last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.038461538461538464,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0038461538461538464,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0038461538461538464,
      "eval_loss": NaN,
      "eval_runtime": 2.6089,
      "eval_samples_per_second": 42.163,
      "eval_steps_per_second": 21.082,
      "step": 1
    },
    {
      "epoch": 0.007692307692307693,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.011538461538461539,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.011538461538461539,
      "eval_loss": NaN,
      "eval_runtime": 2.134,
      "eval_samples_per_second": 51.547,
      "eval_steps_per_second": 25.774,
      "step": 3
    },
    {
      "epoch": 0.015384615384615385,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.019230769230769232,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.023076923076923078,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.023076923076923078,
      "eval_loss": NaN,
      "eval_runtime": 2.1748,
      "eval_samples_per_second": 50.579,
      "eval_steps_per_second": 25.289,
      "step": 6
    },
    {
      "epoch": 0.026923076923076925,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.03076923076923077,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.03461538461538462,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.03461538461538462,
      "eval_loss": NaN,
      "eval_runtime": 2.1864,
      "eval_samples_per_second": 50.31,
      "eval_steps_per_second": 25.155,
      "step": 9
    },
    {
      "epoch": 0.038461538461538464,
      "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": 89038163804160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}