{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02294630564479119,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011473152822395595,
      "eval_loss": 0.37808579206466675,
      "eval_runtime": 130.6054,
      "eval_samples_per_second": 28.1,
      "eval_steps_per_second": 14.05,
      "step": 1
    },
    {
      "epoch": 0.0011473152822395595,
      "grad_norm": 0.5192480087280273,
      "learning_rate": 0.0002,
      "loss": 0.1734,
      "step": 10
    },
    {
      "epoch": 0.002294630564479119,
      "grad_norm": 0.0413350947201252,
      "learning_rate": 0.0002,
      "loss": 0.0051,
      "step": 20
    },
    {
      "epoch": 0.0034419458467186783,
      "grad_norm": 0.002669590525329113,
      "learning_rate": 0.0002,
      "loss": 0.0099,
      "step": 30
    },
    {
      "epoch": 0.004589261128958238,
      "grad_norm": 0.06390757113695145,
      "learning_rate": 0.0002,
      "loss": 0.01,
      "step": 40
    },
    {
      "epoch": 0.005736576411197797,
      "grad_norm": 0.0011162913870066404,
      "learning_rate": 0.0002,
      "loss": 0.0076,
      "step": 50
    },
    {
      "epoch": 0.005736576411197797,
      "eval_loss": 0.004289441276341677,
      "eval_runtime": 130.6395,
      "eval_samples_per_second": 28.093,
      "eval_steps_per_second": 14.046,
      "step": 50
    },
    {
      "epoch": 0.006883891693437357,
      "grad_norm": 0.23345448076725006,
      "learning_rate": 0.0002,
      "loss": 0.0076,
      "step": 60
    },
    {
      "epoch": 0.008031206975676917,
      "grad_norm": 0.24305281043052673,
      "learning_rate": 0.0002,
      "loss": 0.0081,
      "step": 70
    },
    {
      "epoch": 0.009178522257916476,
      "grad_norm": 0.05415942892432213,
      "learning_rate": 0.0002,
      "loss": 0.0032,
      "step": 80
    },
    {
      "epoch": 0.010325837540156035,
      "grad_norm": 0.14089266955852509,
      "learning_rate": 0.0002,
      "loss": 0.0028,
      "step": 90
    },
    {
      "epoch": 0.011473152822395595,
      "grad_norm": 0.4434452950954437,
      "learning_rate": 0.0002,
      "loss": 0.003,
      "step": 100
    },
    {
      "epoch": 0.011473152822395595,
      "eval_loss": 0.005989062134176493,
      "eval_runtime": 130.6565,
      "eval_samples_per_second": 28.089,
      "eval_steps_per_second": 14.044,
      "step": 100
    },
    {
      "epoch": 0.012620468104635154,
      "grad_norm": 0.07541525363922119,
      "learning_rate": 0.0002,
      "loss": 0.0107,
      "step": 110
    },
    {
      "epoch": 0.013767783386874713,
      "grad_norm": 0.1701805144548416,
      "learning_rate": 0.0002,
      "loss": 0.0046,
      "step": 120
    },
    {
      "epoch": 0.014915098669114273,
      "grad_norm": 0.07125061750411987,
      "learning_rate": 0.0002,
      "loss": 0.0031,
      "step": 130
    },
    {
      "epoch": 0.016062413951353834,
      "grad_norm": 0.020574383437633514,
      "learning_rate": 0.0002,
      "loss": 0.004,
      "step": 140
    },
    {
      "epoch": 0.01720972923359339,
      "grad_norm": 0.0034719579853117466,
      "learning_rate": 0.0002,
      "loss": 0.0117,
      "step": 150
    },
    {
      "epoch": 0.01720972923359339,
      "eval_loss": 0.003394440980628133,
      "eval_runtime": 130.6011,
      "eval_samples_per_second": 28.101,
      "eval_steps_per_second": 14.05,
      "step": 150
    },
    {
      "epoch": 0.018357044515832952,
      "grad_norm": 1.1995950937271118,
      "learning_rate": 0.0002,
      "loss": 0.0103,
      "step": 160
    },
    {
      "epoch": 0.01950435979807251,
      "grad_norm": 0.2900412380695343,
      "learning_rate": 0.0002,
      "loss": 0.001,
      "step": 170
    },
    {
      "epoch": 0.02065167508031207,
      "grad_norm": 0.0037594300229102373,
      "learning_rate": 0.0002,
      "loss": 0.0103,
      "step": 180
    },
    {
      "epoch": 0.02179899036255163,
      "grad_norm": 0.0467398539185524,
      "learning_rate": 0.0002,
      "loss": 0.0065,
      "step": 190
    },
    {
      "epoch": 0.02294630564479119,
      "grad_norm": 0.06587290018796921,
      "learning_rate": 0.0002,
      "loss": 0.007,
      "step": 200
    },
    {
      "epoch": 0.02294630564479119,
      "eval_loss": 0.010427200235426426,
      "eval_runtime": 130.676,
      "eval_samples_per_second": 28.085,
      "eval_steps_per_second": 14.042,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.84607147524096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}