{
  "best_metric": 1.1069023609161377,
  "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": 0.5155134797096252,
      "learning_rate": 2e-05,
      "loss": 1.2926,
      "step": 1
    },
    {
      "epoch": 0.002008032128514056,
      "eval_loss": 1.366198182106018,
      "eval_runtime": 43.1393,
      "eval_samples_per_second": 4.868,
      "eval_steps_per_second": 2.434,
      "step": 1
    },
    {
      "epoch": 0.004016064257028112,
      "grad_norm": 0.4950045645236969,
      "learning_rate": 4e-05,
      "loss": 1.3676,
      "step": 2
    },
    {
      "epoch": 0.006024096385542169,
      "grad_norm": 0.455005943775177,
      "learning_rate": 6e-05,
      "loss": 1.4273,
      "step": 3
    },
    {
      "epoch": 0.008032128514056224,
      "grad_norm": 0.4558495283126831,
      "learning_rate": 8e-05,
      "loss": 1.3529,
      "step": 4
    },
    {
      "epoch": 0.010040160642570281,
      "grad_norm": 0.5495745539665222,
      "learning_rate": 0.0001,
      "loss": 1.2247,
      "step": 5
    },
    {
      "epoch": 0.010040160642570281,
      "eval_loss": 1.346940279006958,
      "eval_runtime": 41.5521,
      "eval_samples_per_second": 5.054,
      "eval_steps_per_second": 2.527,
      "step": 5
    },
    {
      "epoch": 0.012048192771084338,
      "grad_norm": 0.5914521217346191,
      "learning_rate": 0.00012,
      "loss": 1.3786,
      "step": 6
    },
    {
      "epoch": 0.014056224899598393,
      "grad_norm": 0.506374716758728,
      "learning_rate": 0.00014,
      "loss": 1.0787,
      "step": 7
    },
    {
      "epoch": 0.01606425702811245,
      "grad_norm": 0.595960259437561,
      "learning_rate": 0.00016,
      "loss": 1.1075,
      "step": 8
    },
    {
      "epoch": 0.018072289156626505,
      "grad_norm": 0.5901023149490356,
      "learning_rate": 0.00018,
      "loss": 0.9768,
      "step": 9
    },
    {
      "epoch": 0.020080321285140562,
      "grad_norm": 0.900346577167511,
      "learning_rate": 0.0002,
      "loss": 1.1413,
      "step": 10
    },
    {
      "epoch": 0.020080321285140562,
      "eval_loss": 1.2411974668502808,
      "eval_runtime": 40.9672,
      "eval_samples_per_second": 5.126,
      "eval_steps_per_second": 2.563,
      "step": 10
    },
    {
      "epoch": 0.02208835341365462,
      "grad_norm": 1.008229374885559,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.1722,
      "step": 11
    },
    {
      "epoch": 0.024096385542168676,
      "grad_norm": 0.8678027987480164,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.1109,
      "step": 12
    },
    {
      "epoch": 0.02610441767068273,
      "grad_norm": 0.9450435042381287,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.1563,
      "step": 13
    },
    {
      "epoch": 0.028112449799196786,
      "grad_norm": 0.816157877445221,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.1604,
      "step": 14
    },
    {
      "epoch": 0.030120481927710843,
      "grad_norm": 0.8615245223045349,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3244,
      "step": 15
    },
    {
      "epoch": 0.030120481927710843,
      "eval_loss": 1.1586683988571167,
      "eval_runtime": 41.0322,
      "eval_samples_per_second": 5.118,
      "eval_steps_per_second": 2.559,
      "step": 15
    },
    {
      "epoch": 0.0321285140562249,
      "grad_norm": 0.7571508884429932,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1881,
      "step": 16
    },
    {
      "epoch": 0.03413654618473896,
      "grad_norm": 0.8747928142547607,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.0047,
      "step": 17
    },
    {
      "epoch": 0.03614457831325301,
      "grad_norm": 0.8475907444953918,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.0417,
      "step": 18
    },
    {
      "epoch": 0.03815261044176707,
      "grad_norm": 1.19319486618042,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.4018,
      "step": 19
    },
    {
      "epoch": 0.040160642570281124,
      "grad_norm": 0.7098384499549866,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.1257,
      "step": 20
    },
    {
      "epoch": 0.040160642570281124,
      "eval_loss": 1.1164677143096924,
      "eval_runtime": 41.0533,
      "eval_samples_per_second": 5.115,
      "eval_steps_per_second": 2.558,
      "step": 20
    },
    {
      "epoch": 0.04216867469879518,
      "grad_norm": 0.7288839817047119,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.1363,
      "step": 21
    },
    {
      "epoch": 0.04417670682730924,
      "grad_norm": 0.81972736120224,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.0716,
      "step": 22
    },
    {
      "epoch": 0.04618473895582329,
      "grad_norm": 0.6999672055244446,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.0502,
      "step": 23
    },
    {
      "epoch": 0.04819277108433735,
      "grad_norm": 0.7532836198806763,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.0596,
      "step": 24
    },
    {
      "epoch": 0.050200803212851405,
      "grad_norm": 0.6574884057044983,
      "learning_rate": 0.0,
      "loss": 0.9523,
      "step": 25
    },
    {
      "epoch": 0.050200803212851405,
      "eval_loss": 1.1069023609161377,
      "eval_runtime": 40.9698,
      "eval_samples_per_second": 5.126,
      "eval_steps_per_second": 2.563,
      "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
}