last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011243851018974,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011243851018973998,
      "grad_norm": 15.085867881774902,
      "learning_rate": 2e-05,
      "loss": 12.9478,
      "step": 1
    },
    {
      "epoch": 0.00022487702037947996,
      "grad_norm": 10.755067825317383,
      "learning_rate": 4e-05,
      "loss": 14.0026,
      "step": 2
    },
    {
      "epoch": 0.00033731553056921994,
      "grad_norm": 10.571486473083496,
      "learning_rate": 6e-05,
      "loss": 12.0079,
      "step": 3
    },
    {
      "epoch": 0.00033731553056921994,
      "eval_loss": 3.196536064147949,
      "eval_runtime": 191.7723,
      "eval_samples_per_second": 19.528,
      "eval_steps_per_second": 9.767,
      "step": 3
    },
    {
      "epoch": 0.0004497540407589599,
      "grad_norm": 8.108671188354492,
      "learning_rate": 8e-05,
      "loss": 15.1813,
      "step": 4
    },
    {
      "epoch": 0.0005621925509487,
      "grad_norm": 8.093324661254883,
      "learning_rate": 0.0001,
      "loss": 12.862,
      "step": 5
    },
    {
      "epoch": 0.0006746310611384399,
      "grad_norm": 9.614452362060547,
      "learning_rate": 0.00012,
      "loss": 9.9826,
      "step": 6
    },
    {
      "epoch": 0.0006746310611384399,
      "eval_loss": 2.9050025939941406,
      "eval_runtime": 198.7754,
      "eval_samples_per_second": 18.84,
      "eval_steps_per_second": 9.423,
      "step": 6
    },
    {
      "epoch": 0.0007870695713281799,
      "grad_norm": 9.192273139953613,
      "learning_rate": 0.00014,
      "loss": 8.8125,
      "step": 7
    },
    {
      "epoch": 0.0008995080815179198,
      "grad_norm": 14.598649978637695,
      "learning_rate": 0.00016,
      "loss": 8.5464,
      "step": 8
    },
    {
      "epoch": 0.00101194659170766,
      "grad_norm": 10.85025405883789,
      "learning_rate": 0.00018,
      "loss": 5.853,
      "step": 9
    },
    {
      "epoch": 0.00101194659170766,
      "eval_loss": 1.798444151878357,
      "eval_runtime": 228.2587,
      "eval_samples_per_second": 16.407,
      "eval_steps_per_second": 8.206,
      "step": 9
    },
    {
      "epoch": 0.0011243851018974,
      "grad_norm": 7.590512752532959,
      "learning_rate": 0.0002,
      "loss": 4.7837,
      "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": 1445776569925632.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}