{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 16.0,
  "eval_steps": 500,
  "global_step": 336,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 328.8559875488281,
      "learning_rate": 5e-06,
      "loss": 127.4109,
      "step": 21
    },
    {
      "epoch": 1.0,
      "eval_loss": 478.246337890625,
      "eval_runtime": 5.1173,
      "eval_samples_per_second": 63.119,
      "eval_steps_per_second": 3.322,
      "step": 21
    },
    {
      "epoch": 2.0,
      "grad_norm": 174.37905883789062,
      "learning_rate": 1e-05,
      "loss": 36.0425,
      "step": 42
    },
    {
      "epoch": 2.0,
      "eval_loss": 390.6916198730469,
      "eval_runtime": 4.0686,
      "eval_samples_per_second": 79.389,
      "eval_steps_per_second": 4.178,
      "step": 42
    },
    {
      "epoch": 3.0,
      "grad_norm": 75.46469116210938,
      "learning_rate": 9.444444444444445e-06,
      "loss": 15.8166,
      "step": 63
    },
    {
      "epoch": 3.0,
      "eval_loss": 175.55548095703125,
      "eval_runtime": 4.1777,
      "eval_samples_per_second": 77.316,
      "eval_steps_per_second": 4.069,
      "step": 63
    },
    {
      "epoch": 4.0,
      "grad_norm": 47.89638900756836,
      "learning_rate": 8.888888888888888e-06,
      "loss": 8.0933,
      "step": 84
    },
    {
      "epoch": 4.0,
      "eval_loss": 119.244384765625,
      "eval_runtime": 4.1061,
      "eval_samples_per_second": 78.663,
      "eval_steps_per_second": 4.14,
      "step": 84
    },
    {
      "epoch": 5.0,
      "grad_norm": 39.76791000366211,
      "learning_rate": 8.333333333333334e-06,
      "loss": 5.7852,
      "step": 105
    },
    {
      "epoch": 5.0,
      "eval_loss": 102.83723449707031,
      "eval_runtime": 3.9939,
      "eval_samples_per_second": 80.873,
      "eval_steps_per_second": 4.256,
      "step": 105
    },
    {
      "epoch": 6.0,
      "grad_norm": 17.662046432495117,
      "learning_rate": 7.77777777777778e-06,
      "loss": 4.1072,
      "step": 126
    },
    {
      "epoch": 6.0,
      "eval_loss": 92.03376770019531,
      "eval_runtime": 3.9224,
      "eval_samples_per_second": 82.348,
      "eval_steps_per_second": 4.334,
      "step": 126
    },
    {
      "epoch": 7.0,
      "grad_norm": 22.999319076538086,
      "learning_rate": 7.222222222222223e-06,
      "loss": 3.0971,
      "step": 147
    },
    {
      "epoch": 7.0,
      "eval_loss": 84.36630249023438,
      "eval_runtime": 4.4688,
      "eval_samples_per_second": 72.278,
      "eval_steps_per_second": 3.804,
      "step": 147
    },
    {
      "epoch": 8.0,
      "grad_norm": 14.748945236206055,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.9596,
      "step": 168
    },
    {
      "epoch": 8.0,
      "eval_loss": 81.93232727050781,
      "eval_runtime": 4.7697,
      "eval_samples_per_second": 67.718,
      "eval_steps_per_second": 3.564,
      "step": 168
    },
    {
      "epoch": 9.0,
      "grad_norm": 55.0167350769043,
      "learning_rate": 6.111111111111112e-06,
      "loss": 1.2031,
      "step": 189
    },
    {
      "epoch": 9.0,
      "eval_loss": 80.85563659667969,
      "eval_runtime": 4.4821,
      "eval_samples_per_second": 72.064,
      "eval_steps_per_second": 3.793,
      "step": 189
    },
    {
      "epoch": 10.0,
      "grad_norm": 59.18910598754883,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.8863,
      "step": 210
    },
    {
      "epoch": 10.0,
      "eval_loss": 98.6752700805664,
      "eval_runtime": 4.4465,
      "eval_samples_per_second": 72.642,
      "eval_steps_per_second": 3.823,
      "step": 210
    },
    {
      "epoch": 11.0,
      "grad_norm": 1.2452582120895386,
      "learning_rate": 5e-06,
      "loss": 0.3703,
      "step": 231
    },
    {
      "epoch": 11.0,
      "eval_loss": 102.78790283203125,
      "eval_runtime": 4.4585,
      "eval_samples_per_second": 72.446,
      "eval_steps_per_second": 3.813,
      "step": 231
    },
    {
      "epoch": 12.0,
      "grad_norm": 51.24710464477539,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.2899,
      "step": 252
    },
    {
      "epoch": 12.0,
      "eval_loss": 105.00616455078125,
      "eval_runtime": 4.4633,
      "eval_samples_per_second": 72.368,
      "eval_steps_per_second": 3.809,
      "step": 252
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.3481183648109436,
      "learning_rate": 3.88888888888889e-06,
      "loss": 0.193,
      "step": 273
    },
    {
      "epoch": 13.0,
      "eval_loss": 119.50952911376953,
      "eval_runtime": 4.454,
      "eval_samples_per_second": 72.519,
      "eval_steps_per_second": 3.817,
      "step": 273
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.8411530256271362,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0836,
      "step": 294
    },
    {
      "epoch": 14.0,
      "eval_loss": 126.7031478881836,
      "eval_runtime": 4.2646,
      "eval_samples_per_second": 75.739,
      "eval_steps_per_second": 3.986,
      "step": 294
    },
    {
      "epoch": 15.0,
      "grad_norm": 16.207983016967773,
      "learning_rate": 2.7777777777777783e-06,
      "loss": 0.1528,
      "step": 315
    },
    {
      "epoch": 15.0,
      "eval_loss": 137.7791748046875,
      "eval_runtime": 4.1698,
      "eval_samples_per_second": 77.462,
      "eval_steps_per_second": 4.077,
      "step": 315
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.5255839824676514,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.035,
      "step": 336
    },
    {
      "epoch": 16.0,
      "eval_loss": 146.33724975585938,
      "eval_runtime": 4.2416,
      "eval_samples_per_second": 76.151,
      "eval_steps_per_second": 4.008,
      "step": 336
    }
  ],
  "logging_steps": 500,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 0.0,
  "train_batch_size": 20,
  "trial_name": null,
  "trial_params": null
}