{
  "best_metric": 1.8633633852005005,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.0021141649048626,
  "eval_steps": 50,
  "global_step": 237,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004228329809725159,
      "eval_loss": 2.096205472946167,
      "eval_runtime": 6.3468,
      "eval_samples_per_second": 15.756,
      "eval_steps_per_second": 3.939,
      "step": 1
    },
    {
      "epoch": 0.042283298097251586,
      "grad_norm": 7.564020156860352,
      "learning_rate": 4.24e-05,
      "loss": 3.6687,
      "step": 10
    },
    {
      "epoch": 0.08456659619450317,
      "grad_norm": 5.9212799072265625,
      "learning_rate": 8.48e-05,
      "loss": 3.7253,
      "step": 20
    },
    {
      "epoch": 0.12684989429175475,
      "grad_norm": 6.140769004821777,
      "learning_rate": 0.0001272,
      "loss": 3.7108,
      "step": 30
    },
    {
      "epoch": 0.16913319238900634,
      "grad_norm": 8.776068687438965,
      "learning_rate": 0.0001696,
      "loss": 3.5971,
      "step": 40
    },
    {
      "epoch": 0.21141649048625794,
      "grad_norm": 44.07782745361328,
      "learning_rate": 0.000212,
      "loss": 3.6765,
      "step": 50
    },
    {
      "epoch": 0.21141649048625794,
      "eval_loss": 2.286642074584961,
      "eval_runtime": 6.5576,
      "eval_samples_per_second": 15.249,
      "eval_steps_per_second": 3.812,
      "step": 50
    },
    {
      "epoch": 0.2536997885835095,
      "grad_norm": 5.269192695617676,
      "learning_rate": 0.00021050764994571535,
      "loss": 3.8943,
      "step": 60
    },
    {
      "epoch": 0.2959830866807611,
      "grad_norm": 5.10400390625,
      "learning_rate": 0.00020607262070143734,
      "loss": 3.5937,
      "step": 70
    },
    {
      "epoch": 0.3382663847780127,
      "grad_norm": 6.93461275100708,
      "learning_rate": 0.00019881979181685374,
      "loss": 3.7963,
      "step": 80
    },
    {
      "epoch": 0.38054968287526425,
      "grad_norm": 10.116086959838867,
      "learning_rate": 0.00018895338517082536,
      "loss": 3.8322,
      "step": 90
    },
    {
      "epoch": 0.42283298097251587,
      "grad_norm": 48.350345611572266,
      "learning_rate": 0.00017675121458398993,
      "loss": 3.6459,
      "step": 100
    },
    {
      "epoch": 0.42283298097251587,
      "eval_loss": 2.329221248626709,
      "eval_runtime": 6.5526,
      "eval_samples_per_second": 15.261,
      "eval_steps_per_second": 3.815,
      "step": 100
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 5.142873287200928,
      "learning_rate": 0.0001625568632627182,
      "loss": 3.9402,
      "step": 110
    },
    {
      "epoch": 0.507399577167019,
      "grad_norm": 5.514346122741699,
      "learning_rate": 0.0001467700093384222,
      "loss": 3.8567,
      "step": 120
    },
    {
      "epoch": 0.5496828752642706,
      "grad_norm": 6.7151103019714355,
      "learning_rate": 0.00012983517191130775,
      "loss": 3.6157,
      "step": 130
    },
    {
      "epoch": 0.5919661733615222,
      "grad_norm": 7.746840000152588,
      "learning_rate": 0.00011222919448238718,
      "loss": 3.9139,
      "step": 140
    },
    {
      "epoch": 0.6342494714587738,
      "grad_norm": 28.235681533813477,
      "learning_rate": 9.444781820961864e-05,
      "loss": 3.6412,
      "step": 150
    },
    {
      "epoch": 0.6342494714587738,
      "eval_loss": 2.091932773590088,
      "eval_runtime": 6.5409,
      "eval_samples_per_second": 15.288,
      "eval_steps_per_second": 3.822,
      "step": 150
    },
    {
      "epoch": 0.6765327695560254,
      "grad_norm": 5.661881923675537,
      "learning_rate": 7.699172305235922e-05,
      "loss": 3.8396,
      "step": 160
    },
    {
      "epoch": 0.718816067653277,
      "grad_norm": 7.51119327545166,
      "learning_rate": 6.035242985127933e-05,
      "loss": 3.8834,
      "step": 170
    },
    {
      "epoch": 0.7610993657505285,
      "grad_norm": 7.847259998321533,
      "learning_rate": 4.4998460306603325e-05,
      "loss": 3.938,
      "step": 180
    },
    {
      "epoch": 0.8033826638477801,
      "grad_norm": 6.869880676269531,
      "learning_rate": 3.136214455575538e-05,
      "loss": 3.6543,
      "step": 190
    },
    {
      "epoch": 0.8456659619450317,
      "grad_norm": 22.58540916442871,
      "learning_rate": 1.9827447816679272e-05,
      "loss": 3.3961,
      "step": 200
    },
    {
      "epoch": 0.8456659619450317,
      "eval_loss": 1.8633633852005005,
      "eval_runtime": 6.5539,
      "eval_samples_per_second": 15.258,
      "eval_steps_per_second": 3.815,
      "step": 200
    },
    {
      "epoch": 0.8879492600422833,
      "grad_norm": 5.115078449249268,
      "learning_rate": 1.0719158868709316e-05,
      "loss": 3.8714,
      "step": 210
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 6.137579441070557,
      "learning_rate": 4.29374479686329e-06,
      "loss": 3.8645,
      "step": 220
    },
    {
      "epoch": 0.9725158562367865,
      "grad_norm": 7.499491214752197,
      "learning_rate": 7.321295075359002e-07,
      "loss": 3.5654,
      "step": 230
    }
  ],
  "logging_steps": 10,
  "max_steps": 237,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 4.371259110457344e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}