last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00047224386673278083,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.722438667327808e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 4.722438667327808e-05,
      "eval_loss": NaN,
      "eval_runtime": 587.2698,
      "eval_samples_per_second": 15.182,
      "eval_steps_per_second": 7.591,
      "step": 1
    },
    {
      "epoch": 9.444877334655616e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00014167316001983425,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00014167316001983425,
      "eval_loss": NaN,
      "eval_runtime": 585.8733,
      "eval_samples_per_second": 15.218,
      "eval_steps_per_second": 7.609,
      "step": 3
    },
    {
      "epoch": 0.00018889754669311232,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00023612193336639041,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0002833463200396685,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0002833463200396685,
      "eval_loss": NaN,
      "eval_runtime": 586.2518,
      "eval_samples_per_second": 15.208,
      "eval_steps_per_second": 7.604,
      "step": 6
    },
    {
      "epoch": 0.00033057070671294655,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00037779509338622464,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00042501948005950273,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00042501948005950273,
      "eval_loss": NaN,
      "eval_runtime": 585.809,
      "eval_samples_per_second": 15.22,
      "eval_steps_per_second": 7.61,
      "step": 9
    },
    {
      "epoch": 0.00047224386673278083,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 1.4104,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3984672593805312.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}