checkpoint-100/trainer_state.json

{
  "best_global_step": 100,
  "best_metric": 0.7661521434783936,
  "best_model_checkpoint": "/content/lora_structeval_t_qwen3_4b/checkpoint-100",
  "epoch": 0.5068102629078239,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05068102629078239,
      "grad_norm": 1.0233957254968118e-05,
      "learning_rate": 9e-05,
      "loss": 1.6154,
      "step": 10
    },
    {
      "epoch": 0.10136205258156478,
      "grad_norm": 9.242238775186706e-06,
      "learning_rate": 0.00019,
      "loss": 1.3072,
      "step": 20
    },
    {
      "epoch": 0.15204307887234716,
      "grad_norm": 9.054802831087727e-06,
      "learning_rate": 0.00019874107050115954,
      "loss": 1.0862,
      "step": 30
    },
    {
      "epoch": 0.20272410516312955,
      "grad_norm": 1.0910169294220395e-05,
      "learning_rate": 0.00019442989534495557,
      "loss": 1.1074,
      "step": 40
    },
    {
      "epoch": 0.25340513145391197,
      "grad_norm": 1.1410435035941191e-05,
      "learning_rate": 0.00018718484526025387,
      "loss": 0.9959,
      "step": 50
    },
    {
      "epoch": 0.25340513145391197,
      "eval_loss": 0.8977804780006409,
      "eval_runtime": 78.7683,
      "eval_samples_per_second": 4.215,
      "eval_steps_per_second": 4.215,
      "step": 50
    },
    {
      "epoch": 0.30408615774469433,
      "grad_norm": 9.305776984547265e-06,
      "learning_rate": 0.0001772310192024389,
      "loss": 0.984,
      "step": 60
    },
    {
      "epoch": 0.35476718403547675,
      "grad_norm": 8.993285518954508e-06,
      "learning_rate": 0.00016487767602017263,
      "loss": 0.9051,
      "step": 70
    },
    {
      "epoch": 0.4054482103262591,
      "grad_norm": 8.788006198301446e-06,
      "learning_rate": 0.00015050862598575476,
      "loss": 0.8835,
      "step": 80
    },
    {
      "epoch": 0.4561292366170415,
      "grad_norm": 8.296872692881152e-06,
      "learning_rate": 0.00013457030606163562,
      "loss": 0.8761,
      "step": 90
    },
    {
      "epoch": 0.5068102629078239,
      "grad_norm": 1.0136979653907474e-05,
      "learning_rate": 0.00011755790939673209,
      "loss": 0.8776,
      "step": 100
    },
    {
      "epoch": 0.5068102629078239,
      "eval_loss": 0.7661521434783936,
      "eval_runtime": 77.5825,
      "eval_samples_per_second": 4.279,
      "eval_steps_per_second": 4.279,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 198,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.262149506475827e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}