{
  "best_metric": 0.5874751210212708,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.004404316229905308,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001761726491962123,
      "grad_norm": 2.332383632659912,
      "learning_rate": 2e-05,
      "loss": 5.4485,
      "step": 1
    },
    {
      "epoch": 0.0001761726491962123,
      "eval_loss": 1.4438605308532715,
      "eval_runtime": 571.794,
      "eval_samples_per_second": 4.182,
      "eval_steps_per_second": 2.092,
      "step": 1
    },
    {
      "epoch": 0.0003523452983924246,
      "grad_norm": 2.122997283935547,
      "learning_rate": 4e-05,
      "loss": 5.9403,
      "step": 2
    },
    {
      "epoch": 0.0005285179475886368,
      "grad_norm": 1.7124838829040527,
      "learning_rate": 6e-05,
      "loss": 5.8954,
      "step": 3
    },
    {
      "epoch": 0.0007046905967848492,
      "grad_norm": 2.1239173412323,
      "learning_rate": 8e-05,
      "loss": 6.1843,
      "step": 4
    },
    {
      "epoch": 0.0008808632459810614,
      "grad_norm": 2.4349913597106934,
      "learning_rate": 0.0001,
      "loss": 6.1111,
      "step": 5
    },
    {
      "epoch": 0.0008808632459810614,
      "eval_loss": 1.3875905275344849,
      "eval_runtime": 569.4516,
      "eval_samples_per_second": 4.199,
      "eval_steps_per_second": 2.1,
      "step": 5
    },
    {
      "epoch": 0.0010570358951772737,
      "grad_norm": 2.5872058868408203,
      "learning_rate": 0.00012,
      "loss": 5.7241,
      "step": 6
    },
    {
      "epoch": 0.001233208544373486,
      "grad_norm": 8.501934051513672,
      "learning_rate": 0.00014,
      "loss": 5.2702,
      "step": 7
    },
    {
      "epoch": 0.0014093811935696984,
      "grad_norm": 3.1528971195220947,
      "learning_rate": 0.00016,
      "loss": 5.2025,
      "step": 8
    },
    {
      "epoch": 0.0015855538427659106,
      "grad_norm": 2.290623903274536,
      "learning_rate": 0.00018,
      "loss": 4.6755,
      "step": 9
    },
    {
      "epoch": 0.0017617264919621229,
      "grad_norm": 2.251638174057007,
      "learning_rate": 0.0002,
      "loss": 4.4578,
      "step": 10
    },
    {
      "epoch": 0.0017617264919621229,
      "eval_loss": 1.096996784210205,
      "eval_runtime": 568.5351,
      "eval_samples_per_second": 4.206,
      "eval_steps_per_second": 2.104,
      "step": 10
    },
    {
      "epoch": 0.0019378991411583351,
      "grad_norm": 2.7614033222198486,
      "learning_rate": 0.00019781476007338058,
      "loss": 4.675,
      "step": 11
    },
    {
      "epoch": 0.0021140717903545474,
      "grad_norm": 2.6491050720214844,
      "learning_rate": 0.0001913545457642601,
      "loss": 4.0089,
      "step": 12
    },
    {
      "epoch": 0.00229024443955076,
      "grad_norm": 2.7330145835876465,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.738,
      "step": 13
    },
    {
      "epoch": 0.002466417088746972,
      "grad_norm": 3.899129629135132,
      "learning_rate": 0.00016691306063588583,
      "loss": 3.2485,
      "step": 14
    },
    {
      "epoch": 0.0026425897379431843,
      "grad_norm": 3.724151134490967,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.1852,
      "step": 15
    },
    {
      "epoch": 0.0026425897379431843,
      "eval_loss": 0.7521843910217285,
      "eval_runtime": 569.0183,
      "eval_samples_per_second": 4.202,
      "eval_steps_per_second": 2.102,
      "step": 15
    },
    {
      "epoch": 0.0028187623871393968,
      "grad_norm": 3.3071093559265137,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.0237,
      "step": 16
    },
    {
      "epoch": 0.002994935036335609,
      "grad_norm": 3.8211424350738525,
      "learning_rate": 0.00011045284632676536,
      "loss": 2.8587,
      "step": 17
    },
    {
      "epoch": 0.0031711076855318212,
      "grad_norm": 4.257937908172607,
      "learning_rate": 8.954715367323468e-05,
      "loss": 2.7275,
      "step": 18
    },
    {
      "epoch": 0.0033472803347280333,
      "grad_norm": 5.022490501403809,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.5972,
      "step": 19
    },
    {
      "epoch": 0.0035234529839242457,
      "grad_norm": 6.477492332458496,
      "learning_rate": 5.000000000000002e-05,
      "loss": 2.4925,
      "step": 20
    },
    {
      "epoch": 0.0035234529839242457,
      "eval_loss": 0.6148508787155151,
      "eval_runtime": 568.4307,
      "eval_samples_per_second": 4.206,
      "eval_steps_per_second": 2.104,
      "step": 20
    },
    {
      "epoch": 0.003699625633120458,
      "grad_norm": 3.870234251022339,
      "learning_rate": 3.308693936411421e-05,
      "loss": 2.6384,
      "step": 21
    },
    {
      "epoch": 0.0038757982823166702,
      "grad_norm": 3.622483730316162,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.3157,
      "step": 22
    },
    {
      "epoch": 0.004051970931512883,
      "grad_norm": 4.57835578918457,
      "learning_rate": 8.645454235739903e-06,
      "loss": 2.6431,
      "step": 23
    },
    {
      "epoch": 0.004228143580709095,
      "grad_norm": 5.53993034362793,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 2.3094,
      "step": 24
    },
    {
      "epoch": 0.004404316229905308,
      "grad_norm": 4.585968494415283,
      "learning_rate": 0.0,
      "loss": 2.3763,
      "step": 25
    },
    {
      "epoch": 0.004404316229905308,
      "eval_loss": 0.5874751210212708,
      "eval_runtime": 568.5406,
      "eval_samples_per_second": 4.206,
      "eval_steps_per_second": 2.104,
      "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": 1.412138652401664e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}