checkpoint-1428/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24991249562478124,
  "eval_steps": 1142,
  "global_step": 1428,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08750437521876094,
      "grad_norm": 8.797028541564941,
      "learning_rate": 1.824991249562478e-05,
      "loss": 3.9704,
      "step": 500
    },
    {
      "epoch": 0.17500875043752187,
      "grad_norm": 7.093753337860107,
      "learning_rate": 1.6499824991249566e-05,
      "loss": 3.6946,
      "step": 1000
    },
    {
      "epoch": 0.19985999299965,
      "eval_gen_len": 36.008,
      "eval_loss": 3.3878133296966553,
      "eval_rouge1": 0.1544,
      "eval_rouge2": 0.0339,
      "eval_rougeL": 0.1176,
      "eval_rougeLsum": 0.1369,
      "eval_runtime": 204.0944,
      "eval_samples_per_second": 2.45,
      "eval_steps_per_second": 0.157,
      "step": 1142
    }
  ],
  "logging_steps": 500,
  "max_steps": 5714,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 714,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5008051345489920.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}