{
  "best_metric": 0.16783047,
  "best_model_checkpoint": "/home/patrickbarker/output/qwen2-vl-7b-instruct/v5-20241227-205641/checkpoint-75",
  "epoch": 5.0,
  "eval_steps": 200,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "acc": 0.79618824,
      "epoch": 0.06666666666666667,
      "grad_norm": 60.2325912978456,
      "learning_rate": 0.0,
      "loss": 1.4069984,
      "memory(GiB)": 54.58,
      "step": 1,
      "train_speed(iter/s)": 0.02356
    },
    {
      "acc": 0.82087338,
      "epoch": 0.3333333333333333,
      "grad_norm": 24.5612524344975,
      "learning_rate": 9.995106621986608e-06,
      "loss": 1.17183995,
      "memory(GiB)": 73.76,
      "step": 5,
      "train_speed(iter/s)": 0.030848
    },
    {
      "acc": 0.83782043,
      "epoch": 0.6666666666666666,
      "grad_norm": 20.128635487004736,
      "learning_rate": 9.82484209015679e-06,
      "loss": 0.9988678,
      "memory(GiB)": 73.76,
      "step": 10,
      "train_speed(iter/s)": 0.032078
    },
    {
      "acc": 0.86735916,
      "epoch": 1.0,
      "grad_norm": 8.494494640812043,
      "learning_rate": 9.419403729161433e-06,
      "loss": 0.72015114,
      "memory(GiB)": 73.76,
      "step": 15,
      "train_speed(iter/s)": 0.032504
    },
    {
      "acc": 0.89613667,
      "epoch": 1.3333333333333333,
      "grad_norm": 4.0574812705218255,
      "learning_rate": 8.798555579374133e-06,
      "loss": 0.58566475,
      "memory(GiB)": 73.76,
      "step": 20,
      "train_speed(iter/s)": 0.032659
    },
    {
      "acc": 0.88684921,
      "epoch": 1.6666666666666665,
      "grad_norm": 6.742631309792843,
      "learning_rate": 7.9925623347132e-06,
      "loss": 0.58472939,
      "memory(GiB)": 73.76,
      "step": 25,
      "train_speed(iter/s)": 0.032798
    },
    {
      "acc": 0.92209816,
      "epoch": 2.0,
      "grad_norm": 5.05572579013588,
      "learning_rate": 7.040714019411203e-06,
      "loss": 0.45826292,
      "memory(GiB)": 73.76,
      "step": 30,
      "train_speed(iter/s)": 0.032892
    },
    {
      "acc": 0.9140625,
      "epoch": 2.3333333333333335,
      "grad_norm": 1.9502052102657774,
      "learning_rate": 5.989410703967095e-06,
      "loss": 0.45564661,
      "memory(GiB)": 73.76,
      "step": 35,
      "train_speed(iter/s)": 0.032925
    },
    {
      "acc": 0.91242561,
      "epoch": 2.6666666666666665,
      "grad_norm": 2.7058645210729177,
      "learning_rate": 4.8899006252776434e-06,
      "loss": 0.45886307,
      "memory(GiB)": 73.76,
      "step": 40,
      "train_speed(iter/s)": 0.032984
    },
    {
      "acc": 0.92076473,
      "epoch": 3.0,
      "grad_norm": 3.446087600085013,
      "learning_rate": 3.7957819715681576e-06,
      "loss": 0.45811167,
      "memory(GiB)": 73.76,
      "step": 45,
      "train_speed(iter/s)": 0.033025
    },
    {
      "acc": 0.92433033,
      "epoch": 3.3333333333333335,
      "grad_norm": 2.5558432936438447,
      "learning_rate": 2.760390113454102e-06,
      "loss": 0.39850535,
      "memory(GiB)": 73.76,
      "step": 50,
      "train_speed(iter/s)": 0.033034
    },
    {
      "acc": 0.93854742,
      "epoch": 3.6666666666666665,
      "grad_norm": 3.6644266665911105,
      "learning_rate": 1.8341976466612901e-06,
      "loss": 0.33202767,
      "memory(GiB)": 73.76,
      "step": 55,
      "train_speed(iter/s)": 0.033064
    },
    {
      "acc": 0.91703873,
      "epoch": 4.0,
      "grad_norm": 3.2494285333084614,
      "learning_rate": 1.0623539873980678e-06,
      "loss": 0.43731127,
      "memory(GiB)": 73.76,
      "step": 60,
      "train_speed(iter/s)": 0.033091
    },
    {
      "acc": 0.92857151,
      "epoch": 4.333333333333333,
      "grad_norm": 2.1823786608490225,
      "learning_rate": 4.824844585528e-07,
      "loss": 0.35523658,
      "memory(GiB)": 73.76,
      "step": 65,
      "train_speed(iter/s)": 0.033095
    },
    {
      "acc": 0.93809528,
      "epoch": 4.666666666666667,
      "grad_norm": 2.2497604778446716,
      "learning_rate": 1.2285615540324237e-07,
      "loss": 0.34353948,
      "memory(GiB)": 73.76,
      "step": 70,
      "train_speed(iter/s)": 0.033115
    },
    {
      "acc": 0.93839283,
      "epoch": 5.0,
      "grad_norm": 2.1104371354292435,
      "learning_rate": 1e-09,
      "loss": 0.31291947,
      "memory(GiB)": 73.76,
      "step": 75,
      "train_speed(iter/s)": 0.033132
    },
    {
      "epoch": 5.0,
      "eval_acc": 0.9376854599406528,
      "eval_loss": 0.1678304672241211,
      "eval_runtime": 9.9956,
      "eval_samples_per_second": 1.201,
      "eval_steps_per_second": 0.2,
      "step": 75
    }
  ],
  "logging_steps": 5,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 181464165515264.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}