trainer_state.json

{
  "best_metric": 3.8989675045013428,
  "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": 4.7985639572143555,
      "eval_rouge1": 0.1363,
      "eval_rouge2": 0.0474,
      "eval_rougeL": 0.114,
      "eval_rougeLsum": 0.1145,
      "eval_runtime": 0.7359,
      "eval_samples_per_second": 66.584,
      "eval_steps_per_second": 1.359,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.617778778076172,
      "eval_rouge1": 0.1354,
      "eval_rouge2": 0.0487,
      "eval_rougeL": 0.1137,
      "eval_rougeLsum": 0.1143,
      "eval_runtime": 0.744,
      "eval_samples_per_second": 65.859,
      "eval_steps_per_second": 1.344,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.4424662590026855,
      "eval_rouge1": 0.1383,
      "eval_rouge2": 0.0497,
      "eval_rougeL": 0.115,
      "eval_rougeLsum": 0.1156,
      "eval_runtime": 0.7339,
      "eval_samples_per_second": 66.765,
      "eval_steps_per_second": 1.363,
      "step": 9
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.281266212463379,
      "eval_rouge1": 0.1376,
      "eval_rouge2": 0.0494,
      "eval_rougeL": 0.1136,
      "eval_rougeLsum": 0.1143,
      "eval_runtime": 0.729,
      "eval_samples_per_second": 67.216,
      "eval_steps_per_second": 1.372,
      "step": 12
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.141903877258301,
      "eval_rouge1": 0.1376,
      "eval_rouge2": 0.0494,
      "eval_rougeL": 0.1136,
      "eval_rougeLsum": 0.1143,
      "eval_runtime": 0.7301,
      "eval_samples_per_second": 67.11,
      "eval_steps_per_second": 1.37,
      "step": 15
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.0332932472229,
      "eval_rouge1": 0.1397,
      "eval_rouge2": 0.0509,
      "eval_rougeL": 0.1159,
      "eval_rougeLsum": 0.1166,
      "eval_runtime": 0.725,
      "eval_samples_per_second": 67.587,
      "eval_steps_per_second": 1.379,
      "step": 18
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 19.0,
      "eval_loss": 3.953413724899292,
      "eval_rouge1": 0.1402,
      "eval_rouge2": 0.0498,
      "eval_rougeL": 0.1162,
      "eval_rougeLsum": 0.1167,
      "eval_runtime": 0.7291,
      "eval_samples_per_second": 67.203,
      "eval_steps_per_second": 1.371,
      "step": 21
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 19.0,
      "eval_loss": 3.8989675045013428,
      "eval_rouge1": 0.1402,
      "eval_rouge2": 0.0498,
      "eval_rougeL": 0.1162,
      "eval_rougeLsum": 0.1167,
      "eval_runtime": 0.7285,
      "eval_samples_per_second": 67.261,
      "eval_steps_per_second": 1.373,
      "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
}