{
  "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": 0.46875,
      "grad_norm": 1.9648877197881578,
      "learning_rate": 2e-05,
      "loss": 0.4134,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.1235947459936142,
      "step": 5,
      "valid_targets_mean": 13794.3,
      "valid_targets_min": 7848
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.381921173789981,
      "learning_rate": 3.9979273472934556e-05,
      "loss": 0.3103,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09376486390829086,
      "step": 10,
      "valid_targets_mean": 14449.4,
      "valid_targets_min": 8164
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.23106508776501453,
      "learning_rate": 3.925834574695599e-05,
      "loss": 0.2519,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.07892575860023499,
      "step": 15,
      "valid_targets_mean": 13925.9,
      "valid_targets_min": 9503
    },
    {
      "epoch": 1.84375,
      "grad_norm": 0.18581965556633898,
      "learning_rate": 3.754365204805189e-05,
      "loss": 0.2284,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0704069659113884,
      "step": 20,
      "valid_targets_mean": 13211.0,
      "valid_targets_min": 5976
    },
    {
      "epoch": 2.28125,
      "grad_norm": 0.16864159995422107,
      "learning_rate": 3.4923673716953717e-05,
      "loss": 0.2029,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06609021127223969,
      "step": 25,
      "valid_targets_mean": 14030.9,
      "valid_targets_min": 6036
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.14396217779187906,
      "learning_rate": 3.153360644229735e-05,
      "loss": 0.1857,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.060772836208343506,
      "step": 30,
      "valid_targets_mean": 14805.3,
      "valid_targets_min": 9784
    },
    {
      "epoch": 3.1875,
      "grad_norm": 0.14325714015192362,
      "learning_rate": 2.7548383915052287e-05,
      "loss": 0.1793,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.057898588478565216,
      "step": 35,
      "valid_targets_mean": 14291.8,
      "valid_targets_min": 7913
    },
    {
      "epoch": 3.65625,
      "grad_norm": 0.1356400268859256,
      "learning_rate": 2.317365092912503e-05,
      "loss": 0.1635,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05161704123020172,
      "step": 40,
      "valid_targets_mean": 14492.5,
      "valid_targets_min": 7853
    },
    {
      "epoch": 4.09375,
      "grad_norm": 0.1572986083073511,
      "learning_rate": 1.8635151732706586e-05,
      "loss": 0.1597,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0520821250975132,
      "step": 45,
      "valid_targets_mean": 14069.8,
      "valid_targets_min": 5516
    },
    {
      "epoch": 4.5625,
      "grad_norm": 0.13629943846637377,
      "learning_rate": 1.4167081210903501e-05,
      "loss": 0.1463,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.045209724456071854,
      "step": 50,
      "valid_targets_mean": 14619.7,
      "valid_targets_min": 9401
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.16093636060874256,
      "learning_rate": 1.0000000000000006e-05,
      "loss": 0.1458,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06920741498470306,
      "step": 55,
      "valid_targets_mean": 13425.2,
      "valid_targets_min": 6387
    },
    {
      "epoch": 5.46875,
      "grad_norm": 0.13686710999035775,
      "learning_rate": 6.348937135626922e-06,
      "loss": 0.1373,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.045050714164972305,
      "step": 60,
      "valid_targets_mean": 14429.8,
      "valid_targets_min": 3326
    },
    {
      "epoch": 5.9375,
      "grad_norm": 0.1404048105910734,
      "learning_rate": 3.402294160019499e-06,
      "loss": 0.1346,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.044851139187812805,
      "step": 65,
      "valid_targets_mean": 14258.1,
      "valid_targets_min": 3977
    },
    {
      "epoch": 6.375,
      "grad_norm": 0.1281286484683331,
      "learning_rate": 1.3121232567865793e-06,
      "loss": 0.1339,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04250744730234146,
      "step": 70,
      "valid_targets_mean": 13733.4,
      "valid_targets_min": 6025
    },
    {
      "epoch": 6.84375,
      "grad_norm": 0.11966419377079712,
      "learning_rate": 1.862810792733849e-07,
      "loss": 0.1314,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04522828757762909,
      "step": 75,
      "valid_targets_mean": 14534.2,
      "valid_targets_min": 9307
    },
    {
      "epoch": 7.0,
      "step": 77,
      "total_flos": 5.7154397037972685e+17,
      "train_loss": 0.0,
      "train_runtime": 0.9635,
      "train_samples_per_second": 7265.245,
      "train_steps_per_second": 79.918
    }
  ],
  "logging_steps": 5,
  "max_steps": 77,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.7154397037972685e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}