trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.0,
  "global_step": 5028,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_bleu": 15.5532,
      "eval_gen_len": 262.7814,
      "eval_loss": 2.603503942489624,
      "eval_runtime": 1071.2105,
      "eval_samples_per_second": 1.563,
      "eval_steps_per_second": 0.196,
      "step": 419
    },
    {
      "epoch": 2.0,
      "eval_bleu": 15.8442,
      "eval_gen_len": 249.9671,
      "eval_loss": 2.534031629562378,
      "eval_runtime": 974.071,
      "eval_samples_per_second": 1.719,
      "eval_steps_per_second": 0.216,
      "step": 838
    },
    {
      "epoch": 3.0,
      "eval_bleu": 15.4747,
      "eval_gen_len": 274.1971,
      "eval_loss": 2.492140293121338,
      "eval_runtime": 1054.8804,
      "eval_samples_per_second": 1.587,
      "eval_steps_per_second": 0.199,
      "step": 1257
    },
    {
      "epoch": 4.0,
      "eval_bleu": 16.1199,
      "eval_gen_len": 258.5263,
      "eval_loss": 2.5081911087036133,
      "eval_runtime": 967.203,
      "eval_samples_per_second": 1.731,
      "eval_steps_per_second": 0.217,
      "step": 1676
    },
    {
      "epoch": 5.0,
      "eval_bleu": 16.2089,
      "eval_gen_len": 260.6117,
      "eval_loss": 2.512809991836548,
      "eval_runtime": 986.3606,
      "eval_samples_per_second": 1.697,
      "eval_steps_per_second": 0.213,
      "step": 2095
    },
    {
      "epoch": 6.0,
      "eval_bleu": 16.0677,
      "eval_gen_len": 256.6434,
      "eval_loss": 2.532682180404663,
      "eval_runtime": 972.4474,
      "eval_samples_per_second": 1.721,
      "eval_steps_per_second": 0.216,
      "step": 2514
    },
    {
      "epoch": 7.0,
      "eval_bleu": 15.9211,
      "eval_gen_len": 254.4606,
      "eval_loss": 2.5517630577087402,
      "eval_runtime": 947.2841,
      "eval_samples_per_second": 1.767,
      "eval_steps_per_second": 0.222,
      "step": 2933
    },
    {
      "epoch": 8.0,
      "eval_bleu": 16.022,
      "eval_gen_len": 257.5149,
      "eval_loss": 2.563725709915161,
      "eval_runtime": 962.17,
      "eval_samples_per_second": 1.74,
      "eval_steps_per_second": 0.218,
      "step": 3352
    },
    {
      "epoch": 9.0,
      "eval_bleu": 16.0511,
      "eval_gen_len": 258.0084,
      "eval_loss": 2.5875699520111084,
      "eval_runtime": 962.6535,
      "eval_samples_per_second": 1.739,
      "eval_steps_per_second": 0.218,
      "step": 3771
    },
    {
      "epoch": 10.0,
      "eval_bleu": 16.0276,
      "eval_gen_len": 257.9409,
      "eval_loss": 2.589696168899536,
      "eval_runtime": 968.2157,
      "eval_samples_per_second": 1.729,
      "eval_steps_per_second": 0.217,
      "step": 4190
    },
    {
      "epoch": 11.0,
      "eval_bleu": 15.9876,
      "eval_gen_len": 258.5191,
      "eval_loss": 2.600374221801758,
      "eval_runtime": 972.9329,
      "eval_samples_per_second": 1.721,
      "eval_steps_per_second": 0.216,
      "step": 4609
    },
    {
      "epoch": 11.93,
      "learning_rate": 2.7844073190135243e-07,
      "loss": 0.8761,
      "step": 5000
    },
    {
      "epoch": 12.0,
      "eval_bleu": 16.0242,
      "eval_gen_len": 259.6051,
      "eval_loss": 2.603928565979004,
      "eval_runtime": 980.0259,
      "eval_samples_per_second": 1.708,
      "eval_steps_per_second": 0.214,
      "step": 5028
    },
    {
      "epoch": 12.0,
      "step": 5028,
      "total_flos": 5449229958905856.0,
      "train_loss": 0.873852771146011,
      "train_runtime": 13341.3267,
      "train_samples_per_second": 3.012,
      "train_steps_per_second": 0.377
    }
  ],
  "max_steps": 5028,
  "num_train_epochs": 12,
  "total_flos": 5449229958905856.0,
  "trial_name": null,
  "trial_params": null
}