{
  "best_metric": 2.0136280059814453,
  "best_model_checkpoint": "cdetr-cd45rb-s/checkpoint-2420",
  "epoch": 10.0,
  "global_step": 2420,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 5e-05,
      "loss": 2.6006,
      "step": 242
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.214585542678833,
      "eval_runtime": 17.9919,
      "eval_samples_per_second": 5.558,
      "eval_steps_per_second": 0.723,
      "step": 242
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0,
      "loss": 2.2409,
      "step": 484
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.110588788986206,
      "eval_runtime": 17.3999,
      "eval_samples_per_second": 5.747,
      "eval_steps_per_second": 0.747,
      "step": 484
    },
    {
      "epoch": 3.0,
      "learning_rate": 4e-05,
      "loss": 2.2027,
      "step": 726
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.145615339279175,
      "eval_runtime": 17.7242,
      "eval_samples_per_second": 5.642,
      "eval_steps_per_second": 0.733,
      "step": 726
    },
    {
      "epoch": 4.0,
      "learning_rate": 2e-05,
      "loss": 2.183,
      "step": 968
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.0863144397735596,
      "eval_runtime": 17.5156,
      "eval_samples_per_second": 5.709,
      "eval_steps_per_second": 0.742,
      "step": 968
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 2.0628,
      "step": 1210
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.0293631553649902,
      "eval_runtime": 17.5041,
      "eval_samples_per_second": 5.713,
      "eval_steps_per_second": 0.743,
      "step": 1210
    },
    {
      "epoch": 6.0,
      "learning_rate": 4e-05,
      "loss": 2.1588,
      "step": 1452
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.0859251022338867,
      "eval_runtime": 17.1118,
      "eval_samples_per_second": 5.844,
      "eval_steps_per_second": 0.76,
      "step": 1452
    },
    {
      "epoch": 7.0,
      "learning_rate": 3e-05,
      "loss": 2.1731,
      "step": 1694
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.073065757751465,
      "eval_runtime": 16.6383,
      "eval_samples_per_second": 6.01,
      "eval_steps_per_second": 0.781,
      "step": 1694
    },
    {
      "epoch": 8.0,
      "learning_rate": 2e-05,
      "loss": 2.1041,
      "step": 1936
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.1051650047302246,
      "eval_runtime": 16.6295,
      "eval_samples_per_second": 6.013,
      "eval_steps_per_second": 0.782,
      "step": 1936
    },
    {
      "epoch": 9.0,
      "learning_rate": 1e-05,
      "loss": 2.0383,
      "step": 2178
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.037771463394165,
      "eval_runtime": 17.1339,
      "eval_samples_per_second": 5.836,
      "eval_steps_per_second": 0.759,
      "step": 2178
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 1.967,
      "step": 2420
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.0136280059814453,
      "eval_runtime": 16.8066,
      "eval_samples_per_second": 5.95,
      "eval_steps_per_second": 0.774,
      "step": 2420
    },
    {
      "epoch": 10.0,
      "step": 2420,
      "total_flos": 4.8214727269632e+18,
      "train_loss": 1.0441367535551718,
      "train_runtime": 1297.7653,
      "train_samples_per_second": 7.444,
      "train_steps_per_second": 1.865
    }
  ],
  "max_steps": 2420,
  "num_train_epochs": 10,
  "total_flos": 4.8214727269632e+18,
  "trial_name": null,
  "trial_params": null
}