{
  "best_metric": 3.7259087562561035,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.027114967462039046,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010845986984815619,
      "grad_norm": 0.4245043396949768,
      "learning_rate": 4e-05,
      "loss": 3.4003,
      "step": 1
    },
    {
      "epoch": 0.0010845986984815619,
      "eval_loss": 4.960307598114014,
      "eval_runtime": 61.399,
      "eval_samples_per_second": 6.336,
      "eval_steps_per_second": 3.176,
      "step": 1
    },
    {
      "epoch": 0.0021691973969631237,
      "grad_norm": 0.5715564489364624,
      "learning_rate": 8e-05,
      "loss": 3.2689,
      "step": 2
    },
    {
      "epoch": 0.0032537960954446853,
      "grad_norm": 0.6942621469497681,
      "learning_rate": 0.00012,
      "loss": 3.5922,
      "step": 3
    },
    {
      "epoch": 0.004338394793926247,
      "grad_norm": 0.7214824557304382,
      "learning_rate": 0.00016,
      "loss": 3.5445,
      "step": 4
    },
    {
      "epoch": 0.005422993492407809,
      "grad_norm": 0.7759473919868469,
      "learning_rate": 0.0002,
      "loss": 3.6989,
      "step": 5
    },
    {
      "epoch": 0.006507592190889371,
      "grad_norm": 0.8291571140289307,
      "learning_rate": 0.00019994532573409262,
      "loss": 3.6764,
      "step": 6
    },
    {
      "epoch": 0.007592190889370932,
      "grad_norm": 0.9556029438972473,
      "learning_rate": 0.00019978136272187747,
      "loss": 3.795,
      "step": 7
    },
    {
      "epoch": 0.008676789587852495,
      "grad_norm": 1.144549012184143,
      "learning_rate": 0.00019950829025450114,
      "loss": 3.7248,
      "step": 8
    },
    {
      "epoch": 0.009761388286334056,
      "grad_norm": 1.3234285116195679,
      "learning_rate": 0.00019912640693269752,
      "loss": 3.4539,
      "step": 9
    },
    {
      "epoch": 0.010845986984815618,
      "grad_norm": 1.3614262342453003,
      "learning_rate": 0.00019863613034027224,
      "loss": 3.6047,
      "step": 10
    },
    {
      "epoch": 0.01193058568329718,
      "grad_norm": 1.3756049871444702,
      "learning_rate": 0.00019803799658748094,
      "loss": 3.5436,
      "step": 11
    },
    {
      "epoch": 0.013015184381778741,
      "grad_norm": 1.3219250440597534,
      "learning_rate": 0.0001973326597248006,
      "loss": 3.5493,
      "step": 12
    },
    {
      "epoch": 0.014099783080260303,
      "grad_norm": 1.5447579622268677,
      "learning_rate": 0.00019652089102773488,
      "loss": 3.8956,
      "step": 13
    },
    {
      "epoch": 0.015184381778741865,
      "grad_norm": 1.5959620475769043,
      "learning_rate": 0.00019560357815343577,
      "loss": 3.6478,
      "step": 14
    },
    {
      "epoch": 0.016268980477223426,
      "grad_norm": 1.4933563470840454,
      "learning_rate": 0.00019458172417006347,
      "loss": 3.42,
      "step": 15
    },
    {
      "epoch": 0.01735357917570499,
      "grad_norm": 1.5751827955245972,
      "learning_rate": 0.0001934564464599461,
      "loss": 3.6736,
      "step": 16
    },
    {
      "epoch": 0.01843817787418655,
      "grad_norm": 1.5476410388946533,
      "learning_rate": 0.00019222897549773848,
      "loss": 3.4862,
      "step": 17
    },
    {
      "epoch": 0.019522776572668113,
      "grad_norm": 1.7731746435165405,
      "learning_rate": 0.00019090065350491626,
      "loss": 3.4728,
      "step": 18
    },
    {
      "epoch": 0.020607375271149676,
      "grad_norm": 1.502807855606079,
      "learning_rate": 0.00018947293298207635,
      "loss": 3.3609,
      "step": 19
    },
    {
      "epoch": 0.021691973969631236,
      "grad_norm": 1.6433446407318115,
      "learning_rate": 0.0001879473751206489,
      "loss": 3.7856,
      "step": 20
    },
    {
      "epoch": 0.0227765726681128,
      "grad_norm": 1.743554949760437,
      "learning_rate": 0.00018632564809575742,
      "loss": 3.8198,
      "step": 21
    },
    {
      "epoch": 0.02386117136659436,
      "grad_norm": 1.7356516122817993,
      "learning_rate": 0.00018460952524209355,
      "loss": 3.5733,
      "step": 22
    },
    {
      "epoch": 0.024945770065075923,
      "grad_norm": 1.7563503980636597,
      "learning_rate": 0.00018280088311480201,
      "loss": 3.2573,
      "step": 23
    },
    {
      "epoch": 0.026030368763557483,
      "grad_norm": 1.850996971130371,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.5953,
      "step": 24
    },
    {
      "epoch": 0.027114967462039046,
      "grad_norm": 1.810422420501709,
      "learning_rate": 0.00017891405093963938,
      "loss": 3.4128,
      "step": 25
    },
    {
      "epoch": 0.027114967462039046,
      "eval_loss": 3.7259087562561035,
      "eval_runtime": 62.2613,
      "eval_samples_per_second": 6.248,
      "eval_steps_per_second": 3.132,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.39742146461696e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}