last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000880514220304658,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.9350474010155263e-05,
      "eval_loss": NaN,
      "eval_runtime": 2149.9224,
      "eval_samples_per_second": 6.673,
      "eval_steps_per_second": 3.336,
      "step": 1
    },
    {
      "epoch": 8.805142203046579e-05,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0001467523700507763,
      "eval_loss": NaN,
      "eval_runtime": 2148.2826,
      "eval_samples_per_second": 6.678,
      "eval_steps_per_second": 3.339,
      "step": 5
    },
    {
      "epoch": 0.00017610284406093158,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0002641542660913974,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0002935047401015526,
      "eval_loss": NaN,
      "eval_runtime": 2148.8863,
      "eval_samples_per_second": 6.676,
      "eval_steps_per_second": 3.338,
      "step": 10
    },
    {
      "epoch": 0.00035220568812186317,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.000440257110152329,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.000440257110152329,
      "eval_loss": NaN,
      "eval_runtime": 2152.1589,
      "eval_samples_per_second": 6.666,
      "eval_steps_per_second": 3.333,
      "step": 15
    },
    {
      "epoch": 0.0005283085321827948,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0005870094802031052,
      "eval_loss": NaN,
      "eval_runtime": 2151.6824,
      "eval_samples_per_second": 6.667,
      "eval_steps_per_second": 3.334,
      "step": 20
    },
    {
      "epoch": 0.0006163599542132605,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0007044113762437263,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0007337618502538816,
      "eval_loss": NaN,
      "eval_runtime": 2151.6873,
      "eval_samples_per_second": 6.667,
      "eval_steps_per_second": 3.334,
      "step": 25
    },
    {
      "epoch": 0.0007924627982741922,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.000880514220304658,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.000880514220304658,
      "eval_loss": NaN,
      "eval_runtime": 2151.8618,
      "eval_samples_per_second": 6.667,
      "eval_steps_per_second": 3.333,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.406628388864e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}