fine_tuned_models/gf-6L-30M-i2048_CellClassifier_cardiomyopathies_220224/trainer_state.json

{
  "best_metric": 0.39658036828041077,
  "best_model_checkpoint": "/n/holyscratch01/xiaoleliu_lab/Users/ctheodoris/models/220224_geneformer_27M_SequenceClassifier_tuning_hCMdCM_L2048_B12_LR1e-05_LScosine_WU500_E1_Oadamw_F2/run-8429a330/checkpoint-7020",
  "epoch": 0.9,
  "global_step": 7020,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 0.00034606438343856935,
      "loss": 0.911,
      "step": 780
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.4531576503366612,
      "eval_loss": 1.4550466537475586,
      "eval_runtime": 66.5164,
      "eval_samples_per_second": 259.004,
      "step": 780
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0006921287668771387,
      "loss": 0.6273,
      "step": 1560
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.5953680055723242,
      "eval_loss": 0.846651554107666,
      "eval_runtime": 66.1267,
      "eval_samples_per_second": 260.53,
      "step": 1560
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0007330550166223805,
      "loss": 0.5592,
      "step": 2340
    },
    {
      "epoch": 0.3,
      "eval_accuracy": 0.5935105641978176,
      "eval_loss": 1.0599186420440674,
      "eval_runtime": 66.2608,
      "eval_samples_per_second": 260.003,
      "step": 2340
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0006283471571048975,
      "loss": 0.3714,
      "step": 3120
    },
    {
      "epoch": 0.4,
      "eval_accuracy": 0.686324587880195,
      "eval_loss": 1.184874415397644,
      "eval_runtime": 66.1411,
      "eval_samples_per_second": 260.473,
      "step": 3120
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005236392975874146,
      "loss": 0.2976,
      "step": 3900
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.7681100534014396,
      "eval_loss": 0.6318939328193665,
      "eval_runtime": 66.3309,
      "eval_samples_per_second": 259.728,
      "step": 3900
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0004189314380699318,
      "loss": 0.2564,
      "step": 4680
    },
    {
      "epoch": 0.6,
      "eval_accuracy": 0.7807058277223126,
      "eval_loss": 0.7283642888069153,
      "eval_runtime": 66.3416,
      "eval_samples_per_second": 259.686,
      "step": 4680
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003142235785524487,
      "loss": 0.2336,
      "step": 5460
    },
    {
      "epoch": 0.7,
      "eval_accuracy": 0.8563965637334572,
      "eval_loss": 0.5184123516082764,
      "eval_runtime": 66.3416,
      "eval_samples_per_second": 259.686,
      "step": 5460
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002095157190349659,
      "loss": 0.1731,
      "step": 6240
    },
    {
      "epoch": 0.8,
      "eval_accuracy": 0.8288832133735778,
      "eval_loss": 0.5823884010314941,
      "eval_runtime": 66.1535,
      "eval_samples_per_second": 260.425,
      "step": 6240
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00010480785951748295,
      "loss": 0.1451,
      "step": 7020
    },
    {
      "epoch": 0.9,
      "eval_accuracy": 0.886812166241003,
      "eval_loss": 0.39658036828041077,
      "eval_runtime": 66.3555,
      "eval_samples_per_second": 259.632,
      "step": 7020
    }
  ],
  "max_steps": 7800,
  "num_train_epochs": 1,
  "total_flos": 0,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 0.0008039341830649843,
    "lr_scheduler_type": "polynomial",
    "num_train_epochs": 1,
    "per_device_train_batch_size": 12,
    "seed": 73.15243080311434,
    "warmup_steps": 1812.6785581609881,
    "weight_decay": 0.2588277764570262
  }
}