{
  "best_metric": 12.4584321975708,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.0673575129533677,
  "eval_steps": 25,
  "global_step": 37,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08290155440414508,
      "grad_norm": 0.01514320820569992,
      "learning_rate": 5e-05,
      "loss": 12.4613,
      "step": 1
    },
    {
      "epoch": 0.08290155440414508,
      "eval_loss": 12.459206581115723,
      "eval_runtime": 0.2163,
      "eval_samples_per_second": 379.053,
      "eval_steps_per_second": 50.849,
      "step": 1
    },
    {
      "epoch": 0.16580310880829016,
      "grad_norm": 0.016940046101808548,
      "learning_rate": 0.0001,
      "loss": 12.4646,
      "step": 2
    },
    {
      "epoch": 0.24870466321243523,
      "grad_norm": 0.020668400451540947,
      "learning_rate": 9.979871469976196e-05,
      "loss": 12.4644,
      "step": 3
    },
    {
      "epoch": 0.3316062176165803,
      "grad_norm": 0.014744357205927372,
      "learning_rate": 9.919647942993148e-05,
      "loss": 12.462,
      "step": 4
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 0.01674213632941246,
      "learning_rate": 9.819814303479267e-05,
      "loss": 12.4649,
      "step": 5
    },
    {
      "epoch": 0.49740932642487046,
      "grad_norm": 0.020822757855057716,
      "learning_rate": 9.681174353198687e-05,
      "loss": 12.4644,
      "step": 6
    },
    {
      "epoch": 0.5803108808290155,
      "grad_norm": 0.015361081808805466,
      "learning_rate": 9.504844339512095e-05,
      "loss": 12.4614,
      "step": 7
    },
    {
      "epoch": 0.6632124352331606,
      "grad_norm": 0.016944194212555885,
      "learning_rate": 9.292243968009331e-05,
      "loss": 12.4609,
      "step": 8
    },
    {
      "epoch": 0.7461139896373057,
      "grad_norm": 0.020996803417801857,
      "learning_rate": 9.045084971874738e-05,
      "loss": 12.4639,
      "step": 9
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 0.01585252955555916,
      "learning_rate": 8.765357330018056e-05,
      "loss": 12.4602,
      "step": 10
    },
    {
      "epoch": 0.9119170984455959,
      "grad_norm": 0.01822737418115139,
      "learning_rate": 8.455313244934324e-05,
      "loss": 12.4607,
      "step": 11
    },
    {
      "epoch": 0.9948186528497409,
      "grad_norm": 0.02217421680688858,
      "learning_rate": 8.117449009293668e-05,
      "loss": 12.4639,
      "step": 12
    },
    {
      "epoch": 1.077720207253886,
      "grad_norm": 0.03750379756093025,
      "learning_rate": 7.754484907260513e-05,
      "loss": 24.2304,
      "step": 13
    },
    {
      "epoch": 1.160621761658031,
      "grad_norm": 0.01910383254289627,
      "learning_rate": 7.369343312364993e-05,
      "loss": 12.4002,
      "step": 14
    },
    {
      "epoch": 1.2435233160621761,
      "grad_norm": 0.022818854078650475,
      "learning_rate": 6.965125158269619e-05,
      "loss": 12.545,
      "step": 15
    },
    {
      "epoch": 1.3264248704663213,
      "grad_norm": 0.01749342679977417,
      "learning_rate": 6.545084971874738e-05,
      "loss": 12.3828,
      "step": 16
    },
    {
      "epoch": 1.4093264248704664,
      "grad_norm": 0.020716814324259758,
      "learning_rate": 6.112604669781572e-05,
      "loss": 12.5032,
      "step": 17
    },
    {
      "epoch": 1.4922279792746114,
      "grad_norm": 0.025025969371199608,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 12.5683,
      "step": 18
    },
    {
      "epoch": 1.5751295336787565,
      "grad_norm": 0.020646177232265472,
      "learning_rate": 5.2243241517525754e-05,
      "loss": 12.3345,
      "step": 19
    },
    {
      "epoch": 1.6580310880829017,
      "grad_norm": 0.022280218079686165,
      "learning_rate": 4.775675848247427e-05,
      "loss": 12.3543,
      "step": 20
    },
    {
      "epoch": 1.7409326424870466,
      "grad_norm": 0.028573088347911835,
      "learning_rate": 4.328833670911724e-05,
      "loss": 12.6777,
      "step": 21
    },
    {
      "epoch": 1.8238341968911918,
      "grad_norm": 0.01995987445116043,
      "learning_rate": 3.887395330218429e-05,
      "loss": 12.3295,
      "step": 22
    },
    {
      "epoch": 1.906735751295337,
      "grad_norm": 0.022720159962773323,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 12.5127,
      "step": 23
    },
    {
      "epoch": 1.9896373056994818,
      "grad_norm": 0.027929486706852913,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 12.5036,
      "step": 24
    },
    {
      "epoch": 2.0725388601036268,
      "grad_norm": 0.04317659139633179,
      "learning_rate": 2.630656687635007e-05,
      "loss": 24.1762,
      "step": 25
    },
    {
      "epoch": 2.0725388601036268,
      "eval_loss": 12.4584321975708,
      "eval_runtime": 0.2152,
      "eval_samples_per_second": 380.993,
      "eval_steps_per_second": 51.109,
      "step": 25
    },
    {
      "epoch": 2.155440414507772,
      "grad_norm": 0.023453839123249054,
      "learning_rate": 2.245515092739488e-05,
      "loss": 12.3639,
      "step": 26
    },
    {
      "epoch": 2.238341968911917,
      "grad_norm": 0.02777229994535446,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 12.6757,
      "step": 27
    },
    {
      "epoch": 2.321243523316062,
      "grad_norm": 0.02316541038453579,
      "learning_rate": 1.544686755065677e-05,
      "loss": 12.2681,
      "step": 28
    },
    {
      "epoch": 2.4041450777202074,
      "grad_norm": 0.02422947622835636,
      "learning_rate": 1.2346426699819458e-05,
      "loss": 12.4471,
      "step": 29
    },
    {
      "epoch": 2.4870466321243523,
      "grad_norm": 0.02776755392551422,
      "learning_rate": 9.549150281252633e-06,
      "loss": 12.5286,
      "step": 30
    },
    {
      "epoch": 2.5699481865284977,
      "grad_norm": 0.022363506257534027,
      "learning_rate": 7.077560319906695e-06,
      "loss": 12.452,
      "step": 31
    },
    {
      "epoch": 2.6528497409326426,
      "grad_norm": 0.024167869240045547,
      "learning_rate": 4.951556604879048e-06,
      "loss": 12.3364,
      "step": 32
    },
    {
      "epoch": 2.7357512953367875,
      "grad_norm": 0.029816903173923492,
      "learning_rate": 3.18825646801314e-06,
      "loss": 12.6708,
      "step": 33
    },
    {
      "epoch": 2.818652849740933,
      "grad_norm": 0.022897807881236076,
      "learning_rate": 1.8018569652073381e-06,
      "loss": 12.2847,
      "step": 34
    },
    {
      "epoch": 2.901554404145078,
      "grad_norm": 0.022587254643440247,
      "learning_rate": 8.035205700685167e-07,
      "loss": 12.4786,
      "step": 35
    },
    {
      "epoch": 2.9844559585492227,
      "grad_norm": 0.028138399124145508,
      "learning_rate": 2.012853002380466e-07,
      "loss": 12.6596,
      "step": 36
    },
    {
      "epoch": 3.0673575129533677,
      "grad_norm": 0.04486376419663429,
      "learning_rate": 0.0,
      "loss": 24.0609,
      "step": 37
    }
  ],
  "logging_steps": 1,
  "max_steps": 37,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 623860776960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}