trainer_state.json

{
  "best_global_step": 2,
  "best_metric": 8.35378646850586,
  "best_model_checkpoint": "/content/drive/MyDrive/train_results/results_t5/afriteva_small/checkpoint-2",
  "epoch": 0.8,
  "eval_steps": 500,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "eval_bleu": 0.006160717733628021,
      "eval_cer": 0.938956994782895,
      "eval_f1": 0.13459920466970887,
      "eval_loss": 8.35378646850586,
      "eval_meteor": 0.04287920903748109,
      "eval_runtime": 5.7683,
      "eval_samples_per_second": 1.734,
      "eval_steps_per_second": 0.347,
      "eval_wer": 1.3618687717511246,
      "step": 2
    },
    {
      "epoch": 0.8,
      "step": 2,
      "total_flos": 4388919705600.0,
      "train_loss": 8.67578125,
      "train_runtime": 7.7134,
      "train_samples_per_second": 10.372,
      "train_steps_per_second": 0.259
    }
  ],
  "logging_steps": 50,
  "max_steps": 2,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4388919705600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}