trainer_state.json

{
  "best_metric": 2.9525649547576904,
  "best_model_checkpoint": "en-to-lg-ufal-al/checkpoint-80",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_bleu": 11.6403,
      "eval_gen_len": 40.7538,
      "eval_loss": 3.0069949626922607,
      "eval_runtime": 1470.7763,
      "eval_samples_per_second": 10.552,
      "eval_steps_per_second": 0.33,
      "step": 16
    },
    {
      "epoch": 2.0,
      "eval_bleu": 11.8539,
      "eval_gen_len": 40.9505,
      "eval_loss": 2.984744071960449,
      "eval_runtime": 1483.5524,
      "eval_samples_per_second": 10.461,
      "eval_steps_per_second": 0.327,
      "step": 32
    },
    {
      "epoch": 3.0,
      "eval_bleu": 11.994,
      "eval_gen_len": 41.184,
      "eval_loss": 2.9674794673919678,
      "eval_runtime": 1494.2286,
      "eval_samples_per_second": 10.387,
      "eval_steps_per_second": 0.325,
      "step": 48
    },
    {
      "epoch": 3.125,
      "grad_norm": 1.9179797172546387,
      "learning_rate": 7.75e-06,
      "loss": 3.246,
      "step": 50
    },
    {
      "epoch": 4.0,
      "eval_bleu": 12.0347,
      "eval_gen_len": 41.2755,
      "eval_loss": 2.9567463397979736,
      "eval_runtime": 1498.1906,
      "eval_samples_per_second": 10.359,
      "eval_steps_per_second": 0.324,
      "step": 64
    },
    {
      "epoch": 5.0,
      "eval_bleu": 12.0533,
      "eval_gen_len": 41.2954,
      "eval_loss": 2.9525649547576904,
      "eval_runtime": 1493.8941,
      "eval_samples_per_second": 10.389,
      "eval_steps_per_second": 0.325,
      "step": 80
    }
  ],
  "logging_steps": 50,
  "max_steps": 80,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 165906284544000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}