last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000497840616326683,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.97840616326683e-05,
      "grad_norm": 8.111016273498535,
      "learning_rate": 2e-05,
      "loss": 13.1234,
      "step": 1
    },
    {
      "epoch": 4.97840616326683e-05,
      "eval_loss": 3.1932132244110107,
      "eval_runtime": 103.559,
      "eval_samples_per_second": 81.673,
      "eval_steps_per_second": 40.837,
      "step": 1
    },
    {
      "epoch": 9.95681232653366e-05,
      "grad_norm": 13.81267261505127,
      "learning_rate": 4e-05,
      "loss": 13.195,
      "step": 2
    },
    {
      "epoch": 0.0001493521848980049,
      "grad_norm": 16.595325469970703,
      "learning_rate": 6e-05,
      "loss": 12.9629,
      "step": 3
    },
    {
      "epoch": 0.0001493521848980049,
      "eval_loss": 3.1768229007720947,
      "eval_runtime": 103.6109,
      "eval_samples_per_second": 81.632,
      "eval_steps_per_second": 40.816,
      "step": 3
    },
    {
      "epoch": 0.0001991362465306732,
      "grad_norm": 6.646209239959717,
      "learning_rate": 8e-05,
      "loss": 11.178,
      "step": 4
    },
    {
      "epoch": 0.0002489203081633415,
      "grad_norm": 7.884037971496582,
      "learning_rate": 0.0001,
      "loss": 11.8304,
      "step": 5
    },
    {
      "epoch": 0.0002987043697960098,
      "grad_norm": 10.244056701660156,
      "learning_rate": 0.00012,
      "loss": 12.695,
      "step": 6
    },
    {
      "epoch": 0.0002987043697960098,
      "eval_loss": 3.0555026531219482,
      "eval_runtime": 102.3066,
      "eval_samples_per_second": 82.673,
      "eval_steps_per_second": 41.337,
      "step": 6
    },
    {
      "epoch": 0.0003484884314286781,
      "grad_norm": 7.098816871643066,
      "learning_rate": 0.00014,
      "loss": 11.0273,
      "step": 7
    },
    {
      "epoch": 0.0003982724930613464,
      "grad_norm": 5.981750011444092,
      "learning_rate": 0.00016,
      "loss": 11.6288,
      "step": 8
    },
    {
      "epoch": 0.0004480565546940147,
      "grad_norm": 9.817290306091309,
      "learning_rate": 0.00018,
      "loss": 13.7312,
      "step": 9
    },
    {
      "epoch": 0.0004480565546940147,
      "eval_loss": 2.9261841773986816,
      "eval_runtime": 102.3599,
      "eval_samples_per_second": 82.63,
      "eval_steps_per_second": 41.315,
      "step": 9
    },
    {
      "epoch": 0.000497840616326683,
      "grad_norm": 18.975074768066406,
      "learning_rate": 0.0002,
      "loss": 11.6206,
      "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": 80699876966400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}