trainer_state.json

{
  "best_metric": 25.6586,
  "best_model_checkpoint": "bin/liputan6-seq_bn-rf64/checkpoint-126",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 315,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.4476851224899292,
      "learning_rate": 0.0008,
      "loss": 2.7121,
      "step": 63
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 33.171,
      "eval_loss": 2.751498222351074,
      "eval_rouge1": 24.5986,
      "eval_rouge2": 10.2547,
      "eval_rougeL": 20.7138,
      "eval_rougeLsum": 22.4882,
      "eval_runtime": 96.6631,
      "eval_samples_per_second": 10.345,
      "eval_steps_per_second": 0.331,
      "step": 63
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.678938388824463,
      "learning_rate": 0.0006,
      "loss": 2.3483,
      "step": 126
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 33.715,
      "eval_loss": 2.7424604892730713,
      "eval_rouge1": 25.6586,
      "eval_rouge2": 10.7898,
      "eval_rougeL": 21.7223,
      "eval_rougeLsum": 23.503,
      "eval_runtime": 102.6905,
      "eval_samples_per_second": 9.738,
      "eval_steps_per_second": 0.312,
      "step": 126
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.481394648551941,
      "learning_rate": 0.0004,
      "loss": 2.2546,
      "step": 189
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 29.451,
      "eval_loss": 2.6605117321014404,
      "eval_rouge1": 24.6676,
      "eval_rouge2": 10.1646,
      "eval_rougeL": 20.9376,
      "eval_rougeLsum": 22.7405,
      "eval_runtime": 86.0126,
      "eval_samples_per_second": 11.626,
      "eval_steps_per_second": 0.372,
      "step": 189
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.5163031816482544,
      "learning_rate": 0.0002,
      "loss": 2.1725,
      "step": 252
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 30.896,
      "eval_loss": 2.7043347358703613,
      "eval_rouge1": 25.3421,
      "eval_rouge2": 10.5863,
      "eval_rougeL": 21.3692,
      "eval_rougeLsum": 23.2586,
      "eval_runtime": 89.3545,
      "eval_samples_per_second": 11.191,
      "eval_steps_per_second": 0.358,
      "step": 252
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.3111423254013062,
      "learning_rate": 0.0,
      "loss": 2.1135,
      "step": 315
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 32.451,
      "eval_loss": 2.7079272270202637,
      "eval_rouge1": 24.9923,
      "eval_rouge2": 10.432,
      "eval_rougeL": 21.1505,
      "eval_rougeLsum": 22.9477,
      "eval_runtime": 99.9269,
      "eval_samples_per_second": 10.007,
      "eval_steps_per_second": 0.32,
      "step": 315
    },
    {
      "epoch": 5.0,
      "step": 315,
      "total_flos": 3430869073920000.0,
      "train_loss": 2.32020258827815,
      "train_runtime": 726.5333,
      "train_samples_per_second": 6.882,
      "train_steps_per_second": 0.434
    }
  ],
  "logging_steps": 500,
  "max_steps": 315,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 3430869073920000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}