{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 289,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03460207612456748,
      "grad_norm": 20.492570877075195,
      "learning_rate": 9.653979238754326e-06,
      "loss": 0.5193,
      "step": 10
    },
    {
      "epoch": 0.06920415224913495,
      "grad_norm": 13.140957832336426,
      "learning_rate": 9.307958477508652e-06,
      "loss": 0.3286,
      "step": 20
    },
    {
      "epoch": 0.10380622837370242,
      "grad_norm": 3.8919756412506104,
      "learning_rate": 8.961937716262975e-06,
      "loss": 0.1891,
      "step": 30
    },
    {
      "epoch": 0.1384083044982699,
      "grad_norm": 8.864481925964355,
      "learning_rate": 8.615916955017302e-06,
      "loss": 0.2073,
      "step": 40
    },
    {
      "epoch": 0.17301038062283736,
      "grad_norm": 8.466791152954102,
      "learning_rate": 8.269896193771627e-06,
      "loss": 0.0768,
      "step": 50
    },
    {
      "epoch": 0.20761245674740483,
      "grad_norm": 14.27080249786377,
      "learning_rate": 7.923875432525952e-06,
      "loss": 0.1692,
      "step": 60
    },
    {
      "epoch": 0.2422145328719723,
      "grad_norm": 3.208296537399292,
      "learning_rate": 7.577854671280277e-06,
      "loss": 0.1812,
      "step": 70
    },
    {
      "epoch": 0.2768166089965398,
      "grad_norm": 4.197875499725342,
      "learning_rate": 7.2318339100346025e-06,
      "loss": 0.1341,
      "step": 80
    },
    {
      "epoch": 0.31141868512110726,
      "grad_norm": 6.3515825271606445,
      "learning_rate": 6.885813148788928e-06,
      "loss": 0.1277,
      "step": 90
    },
    {
      "epoch": 0.3460207612456747,
      "grad_norm": 4.87689733505249,
      "learning_rate": 6.539792387543253e-06,
      "loss": 0.0761,
      "step": 100
    },
    {
      "epoch": 0.3806228373702422,
      "grad_norm": 2.5042741298675537,
      "learning_rate": 6.193771626297579e-06,
      "loss": 0.059,
      "step": 110
    },
    {
      "epoch": 0.41522491349480967,
      "grad_norm": 5.011392593383789,
      "learning_rate": 5.847750865051903e-06,
      "loss": 0.0985,
      "step": 120
    },
    {
      "epoch": 0.44982698961937717,
      "grad_norm": 4.462304592132568,
      "learning_rate": 5.501730103806229e-06,
      "loss": 0.0964,
      "step": 130
    },
    {
      "epoch": 0.4844290657439446,
      "grad_norm": 7.347049236297607,
      "learning_rate": 5.155709342560554e-06,
      "loss": 0.1312,
      "step": 140
    },
    {
      "epoch": 0.5190311418685121,
      "grad_norm": 6.566490650177002,
      "learning_rate": 4.809688581314879e-06,
      "loss": 0.1423,
      "step": 150
    },
    {
      "epoch": 0.5536332179930796,
      "grad_norm": 8.601099014282227,
      "learning_rate": 4.463667820069205e-06,
      "loss": 0.071,
      "step": 160
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 1.2925947904586792,
      "learning_rate": 4.11764705882353e-06,
      "loss": 0.1023,
      "step": 170
    },
    {
      "epoch": 0.6228373702422145,
      "grad_norm": 9.43086051940918,
      "learning_rate": 3.7716262975778552e-06,
      "loss": 0.1289,
      "step": 180
    },
    {
      "epoch": 0.657439446366782,
      "grad_norm": 5.09530782699585,
      "learning_rate": 3.42560553633218e-06,
      "loss": 0.0939,
      "step": 190
    },
    {
      "epoch": 0.6920415224913494,
      "grad_norm": 11.45658016204834,
      "learning_rate": 3.0795847750865054e-06,
      "loss": 0.0839,
      "step": 200
    },
    {
      "epoch": 0.726643598615917,
      "grad_norm": 3.7783803939819336,
      "learning_rate": 2.7335640138408307e-06,
      "loss": 0.0503,
      "step": 210
    },
    {
      "epoch": 0.7612456747404844,
      "grad_norm": 0.32719558477401733,
      "learning_rate": 2.387543252595156e-06,
      "loss": 0.0956,
      "step": 220
    },
    {
      "epoch": 0.7958477508650519,
      "grad_norm": 3.984323024749756,
      "learning_rate": 2.041522491349481e-06,
      "loss": 0.0761,
      "step": 230
    },
    {
      "epoch": 0.8304498269896193,
      "grad_norm": 3.654313087463379,
      "learning_rate": 1.6955017301038063e-06,
      "loss": 0.0784,
      "step": 240
    },
    {
      "epoch": 0.8650519031141869,
      "grad_norm": 0.20838171243667603,
      "learning_rate": 1.3494809688581318e-06,
      "loss": 0.0666,
      "step": 250
    },
    {
      "epoch": 0.8996539792387543,
      "grad_norm": 13.685569763183594,
      "learning_rate": 1.0034602076124569e-06,
      "loss": 0.089,
      "step": 260
    },
    {
      "epoch": 0.9342560553633218,
      "grad_norm": 0.6432996392250061,
      "learning_rate": 6.57439446366782e-07,
      "loss": 0.0624,
      "step": 270
    },
    {
      "epoch": 0.9688581314878892,
      "grad_norm": 9.100397109985352,
      "learning_rate": 3.114186851211073e-07,
      "loss": 0.0828,
      "step": 280
    }
  ],
  "logging_steps": 10,
  "max_steps": 289,
  "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}