checkpoint-2/trainer_state.json

{
  "best_metric": 3.4803478717803955,
  "best_model_checkpoint": "opus-mt-zh-en-finetuned-zh-to-en/checkpoint-2",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_bleu": 5.6918,
      "eval_gen_len": 57.3333,
      "eval_loss": 3.5217063426971436,
      "eval_runtime": 10.9763,
      "eval_samples_per_second": 0.273,
      "eval_steps_per_second": 0.091,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_bleu": 7.6304,
      "eval_gen_len": 55.3333,
      "eval_loss": 3.4803478717803955,
      "eval_runtime": 8.3555,
      "eval_samples_per_second": 0.359,
      "eval_steps_per_second": 0.12,
      "step": 2
    }
  ],
  "logging_steps": 500,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 155720613888.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}