{
  "best_metric": 0.26184663,
  "best_model_checkpoint": "/home/patrickbarker/output/qwen2-vl-7b-instruct/v0-20241218-000939/checkpoint-100",
  "epoch": 5.0,
  "eval_steps": 200,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "acc": 0.78614354,
      "epoch": 0.05,
      "grad_norm": 32.0172921873113,
      "learning_rate": 0.0,
      "loss": 1.30341828,
      "memory(GiB)": 54.56,
      "step": 1,
      "train_speed(iter/s)": 0.023493
    },
    {
      "acc": 0.80234951,
      "epoch": 0.25,
      "grad_norm": 37.62154000246541,
      "learning_rate": 1e-05,
      "loss": 1.23205733,
      "memory(GiB)": 74.75,
      "step": 5,
      "train_speed(iter/s)": 0.030873
    },
    {
      "acc": 0.83633699,
      "epoch": 0.5,
      "grad_norm": 74.22787353731742,
      "learning_rate": 9.93181333636191e-06,
      "loss": 0.93288889,
      "memory(GiB)": 74.75,
      "step": 10,
      "train_speed(iter/s)": 0.032122
    },
    {
      "acc": 0.84369278,
      "epoch": 0.75,
      "grad_norm": 5.440459167288553,
      "learning_rate": 9.729113299882324e-06,
      "loss": 0.84061708,
      "memory(GiB)": 74.75,
      "step": 15,
      "train_speed(iter/s)": 0.032554
    },
    {
      "acc": 0.86311598,
      "epoch": 1.0,
      "grad_norm": 7.873547600114794,
      "learning_rate": 9.397429019156841e-06,
      "loss": 0.72119961,
      "memory(GiB)": 74.75,
      "step": 20,
      "train_speed(iter/s)": 0.032776
    },
    {
      "acc": 0.885886,
      "epoch": 1.25,
      "grad_norm": 5.745656860997658,
      "learning_rate": 8.94580797672727e-06,
      "loss": 0.77134295,
      "memory(GiB)": 74.75,
      "step": 25,
      "train_speed(iter/s)": 0.032863
    },
    {
      "acc": 0.8865592,
      "epoch": 1.5,
      "grad_norm": 16.573461756273073,
      "learning_rate": 8.386569217342893e-06,
      "loss": 0.61206017,
      "memory(GiB)": 74.75,
      "step": 30,
      "train_speed(iter/s)": 0.032959
    },
    {
      "acc": 0.89316502,
      "epoch": 1.75,
      "grad_norm": 5.34427710104793,
      "learning_rate": 7.734967316533076e-06,
      "loss": 0.64310627,
      "memory(GiB)": 74.75,
      "step": 35,
      "train_speed(iter/s)": 0.033027
    },
    {
      "acc": 0.89337797,
      "epoch": 2.0,
      "grad_norm": 3.3194243420102083,
      "learning_rate": 7.008776275552522e-06,
      "loss": 0.58372121,
      "memory(GiB)": 74.75,
      "step": 40,
      "train_speed(iter/s)": 0.03308
    },
    {
      "acc": 0.91168728,
      "epoch": 2.25,
      "grad_norm": 1.99209188413019,
      "learning_rate": 6.2278046929604265e-06,
      "loss": 0.4987381,
      "memory(GiB)": 74.75,
      "step": 45,
      "train_speed(iter/s)": 0.033097
    },
    {
      "acc": 0.90439634,
      "epoch": 2.5,
      "grad_norm": 7.169335908534055,
      "learning_rate": 5.413355437688926e-06,
      "loss": 0.54837952,
      "memory(GiB)": 74.75,
      "step": 50,
      "train_speed(iter/s)": 0.033134
    },
    {
      "acc": 0.90367451,
      "epoch": 2.75,
      "grad_norm": 5.395325589957545,
      "learning_rate": 4.587644562311076e-06,
      "loss": 0.53503237,
      "memory(GiB)": 74.75,
      "step": 55,
      "train_speed(iter/s)": 0.033163
    },
    {
      "acc": 0.92254467,
      "epoch": 3.0,
      "grad_norm": 2.5695200478983646,
      "learning_rate": 3.773195307039575e-06,
      "loss": 0.40150399,
      "memory(GiB)": 74.75,
      "step": 60,
      "train_speed(iter/s)": 0.033186
    },
    {
      "acc": 0.9301857,
      "epoch": 3.25,
      "grad_norm": 3.1556048007324367,
      "learning_rate": 2.9922237244474807e-06,
      "loss": 0.38734879,
      "memory(GiB)": 74.75,
      "step": 65,
      "train_speed(iter/s)": 0.033189
    },
    {
      "acc": 0.91883011,
      "epoch": 3.5,
      "grad_norm": 17.287645910961686,
      "learning_rate": 2.266032683466928e-06,
      "loss": 0.44510117,
      "memory(GiB)": 74.75,
      "step": 70,
      "train_speed(iter/s)": 0.033209
    },
    {
      "acc": 0.93858633,
      "epoch": 3.75,
      "grad_norm": 5.109693472015538,
      "learning_rate": 1.6144307826571085e-06,
      "loss": 0.36709385,
      "memory(GiB)": 74.75,
      "step": 75,
      "train_speed(iter/s)": 0.033226
    },
    {
      "acc": 0.94115381,
      "epoch": 4.0,
      "grad_norm": 3.535417356581457,
      "learning_rate": 1.0551920232727309e-06,
      "loss": 0.34772708,
      "memory(GiB)": 74.75,
      "step": 80,
      "train_speed(iter/s)": 0.03324
    },
    {
      "acc": 0.94864588,
      "epoch": 4.25,
      "grad_norm": 2.6450151758477927,
      "learning_rate": 6.035709808431585e-07,
      "loss": 0.30039248,
      "memory(GiB)": 74.75,
      "step": 85,
      "train_speed(iter/s)": 0.033238
    },
    {
      "acc": 0.95026588,
      "epoch": 4.5,
      "grad_norm": 2.3681008746117964,
      "learning_rate": 2.7188670011767715e-07,
      "loss": 0.28691387,
      "memory(GiB)": 74.75,
      "step": 90,
      "train_speed(iter/s)": 0.033251
    },
    {
      "acc": 0.94560108,
      "epoch": 4.75,
      "grad_norm": 4.066631026473562,
      "learning_rate": 6.918666363808976e-08,
      "loss": 0.29291582,
      "memory(GiB)": 74.75,
      "step": 95,
      "train_speed(iter/s)": 0.033261
    },
    {
      "acc": 0.95544872,
      "epoch": 5.0,
      "grad_norm": 3.609028127209203,
      "learning_rate": 1e-09,
      "loss": 0.26392193,
      "memory(GiB)": 74.75,
      "step": 100,
      "train_speed(iter/s)": 0.033271
    },
    {
      "epoch": 5.0,
      "eval_acc": 0.8952164009111617,
      "eval_loss": 0.2618466317653656,
      "eval_runtime": 23.5294,
      "eval_samples_per_second": 1.488,
      "eval_steps_per_second": 0.213,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 100,
  "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": 240537459228672.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}