{
  "best_metric": 0.25979954936421096,
  "best_model_checkpoint": "./logo-matching-base/checkpoint-510",
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 680,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 72.06623077392578,
      "learning_rate": 9.5e-06,
      "loss": 0.6833,
      "step": 34
    },
    {
      "epoch": 1.0,
      "eval_adjusted_mutual_info_score": 0.0959962302587181,
      "eval_adjusted_rand_score": 0.06912863690017566,
      "eval_completeness_score": 0.5109803955924982,
      "eval_fowlkes_mallows_score": 0.44395093511191686,
      "eval_homogeneity_score": 0.12370192092796624,
      "eval_loss": 0.06912863690017566,
      "eval_pair_confusion_matrix": [
        [
          16212,
          31438
        ],
        [
          2986,
          10620
        ]
      ],
      "step": 34
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0,
      "learning_rate": 9e-06,
      "loss": 0.5711,
      "step": 68
    },
    {
      "epoch": 2.0,
      "eval_adjusted_mutual_info_score": 0.16050612062870448,
      "eval_adjusted_rand_score": 0.04788887456487486,
      "eval_completeness_score": 0.4801879169228485,
      "eval_fowlkes_mallows_score": 0.326241320471177,
      "eval_homogeneity_score": 0.24777791806632807,
      "eval_loss": 0.04788887456487486,
      "eval_pair_confusion_matrix": [
        [
          30178,
          17472
        ],
        [
          7800,
          5806
        ]
      ],
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.0,
      "learning_rate": 8.5e-06,
      "loss": 0.5048,
      "step": 102
    },
    {
      "epoch": 3.0,
      "eval_adjusted_mutual_info_score": 0.14453579947468986,
      "eval_adjusted_rand_score": 0.06941336059571244,
      "eval_completeness_score": 0.48534870125531976,
      "eval_fowlkes_mallows_score": 0.35623205660821267,
      "eval_homogeneity_score": 0.20687927372388243,
      "eval_loss": 0.06941336059571244,
      "eval_pair_confusion_matrix": [
        [
          28728,
          18922
        ],
        [
          6962,
          6644
        ]
      ],
      "step": 102
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.4474,
      "step": 136
    },
    {
      "epoch": 4.0,
      "eval_adjusted_mutual_info_score": 0.15197952267992879,
      "eval_adjusted_rand_score": 0.06395362023662775,
      "eval_completeness_score": 0.5053597877227305,
      "eval_fowlkes_mallows_score": 0.36009183925771726,
      "eval_homogeneity_score": 0.201135083549786,
      "eval_loss": 0.06395362023662775,
      "eval_pair_confusion_matrix": [
        [
          27632,
          20018
        ],
        [
          6716,
          6890
        ]
      ],
      "step": 136
    },
    {
      "epoch": 5.0,
      "grad_norm": 53.12451934814453,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.4433,
      "step": 170
    },
    {
      "epoch": 5.0,
      "eval_adjusted_mutual_info_score": 0.09225927782155577,
      "eval_adjusted_rand_score": 0.04497696614477031,
      "eval_completeness_score": 0.4856685890606832,
      "eval_fowlkes_mallows_score": 0.41794001145778076,
      "eval_homogeneity_score": 0.12954647762487131,
      "eval_loss": 0.04497696614477031,
      "eval_pair_confusion_matrix": [
        [
          16938,
          30712
        ],
        [
          3792,
          9814
        ]
      ],
      "step": 170
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0,
      "learning_rate": 7e-06,
      "loss": 0.4582,
      "step": 204
    },
    {
      "epoch": 6.0,
      "eval_adjusted_mutual_info_score": 0.1550123095541971,
      "eval_adjusted_rand_score": 0.1235971988422464,
      "eval_completeness_score": 0.7625668447266793,
      "eval_fowlkes_mallows_score": 0.5091255095660694,
      "eval_homogeneity_score": 0.13490749128374505,
      "eval_loss": 0.1235971988422464,
      "eval_pair_confusion_matrix": [
        [
          13668,
          33982
        ],
        [
          754,
          12852
        ]
      ],
      "step": 204
    },
    {
      "epoch": 7.0,
      "grad_norm": 24.434818267822266,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.4384,
      "step": 238
    },
    {
      "epoch": 7.0,
      "eval_adjusted_mutual_info_score": 0.17177361413411174,
      "eval_adjusted_rand_score": 0.08374811610033726,
      "eval_completeness_score": 0.5222737901409524,
      "eval_fowlkes_mallows_score": 0.3647858508374196,
      "eval_homogeneity_score": 0.2242118568770657,
      "eval_loss": 0.08374811610033726,
      "eval_pair_confusion_matrix": [
        [
          29196,
          18454
        ],
        [
          6850,
          6756
        ]
      ],
      "step": 238
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0,
      "learning_rate": 6e-06,
      "loss": 0.4388,
      "step": 272
    },
    {
      "epoch": 8.0,
      "eval_adjusted_mutual_info_score": 0.20449439835224686,
      "eval_adjusted_rand_score": 0.20212814342460073,
      "eval_completeness_score": 0.5850787856442333,
      "eval_fowlkes_mallows_score": 0.4533371718722817,
      "eval_homogeneity_score": 0.22520931487447624,
      "eval_loss": 0.20212814342460073,
      "eval_pair_confusion_matrix": [
        [
          30796,
          16854
        ],
        [
          5202,
          8404
        ]
      ],
      "step": 272
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.0,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.4136,
      "step": 306
    },
    {
      "epoch": 9.0,
      "eval_adjusted_mutual_info_score": 0.11177382718405922,
      "eval_adjusted_rand_score": 0.09640002189335507,
      "eval_completeness_score": 0.6506809526372479,
      "eval_fowlkes_mallows_score": 0.4899932693994939,
      "eval_homogeneity_score": 0.10817341204672741,
      "eval_loss": 0.09640002189335507,
      "eval_pair_confusion_matrix": [
        [
          12770,
          34880
        ],
        [
          1174,
          12432
        ]
      ],
      "step": 306
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.0,
      "learning_rate": 5e-06,
      "loss": 0.4148,
      "step": 340
    },
    {
      "epoch": 10.0,
      "eval_adjusted_mutual_info_score": 0.13291287868141516,
      "eval_adjusted_rand_score": 0.0173768729388201,
      "eval_completeness_score": 0.46335582053405955,
      "eval_fowlkes_mallows_score": 0.3147845140860169,
      "eval_homogeneity_score": 0.20737389396161876,
      "eval_loss": 0.0173768729388201,
      "eval_pair_confusion_matrix": [
        [
          28346,
          19304
        ],
        [
          7786,
          5820
        ]
      ],
      "step": 340
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.0,
      "learning_rate": 4.5e-06,
      "loss": 0.4146,
      "step": 374
    },
    {
      "epoch": 11.0,
      "eval_adjusted_mutual_info_score": 0.15463237739434937,
      "eval_adjusted_rand_score": 0.05775589302463435,
      "eval_completeness_score": 0.5013447616164763,
      "eval_fowlkes_mallows_score": 0.34999174740596783,
      "eval_homogeneity_score": 0.21319532171325858,
      "eval_loss": 0.05775589302463435,
      "eval_pair_confusion_matrix": [
        [
          28252,
          19398
        ],
        [
          7026,
          6580
        ]
      ],
      "step": 374
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.4096,
      "step": 408
    },
    {
      "epoch": 12.0,
      "eval_adjusted_mutual_info_score": 0.15954128854018185,
      "eval_adjusted_rand_score": 0.08353262118433151,
      "eval_completeness_score": 0.48657807669089076,
      "eval_fowlkes_mallows_score": 0.3488784926098972,
      "eval_homogeneity_score": 0.23781381627812734,
      "eval_loss": 0.08353262118433151,
      "eval_pair_confusion_matrix": [
        [
          31128,
          16522
        ],
        [
          7482,
          6124
        ]
      ],
      "step": 408
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.0,
      "learning_rate": 3.5e-06,
      "loss": 0.3973,
      "step": 442
    },
    {
      "epoch": 13.0,
      "eval_adjusted_mutual_info_score": 0.19041946370338364,
      "eval_adjusted_rand_score": 0.12553878006056823,
      "eval_completeness_score": 0.5046617692993569,
      "eval_fowlkes_mallows_score": 0.36189400936638344,
      "eval_homogeneity_score": 0.27375639307416655,
      "eval_loss": 0.12553878006056823,
      "eval_pair_confusion_matrix": [
        [
          33812,
          13838
        ],
        [
          7670,
          5936
        ]
      ],
      "step": 442
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.0,
      "learning_rate": 3e-06,
      "loss": 0.4051,
      "step": 476
    },
    {
      "epoch": 14.0,
      "eval_adjusted_mutual_info_score": 0.18691214822396793,
      "eval_adjusted_rand_score": 0.18158266255584393,
      "eval_completeness_score": 0.5245970271191535,
      "eval_fowlkes_mallows_score": 0.41690193788215973,
      "eval_homogeneity_score": 0.24324643119902978,
      "eval_loss": 0.18158266255584393,
      "eval_pair_confusion_matrix": [
        [
          33010,
          14640
        ],
        [
          6422,
          7184
        ]
      ],
      "step": 476
    },
    {
      "epoch": 15.0,
      "grad_norm": 20.364652633666992,
      "learning_rate": 2.5e-06,
      "loss": 0.4062,
      "step": 510
    },
    {
      "epoch": 15.0,
      "eval_adjusted_mutual_info_score": 0.21823634710165685,
      "eval_adjusted_rand_score": 0.25979954936421096,
      "eval_completeness_score": 0.5641057686568595,
      "eval_fowlkes_mallows_score": 0.47949730143044716,
      "eval_homogeneity_score": 0.2648407343665406,
      "eval_loss": 0.25979954936421096,
      "eval_pair_confusion_matrix": [
        [
          33538,
          14112
        ],
        [
          5216,
          8390
        ]
      ],
      "step": 510
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.4025,
      "step": 544
    },
    {
      "epoch": 16.0,
      "eval_adjusted_mutual_info_score": 0.10056939420043334,
      "eval_adjusted_rand_score": 0.0907629141131465,
      "eval_completeness_score": 0.5696556835173626,
      "eval_fowlkes_mallows_score": 0.4759933991482618,
      "eval_homogeneity_score": 0.11380033927304208,
      "eval_loss": 0.0907629141131465,
      "eval_pair_confusion_matrix": [
        [
          14202,
          33448
        ],
        [
          1794,
          11812
        ]
      ],
      "step": 544
    },
    {
      "epoch": 17.0,
      "grad_norm": 0.0,
      "learning_rate": 1.5e-06,
      "loss": 0.4043,
      "step": 578
    },
    {
      "epoch": 17.0,
      "eval_adjusted_mutual_info_score": 0.11845707888523377,
      "eval_adjusted_rand_score": 0.06151994460143414,
      "eval_completeness_score": 0.5431310507543884,
      "eval_fowlkes_mallows_score": 0.4323980307250435,
      "eval_homogeneity_score": 0.14340786222528185,
      "eval_loss": 0.06151994460143414,
      "eval_pair_confusion_matrix": [
        [
          16966,
          30684
        ],
        [
          3408,
          10198
        ]
      ],
      "step": 578
    },
    {
      "epoch": 18.0,
      "grad_norm": 0.0,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.4013,
      "step": 612
    },
    {
      "epoch": 18.0,
      "eval_adjusted_mutual_info_score": 0.20098591140511965,
      "eval_adjusted_rand_score": 0.24115050477114428,
      "eval_completeness_score": 0.5343711342342489,
      "eval_fowlkes_mallows_score": 0.45788735752549203,
      "eval_homogeneity_score": 0.2597787469313228,
      "eval_loss": 0.24115050477114428,
      "eval_pair_confusion_matrix": [
        [
          34176,
          13474
        ],
        [
          5818,
          7788
        ]
      ],
      "step": 612
    },
    {
      "epoch": 19.0,
      "grad_norm": 0.0,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.4006,
      "step": 646
    },
    {
      "epoch": 19.0,
      "eval_adjusted_mutual_info_score": 0.252153502376998,
      "eval_adjusted_rand_score": 0.24023922903374736,
      "eval_completeness_score": 0.5460417717065094,
      "eval_fowlkes_mallows_score": 0.4233209236936553,
      "eval_homogeneity_score": 0.34453853702602516,
      "eval_loss": 0.24023922903374736,
      "eval_pair_confusion_matrix": [
        [
          37986,
          9664
        ],
        [
          7382,
          6224
        ]
      ],
      "step": 646
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.4044,
      "step": 680
    },
    {
      "epoch": 20.0,
      "eval_adjusted_mutual_info_score": 0.08179538296319702,
      "eval_adjusted_rand_score": 0.040227652358330604,
      "eval_completeness_score": 0.48262386100058413,
      "eval_fowlkes_mallows_score": 0.423484876527761,
      "eval_homogeneity_score": 0.11562820805581293,
      "eval_loss": 0.040227652358330604,
      "eval_pair_confusion_matrix": [
        [
          15374,
          32276
        ],
        [
          3428,
          10178
        ]
      ],
      "step": 680
    },
    {
      "epoch": 20.0,
      "step": 680,
      "total_flos": 0.0,
      "train_loss": 0.44298483904670266,
      "train_runtime": 986.129,
      "train_samples_per_second": 21.843,
      "train_steps_per_second": 0.69
    }
  ],
  "logging_steps": 500,
  "max_steps": 680,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}