trainer_state.json

{
  "best_metric": 3.8993899822235107,
  "best_model_checkpoint": "tam_test_output/checkpoint-24",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.796779155731201,
      "eval_rouge1": 0.1363,
      "eval_rouge2": 0.0474,
      "eval_rougeL": 0.114,
      "eval_rougeLsum": 0.1145,
      "eval_runtime": 1.804,
      "eval_samples_per_second": 27.161,
      "eval_steps_per_second": 0.554,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.6129069328308105,
      "eval_rouge1": 0.1365,
      "eval_rouge2": 0.0488,
      "eval_rougeL": 0.1143,
      "eval_rougeLsum": 0.115,
      "eval_runtime": 0.7472,
      "eval_samples_per_second": 65.581,
      "eval_steps_per_second": 1.338,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.438114166259766,
      "eval_rouge1": 0.1388,
      "eval_rouge2": 0.0502,
      "eval_rougeL": 0.1149,
      "eval_rougeLsum": 0.1155,
      "eval_runtime": 0.7266,
      "eval_samples_per_second": 67.441,
      "eval_steps_per_second": 1.376,
      "step": 9
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.277408599853516,
      "eval_rouge1": 0.1376,
      "eval_rouge2": 0.0497,
      "eval_rougeL": 0.1136,
      "eval_rougeLsum": 0.1143,
      "eval_runtime": 0.7431,
      "eval_samples_per_second": 65.942,
      "eval_steps_per_second": 1.346,
      "step": 12
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.141086101531982,
      "eval_rouge1": 0.1391,
      "eval_rouge2": 0.0513,
      "eval_rougeL": 0.1155,
      "eval_rougeLsum": 0.1161,
      "eval_runtime": 0.7243,
      "eval_samples_per_second": 67.655,
      "eval_steps_per_second": 1.381,
      "step": 15
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.033929347991943,
      "eval_rouge1": 0.1396,
      "eval_rouge2": 0.0513,
      "eval_rougeL": 0.1159,
      "eval_rougeLsum": 0.1166,
      "eval_runtime": 0.7239,
      "eval_samples_per_second": 67.685,
      "eval_steps_per_second": 1.381,
      "step": 18
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 19.0,
      "eval_loss": 3.954421043395996,
      "eval_rouge1": 0.1404,
      "eval_rouge2": 0.0528,
      "eval_rougeL": 0.1172,
      "eval_rougeLsum": 0.1176,
      "eval_runtime": 0.7261,
      "eval_samples_per_second": 67.483,
      "eval_steps_per_second": 1.377,
      "step": 21
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 19.0,
      "eval_loss": 3.8993899822235107,
      "eval_rouge1": 0.1402,
      "eval_rouge2": 0.0525,
      "eval_rougeL": 0.1165,
      "eval_rougeLsum": 0.1169,
      "eval_runtime": 0.7293,
      "eval_samples_per_second": 67.187,
      "eval_steps_per_second": 1.371,
      "step": 24
    }
  ],
  "logging_steps": 500,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 426597358239744.0,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}