{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9996440014239943,
  "eval_steps": 250,
  "global_step": 1404,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05055179779280883,
      "grad_norm": 0.6696942448616028,
      "learning_rate": 5.0354609929078e-07,
      "loss": 0.436,
      "step": 71
    },
    {
      "epoch": 0.10110359558561766,
      "grad_norm": 1.0538969039916992,
      "learning_rate": 9.992082343626285e-07,
      "loss": 0.4702,
      "step": 142
    },
    {
      "epoch": 0.15165539337842648,
      "grad_norm": 4.0300822257995605,
      "learning_rate": 9.429928741092636e-07,
      "loss": 0.3861,
      "step": 213
    },
    {
      "epoch": 0.17799928800284798,
      "eval_loss": 0.33530548214912415,
      "eval_runtime": 28.7859,
      "eval_samples_per_second": 17.37,
      "eval_steps_per_second": 8.685,
      "step": 250
    },
    {
      "epoch": 0.2022071911712353,
      "grad_norm": 1.1703342199325562,
      "learning_rate": 8.867775138558986e-07,
      "loss": 0.3824,
      "step": 284
    },
    {
      "epoch": 0.25275898896404414,
      "grad_norm": 1.0430041551589966,
      "learning_rate": 8.305621536025336e-07,
      "loss": 0.3494,
      "step": 355
    },
    {
      "epoch": 0.30331078675685297,
      "grad_norm": 1.1387194395065308,
      "learning_rate": 7.743467933491686e-07,
      "loss": 0.3172,
      "step": 426
    },
    {
      "epoch": 0.3538625845496618,
      "grad_norm": 1.7634204626083374,
      "learning_rate": 7.181314330958036e-07,
      "loss": 0.3075,
      "step": 497
    },
    {
      "epoch": 0.35599857600569595,
      "eval_loss": 0.21360304951667786,
      "eval_runtime": 28.7874,
      "eval_samples_per_second": 17.369,
      "eval_steps_per_second": 8.684,
      "step": 500
    },
    {
      "epoch": 0.4044143823424706,
      "grad_norm": 2.539411783218384,
      "learning_rate": 6.619160728424386e-07,
      "loss": 0.2562,
      "step": 568
    },
    {
      "epoch": 0.45496618013527945,
      "grad_norm": 1.2169667482376099,
      "learning_rate": 6.057007125890736e-07,
      "loss": 0.2832,
      "step": 639
    },
    {
      "epoch": 0.5055179779280883,
      "grad_norm": 1.549967646598816,
      "learning_rate": 5.494853523357086e-07,
      "loss": 0.2606,
      "step": 710
    },
    {
      "epoch": 0.533997864008544,
      "eval_loss": 0.1820104718208313,
      "eval_runtime": 28.7804,
      "eval_samples_per_second": 17.373,
      "eval_steps_per_second": 8.686,
      "step": 750
    },
    {
      "epoch": 0.5560697757208971,
      "grad_norm": 1.2805540561676025,
      "learning_rate": 4.932699920823436e-07,
      "loss": 0.2443,
      "step": 781
    },
    {
      "epoch": 0.6066215735137059,
      "grad_norm": 2.841620683670044,
      "learning_rate": 4.3705463182897863e-07,
      "loss": 0.2421,
      "step": 852
    },
    {
      "epoch": 0.6571733713065148,
      "grad_norm": 1.1338871717453003,
      "learning_rate": 3.808392715756136e-07,
      "loss": 0.2301,
      "step": 923
    },
    {
      "epoch": 0.7077251690993236,
      "grad_norm": 2.319748878479004,
      "learning_rate": 3.246239113222486e-07,
      "loss": 0.2404,
      "step": 994
    },
    {
      "epoch": 0.7119971520113919,
      "eval_loss": 0.16689015924930573,
      "eval_runtime": 28.7832,
      "eval_samples_per_second": 17.371,
      "eval_steps_per_second": 8.686,
      "step": 1000
    },
    {
      "epoch": 0.7582769668921324,
      "grad_norm": 1.218746542930603,
      "learning_rate": 2.684085510688836e-07,
      "loss": 0.2535,
      "step": 1065
    },
    {
      "epoch": 0.8088287646849412,
      "grad_norm": 3.11279296875,
      "learning_rate": 2.1219319081551858e-07,
      "loss": 0.2323,
      "step": 1136
    },
    {
      "epoch": 0.8593805624777501,
      "grad_norm": 2.013932704925537,
      "learning_rate": 1.559778305621536e-07,
      "loss": 0.257,
      "step": 1207
    },
    {
      "epoch": 0.8899964400142399,
      "eval_loss": 0.16124244034290314,
      "eval_runtime": 28.7354,
      "eval_samples_per_second": 17.4,
      "eval_steps_per_second": 8.7,
      "step": 1250
    },
    {
      "epoch": 0.9099323602705589,
      "grad_norm": 1.400206446647644,
      "learning_rate": 9.976247030878859e-08,
      "loss": 0.2368,
      "step": 1278
    },
    {
      "epoch": 0.9604841580633677,
      "grad_norm": 3.216315984725952,
      "learning_rate": 4.35471100554236e-08,
      "loss": 0.217,
      "step": 1349
    },
    {
      "epoch": 0.9996440014239943,
      "step": 1404,
      "total_flos": 1.0823852276239565e+17,
      "train_loss": 0.2917507768016935,
      "train_runtime": 2474.252,
      "train_samples_per_second": 4.541,
      "train_steps_per_second": 0.567
    }
  ],
  "logging_steps": 71,
  "max_steps": 1404,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0823852276239565e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}