{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 22,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 5.410861968994141,
      "learning_rate": 0.0001989821441880933,
      "loss": 3.2071,
      "step": 1
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 4.757542133331299,
      "learning_rate": 0.00019594929736144976,
      "loss": 2.8727,
      "step": 2
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 6.219588279724121,
      "learning_rate": 0.00019096319953545185,
      "loss": 2.9721,
      "step": 3
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.265394687652588,
      "learning_rate": 0.00018412535328311814,
      "loss": 2.5661,
      "step": 4
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 3.197615146636963,
      "learning_rate": 0.00017557495743542585,
      "loss": 2.6573,
      "step": 5
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 2.695573568344116,
      "learning_rate": 0.00016548607339452853,
      "loss": 2.479,
      "step": 6
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 3.21574330329895,
      "learning_rate": 0.00015406408174555976,
      "loss": 2.5781,
      "step": 7
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.4235832691192627,
      "learning_rate": 0.00014154150130018866,
      "loss": 2.4604,
      "step": 8
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 2.524172067642212,
      "learning_rate": 0.00012817325568414297,
      "loss": 2.3458,
      "step": 9
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 3.0898048877716064,
      "learning_rate": 0.00011423148382732853,
      "loss": 2.3869,
      "step": 10
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.021130084991455,
      "learning_rate": 0.0001,
      "loss": 2.2218,
      "step": 11
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 2.629793882369995,
      "learning_rate": 8.57685161726715e-05,
      "loss": 2.3153,
      "step": 12
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 2.5281155109405518,
      "learning_rate": 7.182674431585704e-05,
      "loss": 2.2538,
      "step": 13
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 2.5038318634033203,
      "learning_rate": 5.845849869981137e-05,
      "loss": 2.2725,
      "step": 14
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 2.788825035095215,
      "learning_rate": 4.593591825444028e-05,
      "loss": 2.2729,
      "step": 15
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.199079990386963,
      "learning_rate": 3.45139266054715e-05,
      "loss": 2.3403,
      "step": 16
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 2.322319984436035,
      "learning_rate": 2.4425042564574184e-05,
      "loss": 2.2943,
      "step": 17
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 2.321732997894287,
      "learning_rate": 1.587464671688187e-05,
      "loss": 2.2358,
      "step": 18
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 2.4514646530151367,
      "learning_rate": 9.036800464548157e-06,
      "loss": 2.3498,
      "step": 19
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 3.0407378673553467,
      "learning_rate": 4.050702638550275e-06,
      "loss": 2.349,
      "step": 20
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 2.618478775024414,
      "learning_rate": 1.0178558119067315e-06,
      "loss": 2.2082,
      "step": 21
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.4556992053985596,
      "learning_rate": 0.0,
      "loss": 2.316,
      "step": 22
    }
  ],
  "logging_steps": 1,
  "max_steps": 22,
  "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": 2807061793996800.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}