{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 77,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 2.5707619190216064,
      "learning_rate": 2e-05,
      "loss": 0.7696,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.7344862818717957,
      "step": 5,
      "valid_targets_mean": 10940.0,
      "valid_targets_min": 1296
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 3.0747663974761963,
      "learning_rate": 3.9979273472934556e-05,
      "loss": 0.7194,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.7147436141967773,
      "step": 10,
      "valid_targets_mean": 11399.7,
      "valid_targets_min": 1921
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 1.2209486961364746,
      "learning_rate": 3.925834574695599e-05,
      "loss": 0.6838,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.6719205975532532,
      "step": 15,
      "valid_targets_mean": 10668.7,
      "valid_targets_min": 1431
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.8381664156913757,
      "learning_rate": 3.754365204805189e-05,
      "loss": 0.6437,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.6438973546028137,
      "step": 20,
      "valid_targets_mean": 9851.9,
      "valid_targets_min": 1661
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.6093587875366211,
      "learning_rate": 3.4923673716953717e-05,
      "loss": 0.6272,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.6231866478919983,
      "step": 25,
      "valid_targets_mean": 10324.9,
      "valid_targets_min": 1431
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.4461829960346222,
      "learning_rate": 3.153360644229735e-05,
      "loss": 0.5939,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.5710898041725159,
      "step": 30,
      "valid_targets_mean": 10086.1,
      "valid_targets_min": 1922
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 0.3415960967540741,
      "learning_rate": 2.7548383915052287e-05,
      "loss": 0.5959,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.5762262344360352,
      "step": 35,
      "valid_targets_mean": 11156.6,
      "valid_targets_min": 2289
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.33736804127693176,
      "learning_rate": 2.317365092912503e-05,
      "loss": 0.5729,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.5794134736061096,
      "step": 40,
      "valid_targets_mean": 10489.0,
      "valid_targets_min": 2207
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 0.24178124964237213,
      "learning_rate": 1.8635151732706586e-05,
      "loss": 0.5683,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.5701989531517029,
      "step": 45,
      "valid_targets_mean": 11467.8,
      "valid_targets_min": 1523
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.25526440143585205,
      "learning_rate": 1.4167081210903501e-05,
      "loss": 0.5605,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.5524492859840393,
      "step": 50,
      "valid_targets_mean": 9196.7,
      "valid_targets_min": 1978
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2626790702342987,
      "learning_rate": 1.0000000000000006e-05,
      "loss": 0.548,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.5532940626144409,
      "step": 55,
      "valid_targets_mean": 11774.8,
      "valid_targets_min": 1740
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.21153761446475983,
      "learning_rate": 6.348937135626922e-06,
      "loss": 0.5557,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.5435238480567932,
      "step": 60,
      "valid_targets_mean": 10416.2,
      "valid_targets_min": 1523
    },
    {
      "epoch": 5.909090909090909,
      "grad_norm": 0.22004517912864685,
      "learning_rate": 3.402294160019499e-06,
      "loss": 0.5368,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.5342128276824951,
      "step": 65,
      "valid_targets_mean": 10384.5,
      "valid_targets_min": 1559
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 0.2335129827260971,
      "learning_rate": 1.3121232567865793e-06,
      "loss": 0.541,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.5447248816490173,
      "step": 70,
      "valid_targets_mean": 11540.8,
      "valid_targets_min": 1740
    },
    {
      "epoch": 6.818181818181818,
      "grad_norm": 0.20155416429042816,
      "learning_rate": 1.862810792733849e-07,
      "loss": 0.5444,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.5294170379638672,
      "step": 75,
      "valid_targets_mean": 10089.2,
      "valid_targets_min": 1758
    },
    {
      "epoch": 7.0,
      "step": 77,
      "total_flos": 496687094169600.0,
      "train_loss": 0.0,
      "train_runtime": 1.107,
      "train_samples_per_second": 6323.517,
      "train_steps_per_second": 69.559
    }
  ],
  "logging_steps": 5,
  "max_steps": 77,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 496687094169600.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}