trainer_state.json

{
  "best_metric": 3.8955132961273193,
  "best_model_checkpoint": "en-to-lg-nllb/checkpoint-126",
  "epoch": 4.984126984126984,
  "eval_steps": 50,
  "global_step": 157,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9841269841269841,
      "eval_bleu": 4.9826,
      "eval_gen_len": 21.0615,
      "eval_loss": 4.006349086761475,
      "eval_runtime": 25808.7824,
      "eval_samples_per_second": 13.795,
      "eval_steps_per_second": 0.862,
      "step": 31
    },
    {
      "epoch": 2.0,
      "eval_bleu": 5.1662,
      "eval_gen_len": 21.0337,
      "eval_loss": 3.9251999855041504,
      "eval_runtime": 24598.2105,
      "eval_samples_per_second": 14.474,
      "eval_steps_per_second": 0.905,
      "step": 63
    },
    {
      "epoch": 2.984126984126984,
      "eval_bleu": 5.1982,
      "eval_gen_len": 21.0079,
      "eval_loss": 3.9015612602233887,
      "eval_runtime": 24397.4743,
      "eval_samples_per_second": 14.594,
      "eval_steps_per_second": 0.912,
      "step": 94
    },
    {
      "epoch": 4.0,
      "eval_bleu": 5.1957,
      "eval_gen_len": 21.1682,
      "eval_loss": 3.8955132961273193,
      "eval_runtime": 24834.7491,
      "eval_samples_per_second": 14.337,
      "eval_steps_per_second": 0.896,
      "step": 126
    },
    {
      "epoch": 4.984126984126984,
      "eval_bleu": 5.2696,
      "eval_gen_len": 20.8579,
      "eval_loss": 3.8994901180267334,
      "eval_runtime": 24130.7665,
      "eval_samples_per_second": 14.755,
      "eval_steps_per_second": 0.922,
      "step": 157
    }
  ],
  "logging_steps": 500,
  "max_steps": 310,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 42631431192576.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}