{
  "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": 2.449476580649348,
      "learning_rate": 2e-05,
      "loss": 0.3623,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09593464434146881,
      "step": 5,
      "valid_targets_mean": 4223.8,
      "valid_targets_min": 1764
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.6382870247499054,
      "learning_rate": 3.9979273472934556e-05,
      "loss": 0.2627,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.07572826743125916,
      "step": 10,
      "valid_targets_mean": 3980.9,
      "valid_targets_min": 1525
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.3840671504117775,
      "learning_rate": 3.925834574695599e-05,
      "loss": 0.1981,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05852765589952469,
      "step": 15,
      "valid_targets_mean": 3834.6,
      "valid_targets_min": 2180
    },
    {
      "epoch": 1.84375,
      "grad_norm": 0.26008517504887835,
      "learning_rate": 3.754365204805189e-05,
      "loss": 0.1816,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.050162822008132935,
      "step": 20,
      "valid_targets_mean": 3959.7,
      "valid_targets_min": 1891
    },
    {
      "epoch": 2.28125,
      "grad_norm": 0.22385025236857542,
      "learning_rate": 3.4923673716953717e-05,
      "loss": 0.1609,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05245774984359741,
      "step": 25,
      "valid_targets_mean": 3111.5,
      "valid_targets_min": 1912
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.18472578561931283,
      "learning_rate": 3.153360644229735e-05,
      "loss": 0.1474,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.047335147857666016,
      "step": 30,
      "valid_targets_mean": 3842.9,
      "valid_targets_min": 1877
    },
    {
      "epoch": 3.1875,
      "grad_norm": 0.19297671076845993,
      "learning_rate": 2.7548383915052287e-05,
      "loss": 0.1408,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05119028687477112,
      "step": 35,
      "valid_targets_mean": 3693.0,
      "valid_targets_min": 1891
    },
    {
      "epoch": 3.65625,
      "grad_norm": 0.1727987003610846,
      "learning_rate": 2.317365092912503e-05,
      "loss": 0.126,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03700105473399162,
      "step": 40,
      "valid_targets_mean": 4400.2,
      "valid_targets_min": 1921
    },
    {
      "epoch": 4.09375,
      "grad_norm": 0.14371270225804264,
      "learning_rate": 1.8635151732706586e-05,
      "loss": 0.1307,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03518667072057724,
      "step": 45,
      "valid_targets_mean": 3079.8,
      "valid_targets_min": 1942
    },
    {
      "epoch": 4.5625,
      "grad_norm": 0.18219668333668007,
      "learning_rate": 1.4167081210903501e-05,
      "loss": 0.1211,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04458793252706528,
      "step": 50,
      "valid_targets_mean": 4404.6,
      "valid_targets_min": 1929
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.20640136634739376,
      "learning_rate": 1.0000000000000006e-05,
      "loss": 0.1242,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06789684295654297,
      "step": 55,
      "valid_targets_mean": 4031.6,
      "valid_targets_min": 1907
    },
    {
      "epoch": 5.46875,
      "grad_norm": 0.12885360552030267,
      "learning_rate": 6.348937135626922e-06,
      "loss": 0.113,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0334051139652729,
      "step": 60,
      "valid_targets_mean": 4410.8,
      "valid_targets_min": 1900
    },
    {
      "epoch": 5.9375,
      "grad_norm": 0.18447392989133204,
      "learning_rate": 3.402294160019499e-06,
      "loss": 0.1222,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04631945490837097,
      "step": 65,
      "valid_targets_mean": 3430.5,
      "valid_targets_min": 1907
    },
    {
      "epoch": 6.375,
      "grad_norm": 0.13730502442772544,
      "learning_rate": 1.3121232567865793e-06,
      "loss": 0.1142,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03418249636888504,
      "step": 70,
      "valid_targets_mean": 3291.6,
      "valid_targets_min": 1904
    },
    {
      "epoch": 6.84375,
      "grad_norm": 0.1539125956038368,
      "learning_rate": 1.862810792733849e-07,
      "loss": 0.1202,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03708626702427864,
      "step": 75,
      "valid_targets_mean": 3544.7,
      "valid_targets_min": 1889
    },
    {
      "epoch": 7.0,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.054979901760816574,
      "step": 77,
      "total_flos": 9.529203217976525e+16,
      "train_loss": 0.15973503326440786,
      "train_runtime": 959.4276,
      "train_samples_per_second": 7.296,
      "train_steps_per_second": 0.08,
      "valid_targets_mean": 4215.4,
      "valid_targets_min": 1870
    }
  ],
  "logging_steps": 5,
  "max_steps": 77,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.529203217976525e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}