laptop-tinyllama/checkpoint-100/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.032,
      "grad_norm": 716410.0625,
      "learning_rate": 4.9493333333333336e-05,
      "loss": 2.1967,
      "step": 20
    },
    {
      "epoch": 0.064,
      "grad_norm": 49844.6171875,
      "learning_rate": 4.896e-05,
      "loss": 0.5682,
      "step": 40
    },
    {
      "epoch": 0.096,
      "grad_norm": 14418.5693359375,
      "learning_rate": 4.842666666666667e-05,
      "loss": 0.2278,
      "step": 60
    },
    {
      "epoch": 0.128,
      "grad_norm": 15060.6279296875,
      "learning_rate": 4.789333333333334e-05,
      "loss": 0.1681,
      "step": 80
    },
    {
      "epoch": 0.16,
      "grad_norm": 12125.150390625,
      "learning_rate": 4.736000000000001e-05,
      "loss": 0.1061,
      "step": 100
    }
  ],
  "logging_steps": 20,
  "max_steps": 1875,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2545185875558400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}