trainer_state.json

{
  "best_metric": 3.889864921569824,
  "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": 4.798501491546631,
      "eval_rouge1": 0.1363,
      "eval_rouge2": 0.0474,
      "eval_rougeL": 0.114,
      "eval_rougeLsum": 0.1145,
      "eval_runtime": 0.7381,
      "eval_samples_per_second": 66.387,
      "eval_steps_per_second": 1.355,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.617680072784424,
      "eval_rouge1": 0.1372,
      "eval_rouge2": 0.0493,
      "eval_rougeL": 0.1151,
      "eval_rougeLsum": 0.1157,
      "eval_runtime": 0.7465,
      "eval_samples_per_second": 65.643,
      "eval_steps_per_second": 1.34,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.439517498016357,
      "eval_rouge1": 0.1385,
      "eval_rouge2": 0.0504,
      "eval_rougeL": 0.115,
      "eval_rougeLsum": 0.1155,
      "eval_runtime": 0.7278,
      "eval_samples_per_second": 67.326,
      "eval_steps_per_second": 1.374,
      "step": 9
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.276594638824463,
      "eval_rouge1": 0.1376,
      "eval_rouge2": 0.0501,
      "eval_rougeL": 0.1144,
      "eval_rougeLsum": 0.115,
      "eval_runtime": 0.7366,
      "eval_samples_per_second": 66.523,
      "eval_steps_per_second": 1.358,
      "step": 12
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.136474132537842,
      "eval_rouge1": 0.1397,
      "eval_rouge2": 0.052,
      "eval_rougeL": 0.1165,
      "eval_rougeLsum": 0.117,
      "eval_runtime": 0.7313,
      "eval_samples_per_second": 67.007,
      "eval_steps_per_second": 1.367,
      "step": 15
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 19.0,
      "eval_loss": 4.026683330535889,
      "eval_rouge1": 0.1398,
      "eval_rouge2": 0.052,
      "eval_rougeL": 0.1172,
      "eval_rougeLsum": 0.1177,
      "eval_runtime": 0.7282,
      "eval_samples_per_second": 67.286,
      "eval_steps_per_second": 1.373,
      "step": 18
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 19.0,
      "eval_loss": 3.945326566696167,
      "eval_rouge1": 0.1401,
      "eval_rouge2": 0.0523,
      "eval_rougeL": 0.1176,
      "eval_rougeLsum": 0.118,
      "eval_runtime": 0.7279,
      "eval_samples_per_second": 67.317,
      "eval_steps_per_second": 1.374,
      "step": 21
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 19.0,
      "eval_loss": 3.889864921569824,
      "eval_rouge1": 0.141,
      "eval_rouge2": 0.0536,
      "eval_rougeL": 0.1187,
      "eval_rougeLsum": 0.1187,
      "eval_runtime": 0.7486,
      "eval_samples_per_second": 65.459,
      "eval_steps_per_second": 1.336,
      "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
}