trainer_state.json

{
  "best_metric": 0.016960136592388153,
  "best_model_checkpoint": "./drive/MyDrive/Models/LazBF_ft/checkpoint-2441",
  "epoch": 0.999795207864018,
  "eval_steps": 500,
  "global_step": 2441,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2047921359819783,
      "grad_norm": 0.34956222772598267,
      "learning_rate": 0.00015903318312167147,
      "loss": 0.077,
      "step": 500
    },
    {
      "epoch": 0.4095842719639566,
      "grad_norm": 0.20318002998828888,
      "learning_rate": 0.00011806636624334291,
      "loss": 0.0315,
      "step": 1000
    },
    {
      "epoch": 0.6143764079459348,
      "grad_norm": 0.19855135679244995,
      "learning_rate": 7.709954936501435e-05,
      "loss": 0.0255,
      "step": 1500
    },
    {
      "epoch": 0.8191685439279132,
      "grad_norm": 0.213591068983078,
      "learning_rate": 3.613273248668579e-05,
      "loss": 0.0219,
      "step": 2000
    },
    {
      "epoch": 0.999795207864018,
      "eval_accuracy": 0.99414,
      "eval_loss": 0.016960136592388153,
      "eval_runtime": 42.6528,
      "eval_samples_per_second": 1172.256,
      "eval_steps_per_second": 4.595,
      "step": 2441
    }
  ],
  "logging_steps": 500,
  "max_steps": 2441,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.346203400255181e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}