norm": 0.7213367223739624,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.0493,
      "step": 23
    },
    {
      "epoch": 0.04819277108433735,
      "grad_norm": 0.7987662553787231,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.0579,
      "step": 24
    },
    {
      "epoch": 0.050200803212851405,
      "grad_norm": 0.6784000992774963,
      "learning_rate": 0.0,
      "loss": 0.9505,
      "step": 25
    },
    {
      "epoch": 0.050200803212851405,
      "eval_loss": 1.1075838804244995,
      "eval_runtime": 31.7049,
      "eval_samples_per_second": 6.624,
      "eval_steps_per_second": 3.312,
      "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": 5317497213419520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}