{
  "best_global_step": 50,
  "best_metric": 0.06661392003297806,
  "best_model_checkpoint": "./lifestyle-advisor-qwen-adapters/checkpoint-50",
  "epoch": 0.37037037037037035,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007407407407407408,
      "grad_norm": 0.8554655909538269,
      "learning_rate": 0.0,
      "loss": 2.2753,
      "step": 1
    },
    {
      "epoch": 0.014814814814814815,
      "grad_norm": 0.7770459651947021,
      "learning_rate": 2e-05,
      "loss": 2.2117,
      "step": 2
    },
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 0.8054313063621521,
      "learning_rate": 4e-05,
      "loss": 2.2692,
      "step": 3
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 0.8971659541130066,
      "learning_rate": 6e-05,
      "loss": 2.2754,
      "step": 4
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.7792930006980896,
      "learning_rate": 8e-05,
      "loss": 2.1906,
      "step": 5
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 1.0174905061721802,
      "learning_rate": 0.0001,
      "loss": 2.0765,
      "step": 6
    },
    {
      "epoch": 0.05185185185185185,
      "grad_norm": 0.7820740938186646,
      "learning_rate": 0.00012,
      "loss": 1.9413,
      "step": 7
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 0.7353349328041077,
      "learning_rate": 0.00014,
      "loss": 1.8044,
      "step": 8
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.702397346496582,
      "learning_rate": 0.00016,
      "loss": 1.6369,
      "step": 9
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.6150615215301514,
      "learning_rate": 0.00018,
      "loss": 1.4686,
      "step": 10
    },
    {
      "epoch": 0.08148148148148149,
      "grad_norm": 0.5668545961380005,
      "learning_rate": 0.0002,
      "loss": 1.2712,
      "step": 11
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.6054787635803223,
      "learning_rate": 0.00019777777777777778,
      "loss": 1.1116,
      "step": 12
    },
    {
      "epoch": 0.0962962962962963,
      "grad_norm": 0.6496606469154358,
      "learning_rate": 0.00019555555555555556,
      "loss": 0.941,
      "step": 13
    },
    {
      "epoch": 0.1037037037037037,
      "grad_norm": 0.5952312350273132,
      "learning_rate": 0.00019333333333333333,
      "loss": 0.8313,
      "step": 14
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.539272665977478,
      "learning_rate": 0.00019111111111111114,
      "loss": 0.6799,
      "step": 15
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.6647361516952515,
      "learning_rate": 0.00018888888888888888,
      "loss": 0.5579,
      "step": 16
    },
    {
      "epoch": 0.1259259259259259,
      "grad_norm": 0.4626752734184265,
      "learning_rate": 0.0001866666666666667,
      "loss": 0.4265,
      "step": 17
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.4744594395160675,
      "learning_rate": 0.00018444444444444446,
      "loss": 0.3297,
      "step": 18
    },
    {
      "epoch": 0.14074074074074075,
      "grad_norm": 0.5266918540000916,
      "learning_rate": 0.00018222222222222224,
      "loss": 0.2863,
      "step": 19
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.5599148273468018,
      "learning_rate": 0.00018,
      "loss": 0.227,
      "step": 20
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 0.332426518201828,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.167,
      "step": 21
    },
    {
      "epoch": 0.16296296296296298,
      "grad_norm": 0.3609375059604645,
      "learning_rate": 0.00017555555555555556,
      "loss": 0.1485,
      "step": 22
    },
    {
      "epoch": 0.17037037037037037,
      "grad_norm": 0.29623323678970337,
      "learning_rate": 0.00017333333333333334,
      "loss": 0.1369,
      "step": 23
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.2666948139667511,
      "learning_rate": 0.0001711111111111111,
      "loss": 0.1193,
      "step": 24
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.32019367814064026,
      "learning_rate": 0.00016888888888888889,
      "loss": 0.1249,
      "step": 25
    },
    {
      "epoch": 0.1925925925925926,
      "grad_norm": 0.28152069449424744,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.1102,
      "step": 26
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.28925931453704834,
      "learning_rate": 0.00016444444444444444,
      "loss": 0.0936,
      "step": 27
    },
    {
      "epoch": 0.2074074074074074,
      "grad_norm": 0.21765638887882233,
      "learning_rate": 0.00016222222222222224,
      "loss": 0.1021,
      "step": 28
    },
    {
      "epoch": 0.21481481481481482,
      "grad_norm": 0.22364364564418793,
      "learning_rate": 0.00016,
      "loss": 0.0953,
      "step": 29
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.2058999389410019,
      "learning_rate": 0.0001577777777777778,
      "loss": 0.0952,
      "step": 30
    },
    {
      "epoch": 0.22962962962962963,
      "grad_norm": 0.17060202360153198,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.0866,
      "step": 31
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.17542508244514465,
      "learning_rate": 0.00015333333333333334,
      "loss": 0.0783,
      "step": 32
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 0.23341824114322662,
      "learning_rate": 0.0001511111111111111,
      "loss": 0.1003,
      "step": 33
    },
    {
      "epoch": 0.2518518518518518,
      "grad_norm": 0.17184007167816162,
      "learning_rate": 0.0001488888888888889,
      "loss": 0.0774,
      "step": 34
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.18990236520767212,
      "learning_rate": 0.00014666666666666666,
      "loss": 0.0852,
      "step": 35
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.17710138857364655,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.0798,
      "step": 36
    },
    {
      "epoch": 0.2740740740740741,
      "grad_norm": 0.1709614247083664,
      "learning_rate": 0.00014222222222222224,
      "loss": 0.0787,
      "step": 37
    },
    {
      "epoch": 0.2814814814814815,
      "grad_norm": 0.2045363336801529,
      "learning_rate": 0.00014,
      "loss": 0.0647,
      "step": 38
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 0.17839980125427246,
      "learning_rate": 0.0001377777777777778,
      "loss": 0.0647,
      "step": 39
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.1639847755432129,
      "learning_rate": 0.00013555555555555556,
      "loss": 0.0633,
      "step": 40
    },
    {
      "epoch": 0.3037037037037037,
      "grad_norm": 0.142787903547287,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.0669,
      "step": 41
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 0.1273476481437683,
      "learning_rate": 0.00013111111111111111,
      "loss": 0.0669,
      "step": 42
    },
    {
      "epoch": 0.31851851851851853,
      "grad_norm": 0.12263656407594681,
      "learning_rate": 0.00012888888888888892,
      "loss": 0.0555,
      "step": 43
    },
    {
      "epoch": 0.32592592592592595,
      "grad_norm": 0.1499451845884323,
      "learning_rate": 0.00012666666666666666,
      "loss": 0.0664,
      "step": 44
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.11736824363470078,
      "learning_rate": 0.00012444444444444444,
      "loss": 0.0646,
      "step": 45
    },
    {
      "epoch": 0.34074074074074073,
      "grad_norm": 0.12536290287971497,
      "learning_rate": 0.00012222222222222224,
      "loss": 0.0681,
      "step": 46
    },
    {
      "epoch": 0.34814814814814815,
      "grad_norm": 0.12962676584720612,
      "learning_rate": 0.00012,
      "loss": 0.0746,
      "step": 47
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.07444795221090317,
      "learning_rate": 0.00011777777777777779,
      "loss": 0.0598,
      "step": 48
    },
    {
      "epoch": 0.362962962962963,
      "grad_norm": 0.3645591139793396,
      "learning_rate": 0.00011555555555555555,
      "loss": 0.0771,
      "step": 49
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.08011030405759811,
      "learning_rate": 0.00011333333333333334,
      "loss": 0.062,
      "step": 50
    },
    {
      "epoch": 0.37037037037037035,
      "eval_loss": 0.06661392003297806,
      "eval_runtime": 12.7288,
      "eval_samples_per_second": 9.427,
      "eval_steps_per_second": 4.714,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9609617693958144.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}