{
  "best_global_step": 76,
  "best_metric": 1.4253603219985962,
  "best_model_checkpoint": "autodl-tmp/fine-tuned-lora/checkpoint-76",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 76,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.991044282913208,
      "learning_rate": 0.0,
      "loss": 2.1624,
      "step": 1
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 1.0417003631591797,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.1768,
      "step": 2
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.072008490562439,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.2301,
      "step": 3
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.9654397368431091,
      "learning_rate": 6e-06,
      "loss": 2.1145,
      "step": 4
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 1.0050045251846313,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0663,
      "step": 5
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.098430871963501,
      "learning_rate": 1e-05,
      "loss": 2.268,
      "step": 6
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.984906017780304,
      "learning_rate": 1.2e-05,
      "loss": 2.1513,
      "step": 7
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.9754630923271179,
      "learning_rate": 1.4e-05,
      "loss": 2.0979,
      "step": 8
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.9271889328956604,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.0335,
      "step": 9
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.8084726929664612,
      "learning_rate": 1.8e-05,
      "loss": 2.0471,
      "step": 10
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.7331921458244324,
      "learning_rate": 2e-05,
      "loss": 1.9383,
      "step": 11
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.8261972665786743,
      "learning_rate": 1.9764705882352945e-05,
      "loss": 2.1136,
      "step": 12
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.7031018137931824,
      "learning_rate": 1.9529411764705885e-05,
      "loss": 1.9643,
      "step": 13
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.609250009059906,
      "learning_rate": 1.9294117647058825e-05,
      "loss": 1.7862,
      "step": 14
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.682807981967926,
      "learning_rate": 1.9058823529411764e-05,
      "loss": 1.975,
      "step": 15
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.5955848693847656,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 1.8278,
      "step": 16
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.5948333144187927,
      "learning_rate": 1.8588235294117647e-05,
      "loss": 1.8618,
      "step": 17
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.561774492263794,
      "learning_rate": 1.8352941176470587e-05,
      "loss": 1.8627,
      "step": 18
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.504706621170044,
      "learning_rate": 1.811764705882353e-05,
      "loss": 1.7751,
      "step": 19
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.8960705995559692,
      "eval_runtime": 30.4669,
      "eval_samples_per_second": 8.632,
      "eval_steps_per_second": 0.098,
      "step": 19
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.5365819931030273,
      "learning_rate": 1.7882352941176474e-05,
      "loss": 1.9505,
      "step": 20
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 0.46491557359695435,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.6709,
      "step": 21
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 0.4849880337715149,
      "learning_rate": 1.7411764705882353e-05,
      "loss": 1.755,
      "step": 22
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 0.42490944266319275,
      "learning_rate": 1.7176470588235293e-05,
      "loss": 1.6702,
      "step": 23
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 0.4460708498954773,
      "learning_rate": 1.6941176470588237e-05,
      "loss": 1.7768,
      "step": 24
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 0.38298019766807556,
      "learning_rate": 1.670588235294118e-05,
      "loss": 1.6531,
      "step": 25
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": 0.414841890335083,
      "learning_rate": 1.647058823529412e-05,
      "loss": 1.6762,
      "step": 26
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 0.36949920654296875,
      "learning_rate": 1.623529411764706e-05,
      "loss": 1.5959,
      "step": 27
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 0.34017208218574524,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.5484,
      "step": 28
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 0.3720543682575226,
      "learning_rate": 1.5764705882352943e-05,
      "loss": 1.6612,
      "step": 29
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 0.3782600164413452,
      "learning_rate": 1.5529411764705882e-05,
      "loss": 1.5711,
      "step": 30
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 0.3374978303909302,
      "learning_rate": 1.5294117647058822e-05,
      "loss": 1.4678,
      "step": 31
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 0.6604728698730469,
      "learning_rate": 1.5058823529411765e-05,
      "loss": 1.6217,
      "step": 32
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 0.3361934721469879,
      "learning_rate": 1.4823529411764707e-05,
      "loss": 1.4735,
      "step": 33
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": 0.419023334980011,
      "learning_rate": 1.4588235294117647e-05,
      "loss": 1.6204,
      "step": 34
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 0.49251654744148254,
      "learning_rate": 1.435294117647059e-05,
      "loss": 1.8546,
      "step": 35
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 0.4037458598613739,
      "learning_rate": 1.4117647058823532e-05,
      "loss": 1.585,
      "step": 36
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 0.373178094625473,
      "learning_rate": 1.3882352941176471e-05,
      "loss": 1.5054,
      "step": 37
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.43062394857406616,
      "learning_rate": 1.3647058823529413e-05,
      "loss": 1.6575,
      "step": 38
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.624245285987854,
      "eval_runtime": 29.8113,
      "eval_samples_per_second": 8.822,
      "eval_steps_per_second": 0.101,
      "step": 38
    },
    {
      "epoch": 2.0526315789473686,
      "grad_norm": 0.3876766264438629,
      "learning_rate": 1.3411764705882353e-05,
      "loss": 1.5434,
      "step": 39
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.36470478773117065,
      "learning_rate": 1.3176470588235294e-05,
      "loss": 1.5223,
      "step": 40
    },
    {
      "epoch": 2.1578947368421053,
      "grad_norm": 0.4518483579158783,
      "learning_rate": 1.2941176470588238e-05,
      "loss": 1.4864,
      "step": 41
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 0.39963680505752563,
      "learning_rate": 1.2705882352941177e-05,
      "loss": 1.5323,
      "step": 42
    },
    {
      "epoch": 2.263157894736842,
      "grad_norm": 0.34100541472435,
      "learning_rate": 1.2470588235294119e-05,
      "loss": 1.4836,
      "step": 43
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 0.371075302362442,
      "learning_rate": 1.223529411764706e-05,
      "loss": 1.4348,
      "step": 44
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 0.3133174180984497,
      "learning_rate": 1.2e-05,
      "loss": 1.4263,
      "step": 45
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 0.36948636174201965,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.4778,
      "step": 46
    },
    {
      "epoch": 2.473684210526316,
      "grad_norm": 0.3147697150707245,
      "learning_rate": 1.1529411764705882e-05,
      "loss": 1.4395,
      "step": 47
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 0.3104805648326874,
      "learning_rate": 1.1294117647058825e-05,
      "loss": 1.4344,
      "step": 48
    },
    {
      "epoch": 2.5789473684210527,
      "grad_norm": 0.2887001037597656,
      "learning_rate": 1.1058823529411766e-05,
      "loss": 1.456,
      "step": 49
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 0.27948662638664246,
      "learning_rate": 1.0823529411764706e-05,
      "loss": 1.4507,
      "step": 50
    },
    {
      "epoch": 2.6842105263157894,
      "grad_norm": 0.29038968682289124,
      "learning_rate": 1.0588235294117648e-05,
      "loss": 1.4486,
      "step": 51
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 0.28142035007476807,
      "learning_rate": 1.035294117647059e-05,
      "loss": 1.5234,
      "step": 52
    },
    {
      "epoch": 2.7894736842105265,
      "grad_norm": 0.2857128083705902,
      "learning_rate": 1.011764705882353e-05,
      "loss": 1.4186,
      "step": 53
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 0.27921512722969055,
      "learning_rate": 9.882352941176472e-06,
      "loss": 1.4161,
      "step": 54
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 0.2870796024799347,
      "learning_rate": 9.647058823529412e-06,
      "loss": 1.4665,
      "step": 55
    },
    {
      "epoch": 2.9473684210526314,
      "grad_norm": 0.2911064326763153,
      "learning_rate": 9.411764705882354e-06,
      "loss": 1.3341,
      "step": 56
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.29733651876449585,
      "learning_rate": 9.176470588235294e-06,
      "loss": 1.3136,
      "step": 57
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.4926354885101318,
      "eval_runtime": 29.9258,
      "eval_samples_per_second": 8.788,
      "eval_steps_per_second": 0.1,
      "step": 57
    },
    {
      "epoch": 3.0526315789473686,
      "grad_norm": 0.2842563986778259,
      "learning_rate": 8.941176470588237e-06,
      "loss": 1.3403,
      "step": 58
    },
    {
      "epoch": 3.1052631578947367,
      "grad_norm": 0.2729772627353668,
      "learning_rate": 8.705882352941177e-06,
      "loss": 1.4465,
      "step": 59
    },
    {
      "epoch": 3.1578947368421053,
      "grad_norm": 0.27147042751312256,
      "learning_rate": 8.470588235294118e-06,
      "loss": 1.4449,
      "step": 60
    },
    {
      "epoch": 3.2105263157894735,
      "grad_norm": 0.2780725657939911,
      "learning_rate": 8.23529411764706e-06,
      "loss": 1.4588,
      "step": 61
    },
    {
      "epoch": 3.263157894736842,
      "grad_norm": 0.279209703207016,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.344,
      "step": 62
    },
    {
      "epoch": 3.3157894736842106,
      "grad_norm": 0.42355313897132874,
      "learning_rate": 7.764705882352941e-06,
      "loss": 1.4197,
      "step": 63
    },
    {
      "epoch": 3.3684210526315788,
      "grad_norm": 0.27756112813949585,
      "learning_rate": 7.529411764705883e-06,
      "loss": 1.2938,
      "step": 64
    },
    {
      "epoch": 3.4210526315789473,
      "grad_norm": 0.2620949447154999,
      "learning_rate": 7.294117647058823e-06,
      "loss": 1.4932,
      "step": 65
    },
    {
      "epoch": 3.473684210526316,
      "grad_norm": 0.28503599762916565,
      "learning_rate": 7.058823529411766e-06,
      "loss": 1.5613,
      "step": 66
    },
    {
      "epoch": 3.526315789473684,
      "grad_norm": 0.26462414860725403,
      "learning_rate": 6.8235294117647065e-06,
      "loss": 1.3213,
      "step": 67
    },
    {
      "epoch": 3.5789473684210527,
      "grad_norm": 0.26519039273262024,
      "learning_rate": 6.588235294117647e-06,
      "loss": 1.4058,
      "step": 68
    },
    {
      "epoch": 3.6315789473684212,
      "grad_norm": 0.2812947928905487,
      "learning_rate": 6.352941176470589e-06,
      "loss": 1.1533,
      "step": 69
    },
    {
      "epoch": 3.6842105263157894,
      "grad_norm": 0.26864585280418396,
      "learning_rate": 6.11764705882353e-06,
      "loss": 1.2935,
      "step": 70
    },
    {
      "epoch": 3.736842105263158,
      "grad_norm": 0.27379095554351807,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.3692,
      "step": 71
    },
    {
      "epoch": 3.7894736842105265,
      "grad_norm": 0.2734774947166443,
      "learning_rate": 5.6470588235294125e-06,
      "loss": 1.3805,
      "step": 72
    },
    {
      "epoch": 3.8421052631578947,
      "grad_norm": 0.2809073328971863,
      "learning_rate": 5.411764705882353e-06,
      "loss": 1.3503,
      "step": 73
    },
    {
      "epoch": 3.8947368421052633,
      "grad_norm": 0.2657577097415924,
      "learning_rate": 5.176470588235295e-06,
      "loss": 1.1972,
      "step": 74
    },
    {
      "epoch": 3.9473684210526314,
      "grad_norm": 0.26183557510375977,
      "learning_rate": 4.941176470588236e-06,
      "loss": 1.3515,
      "step": 75
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.29608941078186035,
      "learning_rate": 4.705882352941177e-06,
      "loss": 1.1138,
      "step": 76
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.4253603219985962,
      "eval_runtime": 29.788,
      "eval_samples_per_second": 8.829,
      "eval_steps_per_second": 0.101,
      "step": 76
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.1
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.300432166000026e+17,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}