{
  "best_metric": 0.36268436908721924,
  "best_model_checkpoint": "./ttm_finetuned_models_moderna/output/checkpoint-34",
  "epoch": 17.0,
  "eval_steps": 500,
  "global_step": 34,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 4.056020736694336,
      "learning_rate": 1.8667028184439364e-05,
      "loss": 1.0024,
      "step": 2
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.4427066445350647,
      "eval_runtime": 0.3723,
      "eval_samples_per_second": 185.339,
      "eval_steps_per_second": 2.686,
      "step": 2
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.923017740249634,
      "learning_rate": 1.8968955754218564e-05,
      "loss": 0.9065,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.40708231925964355,
      "eval_runtime": 0.361,
      "eval_samples_per_second": 191.131,
      "eval_steps_per_second": 2.77,
      "step": 4
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.819862723350525,
      "learning_rate": 1.9471865185452704e-05,
      "loss": 0.8237,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.393745094537735,
      "eval_runtime": 0.3519,
      "eval_samples_per_second": 196.077,
      "eval_steps_per_second": 2.842,
      "step": 6
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4791889190673828,
      "learning_rate": 2.017530198824305e-05,
      "loss": 0.7897,
      "step": 8
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.38901111483573914,
      "eval_runtime": 0.3611,
      "eval_samples_per_second": 191.097,
      "eval_steps_per_second": 2.77,
      "step": 8
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.0808687210083008,
      "learning_rate": 2.1078630451860426e-05,
      "loss": 0.7637,
      "step": 10
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.3875712752342224,
      "eval_runtime": 0.3339,
      "eval_samples_per_second": 206.657,
      "eval_steps_per_second": 2.995,
      "step": 10
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7717658877372742,
      "learning_rate": 2.2181034219250504e-05,
      "loss": 0.761,
      "step": 12
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.38537338376045227,
      "eval_runtime": 0.3572,
      "eval_samples_per_second": 193.195,
      "eval_steps_per_second": 2.8,
      "step": 12
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.70772784948349,
      "learning_rate": 2.3481517024792826e-05,
      "loss": 0.7687,
      "step": 14
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.3826580345630646,
      "eval_runtime": 0.3504,
      "eval_samples_per_second": 196.904,
      "eval_steps_per_second": 2.854,
      "step": 14
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.8968775272369385,
      "learning_rate": 2.4978903594647175e-05,
      "loss": 0.7411,
      "step": 16
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.37533628940582275,
      "eval_runtime": 0.359,
      "eval_samples_per_second": 192.223,
      "eval_steps_per_second": 2.786,
      "step": 16
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.8349848389625549,
      "learning_rate": 2.6671840708873478e-05,
      "loss": 0.7507,
      "step": 18
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.3686024844646454,
      "eval_runtime": 0.359,
      "eval_samples_per_second": 192.224,
      "eval_steps_per_second": 2.786,
      "step": 18
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.8916922807693481,
      "learning_rate": 2.8558798424365177e-05,
      "loss": 0.7418,
      "step": 20
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.36738961935043335,
      "eval_runtime": 0.7302,
      "eval_samples_per_second": 94.489,
      "eval_steps_per_second": 1.369,
      "step": 20
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.632808268070221,
      "learning_rate": 3.0638071457491495e-05,
      "loss": 0.7092,
      "step": 22
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.3688909411430359,
      "eval_runtime": 0.3526,
      "eval_samples_per_second": 195.693,
      "eval_steps_per_second": 2.836,
      "step": 22
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.6958911418914795,
      "learning_rate": 3.290778072519786e-05,
      "loss": 0.7476,
      "step": 24
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.3743250370025635,
      "eval_runtime": 0.3634,
      "eval_samples_per_second": 189.876,
      "eval_steps_per_second": 2.752,
      "step": 24
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.8087581992149353,
      "learning_rate": 3.5365875043173484e-05,
      "loss": 0.7315,
      "step": 26
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.375684916973114,
      "eval_runtime": 0.3555,
      "eval_samples_per_second": 194.088,
      "eval_steps_per_second": 2.813,
      "step": 26
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.8785252571105957,
      "learning_rate": 3.801013297955e-05,
      "loss": 0.7262,
      "step": 28
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.3696945905685425,
      "eval_runtime": 0.3621,
      "eval_samples_per_second": 190.574,
      "eval_steps_per_second": 2.762,
      "step": 28
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.671592652797699,
      "learning_rate": 4.083816486245606e-05,
      "loss": 0.7121,
      "step": 30
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.3645818829536438,
      "eval_runtime": 0.3601,
      "eval_samples_per_second": 191.597,
      "eval_steps_per_second": 2.777,
      "step": 30
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.6458890438079834,
      "learning_rate": 4.3847414939614856e-05,
      "loss": 0.737,
      "step": 32
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.36310243606567383,
      "eval_runtime": 0.35,
      "eval_samples_per_second": 197.168,
      "eval_steps_per_second": 2.858,
      "step": 32
    },
    {
      "epoch": 17.0,
      "grad_norm": 0.4557172954082489,
      "learning_rate": 4.703516368803146e-05,
      "loss": 0.707,
      "step": 34
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.36268436908721924,
      "eval_runtime": 0.3494,
      "eval_samples_per_second": 197.489,
      "eval_steps_per_second": 2.862,
      "step": 34
    }
  ],
  "logging_steps": 500,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 10,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9002664340200.0,
  "train_batch_size": 288,
  "trial_name": null,
  "trial_params": null
}