{
  "best_metric": 3.3368725776672363,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0034155338479404333,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013662135391761732,
      "grad_norm": 0.41503530740737915,
      "learning_rate": 2e-05,
      "loss": 3.6863,
      "step": 1
    },
    {
      "epoch": 0.00013662135391761732,
      "eval_loss": 3.6566286087036133,
      "eval_runtime": 274.7114,
      "eval_samples_per_second": 11.219,
      "eval_steps_per_second": 5.61,
      "step": 1
    },
    {
      "epoch": 0.00027324270783523464,
      "grad_norm": 0.530142068862915,
      "learning_rate": 4e-05,
      "loss": 3.7816,
      "step": 2
    },
    {
      "epoch": 0.000409864061752852,
      "grad_norm": 0.5074614882469177,
      "learning_rate": 6e-05,
      "loss": 3.6026,
      "step": 3
    },
    {
      "epoch": 0.0005464854156704693,
      "grad_norm": 0.41826096177101135,
      "learning_rate": 8e-05,
      "loss": 3.5327,
      "step": 4
    },
    {
      "epoch": 0.0006831067695880866,
      "grad_norm": 0.4542267620563507,
      "learning_rate": 0.0001,
      "loss": 3.6849,
      "step": 5
    },
    {
      "epoch": 0.0006831067695880866,
      "eval_loss": 3.6481592655181885,
      "eval_runtime": 274.559,
      "eval_samples_per_second": 11.225,
      "eval_steps_per_second": 5.613,
      "step": 5
    },
    {
      "epoch": 0.000819728123505704,
      "grad_norm": 0.4613437354564667,
      "learning_rate": 0.00012,
      "loss": 3.6748,
      "step": 6
    },
    {
      "epoch": 0.0009563494774233213,
      "grad_norm": 0.43140262365341187,
      "learning_rate": 0.00014,
      "loss": 3.6495,
      "step": 7
    },
    {
      "epoch": 0.0010929708313409385,
      "grad_norm": 0.508523166179657,
      "learning_rate": 0.00016,
      "loss": 3.5744,
      "step": 8
    },
    {
      "epoch": 0.001229592185258556,
      "grad_norm": 0.5903449654579163,
      "learning_rate": 0.00018,
      "loss": 3.652,
      "step": 9
    },
    {
      "epoch": 0.0013662135391761731,
      "grad_norm": 0.6628793478012085,
      "learning_rate": 0.0002,
      "loss": 3.6317,
      "step": 10
    },
    {
      "epoch": 0.0013662135391761731,
      "eval_loss": 3.5298969745635986,
      "eval_runtime": 272.1789,
      "eval_samples_per_second": 11.323,
      "eval_steps_per_second": 5.662,
      "step": 10
    },
    {
      "epoch": 0.0015028348930937905,
      "grad_norm": 0.4435620903968811,
      "learning_rate": 0.00019781476007338058,
      "loss": 3.464,
      "step": 11
    },
    {
      "epoch": 0.001639456247011408,
      "grad_norm": 0.43545401096343994,
      "learning_rate": 0.0001913545457642601,
      "loss": 3.4121,
      "step": 12
    },
    {
      "epoch": 0.0017760776009290251,
      "grad_norm": 0.5440512299537659,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.4155,
      "step": 13
    },
    {
      "epoch": 0.0019126989548466425,
      "grad_norm": 0.45815685391426086,
      "learning_rate": 0.00016691306063588583,
      "loss": 3.4596,
      "step": 14
    },
    {
      "epoch": 0.0020493203087642597,
      "grad_norm": 0.5188146829605103,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.4601,
      "step": 15
    },
    {
      "epoch": 0.0020493203087642597,
      "eval_loss": 3.417468786239624,
      "eval_runtime": 273.2435,
      "eval_samples_per_second": 11.279,
      "eval_steps_per_second": 5.64,
      "step": 15
    },
    {
      "epoch": 0.002185941662681877,
      "grad_norm": 0.5342440605163574,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.5198,
      "step": 16
    },
    {
      "epoch": 0.0023225630165994945,
      "grad_norm": 0.6059970855712891,
      "learning_rate": 0.00011045284632676536,
      "loss": 3.4275,
      "step": 17
    },
    {
      "epoch": 0.002459184370517112,
      "grad_norm": 0.5621078014373779,
      "learning_rate": 8.954715367323468e-05,
      "loss": 3.3777,
      "step": 18
    },
    {
      "epoch": 0.0025958057244347293,
      "grad_norm": 0.37497401237487793,
      "learning_rate": 6.909830056250527e-05,
      "loss": 3.2164,
      "step": 19
    },
    {
      "epoch": 0.0027324270783523463,
      "grad_norm": 0.44177472591400146,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.3615,
      "step": 20
    },
    {
      "epoch": 0.0027324270783523463,
      "eval_loss": 3.345660924911499,
      "eval_runtime": 272.3123,
      "eval_samples_per_second": 11.318,
      "eval_steps_per_second": 5.659,
      "step": 20
    },
    {
      "epoch": 0.0028690484322699637,
      "grad_norm": 0.5123682022094727,
      "learning_rate": 3.308693936411421e-05,
      "loss": 3.3068,
      "step": 21
    },
    {
      "epoch": 0.003005669786187581,
      "grad_norm": 0.4870153069496155,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 3.3925,
      "step": 22
    },
    {
      "epoch": 0.0031422911401051985,
      "grad_norm": 0.5168713927268982,
      "learning_rate": 8.645454235739903e-06,
      "loss": 3.3663,
      "step": 23
    },
    {
      "epoch": 0.003278912494022816,
      "grad_norm": 0.4930650293827057,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 3.3488,
      "step": 24
    },
    {
      "epoch": 0.0034155338479404333,
      "grad_norm": 0.28963905572891235,
      "learning_rate": 0.0,
      "loss": 3.2502,
      "step": 25
    },
    {
      "epoch": 0.0034155338479404333,
      "eval_loss": 3.3368725776672363,
      "eval_runtime": 272.0598,
      "eval_samples_per_second": 11.328,
      "eval_steps_per_second": 5.664,
      "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": 1266170292338688.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}