{
  "best_metric": 1.84548545,
  "best_model_checkpoint": "/public1/home/stu52275901020/swift/model_output/\u9ad8\u795e\u7ecf\u8d28/internvl2-8b/v36-20241204-000354/checkpoint-150",
  "epoch": 1.702127659574468,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "acc": 0.4818837,
      "epoch": 0.011347517730496455,
      "grad_norm": 1.6654787063598633,
      "learning_rate": 7.142857142857143e-06,
      "loss": 2.21617293,
      "memory(GiB)": 21.82,
      "step": 1,
      "train_speed(iter/s)": 0.047704
    },
    {
      "acc": 0.50631422,
      "epoch": 0.05673758865248227,
      "grad_norm": 1.5600533485412598,
      "learning_rate": 3.571428571428572e-05,
      "loss": 2.20940375,
      "memory(GiB)": 23.14,
      "step": 5,
      "train_speed(iter/s)": 0.099488
    },
    {
      "acc": 0.51391821,
      "epoch": 0.11347517730496454,
      "grad_norm": 1.7131439447402954,
      "learning_rate": 7.142857142857143e-05,
      "loss": 2.04298916,
      "memory(GiB)": 23.14,
      "step": 10,
      "train_speed(iter/s)": 0.114765
    },
    {
      "acc": 0.55212674,
      "epoch": 0.1702127659574468,
      "grad_norm": 1.686623215675354,
      "learning_rate": 9.999605221019081e-05,
      "loss": 1.88184052,
      "memory(GiB)": 24.5,
      "step": 15,
      "train_speed(iter/s)": 0.12107
    },
    {
      "acc": 0.53304815,
      "epoch": 0.22695035460992907,
      "grad_norm": 1.0942801237106323,
      "learning_rate": 9.98579450130307e-05,
      "loss": 1.94336758,
      "memory(GiB)": 24.5,
      "step": 20,
      "train_speed(iter/s)": 0.124439
    },
    {
      "acc": 0.56079154,
      "epoch": 0.28368794326241137,
      "grad_norm": 0.9606024622917175,
      "learning_rate": 9.952307128483256e-05,
      "loss": 1.77457695,
      "memory(GiB)": 24.5,
      "step": 25,
      "train_speed(iter/s)": 0.126437
    },
    {
      "acc": 0.55825844,
      "epoch": 0.3404255319148936,
      "grad_norm": 0.922258198261261,
      "learning_rate": 9.899275261921234e-05,
      "loss": 1.84706001,
      "memory(GiB)": 24.5,
      "step": 30,
      "train_speed(iter/s)": 0.127904
    },
    {
      "acc": 0.56207647,
      "epoch": 0.3971631205673759,
      "grad_norm": 1.0378409624099731,
      "learning_rate": 9.82690819416637e-05,
      "loss": 1.753508,
      "memory(GiB)": 24.5,
      "step": 35,
      "train_speed(iter/s)": 0.128886
    },
    {
      "acc": 0.57356367,
      "epoch": 0.45390070921985815,
      "grad_norm": 1.1508853435516357,
      "learning_rate": 9.735491524973722e-05,
      "loss": 1.75303555,
      "memory(GiB)": 24.5,
      "step": 40,
      "train_speed(iter/s)": 0.129863
    },
    {
      "acc": 0.55143838,
      "epoch": 0.5106382978723404,
      "grad_norm": 1.2086931467056274,
      "learning_rate": 9.62538603417229e-05,
      "loss": 1.85968819,
      "memory(GiB)": 25.91,
      "step": 45,
      "train_speed(iter/s)": 0.130489
    },
    {
      "acc": 0.55636163,
      "epoch": 0.5673758865248227,
      "grad_norm": 1.0430564880371094,
      "learning_rate": 9.497026257831855e-05,
      "loss": 1.7241251,
      "memory(GiB)": 25.91,
      "step": 50,
      "train_speed(iter/s)": 0.131006
    },
    {
      "epoch": 0.5673758865248227,
      "eval_acc": 0.5656192236598891,
      "eval_loss": 1.916869044303894,
      "eval_runtime": 2.4464,
      "eval_samples_per_second": 5.723,
      "eval_steps_per_second": 5.723,
      "step": 50
    },
    {
      "acc": 0.54153261,
      "epoch": 0.624113475177305,
      "grad_norm": 1.2167576551437378,
      "learning_rate": 9.35091877334763e-05,
      "loss": 1.82617283,
      "memory(GiB)": 26.3,
      "step": 55,
      "train_speed(iter/s)": 0.129776
    },
    {
      "acc": 0.56068554,
      "epoch": 0.6808510638297872,
      "grad_norm": 1.3103394508361816,
      "learning_rate": 9.18764020021071e-05,
      "loss": 1.67511196,
      "memory(GiB)": 26.3,
      "step": 60,
      "train_speed(iter/s)": 0.130279
    },
    {
      "acc": 0.58310304,
      "epoch": 0.7375886524822695,
      "grad_norm": 1.0143637657165527,
      "learning_rate": 9.007834924354383e-05,
      "loss": 1.67270927,
      "memory(GiB)": 26.3,
      "step": 65,
      "train_speed(iter/s)": 0.130674
    },
    {
      "acc": 0.57467747,
      "epoch": 0.7943262411347518,
      "grad_norm": 1.3850369453430176,
      "learning_rate": 8.81221255505724e-05,
      "loss": 1.70278339,
      "memory(GiB)": 26.3,
      "step": 70,
      "train_speed(iter/s)": 0.131012
    },
    {
      "acc": 0.5916081,
      "epoch": 0.851063829787234,
      "grad_norm": 1.0732088088989258,
      "learning_rate": 8.601545124439535e-05,
      "loss": 1.63483982,
      "memory(GiB)": 26.3,
      "step": 75,
      "train_speed(iter/s)": 0.131314
    },
    {
      "acc": 0.56617246,
      "epoch": 0.9078014184397163,
      "grad_norm": 1.084026575088501,
      "learning_rate": 8.376664040605122e-05,
      "loss": 1.73948345,
      "memory(GiB)": 26.3,
      "step": 80,
      "train_speed(iter/s)": 0.131575
    },
    {
      "acc": 0.54482946,
      "epoch": 0.9645390070921985,
      "grad_norm": 1.0596380233764648,
      "learning_rate": 8.138456806453503e-05,
      "loss": 1.84302387,
      "memory(GiB)": 26.3,
      "step": 85,
      "train_speed(iter/s)": 0.131746
    },
    {
      "acc": 0.60235672,
      "epoch": 1.0212765957446808,
      "grad_norm": 0.9688817858695984,
      "learning_rate": 7.887863517111338e-05,
      "loss": 1.53876371,
      "memory(GiB)": 26.3,
      "step": 90,
      "train_speed(iter/s)": 0.131937
    },
    {
      "acc": 0.61323328,
      "epoch": 1.0780141843971631,
      "grad_norm": 1.1411057710647583,
      "learning_rate": 7.62587314980648e-05,
      "loss": 1.45239391,
      "memory(GiB)": 26.3,
      "step": 95,
      "train_speed(iter/s)": 0.132127
    },
    {
      "acc": 0.59773045,
      "epoch": 1.1347517730496455,
      "grad_norm": 1.1101690530776978,
      "learning_rate": 7.353519660826665e-05,
      "loss": 1.54209366,
      "memory(GiB)": 26.3,
      "step": 100,
      "train_speed(iter/s)": 0.132289
    },
    {
      "epoch": 1.1347517730496455,
      "eval_acc": 0.5360443622920518,
      "eval_loss": 1.8874558210372925,
      "eval_runtime": 2.3721,
      "eval_samples_per_second": 5.902,
      "eval_steps_per_second": 5.902,
      "step": 100
    },
    {
      "acc": 0.61074128,
      "epoch": 1.1914893617021276,
      "grad_norm": 1.1275923252105713,
      "learning_rate": 7.071877904966423e-05,
      "loss": 1.45454111,
      "memory(GiB)": 26.3,
      "step": 105,
      "train_speed(iter/s)": 0.131567
    },
    {
      "acc": 0.60273228,
      "epoch": 1.24822695035461,
      "grad_norm": 1.3083913326263428,
      "learning_rate": 6.782059393566253e-05,
      "loss": 1.48250647,
      "memory(GiB)": 26.3,
      "step": 110,
      "train_speed(iter/s)": 0.13177
    },
    {
      "acc": 0.62370677,
      "epoch": 1.3049645390070923,
      "grad_norm": 1.0839005708694458,
      "learning_rate": 6.485207907885175e-05,
      "loss": 1.46015568,
      "memory(GiB)": 26.3,
      "step": 115,
      "train_speed(iter/s)": 0.131889
    },
    {
      "acc": 0.61979499,
      "epoch": 1.3617021276595744,
      "grad_norm": 1.2509405612945557,
      "learning_rate": 6.182494985118624e-05,
      "loss": 1.45815115,
      "memory(GiB)": 26.3,
      "step": 120,
      "train_speed(iter/s)": 0.132091
    },
    {
      "acc": 0.61155128,
      "epoch": 1.4184397163120568,
      "grad_norm": 1.4081703424453735,
      "learning_rate": 5.875115294876381e-05,
      "loss": 1.44713774,
      "memory(GiB)": 26.3,
      "step": 125,
      "train_speed(iter/s)": 0.132225
    },
    {
      "acc": 0.61849551,
      "epoch": 1.475177304964539,
      "grad_norm": 1.3654893636703491,
      "learning_rate": 5.564281924367408e-05,
      "loss": 1.39691505,
      "memory(GiB)": 26.3,
      "step": 130,
      "train_speed(iter/s)": 0.132372
    },
    {
      "acc": 0.62567844,
      "epoch": 1.5319148936170213,
      "grad_norm": 1.5169520378112793,
      "learning_rate": 5.2512215908988484e-05,
      "loss": 1.41729832,
      "memory(GiB)": 26.3,
      "step": 135,
      "train_speed(iter/s)": 0.132474
    },
    {
      "acc": 0.63134012,
      "epoch": 1.5886524822695036,
      "grad_norm": 1.4038567543029785,
      "learning_rate": 4.9371698005832365e-05,
      "loss": 1.37339115,
      "memory(GiB)": 26.3,
      "step": 140,
      "train_speed(iter/s)": 0.132568
    },
    {
      "acc": 0.61558661,
      "epoch": 1.645390070921986,
      "grad_norm": 1.513599157333374,
      "learning_rate": 4.623365972360337e-05,
      "loss": 1.44473677,
      "memory(GiB)": 26.3,
      "step": 145,
      "train_speed(iter/s)": 0.132637
    },
    {
      "acc": 0.62634563,
      "epoch": 1.702127659574468,
      "grad_norm": 1.3617616891860962,
      "learning_rate": 4.31104854657681e-05,
      "loss": 1.38092842,
      "memory(GiB)": 26.3,
      "step": 150,
      "train_speed(iter/s)": 0.13276
    },
    {
      "epoch": 1.702127659574468,
      "eval_acc": 0.5489833641404805,
      "eval_loss": 1.8454854488372803,
      "eval_runtime": 2.5064,
      "eval_samples_per_second": 5.586,
      "eval_steps_per_second": 5.586,
      "step": 150
    }
  ],
  "logging_steps": 5,
  "max_steps": 264,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}