last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0021325371861171828,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.108457287057277e-05,
      "eval_loss": NaN,
      "eval_runtime": 1217.7733,
      "eval_samples_per_second": 4.865,
      "eval_steps_per_second": 2.432,
      "step": 1
    },
    {
      "epoch": 0.00021325371861171828,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00042650743722343656,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005686765829645822,
      "eval_loss": NaN,
      "eval_runtime": 1217.6516,
      "eval_samples_per_second": 4.865,
      "eval_steps_per_second": 2.433,
      "step": 8
    },
    {
      "epoch": 0.0006397611558351549,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0008530148744468731,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0010662685930585914,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0011373531659291643,
      "eval_loss": NaN,
      "eval_runtime": 1218.9221,
      "eval_samples_per_second": 4.86,
      "eval_steps_per_second": 2.43,
      "step": 16
    },
    {
      "epoch": 0.0012795223116703097,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.001492776030282028,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0017060297488937462,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0017060297488937462,
      "eval_loss": NaN,
      "eval_runtime": 1219.172,
      "eval_samples_per_second": 4.859,
      "eval_steps_per_second": 2.43,
      "step": 24
    },
    {
      "epoch": 0.0019192834675054646,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0021325371861171828,
      "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": 2.073272468373504e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}