{
  "best_metric": 0.15553146600723267,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.017752529735487306,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007101011894194922,
      "grad_norm": 0.7088547945022583,
      "learning_rate": 2e-05,
      "loss": 0.4879,
      "step": 1
    },
    {
      "epoch": 0.0007101011894194922,
      "eval_loss": 0.48425838351249695,
      "eval_runtime": 174.3603,
      "eval_samples_per_second": 3.401,
      "eval_steps_per_second": 1.703,
      "step": 1
    },
    {
      "epoch": 0.0014202023788389845,
      "grad_norm": 0.6956668496131897,
      "learning_rate": 4e-05,
      "loss": 0.4399,
      "step": 2
    },
    {
      "epoch": 0.002130303568258477,
      "grad_norm": 0.7884685397148132,
      "learning_rate": 6e-05,
      "loss": 0.4986,
      "step": 3
    },
    {
      "epoch": 0.002840404757677969,
      "grad_norm": 0.652370274066925,
      "learning_rate": 8e-05,
      "loss": 0.4597,
      "step": 4
    },
    {
      "epoch": 0.0035505059470974615,
      "grad_norm": 0.5573405623435974,
      "learning_rate": 0.0001,
      "loss": 0.4164,
      "step": 5
    },
    {
      "epoch": 0.0035505059470974615,
      "eval_loss": 0.3724066913127899,
      "eval_runtime": 174.2204,
      "eval_samples_per_second": 3.404,
      "eval_steps_per_second": 1.705,
      "step": 5
    },
    {
      "epoch": 0.004260607136516954,
      "grad_norm": 0.4771481454372406,
      "learning_rate": 0.00012,
      "loss": 0.3851,
      "step": 6
    },
    {
      "epoch": 0.004970708325936446,
      "grad_norm": 0.559291660785675,
      "learning_rate": 0.00014,
      "loss": 0.3149,
      "step": 7
    },
    {
      "epoch": 0.005680809515355938,
      "grad_norm": 0.4687493145465851,
      "learning_rate": 0.00016,
      "loss": 0.3091,
      "step": 8
    },
    {
      "epoch": 0.00639091070477543,
      "grad_norm": 0.4188617467880249,
      "learning_rate": 0.00018,
      "loss": 0.2673,
      "step": 9
    },
    {
      "epoch": 0.007101011894194923,
      "grad_norm": 0.38055554032325745,
      "learning_rate": 0.0002,
      "loss": 0.2534,
      "step": 10
    },
    {
      "epoch": 0.007101011894194923,
      "eval_loss": 0.230683833360672,
      "eval_runtime": 174.0967,
      "eval_samples_per_second": 3.406,
      "eval_steps_per_second": 1.706,
      "step": 10
    },
    {
      "epoch": 0.0078111130836144155,
      "grad_norm": 0.37593263387680054,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.2421,
      "step": 11
    },
    {
      "epoch": 0.008521214273033907,
      "grad_norm": 0.39975905418395996,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.2147,
      "step": 12
    },
    {
      "epoch": 0.009231315462453399,
      "grad_norm": 0.3451046347618103,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.2199,
      "step": 13
    },
    {
      "epoch": 0.009941416651872892,
      "grad_norm": 0.30507731437683105,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.1502,
      "step": 14
    },
    {
      "epoch": 0.010651517841292384,
      "grad_norm": 0.3645358979701996,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.1933,
      "step": 15
    },
    {
      "epoch": 0.010651517841292384,
      "eval_loss": 0.17332763969898224,
      "eval_runtime": 173.1726,
      "eval_samples_per_second": 3.424,
      "eval_steps_per_second": 1.715,
      "step": 15
    },
    {
      "epoch": 0.011361619030711876,
      "grad_norm": 0.29906368255615234,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.1612,
      "step": 16
    },
    {
      "epoch": 0.012071720220131369,
      "grad_norm": 0.31010934710502625,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.1729,
      "step": 17
    },
    {
      "epoch": 0.01278182140955086,
      "grad_norm": 0.29333606362342834,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.1675,
      "step": 18
    },
    {
      "epoch": 0.013491922598970352,
      "grad_norm": 0.3287576735019684,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.1723,
      "step": 19
    },
    {
      "epoch": 0.014202023788389846,
      "grad_norm": 0.26639440655708313,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.1551,
      "step": 20
    },
    {
      "epoch": 0.014202023788389846,
      "eval_loss": 0.15883538126945496,
      "eval_runtime": 172.9527,
      "eval_samples_per_second": 3.429,
      "eval_steps_per_second": 1.717,
      "step": 20
    },
    {
      "epoch": 0.014912124977809338,
      "grad_norm": 0.29583197832107544,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.1597,
      "step": 21
    },
    {
      "epoch": 0.015622226167228831,
      "grad_norm": 0.20675452053546906,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.1089,
      "step": 22
    },
    {
      "epoch": 0.016332327356648323,
      "grad_norm": 0.2454639971256256,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.1296,
      "step": 23
    },
    {
      "epoch": 0.017042428546067814,
      "grad_norm": 0.2648043930530548,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.1249,
      "step": 24
    },
    {
      "epoch": 0.017752529735487306,
      "grad_norm": 0.22896485030651093,
      "learning_rate": 0.0,
      "loss": 0.1387,
      "step": 25
    },
    {
      "epoch": 0.017752529735487306,
      "eval_loss": 0.15553146600723267,
      "eval_runtime": 172.9969,
      "eval_samples_per_second": 3.428,
      "eval_steps_per_second": 1.717,
      "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": 8876602394935296.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}