last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07633587786259542,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002544529262086514,
      "eval_loss": NaN,
      "eval_runtime": 18.4714,
      "eval_samples_per_second": 8.987,
      "eval_steps_per_second": 4.493,
      "step": 1
    },
    {
      "epoch": 0.007633587786259542,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.015267175572519083,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.020356234096692113,
      "eval_loss": NaN,
      "eval_runtime": 18.4825,
      "eval_samples_per_second": 8.981,
      "eval_steps_per_second": 4.491,
      "step": 8
    },
    {
      "epoch": 0.022900763358778626,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.030534351145038167,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.03816793893129771,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.04071246819338423,
      "eval_loss": NaN,
      "eval_runtime": 18.5001,
      "eval_samples_per_second": 8.973,
      "eval_steps_per_second": 4.486,
      "step": 16
    },
    {
      "epoch": 0.04580152671755725,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.05343511450381679,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.061068702290076333,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.061068702290076333,
      "eval_loss": NaN,
      "eval_runtime": 18.4795,
      "eval_samples_per_second": 8.983,
      "eval_steps_per_second": 4.491,
      "step": 24
    },
    {
      "epoch": 0.06870229007633588,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.07633587786259542,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "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": 9801969665310720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}