{
  "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": 2.10301770623606,
      "learning_rate": 2e-05,
      "loss": 0.9046,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.2581600546836853,
      "step": 5,
      "valid_targets_mean": 10397.8,
      "valid_targets_min": 2361
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.8298007078777984,
      "learning_rate": 3.9979273472934556e-05,
      "loss": 0.7445,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.22804319858551025,
      "step": 10,
      "valid_targets_mean": 11106.3,
      "valid_targets_min": 2024
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.515344155564671,
      "learning_rate": 3.925834574695599e-05,
      "loss": 0.6488,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.22954849898815155,
      "step": 15,
      "valid_targets_mean": 11634.1,
      "valid_targets_min": 2357
    },
    {
      "epoch": 1.84375,
      "grad_norm": 0.3660239736366475,
      "learning_rate": 3.754365204805189e-05,
      "loss": 0.5949,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.22694508731365204,
      "step": 20,
      "valid_targets_mean": 11225.4,
      "valid_targets_min": 2461
    },
    {
      "epoch": 2.28125,
      "grad_norm": 0.27292733400663777,
      "learning_rate": 3.4923673716953717e-05,
      "loss": 0.5652,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.18925194442272186,
      "step": 25,
      "valid_targets_mean": 10048.5,
      "valid_targets_min": 1446
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.36409223834338156,
      "learning_rate": 3.153360644229735e-05,
      "loss": 0.5227,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.17960882186889648,
      "step": 30,
      "valid_targets_mean": 10494.9,
      "valid_targets_min": 2380
    },
    {
      "epoch": 3.1875,
      "grad_norm": 0.2555126601067686,
      "learning_rate": 2.7548383915052287e-05,
      "loss": 0.5181,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.15779513120651245,
      "step": 35,
      "valid_targets_mean": 10709.0,
      "valid_targets_min": 2289
    },
    {
      "epoch": 3.65625,
      "grad_norm": 0.2577416185881177,
      "learning_rate": 2.317365092912503e-05,
      "loss": 0.4852,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.1629004180431366,
      "step": 40,
      "valid_targets_mean": 10705.1,
      "valid_targets_min": 3649
    },
    {
      "epoch": 4.09375,
      "grad_norm": 0.24619281480307031,
      "learning_rate": 1.8635151732706586e-05,
      "loss": 0.4774,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.14550036191940308,
      "step": 45,
      "valid_targets_mean": 11062.9,
      "valid_targets_min": 2003
    },
    {
      "epoch": 4.5625,
      "grad_norm": 0.23324714280261716,
      "learning_rate": 1.4167081210903501e-05,
      "loss": 0.4606,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.1585627794265747,
      "step": 50,
      "valid_targets_mean": 9806.9,
      "valid_targets_min": 3222
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.23824699136328265,
      "learning_rate": 1.0000000000000006e-05,
      "loss": 0.4478,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.23112225532531738,
      "step": 55,
      "valid_targets_mean": 12590.4,
      "valid_targets_min": 2809
    },
    {
      "epoch": 5.46875,
      "grad_norm": 0.21658131613971135,
      "learning_rate": 6.348937135626922e-06,
      "loss": 0.4461,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.14610230922698975,
      "step": 60,
      "valid_targets_mean": 10790.1,
      "valid_targets_min": 1523
    },
    {
      "epoch": 5.9375,
      "grad_norm": 0.20397993864925343,
      "learning_rate": 3.402294160019499e-06,
      "loss": 0.4292,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.15167397260665894,
      "step": 65,
      "valid_targets_mean": 11000.0,
      "valid_targets_min": 1559
    },
    {
      "epoch": 6.375,
      "grad_norm": 0.18468343250230315,
      "learning_rate": 1.3121232567865793e-06,
      "loss": 0.4276,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.14748680591583252,
      "step": 70,
      "valid_targets_mean": 12062.0,
      "valid_targets_min": 3167
    },
    {
      "epoch": 6.84375,
      "grad_norm": 0.19194397653199538,
      "learning_rate": 1.862810792733849e-07,
      "loss": 0.4309,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.13902604579925537,
      "step": 75,
      "valid_targets_mean": 9972.5,
      "valid_targets_min": 3772
    },
    {
      "epoch": 7.0,
      "step": 77,
      "total_flos": 2.891732460272353e+17,
      "train_loss": 0.0,
      "train_runtime": 1.7135,
      "train_samples_per_second": 4085.295,
      "train_steps_per_second": 44.938
    }
  ],
  "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": 2.891732460272353e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}