last-checkpoint/trainer_state.json

{
  "best_metric": 0.28598517179489136,
  "best_model_checkpoint": "./opt_trained/checkpoint-644",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2898,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.2863014340400696,
      "eval_runtime": 114.3677,
      "eval_samples_per_second": 24.972,
      "eval_steps_per_second": 6.243,
      "step": 322
    },
    {
      "epoch": 1.5540856031128405,
      "grad_norm": 2.4725921154022217,
      "learning_rate": 3.940433505043101e-05,
      "loss": 0.2885,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.28598517179489136,
      "eval_runtime": 114.3207,
      "eval_samples_per_second": 24.982,
      "eval_steps_per_second": 6.246,
      "step": 644
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.286264568567276,
      "eval_runtime": 115.3694,
      "eval_samples_per_second": 24.755,
      "eval_steps_per_second": 6.189,
      "step": 966
    },
    {
      "epoch": 3.1058365758754864,
      "grad_norm": 3.0103938579559326,
      "learning_rate": 3.765282187493851e-05,
      "loss": 0.2855,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.28652164340019226,
      "eval_runtime": 115.3469,
      "eval_samples_per_second": 24.76,
      "eval_steps_per_second": 6.19,
      "step": 1288
    },
    {
      "epoch": 4.659922178988327,
      "grad_norm": 2.680344820022583,
      "learning_rate": 3.484979197425745e-05,
      "loss": 0.2825,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.2863679528236389,
      "eval_runtime": 115.3268,
      "eval_samples_per_second": 24.764,
      "eval_steps_per_second": 6.191,
      "step": 1610
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.2881246507167816,
      "eval_runtime": 115.3108,
      "eval_samples_per_second": 24.768,
      "eval_steps_per_second": 6.192,
      "step": 1932
    },
    {
      "epoch": 6.211673151750973,
      "grad_norm": 3.0973498821258545,
      "learning_rate": 3.1162212014830765e-05,
      "loss": 0.2787,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.2881006598472595,
      "eval_runtime": 115.2521,
      "eval_samples_per_second": 24.78,
      "eval_steps_per_second": 6.195,
      "step": 2254
    },
    {
      "epoch": 7.765758754863813,
      "grad_norm": 3.3326103687286377,
      "learning_rate": 2.680973820971481e-05,
      "loss": 0.2756,
      "step": 2500
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.2883214056491852,
      "eval_runtime": 115.3007,
      "eval_samples_per_second": 24.77,
      "eval_steps_per_second": 6.193,
      "step": 2576
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.28775903582572937,
      "eval_runtime": 115.3453,
      "eval_samples_per_second": 24.76,
      "eval_steps_per_second": 6.19,
      "step": 2898
    }
  ],
  "logging_steps": 500,
  "max_steps": 6420,
  "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": 9.134573980032e+16,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}