last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.17275747508305647,
  "eval_steps": 10,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013289036544850499,
      "eval_loss": 2.996713399887085,
      "eval_runtime": 1.7935,
      "eval_samples_per_second": 17.842,
      "eval_steps_per_second": 8.921,
      "step": 1
    },
    {
      "epoch": 0.0664451827242525,
      "grad_norm": 3.3227691650390625,
      "learning_rate": 5e-05,
      "loss": 2.7445,
      "step": 5
    },
    {
      "epoch": 0.132890365448505,
      "grad_norm": 2.976918935775757,
      "learning_rate": 0.0001,
      "loss": 2.4895,
      "step": 10
    },
    {
      "epoch": 0.132890365448505,
      "eval_loss": 2.711103916168213,
      "eval_runtime": 1.1402,
      "eval_samples_per_second": 28.066,
      "eval_steps_per_second": 14.033,
      "step": 10
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 99740943384576.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}