checkpoint-434/trainer_state.json

{
  "best_metric": 6.03105354309082,
  "best_model_checkpoint": "bill_sum_finetune_test_gpt2_medium/checkpoint-403",
  "epoch": 14.0,
  "eval_steps": 500,
  "global_step": 434,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.400322914123535,
      "eval_rouge1": 0.3998,
      "eval_rouge2": 0.1672,
      "eval_rougeL": 0.2188,
      "eval_rougeLsum": 0.3449,
      "eval_runtime": 34.2204,
      "eval_samples_per_second": 7.247,
      "eval_steps_per_second": 0.234,
      "step": 31
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.197171688079834,
      "eval_rouge1": 0.4092,
      "eval_rouge2": 0.1715,
      "eval_rougeL": 0.2241,
      "eval_rougeLsum": 0.3526,
      "eval_runtime": 34.6438,
      "eval_samples_per_second": 7.159,
      "eval_steps_per_second": 0.231,
      "step": 62
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.118707656860352,
      "eval_rouge1": 0.3997,
      "eval_rouge2": 0.1673,
      "eval_rougeL": 0.2187,
      "eval_rougeLsum": 0.3447,
      "eval_runtime": 34.107,
      "eval_samples_per_second": 7.271,
      "eval_steps_per_second": 0.235,
      "step": 93
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.087508201599121,
      "eval_rouge1": 0.4,
      "eval_rouge2": 0.1676,
      "eval_rougeL": 0.219,
      "eval_rougeLsum": 0.3451,
      "eval_runtime": 34.99,
      "eval_samples_per_second": 7.088,
      "eval_steps_per_second": 0.229,
      "step": 124
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.069467544555664,
      "eval_rouge1": 0.3999,
      "eval_rouge2": 0.1674,
      "eval_rougeL": 0.2189,
      "eval_rougeLsum": 0.3449,
      "eval_runtime": 33.9661,
      "eval_samples_per_second": 7.301,
      "eval_steps_per_second": 0.236,
      "step": 155
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.058210372924805,
      "eval_rouge1": 0.3997,
      "eval_rouge2": 0.1674,
      "eval_rougeL": 0.2188,
      "eval_rougeLsum": 0.3446,
      "eval_runtime": 34.8589,
      "eval_samples_per_second": 7.114,
      "eval_steps_per_second": 0.229,
      "step": 186
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.04926872253418,
      "eval_rouge1": 0.3998,
      "eval_rouge2": 0.1673,
      "eval_rougeL": 0.2188,
      "eval_rougeLsum": 0.3449,
      "eval_runtime": 34.0483,
      "eval_samples_per_second": 7.284,
      "eval_steps_per_second": 0.235,
      "step": 217
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.043769836425781,
      "eval_rouge1": 0.403,
      "eval_rouge2": 0.1689,
      "eval_rougeL": 0.2205,
      "eval_rougeLsum": 0.3473,
      "eval_runtime": 34.9445,
      "eval_samples_per_second": 7.097,
      "eval_steps_per_second": 0.229,
      "step": 248
    },
    {
      "epoch": 9.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.037980079650879,
      "eval_rouge1": 0.401,
      "eval_rouge2": 0.168,
      "eval_rougeL": 0.2195,
      "eval_rougeLsum": 0.3458,
      "eval_runtime": 33.8278,
      "eval_samples_per_second": 7.331,
      "eval_steps_per_second": 0.236,
      "step": 279
    },
    {
      "epoch": 10.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.0378899574279785,
      "eval_rouge1": 0.4082,
      "eval_rouge2": 0.1713,
      "eval_rougeL": 0.2236,
      "eval_rougeLsum": 0.3519,
      "eval_runtime": 34.7389,
      "eval_samples_per_second": 7.139,
      "eval_steps_per_second": 0.23,
      "step": 310
    },
    {
      "epoch": 11.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.032817840576172,
      "eval_rouge1": 0.4137,
      "eval_rouge2": 0.1739,
      "eval_rougeL": 0.2265,
      "eval_rougeLsum": 0.3568,
      "eval_runtime": 33.5201,
      "eval_samples_per_second": 7.399,
      "eval_steps_per_second": 0.239,
      "step": 341
    },
    {
      "epoch": 12.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.0318193435668945,
      "eval_rouge1": 0.4081,
      "eval_rouge2": 0.1714,
      "eval_rougeL": 0.2235,
      "eval_rougeLsum": 0.3518,
      "eval_runtime": 34.3788,
      "eval_samples_per_second": 7.214,
      "eval_steps_per_second": 0.233,
      "step": 372
    },
    {
      "epoch": 13.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.03105354309082,
      "eval_rouge1": 0.4106,
      "eval_rouge2": 0.1726,
      "eval_rougeL": 0.2248,
      "eval_rougeLsum": 0.3538,
      "eval_runtime": 33.8705,
      "eval_samples_per_second": 7.322,
      "eval_steps_per_second": 0.236,
      "step": 403
    },
    {
      "epoch": 14.0,
      "eval_gen_len": 600.0,
      "eval_loss": 6.0320916175842285,
      "eval_rouge1": 0.4058,
      "eval_rouge2": 0.1703,
      "eval_rougeL": 0.2222,
      "eval_rougeLsum": 0.3499,
      "eval_runtime": 34.9479,
      "eval_samples_per_second": 7.096,
      "eval_steps_per_second": 0.229,
      "step": 434
    }
  ],
  "logging_steps": 500,
  "max_steps": 465,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "total_flos": 1.2858789816434688e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}