{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4043807919123842,
  "eval_steps": 15,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02527379949452401,
      "grad_norm": 14.990800857543945,
      "learning_rate": 9.999802884287873e-06,
      "loss": 2.5024,
      "step": 15
    },
    {
      "epoch": 0.02527379949452401,
      "eval_loss": 2.251873016357422,
      "eval_runtime": 2381.2021,
      "eval_samples_per_second": 0.519,
      "eval_steps_per_second": 0.13,
      "step": 15
    },
    {
      "epoch": 0.05054759898904802,
      "grad_norm": 11.093191146850586,
      "learning_rate": 9.996846459432971e-06,
      "loss": 2.0154,
      "step": 30
    },
    {
      "epoch": 0.05054759898904802,
      "eval_loss": 1.9771775007247925,
      "eval_runtime": 2379.4231,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 30
    },
    {
      "epoch": 0.07582139848357203,
      "grad_norm": 10.310027122497559,
      "learning_rate": 9.990344375946395e-06,
      "loss": 1.8536,
      "step": 45
    },
    {
      "epoch": 0.07582139848357203,
      "eval_loss": 1.8929402828216553,
      "eval_runtime": 2379.7201,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 45
    },
    {
      "epoch": 0.10109519797809605,
      "grad_norm": 14.144546508789062,
      "learning_rate": 9.980301247571758e-06,
      "loss": 1.8062,
      "step": 60
    },
    {
      "epoch": 0.10109519797809605,
      "eval_loss": 1.8586353063583374,
      "eval_runtime": 2379.9138,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 60
    },
    {
      "epoch": 0.12636899747262004,
      "grad_norm": 12.928871154785156,
      "learning_rate": 9.966724200704695e-06,
      "loss": 1.8739,
      "step": 75
    },
    {
      "epoch": 0.12636899747262004,
      "eval_loss": 1.8373581171035767,
      "eval_runtime": 2379.1727,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 75
    },
    {
      "epoch": 0.15164279696714406,
      "grad_norm": 11.413592338562012,
      "learning_rate": 9.94962286933613e-06,
      "loss": 1.8687,
      "step": 90
    },
    {
      "epoch": 0.15164279696714406,
      "eval_loss": 1.8189234733581543,
      "eval_runtime": 2379.5736,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 90
    },
    {
      "epoch": 0.17691659646166807,
      "grad_norm": 10.060262680053711,
      "learning_rate": 9.929009388216183e-06,
      "loss": 1.749,
      "step": 105
    },
    {
      "epoch": 0.17691659646166807,
      "eval_loss": 1.8106799125671387,
      "eval_runtime": 2379.2612,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 105
    },
    {
      "epoch": 0.2021903959561921,
      "grad_norm": 11.168642044067383,
      "learning_rate": 9.904898384243608e-06,
      "loss": 1.826,
      "step": 120
    },
    {
      "epoch": 0.2021903959561921,
      "eval_loss": 1.8040649890899658,
      "eval_runtime": 2380.0282,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 120
    },
    {
      "epoch": 0.22746419545071608,
      "grad_norm": 9.17194938659668,
      "learning_rate": 9.877306966086854e-06,
      "loss": 1.7828,
      "step": 135
    },
    {
      "epoch": 0.22746419545071608,
      "eval_loss": 1.7994695901870728,
      "eval_runtime": 2379.6821,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 135
    },
    {
      "epoch": 0.2527379949452401,
      "grad_norm": 9.84255599975586,
      "learning_rate": 9.846254712044102e-06,
      "loss": 1.7225,
      "step": 150
    },
    {
      "epoch": 0.2527379949452401,
      "eval_loss": 1.7961242198944092,
      "eval_runtime": 2379.9202,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 150
    },
    {
      "epoch": 0.2780117944397641,
      "grad_norm": 8.864015579223633,
      "learning_rate": 9.811763656150912e-06,
      "loss": 1.8227,
      "step": 165
    },
    {
      "epoch": 0.2780117944397641,
      "eval_loss": 1.7934980392456055,
      "eval_runtime": 2379.8003,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 165
    },
    {
      "epoch": 0.3032855939342881,
      "grad_norm": 10.471166610717773,
      "learning_rate": 9.773858272545329e-06,
      "loss": 1.7436,
      "step": 180
    },
    {
      "epoch": 0.3032855939342881,
      "eval_loss": 1.791121006011963,
      "eval_runtime": 2379.8892,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 180
    },
    {
      "epoch": 0.32855939342881213,
      "grad_norm": 12.403428077697754,
      "learning_rate": 9.732565458101545e-06,
      "loss": 1.843,
      "step": 195
    },
    {
      "epoch": 0.32855939342881213,
      "eval_loss": 1.7891260385513306,
      "eval_runtime": 2379.2135,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 195
    },
    {
      "epoch": 0.35383319292333615,
      "grad_norm": 10.464547157287598,
      "learning_rate": 9.687914513344432e-06,
      "loss": 1.7454,
      "step": 210
    },
    {
      "epoch": 0.35383319292333615,
      "eval_loss": 1.78617262840271,
      "eval_runtime": 2378.8348,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 210
    },
    {
      "epoch": 0.37910699241786017,
      "grad_norm": 8.834742546081543,
      "learning_rate": 9.639937121658492e-06,
      "loss": 1.7015,
      "step": 225
    },
    {
      "epoch": 0.37910699241786017,
      "eval_loss": 1.7838687896728516,
      "eval_runtime": 2379.7979,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 225
    },
    {
      "epoch": 0.4043807919123842,
      "grad_norm": 8.59927749633789,
      "learning_rate": 9.588667326805996e-06,
      "loss": 1.7009,
      "step": 240
    },
    {
      "epoch": 0.4043807919123842,
      "eval_loss": 1.7831588983535767,
      "eval_runtime": 2379.7143,
      "eval_samples_per_second": 0.52,
      "eval_steps_per_second": 0.13,
      "step": 240
    }
  ],
  "logging_steps": 15,
  "max_steps": 1779,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4792379146940416e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}