{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3931932558073412,
  "eval_steps": 7000,
  "global_step": 49000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19902760797247732,
      "grad_norm": 0.001206448650918901,
      "learning_rate": 9.945984363894813e-06,
      "loss": 0.0113,
      "step": 7000
    },
    {
      "epoch": 0.19902760797247732,
      "eval_loss": 0.003107509110122919,
      "eval_runtime": 304.4798,
      "eval_samples_per_second": 231.02,
      "eval_steps_per_second": 28.879,
      "step": 7000
    },
    {
      "epoch": 0.39805521594495463,
      "grad_norm": 0.26781165599823,
      "learning_rate": 8.900753471180123e-06,
      "loss": 0.0022,
      "step": 14000
    },
    {
      "epoch": 0.39805521594495463,
      "eval_loss": 0.0018909029895439744,
      "eval_runtime": 304.1801,
      "eval_samples_per_second": 231.248,
      "eval_steps_per_second": 28.907,
      "step": 14000
    },
    {
      "epoch": 0.597082823917432,
      "grad_norm": 0.00027483125450089574,
      "learning_rate": 7.795346486170566e-06,
      "loss": 0.0019,
      "step": 21000
    },
    {
      "epoch": 0.597082823917432,
      "eval_loss": 0.0012107242364436388,
      "eval_runtime": 304.0636,
      "eval_samples_per_second": 231.336,
      "eval_steps_per_second": 28.918,
      "step": 21000
    },
    {
      "epoch": 0.7961104318899093,
      "grad_norm": 0.21627014875411987,
      "learning_rate": 6.6900974615761295e-06,
      "loss": 0.0017,
      "step": 28000
    },
    {
      "epoch": 0.7961104318899093,
      "eval_loss": 0.001225769054144621,
      "eval_runtime": 304.172,
      "eval_samples_per_second": 231.254,
      "eval_steps_per_second": 28.908,
      "step": 28000
    },
    {
      "epoch": 0.9951380398623866,
      "grad_norm": 0.003856346942484379,
      "learning_rate": 5.584690476566573e-06,
      "loss": 0.0013,
      "step": 35000
    },
    {
      "epoch": 0.9951380398623866,
      "eval_loss": 0.0011495049111545086,
      "eval_runtime": 304.9212,
      "eval_samples_per_second": 230.686,
      "eval_steps_per_second": 28.837,
      "step": 35000
    },
    {
      "epoch": 1.194165647834864,
      "grad_norm": 0.00557931000366807,
      "learning_rate": 4.479283491557016e-06,
      "loss": 0.0012,
      "step": 42000
    },
    {
      "epoch": 1.194165647834864,
      "eval_loss": 0.0007833261624909937,
      "eval_runtime": 304.4978,
      "eval_samples_per_second": 231.007,
      "eval_steps_per_second": 28.877,
      "step": 42000
    },
    {
      "epoch": 1.3931932558073412,
      "grad_norm": 0.0003088970552198589,
      "learning_rate": 3.374192427377699e-06,
      "loss": 0.0005,
      "step": 49000
    },
    {
      "epoch": 1.3931932558073412,
      "eval_loss": 0.0007826934452168643,
      "eval_runtime": 305.4918,
      "eval_samples_per_second": 230.255,
      "eval_steps_per_second": 28.783,
      "step": 49000
    }
  ],
  "logging_steps": 7000,
  "max_steps": 70342,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 7000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}