{
  "best_global_step": 229,
  "best_metric": 0.22058944404125214,
  "best_model_checkpoint": "./lora_qwen32b_python_abdiff_v1/checkpoint-229",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 229,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.043835616438356165,
      "grad_norm": 0.40441757440567017,
      "learning_rate": 3.913043478260869e-06,
      "loss": 1.0102,
      "step": 10
    },
    {
      "epoch": 0.08767123287671233,
      "grad_norm": 0.533530056476593,
      "learning_rate": 8.260869565217392e-06,
      "loss": 0.9822,
      "step": 20
    },
    {
      "epoch": 0.13150684931506848,
      "grad_norm": 0.4025503993034363,
      "learning_rate": 1.2608695652173912e-05,
      "loss": 0.8889,
      "step": 30
    },
    {
      "epoch": 0.17534246575342466,
      "grad_norm": 0.4503121078014374,
      "learning_rate": 1.6956521739130433e-05,
      "loss": 0.7945,
      "step": 40
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.49986398220062256,
      "learning_rate": 2.1304347826086958e-05,
      "loss": 0.5944,
      "step": 50
    },
    {
      "epoch": 0.26301369863013696,
      "grad_norm": 0.2905503809452057,
      "learning_rate": 2.565217391304348e-05,
      "loss": 0.3898,
      "step": 60
    },
    {
      "epoch": 0.30684931506849317,
      "grad_norm": 0.2511512339115143,
      "learning_rate": 3e-05,
      "loss": 0.3061,
      "step": 70
    },
    {
      "epoch": 0.3506849315068493,
      "grad_norm": 0.1779242306947708,
      "learning_rate": 2.9514563106796115e-05,
      "loss": 0.2615,
      "step": 80
    },
    {
      "epoch": 0.39452054794520547,
      "grad_norm": 0.1652904450893402,
      "learning_rate": 2.9029126213592237e-05,
      "loss": 0.2475,
      "step": 90
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.20759467780590057,
      "learning_rate": 2.854368932038835e-05,
      "loss": 0.2251,
      "step": 100
    },
    {
      "epoch": 0.4821917808219178,
      "grad_norm": 0.1608869731426239,
      "learning_rate": 2.8058252427184466e-05,
      "loss": 0.2169,
      "step": 110
    },
    {
      "epoch": 0.5260273972602739,
      "grad_norm": 0.26152652502059937,
      "learning_rate": 2.757281553398058e-05,
      "loss": 0.2109,
      "step": 120
    },
    {
      "epoch": 0.5698630136986301,
      "grad_norm": 0.18110939860343933,
      "learning_rate": 2.7087378640776702e-05,
      "loss": 0.2007,
      "step": 130
    },
    {
      "epoch": 0.6136986301369863,
      "grad_norm": 0.16133858263492584,
      "learning_rate": 2.6601941747572816e-05,
      "loss": 0.1955,
      "step": 140
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.19972704350948334,
      "learning_rate": 2.611650485436893e-05,
      "loss": 0.187,
      "step": 150
    },
    {
      "epoch": 0.7013698630136986,
      "grad_norm": 0.16258665919303894,
      "learning_rate": 2.563106796116505e-05,
      "loss": 0.1772,
      "step": 160
    },
    {
      "epoch": 0.7452054794520548,
      "grad_norm": 0.16635586321353912,
      "learning_rate": 2.5145631067961167e-05,
      "loss": 0.1758,
      "step": 170
    },
    {
      "epoch": 0.7890410958904109,
      "grad_norm": 0.19430042803287506,
      "learning_rate": 2.466019417475728e-05,
      "loss": 0.1567,
      "step": 180
    },
    {
      "epoch": 0.8328767123287671,
      "grad_norm": 0.19939476251602173,
      "learning_rate": 2.41747572815534e-05,
      "loss": 0.1588,
      "step": 190
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.19492687284946442,
      "learning_rate": 2.3689320388349514e-05,
      "loss": 0.1609,
      "step": 200
    },
    {
      "epoch": 0.9205479452054794,
      "grad_norm": 0.21758480370044708,
      "learning_rate": 2.3203883495145632e-05,
      "loss": 0.1458,
      "step": 210
    },
    {
      "epoch": 0.9643835616438357,
      "grad_norm": 0.19706270098686218,
      "learning_rate": 2.2718446601941746e-05,
      "loss": 0.1365,
      "step": 220
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.22058944404125214,
      "eval_runtime": 238.0297,
      "eval_samples_per_second": 5.184,
      "eval_steps_per_second": 2.592,
      "step": 229
    }
  ],
  "logging_steps": 10,
  "max_steps": 687,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1087263591254344e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}