{
  "best_metric": 1.940207600593567,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.0,
  "eval_steps": 25,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 2.6908509731292725,
      "learning_rate": 2e-05,
      "loss": 3.3476,
      "step": 1
    },
    {
      "epoch": 0.037037037037037035,
      "eval_loss": 3.1031181812286377,
      "eval_runtime": 3.1419,
      "eval_samples_per_second": 14.641,
      "eval_steps_per_second": 1.91,
      "step": 1
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.918897867202759,
      "learning_rate": 4e-05,
      "loss": 3.2139,
      "step": 2
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 2.835937261581421,
      "learning_rate": 6e-05,
      "loss": 2.8209,
      "step": 3
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 3.0771942138671875,
      "learning_rate": 8e-05,
      "loss": 2.954,
      "step": 4
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 2.512427568435669,
      "learning_rate": 0.0001,
      "loss": 2.4512,
      "step": 5
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 2.5859789848327637,
      "learning_rate": 9.949107209404665e-05,
      "loss": 2.3364,
      "step": 6
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 1.733902931213379,
      "learning_rate": 9.797464868072488e-05,
      "loss": 2.3506,
      "step": 7
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 2.2299413681030273,
      "learning_rate": 9.548159976772592e-05,
      "loss": 2.7624,
      "step": 8
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 3.0543603897094727,
      "learning_rate": 9.206267664155907e-05,
      "loss": 2.1164,
      "step": 9
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.5863101482391357,
      "learning_rate": 8.778747871771292e-05,
      "loss": 1.7827,
      "step": 10
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 1.7515696287155151,
      "learning_rate": 8.274303669726426e-05,
      "loss": 2.278,
      "step": 11
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.6946384906768799,
      "learning_rate": 7.703204087277988e-05,
      "loss": 1.9675,
      "step": 12
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 1.7334179878234863,
      "learning_rate": 7.077075065009433e-05,
      "loss": 2.0629,
      "step": 13
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 1.7637220621109009,
      "learning_rate": 6.408662784207149e-05,
      "loss": 1.9724,
      "step": 14
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.2732926607131958,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 1.9902,
      "step": 15
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.2487651109695435,
      "learning_rate": 5e-05,
      "loss": 1.9001,
      "step": 16
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 1.343316912651062,
      "learning_rate": 4.288425808633575e-05,
      "loss": 1.8352,
      "step": 17
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.3064125776290894,
      "learning_rate": 3.591337215792852e-05,
      "loss": 2.151,
      "step": 18
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 1.4898581504821777,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 1.8626,
      "step": 19
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.7274696826934814,
      "learning_rate": 2.296795912722014e-05,
      "loss": 1.9821,
      "step": 20
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 1.1525099277496338,
      "learning_rate": 1.725696330273575e-05,
      "loss": 1.917,
      "step": 21
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 1.4067116975784302,
      "learning_rate": 1.2212521282287092e-05,
      "loss": 1.6533,
      "step": 22
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 1.2512614727020264,
      "learning_rate": 7.937323358440935e-06,
      "loss": 1.9396,
      "step": 23
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.2110347747802734,
      "learning_rate": 4.5184002322740785e-06,
      "loss": 1.8162,
      "step": 24
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 1.2910479307174683,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 1.8365,
      "step": 25
    },
    {
      "epoch": 0.9259259259259259,
      "eval_loss": 1.940207600593567,
      "eval_runtime": 2.9484,
      "eval_samples_per_second": 15.602,
      "eval_steps_per_second": 2.035,
      "step": 25
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 1.2259421348571777,
      "learning_rate": 5.089279059533658e-07,
      "loss": 1.9491,
      "step": 26
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.2239744663238525,
      "learning_rate": 0.0,
      "loss": 1.9371,
      "step": 27
    }
  ],
  "logging_steps": 1,
  "max_steps": 27,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 2.468309889712128e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}