{
  "best_metric": 0.9011407494544983,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.11695906432748537,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 9.453889846801758,
      "learning_rate": 2e-05,
      "loss": 4.7296,
      "step": 1
    },
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 5.260961055755615,
      "eval_runtime": 26.6337,
      "eval_samples_per_second": 3.379,
      "eval_steps_per_second": 1.69,
      "step": 1
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 10.820595741271973,
      "learning_rate": 4e-05,
      "loss": 4.8983,
      "step": 2
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 9.19504165649414,
      "learning_rate": 6e-05,
      "loss": 4.1725,
      "step": 3
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 9.558367729187012,
      "learning_rate": 8e-05,
      "loss": 4.2239,
      "step": 4
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 9.154425621032715,
      "learning_rate": 0.0001,
      "loss": 4.1621,
      "step": 5
    },
    {
      "epoch": 0.023391812865497075,
      "eval_loss": 4.070769786834717,
      "eval_runtime": 26.4697,
      "eval_samples_per_second": 3.4,
      "eval_steps_per_second": 1.7,
      "step": 5
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 8.579410552978516,
      "learning_rate": 0.00012,
      "loss": 4.1796,
      "step": 6
    },
    {
      "epoch": 0.03274853801169591,
      "grad_norm": 8.45848274230957,
      "learning_rate": 0.00014,
      "loss": 3.1287,
      "step": 7
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": 9.319890975952148,
      "learning_rate": 0.00016,
      "loss": 3.3022,
      "step": 8
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 10.462218284606934,
      "learning_rate": 0.00018,
      "loss": 2.903,
      "step": 9
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 7.063426494598389,
      "learning_rate": 0.0002,
      "loss": 1.8767,
      "step": 10
    },
    {
      "epoch": 0.04678362573099415,
      "eval_loss": 1.9391567707061768,
      "eval_runtime": 26.1689,
      "eval_samples_per_second": 3.439,
      "eval_steps_per_second": 1.72,
      "step": 10
    },
    {
      "epoch": 0.05146198830409357,
      "grad_norm": 9.926719665527344,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.3138,
      "step": 11
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 14.804326057434082,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.9516,
      "step": 12
    },
    {
      "epoch": 0.0608187134502924,
      "grad_norm": 8.775808334350586,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.8863,
      "step": 13
    },
    {
      "epoch": 0.06549707602339182,
      "grad_norm": 6.910097122192383,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.3831,
      "step": 14
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 5.409313201904297,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.7087,
      "step": 15
    },
    {
      "epoch": 0.07017543859649122,
      "eval_loss": 1.1476986408233643,
      "eval_runtime": 26.1721,
      "eval_samples_per_second": 3.439,
      "eval_steps_per_second": 1.719,
      "step": 15
    },
    {
      "epoch": 0.07485380116959064,
      "grad_norm": 9.346149444580078,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.0891,
      "step": 16
    },
    {
      "epoch": 0.07953216374269007,
      "grad_norm": 10.158652305603027,
      "learning_rate": 0.00011045284632676536,
      "loss": 2.0267,
      "step": 17
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 4.964000225067139,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.2333,
      "step": 18
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 5.4748687744140625,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.9683,
      "step": 19
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 5.57765007019043,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.2293,
      "step": 20
    },
    {
      "epoch": 0.0935672514619883,
      "eval_loss": 0.9479895830154419,
      "eval_runtime": 26.3373,
      "eval_samples_per_second": 3.417,
      "eval_steps_per_second": 1.709,
      "step": 20
    },
    {
      "epoch": 0.09824561403508772,
      "grad_norm": 9.377281188964844,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.6739,
      "step": 21
    },
    {
      "epoch": 0.10292397660818714,
      "grad_norm": 3.76743221282959,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.7675,
      "step": 22
    },
    {
      "epoch": 0.10760233918128655,
      "grad_norm": 3.458677053451538,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.3672,
      "step": 23
    },
    {
      "epoch": 0.11228070175438597,
      "grad_norm": 5.041811466217041,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.9003,
      "step": 24
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 3.511387348175049,
      "learning_rate": 0.0,
      "loss": 0.5517,
      "step": 25
    },
    {
      "epoch": 0.11695906432748537,
      "eval_loss": 0.9011407494544983,
      "eval_runtime": 26.3362,
      "eval_samples_per_second": 3.417,
      "eval_steps_per_second": 1.709,
      "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": 5542165107179520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}