trainer_state.json

{
  "best_metric": 5.2587,
  "best_model_checkpoint": "bin/liputan6-unipelt/checkpoint-189",
  "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": 1.8045581579208374,
      "learning_rate": 0.0008,
      "loss": 3.9747,
      "step": 63
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 127.0,
      "eval_loss": 3.104259490966797,
      "eval_rouge1": 3.9543,
      "eval_rouge2": 1.0191,
      "eval_rougeL": 3.7375,
      "eval_rougeLsum": 3.7922,
      "eval_runtime": 736.3876,
      "eval_samples_per_second": 1.358,
      "eval_steps_per_second": 0.043,
      "step": 63
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7170506715774536,
      "learning_rate": 0.0006,
      "loss": 3.0262,
      "step": 126
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 127.0,
      "eval_loss": 2.7314035892486572,
      "eval_rouge1": 5.0276,
      "eval_rouge2": 1.3105,
      "eval_rougeL": 4.1292,
      "eval_rougeLsum": 4.3574,
      "eval_runtime": 743.2532,
      "eval_samples_per_second": 1.345,
      "eval_steps_per_second": 0.043,
      "step": 126
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.0221407413482666,
      "learning_rate": 0.0004,
      "loss": 2.6214,
      "step": 189
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 127.0,
      "eval_loss": 2.564530849456787,
      "eval_rouge1": 5.2587,
      "eval_rouge2": 1.2673,
      "eval_rougeL": 3.8487,
      "eval_rougeLsum": 4.3728,
      "eval_runtime": 744.0563,
      "eval_samples_per_second": 1.344,
      "eval_steps_per_second": 0.043,
      "step": 189
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.192720890045166,
      "learning_rate": 0.0002,
      "loss": 2.3496,
      "step": 252
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 127.0,
      "eval_loss": 2.415849208831787,
      "eval_rouge1": 4.4309,
      "eval_rouge2": 0.9142,
      "eval_rougeL": 3.2152,
      "eval_rougeLsum": 3.5296,
      "eval_runtime": 745.8849,
      "eval_samples_per_second": 1.341,
      "eval_steps_per_second": 0.043,
      "step": 252
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.1153810024261475,
      "learning_rate": 0.0,
      "loss": 2.1749,
      "step": 315
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 127.0,
      "eval_loss": 2.367219924926758,
      "eval_rouge1": 5.0669,
      "eval_rouge2": 1.0704,
      "eval_rougeL": 3.6335,
      "eval_rougeLsum": 4.1011,
      "eval_runtime": 730.8251,
      "eval_samples_per_second": 1.368,
      "eval_steps_per_second": 0.044,
      "step": 315
    },
    {
      "epoch": 5.0,
      "step": 315,
      "total_flos": 3920273141760000.0,
      "train_loss": 2.8293707469153024,
      "train_runtime": 4145.4302,
      "train_samples_per_second": 1.206,
      "train_steps_per_second": 0.076
    }
  ],
  "logging_steps": 500,
  "max_steps": 315,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 3920273141760000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}