checkpoint-200/trainer_state.json

{
  "best_global_step": 200,
  "best_metric": 0.5700864791870117,
  "best_model_checkpoint": "Llama-3.2-1B-it-Medical-LoRA/checkpoint-200",
  "epoch": 0.45300113250283125,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11325028312570781,
      "grad_norm": 0.6456167697906494,
      "learning_rate": 0.00019075425790754258,
      "loss": 0.643,
      "step": 50
    },
    {
      "epoch": 0.22650056625141562,
      "grad_norm": 1.0792498588562012,
      "learning_rate": 0.0001664233576642336,
      "loss": 0.6465,
      "step": 100
    },
    {
      "epoch": 0.22650056625141562,
      "eval_loss": 0.5826964378356934,
      "eval_runtime": 394.3597,
      "eval_samples_per_second": 3.979,
      "eval_steps_per_second": 0.5,
      "step": 100
    },
    {
      "epoch": 0.33975084937712347,
      "grad_norm": 0.5628879070281982,
      "learning_rate": 0.0001420924574209246,
      "loss": 0.5815,
      "step": 150
    },
    {
      "epoch": 0.45300113250283125,
      "grad_norm": 0.5532649755477905,
      "learning_rate": 0.00011776155717761557,
      "loss": 0.5435,
      "step": 200
    },
    {
      "epoch": 0.45300113250283125,
      "eval_loss": 0.5700864791870117,
      "eval_runtime": 394.4221,
      "eval_samples_per_second": 3.978,
      "eval_steps_per_second": 0.499,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 441,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.251873408627507e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}