llama-factory/saves/Qwen2-72B-Instruct/checkpoint-35/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19900497512437812,
  "eval_steps": 35,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 2.917722702026367,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.3615,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 2.65405011177063,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.2182,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 4.0127272605896,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.8944,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 0.8177616000175476,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.512,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 0.3800067901611328,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.3435,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 0.3455258309841156,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.3027,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 0.3401183485984802,
      "learning_rate": 0.0001,
      "loss": 0.3045,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.2556740641593933,
      "eval_runtime": 1374.6693,
      "eval_samples_per_second": 1.819,
      "eval_steps_per_second": 1.819,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.376053838164787e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}