trainer_state.json

{
  "best_metric": 3.8852169513702393,
  "best_model_checkpoint": "tam_test_output/checkpoint-24",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.797638416290283,
      "eval_rouge1": 0.1363,
      "eval_rouge2": 0.0474,
      "eval_rougeL": 0.114,
      "eval_rougeLsum": 0.1145,
      "eval_runtime": 0.7327,
      "eval_samples_per_second": 66.879,
      "eval_steps_per_second": 1.365,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.6144208908081055,
      "eval_rouge1": 0.1354,
      "eval_rouge2": 0.0487,
      "eval_rougeL": 0.1137,
      "eval_rougeLsum": 0.1143,
      "eval_runtime": 0.7337,
      "eval_samples_per_second": 66.787,
      "eval_steps_per_second": 1.363,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.4348673820495605,
      "eval_rouge1": 0.1378,
      "eval_rouge2": 0.0494,
      "eval_rougeL": 0.1143,
      "eval_rougeLsum": 0.1149,
      "eval_runtime": 0.7364,
      "eval_samples_per_second": 66.542,
      "eval_steps_per_second": 1.358,
      "step": 9
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.26930570602417,
      "eval_rouge1": 0.1377,
      "eval_rouge2": 0.0494,
      "eval_rougeL": 0.1136,
      "eval_rougeLsum": 0.1142,
      "eval_runtime": 0.7305,
      "eval_samples_per_second": 67.076,
      "eval_steps_per_second": 1.369,
      "step": 12
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.129164218902588,
      "eval_rouge1": 0.1388,
      "eval_rouge2": 0.0509,
      "eval_rougeL": 0.1152,
      "eval_rougeLsum": 0.1157,
      "eval_runtime": 0.7242,
      "eval_samples_per_second": 67.656,
      "eval_steps_per_second": 1.381,
      "step": 15
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.020381450653076,
      "eval_rouge1": 0.1396,
      "eval_rouge2": 0.0509,
      "eval_rougeL": 0.1159,
      "eval_rougeLsum": 0.1165,
      "eval_runtime": 0.7443,
      "eval_samples_per_second": 65.836,
      "eval_steps_per_second": 1.344,
      "step": 18
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 19.0,
      "eval_loss": 3.9399197101593018,
      "eval_rouge1": 0.1396,
      "eval_rouge2": 0.0509,
      "eval_rougeL": 0.1159,
      "eval_rougeLsum": 0.1165,
      "eval_runtime": 0.7366,
      "eval_samples_per_second": 66.521,
      "eval_steps_per_second": 1.358,
      "step": 21
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 19.0,
      "eval_loss": 3.8852169513702393,
      "eval_rouge1": 0.1396,
      "eval_rouge2": 0.0509,
      "eval_rougeL": 0.1159,
      "eval_rougeLsum": 0.1165,
      "eval_runtime": 0.7316,
      "eval_samples_per_second": 66.972,
      "eval_steps_per_second": 1.367,
      "step": 24
    }
  ],
  "logging_steps": 500,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 426597358239744.0,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}