{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005072708826513358,
  "eval_steps": 4,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016909029421711193,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00016909029421711193,
      "eval_loss": NaN,
      "eval_runtime": 180.1735,
      "eval_samples_per_second": 13.82,
      "eval_steps_per_second": 3.458,
      "step": 1
    },
    {
      "epoch": 0.00033818058843422386,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0005072708826513358,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0006763611768684477,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0006763611768684477,
      "eval_loss": NaN,
      "eval_runtime": 179.0673,
      "eval_samples_per_second": 13.905,
      "eval_steps_per_second": 3.479,
      "step": 4
    },
    {
      "epoch": 0.0008454514710855597,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0010145417653026716,
      "grad_norm": NaN,
      "learning_rate": 9.960573506572391e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0011836320595197836,
      "grad_norm": NaN,
      "learning_rate": 9.842915805643156e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0013527223537368955,
      "grad_norm": NaN,
      "learning_rate": 9.648882429441258e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0013527223537368955,
      "eval_loss": NaN,
      "eval_runtime": 179.199,
      "eval_samples_per_second": 13.895,
      "eval_steps_per_second": 3.477,
      "step": 8
    },
    {
      "epoch": 0.0015218126479540075,
      "grad_norm": NaN,
      "learning_rate": 9.381533400219319e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0016909029421711193,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0018599932363882314,
      "grad_norm": NaN,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.002029083530605343,
      "grad_norm": NaN,
      "learning_rate": 8.18711994874345e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.002029083530605343,
      "eval_loss": NaN,
      "eval_runtime": 178.882,
      "eval_samples_per_second": 13.92,
      "eval_steps_per_second": 3.483,
      "step": 12
    },
    {
      "epoch": 0.002198173824822455,
      "grad_norm": NaN,
      "learning_rate": 7.679133974894984e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0023672641190395673,
      "grad_norm": NaN,
      "learning_rate": 7.128896457825364e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.002536354413256679,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.002705444707473791,
      "grad_norm": NaN,
      "learning_rate": 5.936906572928625e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.002705444707473791,
      "eval_loss": NaN,
      "eval_runtime": 178.872,
      "eval_samples_per_second": 13.921,
      "eval_steps_per_second": 3.483,
      "step": 16
    },
    {
      "epoch": 0.0028745350016909027,
      "grad_norm": NaN,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.003043625295908015,
      "grad_norm": NaN,
      "learning_rate": 4.686047402353433e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.003212715590125127,
      "grad_norm": NaN,
      "learning_rate": 4.063093427071376e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0033818058843422386,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0033818058843422386,
      "eval_loss": NaN,
      "eval_runtime": 178.9134,
      "eval_samples_per_second": 13.917,
      "eval_steps_per_second": 3.482,
      "step": 20
    },
    {
      "epoch": 0.003550896178559351,
      "grad_norm": NaN,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0037199864727764627,
      "grad_norm": NaN,
      "learning_rate": 2.320866025105016e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0038890767669935745,
      "grad_norm": NaN,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.004058167061210686,
      "grad_norm": NaN,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.004058167061210686,
      "eval_loss": NaN,
      "eval_runtime": 178.8598,
      "eval_samples_per_second": 13.922,
      "eval_steps_per_second": 3.483,
      "step": 24
    },
    {
      "epoch": 0.004227257355427798,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.00439634764964491,
      "grad_norm": NaN,
      "learning_rate": 6.184665997806832e-07,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.004565437943862023,
      "grad_norm": NaN,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0047345282380791345,
      "grad_norm": NaN,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.0047345282380791345,
      "eval_loss": NaN,
      "eval_runtime": 179.2939,
      "eval_samples_per_second": 13.888,
      "eval_steps_per_second": 3.475,
      "step": 28
    },
    {
      "epoch": 0.004903618532296246,
      "grad_norm": NaN,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.005072708826513358,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4681361906466816.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}