last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008356487768191029,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.356487768191029e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 8.356487768191029e-05,
      "eval_loss": NaN,
      "eval_runtime": 559.9179,
      "eval_samples_per_second": 9.0,
      "eval_steps_per_second": 4.501,
      "step": 1
    },
    {
      "epoch": 0.00016712975536382058,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0002506946330457309,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0002506946330457309,
      "eval_loss": NaN,
      "eval_runtime": 560.0029,
      "eval_samples_per_second": 8.998,
      "eval_steps_per_second": 4.5,
      "step": 3
    },
    {
      "epoch": 0.00033425951072764117,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00041782438840955145,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0005013892660914618,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005013892660914618,
      "eval_loss": NaN,
      "eval_runtime": 559.6637,
      "eval_samples_per_second": 9.004,
      "eval_steps_per_second": 4.503,
      "step": 6
    },
    {
      "epoch": 0.0005849541437733721,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0006685190214552823,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0007520838991371926,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0007520838991371926,
      "eval_loss": NaN,
      "eval_runtime": 559.606,
      "eval_samples_per_second": 9.005,
      "eval_steps_per_second": 4.503,
      "step": 9
    },
    {
      "epoch": 0.0008356487768191029,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 3495193466634240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}