trainer_state.json

{
  "best_metric": 42.9261,
  "best_model_checkpoint": "bin/liputan6-lora-16/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": 1.2134227752685547,
      "learning_rate": 0.0008,
      "loss": 1.2779,
      "step": 63
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 52.145,
      "eval_loss": 0.37336987257003784,
      "eval_rouge1": 40.6247,
      "eval_rouge2": 32.4945,
      "eval_rougeL": 37.6262,
      "eval_rougeLsum": 39.2634,
      "eval_runtime": 448.1941,
      "eval_samples_per_second": 2.231,
      "eval_steps_per_second": 0.071,
      "step": 63
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2146146297454834,
      "learning_rate": 0.0006,
      "loss": 0.533,
      "step": 126
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 53.098,
      "eval_loss": 0.2652311325073242,
      "eval_rouge1": 42.9261,
      "eval_rouge2": 34.4419,
      "eval_rougeL": 39.4137,
      "eval_rougeLsum": 41.4698,
      "eval_runtime": 322.7452,
      "eval_samples_per_second": 3.098,
      "eval_steps_per_second": 0.099,
      "step": 126
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.5715835094451904,
      "learning_rate": 0.0004,
      "loss": 0.4176,
      "step": 189
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 50.993,
      "eval_loss": 0.22850000858306885,
      "eval_rouge1": 40.0567,
      "eval_rouge2": 30.7942,
      "eval_rougeL": 36.765,
      "eval_rougeLsum": 38.66,
      "eval_runtime": 323.3178,
      "eval_samples_per_second": 3.093,
      "eval_steps_per_second": 0.099,
      "step": 189
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0843775272369385,
      "learning_rate": 0.0002,
      "loss": 0.364,
      "step": 252
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 55.49,
      "eval_loss": 0.2309255301952362,
      "eval_rouge1": 42.2149,
      "eval_rouge2": 33.065,
      "eval_rougeL": 38.5226,
      "eval_rougeLsum": 40.8353,
      "eval_runtime": 351.6114,
      "eval_samples_per_second": 2.844,
      "eval_steps_per_second": 0.091,
      "step": 252
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.0948582887649536,
      "learning_rate": 0.0,
      "loss": 0.3343,
      "step": 315
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 54.221,
      "eval_loss": 0.22110214829444885,
      "eval_rouge1": 41.3186,
      "eval_rouge2": 32.0318,
      "eval_rougeL": 37.7094,
      "eval_rougeLsum": 39.8931,
      "eval_runtime": 331.1377,
      "eval_samples_per_second": 3.02,
      "eval_steps_per_second": 0.097,
      "step": 315
    },
    {
      "epoch": 5.0,
      "step": 315,
      "total_flos": 3450965852160000.0,
      "train_loss": 0.58534057253883,
      "train_runtime": 2138.3119,
      "train_samples_per_second": 2.338,
      "train_steps_per_second": 0.147
    }
  ],
  "logging_steps": 500,
  "max_steps": 315,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 3450965852160000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}