{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 4.714256763458252,
      "learning_rate": 0.0,
      "loss": 0.2629,
      "step": 1
    },
    {
      "epoch": 0.13114754098360656,
      "grad_norm": 4.481027126312256,
      "learning_rate": 1e-05,
      "loss": 0.2511,
      "step": 2
    },
    {
      "epoch": 0.19672131147540983,
      "grad_norm": 1.4797923564910889,
      "learning_rate": 2e-05,
      "loss": 0.1746,
      "step": 3
    },
    {
      "epoch": 0.26229508196721313,
      "grad_norm": 1.0449162721633911,
      "learning_rate": 3.0000000000000004e-05,
      "loss": 0.1525,
      "step": 4
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 0.559347927570343,
      "learning_rate": 4e-05,
      "loss": 0.139,
      "step": 5
    },
    {
      "epoch": 0.39344262295081966,
      "grad_norm": 0.7299180030822754,
      "learning_rate": 3.9874244197864856e-05,
      "loss": 0.1668,
      "step": 6
    },
    {
      "epoch": 0.45901639344262296,
      "grad_norm": 0.46966561675071716,
      "learning_rate": 3.949855824363647e-05,
      "loss": 0.1511,
      "step": 7
    },
    {
      "epoch": 0.5245901639344263,
      "grad_norm": 0.3275943398475647,
      "learning_rate": 3.8877666606167354e-05,
      "loss": 0.1436,
      "step": 8
    },
    {
      "epoch": 0.5901639344262295,
      "grad_norm": 0.25042107701301575,
      "learning_rate": 3.801937735804838e-05,
      "loss": 0.1316,
      "step": 9
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 0.2314835488796234,
      "learning_rate": 3.6934483984565684e-05,
      "loss": 0.1313,
      "step": 10
    },
    {
      "epoch": 0.7213114754098361,
      "grad_norm": 0.20796050131320953,
      "learning_rate": 3.56366296493606e-05,
      "loss": 0.1231,
      "step": 11
    },
    {
      "epoch": 0.7868852459016393,
      "grad_norm": 0.17153136432170868,
      "learning_rate": 3.4142135623730954e-05,
      "loss": 0.117,
      "step": 12
    },
    {
      "epoch": 0.8524590163934426,
      "grad_norm": 0.17973053455352783,
      "learning_rate": 3.246979603717467e-05,
      "loss": 0.115,
      "step": 13
    },
    {
      "epoch": 0.9180327868852459,
      "grad_norm": 0.15800680220127106,
      "learning_rate": 3.064064153030673e-05,
      "loss": 0.1185,
      "step": 14
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 0.1504051834344864,
      "learning_rate": 2.8677674782351164e-05,
      "loss": 0.12,
      "step": 15
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.1504051834344864,
      "learning_rate": 2.6605581239103347e-05,
      "loss": 0.1019,
      "step": 16
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 32,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 29087666012160.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}