trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9911504424778761,
  "eval_steps": 500,
  "global_step": 56,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 8.499995871638447,
      "learning_rate": 9.842915805643156e-07,
      "loss": 1.1912,
      "step": 10
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 5.116697393253428,
      "learning_rate": 8.187119948743449e-07,
      "loss": 0.9246,
      "step": 20
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 3.644477495387357,
      "learning_rate": 5.313952597646567e-07,
      "loss": 0.7937,
      "step": 30
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 2.957805249618061,
      "learning_rate": 2.3208660251050156e-07,
      "loss": 0.8105,
      "step": 40
    },
    {
      "epoch": 0.8849557522123894,
      "grad_norm": 3.861269832154213,
      "learning_rate": 3.5111757055874326e-08,
      "loss": 0.7645,
      "step": 50
    },
    {
      "epoch": 0.9911504424778761,
      "step": 56,
      "total_flos": 918655795200.0,
      "train_loss": 0.8788500343050275,
      "train_runtime": 257.2493,
      "train_samples_per_second": 3.499,
      "train_steps_per_second": 0.218
    }
  ],
  "logging_steps": 10,
  "max_steps": 56,
  "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": 918655795200.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}