checkpoints/checkpoint-147/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 147,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.0,
      "eval_loss": 10.322837829589844,
      "eval_normalizer": 95717.0,
      "eval_runtime": 87.7846,
      "eval_samples_per_second": 608.956,
      "eval_steps_per_second": 1.196,
      "step": 49
    },
    {
      "epoch": 1.020460358056266,
      "grad_norm": 46.59355545043945,
      "learning_rate": 2.5e-06,
      "loss": 10.6797,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.0,
      "eval_loss": 9.83644962310791,
      "eval_normalizer": 95497.0,
      "eval_runtime": 86.1922,
      "eval_samples_per_second": 620.207,
      "eval_steps_per_second": 1.218,
      "step": 98
    },
    {
      "epoch": 2.040920716112532,
      "grad_norm": 37.12765121459961,
      "learning_rate": 5e-06,
      "loss": 9.9107,
      "step": 100
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.0,
      "eval_loss": 9.46417236328125,
      "eval_normalizer": 95100.0,
      "eval_runtime": 85.1382,
      "eval_samples_per_second": 627.885,
      "eval_steps_per_second": 1.233,
      "step": 147
    }
  ],
  "logging_steps": 50,
  "max_steps": 480,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.749219620879565e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}