{
  "best_metric": 8.271754264831543,
  "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/fict-full-lstm-42/checkpoints/checkpoint-70",
  "epoch": 0.56,
  "eval_steps": 10,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 4.600000000000001e-05,
      "loss": 10.813,
      "step": 10
    },
    {
      "epoch": 0.08,
      "eval_loss": 10.803234100341797,
      "eval_runtime": 2.8007,
      "eval_samples_per_second": 357.057,
      "eval_steps_per_second": 44.632,
      "step": 10
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.2e-05,
      "loss": 10.793,
      "step": 20
    },
    {
      "epoch": 0.16,
      "eval_loss": 10.778646469116211,
      "eval_runtime": 2.6573,
      "eval_samples_per_second": 376.32,
      "eval_steps_per_second": 47.04,
      "step": 20
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.8e-05,
      "loss": 10.7565,
      "step": 30
    },
    {
      "epoch": 0.24,
      "eval_loss": 10.711685180664062,
      "eval_runtime": 2.8706,
      "eval_samples_per_second": 348.354,
      "eval_steps_per_second": 43.544,
      "step": 30
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 10.5835,
      "step": 40
    },
    {
      "epoch": 0.32,
      "eval_loss": 10.208820343017578,
      "eval_runtime": 2.7457,
      "eval_samples_per_second": 364.201,
      "eval_steps_per_second": 45.525,
      "step": 40
    },
    {
      "epoch": 0.4,
      "learning_rate": 3e-05,
      "loss": 9.8124,
      "step": 50
    },
    {
      "epoch": 0.4,
      "eval_loss": 9.19725227355957,
      "eval_runtime": 2.6505,
      "eval_samples_per_second": 377.282,
      "eval_steps_per_second": 47.16,
      "step": 50
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 9.0079,
      "step": 60
    },
    {
      "epoch": 0.48,
      "eval_loss": 8.602240562438965,
      "eval_runtime": 2.6478,
      "eval_samples_per_second": 377.678,
      "eval_steps_per_second": 47.21,
      "step": 60
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 8.5534,
      "step": 70
    },
    {
      "epoch": 0.56,
      "eval_loss": 8.271754264831543,
      "eval_runtime": 2.841,
      "eval_samples_per_second": 351.994,
      "eval_steps_per_second": 43.999,
      "step": 70
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 4923721736640.0,
  "trial_name": null,
  "trial_params": null
}