{
  "best_metric": 0.43766666666666665,
  "best_model_checkpoint": "clip-vit-large-patch14-finetuned-clip-vit-large-patch14-mnist_linear_probe/checkpoint-315",
  "epoch": 2.985781990521327,
  "eval_steps": 500,
  "global_step": 315,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0947867298578199,
      "grad_norm": 2.288234233856201,
      "learning_rate": 1.5625e-05,
      "loss": 2.4094,
      "step": 10
    },
    {
      "epoch": 0.1895734597156398,
      "grad_norm": 2.1556286811828613,
      "learning_rate": 3.125e-05,
      "loss": 2.3858,
      "step": 20
    },
    {
      "epoch": 0.2843601895734597,
      "grad_norm": 2.1012516021728516,
      "learning_rate": 4.6875e-05,
      "loss": 2.3743,
      "step": 30
    },
    {
      "epoch": 0.3791469194312796,
      "grad_norm": 1.212685227394104,
      "learning_rate": 4.858657243816255e-05,
      "loss": 2.3353,
      "step": 40
    },
    {
      "epoch": 0.47393364928909953,
      "grad_norm": 1.0641510486602783,
      "learning_rate": 4.6819787985865726e-05,
      "loss": 2.3048,
      "step": 50
    },
    {
      "epoch": 0.5687203791469194,
      "grad_norm": 0.9478774070739746,
      "learning_rate": 4.50530035335689e-05,
      "loss": 2.2905,
      "step": 60
    },
    {
      "epoch": 0.6635071090047393,
      "grad_norm": 0.7033135294914246,
      "learning_rate": 4.328621908127209e-05,
      "loss": 2.2732,
      "step": 70
    },
    {
      "epoch": 0.7582938388625592,
      "grad_norm": 0.8783323168754578,
      "learning_rate": 4.1519434628975266e-05,
      "loss": 2.2636,
      "step": 80
    },
    {
      "epoch": 0.8530805687203792,
      "grad_norm": 0.9178075790405273,
      "learning_rate": 3.975265017667845e-05,
      "loss": 2.2455,
      "step": 90
    },
    {
      "epoch": 0.9478672985781991,
      "grad_norm": 0.6878641843795776,
      "learning_rate": 3.7985865724381624e-05,
      "loss": 2.2376,
      "step": 100
    },
    {
      "epoch": 0.995260663507109,
      "eval_accuracy": 0.2981666666666667,
      "eval_loss": 2.2017133235931396,
      "eval_runtime": 24.7638,
      "eval_samples_per_second": 242.289,
      "eval_steps_per_second": 1.898,
      "step": 105
    },
    {
      "epoch": 1.042654028436019,
      "grad_norm": 0.9457613229751587,
      "learning_rate": 3.621908127208481e-05,
      "loss": 2.2256,
      "step": 110
    },
    {
      "epoch": 1.1374407582938388,
      "grad_norm": 0.850648820400238,
      "learning_rate": 3.445229681978799e-05,
      "loss": 2.2144,
      "step": 120
    },
    {
      "epoch": 1.2322274881516588,
      "grad_norm": 0.8362263441085815,
      "learning_rate": 3.2685512367491163e-05,
      "loss": 2.2111,
      "step": 130
    },
    {
      "epoch": 1.3270142180094786,
      "grad_norm": 0.6047300100326538,
      "learning_rate": 3.0918727915194346e-05,
      "loss": 2.2002,
      "step": 140
    },
    {
      "epoch": 1.4218009478672986,
      "grad_norm": 0.9275925755500793,
      "learning_rate": 2.915194346289753e-05,
      "loss": 2.1941,
      "step": 150
    },
    {
      "epoch": 1.5165876777251186,
      "grad_norm": 0.8383633494377136,
      "learning_rate": 2.738515901060071e-05,
      "loss": 2.1916,
      "step": 160
    },
    {
      "epoch": 1.6113744075829384,
      "grad_norm": 0.7653341293334961,
      "learning_rate": 2.5618374558303885e-05,
      "loss": 2.1859,
      "step": 170
    },
    {
      "epoch": 1.7061611374407581,
      "grad_norm": 0.775774359703064,
      "learning_rate": 2.3851590106007068e-05,
      "loss": 2.1796,
      "step": 180
    },
    {
      "epoch": 1.8009478672985781,
      "grad_norm": 0.932090699672699,
      "learning_rate": 2.2084805653710246e-05,
      "loss": 2.1708,
      "step": 190
    },
    {
      "epoch": 1.8957345971563981,
      "grad_norm": 0.9772677421569824,
      "learning_rate": 2.031802120141343e-05,
      "loss": 2.1684,
      "step": 200
    },
    {
      "epoch": 1.9905213270142181,
      "grad_norm": 0.7905783653259277,
      "learning_rate": 1.855123674911661e-05,
      "loss": 2.1641,
      "step": 210
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4041666666666667,
      "eval_loss": 2.1207876205444336,
      "eval_runtime": 24.705,
      "eval_samples_per_second": 242.866,
      "eval_steps_per_second": 1.902,
      "step": 211
    },
    {
      "epoch": 2.085308056872038,
      "grad_norm": 1.0608142614364624,
      "learning_rate": 1.678445229681979e-05,
      "loss": 2.1633,
      "step": 220
    },
    {
      "epoch": 2.1800947867298577,
      "grad_norm": 1.0211544036865234,
      "learning_rate": 1.501766784452297e-05,
      "loss": 2.1518,
      "step": 230
    },
    {
      "epoch": 2.2748815165876777,
      "grad_norm": 0.9483183026313782,
      "learning_rate": 1.3250883392226149e-05,
      "loss": 2.1507,
      "step": 240
    },
    {
      "epoch": 2.3696682464454977,
      "grad_norm": 0.6434796452522278,
      "learning_rate": 1.148409893992933e-05,
      "loss": 2.1477,
      "step": 250
    },
    {
      "epoch": 2.4644549763033177,
      "grad_norm": 0.7338018417358398,
      "learning_rate": 9.717314487632508e-06,
      "loss": 2.1439,
      "step": 260
    },
    {
      "epoch": 2.5592417061611377,
      "grad_norm": 0.8191038966178894,
      "learning_rate": 7.950530035335689e-06,
      "loss": 2.1466,
      "step": 270
    },
    {
      "epoch": 2.654028436018957,
      "grad_norm": 0.8383843898773193,
      "learning_rate": 6.18374558303887e-06,
      "loss": 2.1435,
      "step": 280
    },
    {
      "epoch": 2.748815165876777,
      "grad_norm": 0.7335329055786133,
      "learning_rate": 4.41696113074205e-06,
      "loss": 2.1399,
      "step": 290
    },
    {
      "epoch": 2.843601895734597,
      "grad_norm": 0.9002769589424133,
      "learning_rate": 2.65017667844523e-06,
      "loss": 2.142,
      "step": 300
    },
    {
      "epoch": 2.938388625592417,
      "grad_norm": 0.8580403327941895,
      "learning_rate": 8.8339222614841e-07,
      "loss": 2.1453,
      "step": 310
    },
    {
      "epoch": 2.985781990521327,
      "eval_accuracy": 0.43766666666666665,
      "eval_loss": 2.0961079597473145,
      "eval_runtime": 24.9225,
      "eval_samples_per_second": 240.747,
      "eval_steps_per_second": 1.886,
      "step": 315
    },
    {
      "epoch": 2.985781990521327,
      "step": 315,
      "total_flos": 4.411646023570175e+19,
      "train_loss": 2.214817982628232,
      "train_runtime": 948.9642,
      "train_samples_per_second": 170.712,
      "train_steps_per_second": 0.332
    }
  ],
  "logging_steps": 10,
  "max_steps": 315,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 4.411646023570175e+19,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}