{
  "best_metric": 0.6794732809066772,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.09149130832570906,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036596523330283625,
      "grad_norm": 13.641276359558105,
      "learning_rate": 2e-05,
      "loss": 6.7335,
      "step": 1
    },
    {
      "epoch": 0.0036596523330283625,
      "eval_loss": 6.834547519683838,
      "eval_runtime": 17.2391,
      "eval_samples_per_second": 6.671,
      "eval_steps_per_second": 3.364,
      "step": 1
    },
    {
      "epoch": 0.007319304666056725,
      "grad_norm": 12.143208503723145,
      "learning_rate": 4e-05,
      "loss": 6.7457,
      "step": 2
    },
    {
      "epoch": 0.010978956999085087,
      "grad_norm": 13.991223335266113,
      "learning_rate": 6e-05,
      "loss": 7.0013,
      "step": 3
    },
    {
      "epoch": 0.01463860933211345,
      "grad_norm": 14.235078811645508,
      "learning_rate": 8e-05,
      "loss": 6.7226,
      "step": 4
    },
    {
      "epoch": 0.018298261665141813,
      "grad_norm": 16.857908248901367,
      "learning_rate": 0.0001,
      "loss": 6.2416,
      "step": 5
    },
    {
      "epoch": 0.018298261665141813,
      "eval_loss": 4.890503883361816,
      "eval_runtime": 16.2114,
      "eval_samples_per_second": 7.094,
      "eval_steps_per_second": 3.578,
      "step": 5
    },
    {
      "epoch": 0.021957913998170174,
      "grad_norm": 21.536624908447266,
      "learning_rate": 0.00012,
      "loss": 5.0447,
      "step": 6
    },
    {
      "epoch": 0.025617566331198535,
      "grad_norm": 12.23508358001709,
      "learning_rate": 0.00014,
      "loss": 3.1408,
      "step": 7
    },
    {
      "epoch": 0.0292772186642269,
      "grad_norm": 7.930720329284668,
      "learning_rate": 0.00016,
      "loss": 1.7007,
      "step": 8
    },
    {
      "epoch": 0.03293687099725526,
      "grad_norm": 3.778163433074951,
      "learning_rate": 0.00018,
      "loss": 0.9994,
      "step": 9
    },
    {
      "epoch": 0.036596523330283626,
      "grad_norm": 2.764580249786377,
      "learning_rate": 0.0002,
      "loss": 0.6292,
      "step": 10
    },
    {
      "epoch": 0.036596523330283626,
      "eval_loss": 0.7933573722839355,
      "eval_runtime": 15.7961,
      "eval_samples_per_second": 7.28,
      "eval_steps_per_second": 3.672,
      "step": 10
    },
    {
      "epoch": 0.04025617566331199,
      "grad_norm": 3.100653648376465,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.7535,
      "step": 11
    },
    {
      "epoch": 0.04391582799634035,
      "grad_norm": 4.180665969848633,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.9231,
      "step": 12
    },
    {
      "epoch": 0.04757548032936871,
      "grad_norm": 1.741687297821045,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.7421,
      "step": 13
    },
    {
      "epoch": 0.05123513266239707,
      "grad_norm": 0.9916728138923645,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.7143,
      "step": 14
    },
    {
      "epoch": 0.05489478499542543,
      "grad_norm": 1.542258620262146,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.624,
      "step": 15
    },
    {
      "epoch": 0.05489478499542543,
      "eval_loss": 0.6847359538078308,
      "eval_runtime": 16.3455,
      "eval_samples_per_second": 7.036,
      "eval_steps_per_second": 3.548,
      "step": 15
    },
    {
      "epoch": 0.0585544373284538,
      "grad_norm": 1.3992561101913452,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.704,
      "step": 16
    },
    {
      "epoch": 0.06221408966148216,
      "grad_norm": 1.114954948425293,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.598,
      "step": 17
    },
    {
      "epoch": 0.06587374199451052,
      "grad_norm": 0.8004631996154785,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.6342,
      "step": 18
    },
    {
      "epoch": 0.06953339432753888,
      "grad_norm": 2.392939329147339,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.9097,
      "step": 19
    },
    {
      "epoch": 0.07319304666056725,
      "grad_norm": 1.1565158367156982,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.5315,
      "step": 20
    },
    {
      "epoch": 0.07319304666056725,
      "eval_loss": 0.6794732809066772,
      "eval_runtime": 16.1432,
      "eval_samples_per_second": 7.124,
      "eval_steps_per_second": 3.593,
      "step": 20
    },
    {
      "epoch": 0.0768526989935956,
      "grad_norm": 1.2884169816970825,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.7178,
      "step": 21
    },
    {
      "epoch": 0.08051235132662397,
      "grad_norm": 0.535166323184967,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.6209,
      "step": 22
    },
    {
      "epoch": 0.08417200365965233,
      "grad_norm": 2.09920334815979,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.9255,
      "step": 23
    },
    {
      "epoch": 0.0878316559926807,
      "grad_norm": 1.7739763259887695,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.7789,
      "step": 24
    },
    {
      "epoch": 0.09149130832570906,
      "grad_norm": 0.6234230995178223,
      "learning_rate": 0.0,
      "loss": 0.5827,
      "step": 25
    },
    {
      "epoch": 0.09149130832570906,
      "eval_loss": 0.6813143491744995,
      "eval_runtime": 16.3123,
      "eval_samples_per_second": 7.05,
      "eval_steps_per_second": 3.556,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4119557308416000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}