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": 7.980721473693848,
      "learning_rate": 2e-05,
      "loss": 13.1234,
      "step": 1
    },
    {
      "epoch": 4.97840616326683e-05,
      "eval_loss": 3.1932132244110107,
      "eval_runtime": 103.3552,
      "eval_samples_per_second": 81.834,
      "eval_steps_per_second": 40.917,
      "step": 1
    },
    {
      "epoch": 9.95681232653366e-05,
      "grad_norm": 13.435827255249023,
      "learning_rate": 4e-05,
      "loss": 13.195,
      "step": 2
    },
    {
      "epoch": 0.0001493521848980049,
      "grad_norm": 15.840622901916504,
      "learning_rate": 6e-05,
      "loss": 13.0771,
      "step": 3
    },
    {
      "epoch": 0.0001493521848980049,
      "eval_loss": 3.177058458328247,
      "eval_runtime": 103.2353,
      "eval_samples_per_second": 81.929,
      "eval_steps_per_second": 40.965,
      "step": 3
    },
    {
      "epoch": 0.0001991362465306732,
      "grad_norm": 6.610230445861816,
      "learning_rate": 8e-05,
      "loss": 11.0908,
      "step": 4
    },
    {
      "epoch": 0.0002489203081633415,
      "grad_norm": 7.55332088470459,
      "learning_rate": 0.0001,
      "loss": 11.9893,
      "step": 5
    },
    {
      "epoch": 0.0002987043697960098,
      "grad_norm": 10.034672737121582,
      "learning_rate": 0.00012,
      "loss": 12.9387,
      "step": 6
    },
    {
      "epoch": 0.0002987043697960098,
      "eval_loss": 3.056739330291748,
      "eval_runtime": 102.9204,
      "eval_samples_per_second": 82.18,
      "eval_steps_per_second": 41.09,
      "step": 6
    },
    {
      "epoch": 0.0003484884314286781,
      "grad_norm": 6.793731212615967,
      "learning_rate": 0.00014,
      "loss": 11.0306,
      "step": 7
    },
    {
      "epoch": 0.0003982724930613464,
      "grad_norm": 6.054509162902832,
      "learning_rate": 0.00016,
      "loss": 11.7016,
      "step": 8
    },
    {
      "epoch": 0.0004480565546940147,
      "grad_norm": 9.548287391662598,
      "learning_rate": 0.00018,
      "loss": 13.7429,
      "step": 9
    },
    {
      "epoch": 0.0004480565546940147,
      "eval_loss": 2.9261560440063477,
      "eval_runtime": 105.2189,
      "eval_samples_per_second": 80.385,
      "eval_steps_per_second": 40.192,
      "step": 9
    },
    {
      "epoch": 0.000497840616326683,
      "grad_norm": 5.581520080566406,
      "learning_rate": 0.0002,
      "loss": 11.6552,
      "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
}