last-checkpoint/trainer_state.json

{
  "best_metric": 1.31853449344635,
  "best_model_checkpoint": "./opt_trained/checkpoint-374",
  "epoch": 17.0,
  "eval_steps": 500,
  "global_step": 374,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.8587957620620728,
      "eval_runtime": 8.062,
      "eval_samples_per_second": 37.212,
      "eval_steps_per_second": 9.303,
      "step": 22
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.4884560108184814,
      "eval_runtime": 8.0476,
      "eval_samples_per_second": 37.278,
      "eval_steps_per_second": 9.32,
      "step": 44
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3922361135482788,
      "eval_runtime": 8.0491,
      "eval_samples_per_second": 37.271,
      "eval_steps_per_second": 9.318,
      "step": 66
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.3830264806747437,
      "eval_runtime": 8.0646,
      "eval_samples_per_second": 37.2,
      "eval_steps_per_second": 9.3,
      "step": 88
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.354698896408081,
      "eval_runtime": 8.0581,
      "eval_samples_per_second": 37.23,
      "eval_steps_per_second": 9.307,
      "step": 110
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.3555606603622437,
      "eval_runtime": 8.0406,
      "eval_samples_per_second": 37.311,
      "eval_steps_per_second": 9.328,
      "step": 132
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.367162823677063,
      "eval_runtime": 8.0926,
      "eval_samples_per_second": 37.071,
      "eval_steps_per_second": 9.268,
      "step": 154
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.350898027420044,
      "eval_runtime": 8.0696,
      "eval_samples_per_second": 37.177,
      "eval_steps_per_second": 9.294,
      "step": 176
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.3414418697357178,
      "eval_runtime": 8.0548,
      "eval_samples_per_second": 37.245,
      "eval_steps_per_second": 9.311,
      "step": 198
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.3427915573120117,
      "eval_runtime": 8.0486,
      "eval_samples_per_second": 37.274,
      "eval_steps_per_second": 9.318,
      "step": 220
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.3360599279403687,
      "eval_runtime": 8.0639,
      "eval_samples_per_second": 37.203,
      "eval_steps_per_second": 9.301,
      "step": 242
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.3332167863845825,
      "eval_runtime": 8.1186,
      "eval_samples_per_second": 36.952,
      "eval_steps_per_second": 9.238,
      "step": 264
    },
    {
      "epoch": 13.0,
      "eval_loss": 1.3333313465118408,
      "eval_runtime": 8.1186,
      "eval_samples_per_second": 36.952,
      "eval_steps_per_second": 9.238,
      "step": 286
    },
    {
      "epoch": 14.0,
      "eval_loss": 1.3279589414596558,
      "eval_runtime": 8.1077,
      "eval_samples_per_second": 37.002,
      "eval_steps_per_second": 9.25,
      "step": 308
    },
    {
      "epoch": 15.0,
      "eval_loss": 1.323224663734436,
      "eval_runtime": 8.1229,
      "eval_samples_per_second": 36.933,
      "eval_steps_per_second": 9.233,
      "step": 330
    },
    {
      "epoch": 16.0,
      "eval_loss": 1.3214843273162842,
      "eval_runtime": 8.1269,
      "eval_samples_per_second": 36.914,
      "eval_steps_per_second": 9.229,
      "step": 352
    },
    {
      "epoch": 17.0,
      "eval_loss": 1.31853449344635,
      "eval_runtime": 8.1214,
      "eval_samples_per_second": 36.939,
      "eval_steps_per_second": 9.235,
      "step": 374
    }
  ],
  "logging_steps": 500,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2060141954048e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}