ThyroidTumorClassification

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 30.0,
-    "eval_f1": 0.8837209302325582,
-    "eval_loss": 0.5682619214057922,
-    "eval_runtime": 0.6789,
-    "eval_samples_per_second": 139.94,
-    "eval_steps_per_second": 4.419,
-    "total_flos": 2.8570124903878656e+17,
-    "train_loss": 0.5013438595665826,
-    "train_runtime": 222.831,
-    "train_samples_per_second": 51.025,
-    "train_steps_per_second": 0.404
+    "eval_f1": 0.8780487804878049,
+    "eval_loss": 0.5805598497390747,
+    "eval_runtime": 0.5669,
+    "eval_samples_per_second": 176.397,
+    "eval_steps_per_second": 7.056,
+    "total_flos": 2.7816295750742016e+17,
+    "train_loss": 0.517905675040351,
+    "train_runtime": 173.4592,
+    "train_samples_per_second": 63.819,
+    "train_steps_per_second": 0.519
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 30.0,
-    "eval_f1": 0.8837209302325582,
-    "eval_loss": 0.5682619214057922,
-    "eval_runtime": 0.6789,
-    "eval_samples_per_second": 139.94,
-    "eval_steps_per_second": 4.419
+    "eval_f1": 0.8780487804878049,
+    "eval_loss": 0.5805598497390747,
+    "eval_runtime": 0.5669,
+    "eval_samples_per_second": 176.397,
+    "eval_steps_per_second": 7.056
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f5768f543feec39b661a0d3347394478b69fe2fb6010928ea157000d3c03bb2
+oid sha256:e79878a64b056dd7f9a915a586397ecc0f0542a41c021a2a5ed9710093168831
 size 111347349

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 30.0,
-    "total_flos": 2.8570124903878656e+17,
-    "train_loss": 0.5013438595665826,
-    "train_runtime": 222.831,
-    "train_samples_per_second": 51.025,
-    "train_steps_per_second": 0.404
+    "total_flos": 2.7816295750742016e+17,
+    "train_loss": 0.517905675040351,
+    "train_runtime": 173.4592,
+    "train_samples_per_second": 63.819,
+    "train_steps_per_second": 0.519
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.8837209302325582,
-  "best_model_checkpoint": "Cvt-finetuned-thyroid/checkpoint-27",
+  "best_metric": 0.8780487804878049,
+  "best_model_checkpoint": "Cvt-finetuned-thyroid/checkpoint-33",
   "epoch": 30.0,
   "global_step": 90,
   "is_hyper_param_search": false,
@@ -9,305 +9,305 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_f1": 0.5052631578947367,
-      "eval_loss": 0.687919557094574,
-      "eval_runtime": 0.6589,
-      "eval_samples_per_second": 144.182,
-      "eval_steps_per_second": 4.553,
+      "eval_f1": 0.19148936170212766,
+      "eval_loss": 0.7407425045967102,
+      "eval_runtime": 0.5779,
+      "eval_samples_per_second": 173.027,
+      "eval_steps_per_second": 6.921,
       "step": 3
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.673076923076923,
-      "eval_loss": 0.6748365759849548,
-      "eval_runtime": 0.6341,
-      "eval_samples_per_second": 149.822,
-      "eval_steps_per_second": 4.731,
+      "eval_f1": 0.3773584905660377,
+      "eval_loss": 0.729247510433197,
+      "eval_runtime": 0.5528,
+      "eval_samples_per_second": 180.896,
+      "eval_steps_per_second": 7.236,
       "step": 6
     },
     {
       "epoch": 3.0,
-      "eval_f1": 0.8034188034188033,
-      "eval_loss": 0.6552020311355591,
-      "eval_runtime": 0.6415,
-      "eval_samples_per_second": 148.089,
-      "eval_steps_per_second": 4.676,
+      "eval_f1": 0.4786324786324786,
+      "eval_loss": 0.7105527520179749,
+      "eval_runtime": 0.558,
+      "eval_samples_per_second": 179.203,
+      "eval_steps_per_second": 7.168,
       "step": 9
     },
     {
       "epoch": 4.0,
-      "eval_f1": 0.88,
-      "eval_loss": 0.6357027888298035,
-      "eval_runtime": 0.6465,
-      "eval_samples_per_second": 146.936,
-      "eval_steps_per_second": 4.64,
+      "eval_f1": 0.6060606060606061,
+      "eval_loss": 0.6890331506729126,
+      "eval_runtime": 0.5504,
+      "eval_samples_per_second": 181.671,
+      "eval_steps_per_second": 7.267,
       "step": 12
     },
     {
       "epoch": 5.0,
-      "eval_f1": 0.8615384615384616,
-      "eval_loss": 0.6192407011985779,
-      "eval_runtime": 0.6387,
-      "eval_samples_per_second": 148.729,
-      "eval_steps_per_second": 4.697,
+      "eval_f1": 0.7,
+      "eval_loss": 0.6695859432220459,
+      "eval_runtime": 0.5595,
+      "eval_samples_per_second": 178.745,
+      "eval_steps_per_second": 7.15,
       "step": 15
     },
     {
       "epoch": 6.0,
-      "eval_f1": 0.8769230769230769,
-      "eval_loss": 0.604374349117279,
-      "eval_runtime": 0.645,
-      "eval_samples_per_second": 147.298,
-      "eval_steps_per_second": 4.652,
+      "eval_f1": 0.7761194029850746,
+      "eval_loss": 0.6517141461372375,
+      "eval_runtime": 0.5632,
+      "eval_samples_per_second": 177.548,
+      "eval_steps_per_second": 7.102,
       "step": 18
     },
     {
       "epoch": 7.0,
-      "eval_f1": 0.8769230769230769,
-      "eval_loss": 0.5909456014633179,
-      "eval_runtime": 0.6526,
-      "eval_samples_per_second": 145.576,
-      "eval_steps_per_second": 4.597,
+      "eval_f1": 0.828125,
+      "eval_loss": 0.6349117755889893,
+      "eval_runtime": 0.5567,
+      "eval_samples_per_second": 179.616,
+      "eval_steps_per_second": 7.185,
       "step": 21
     },
     {
       "epoch": 8.0,
-      "eval_f1": 0.8769230769230769,
-      "eval_loss": 0.5791701674461365,
-      "eval_runtime": 0.6491,
-      "eval_samples_per_second": 146.347,
-      "eval_steps_per_second": 4.621,
+      "eval_f1": 0.8503937007874015,
+      "eval_loss": 0.618772029876709,
+      "eval_runtime": 0.5546,
+      "eval_samples_per_second": 180.325,
+      "eval_steps_per_second": 7.213,
       "step": 24
     },
     {
       "epoch": 8.33,
       "learning_rate": 8.024691358024692e-06,
-      "loss": 0.638,
+      "loss": 0.634,
       "step": 25
     },
     {
       "epoch": 9.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.5682619214057922,
-      "eval_runtime": 0.6497,
-      "eval_samples_per_second": 146.222,
-      "eval_steps_per_second": 4.618,
+      "eval_f1": 0.8709677419354839,
+      "eval_loss": 0.6039881706237793,
+      "eval_runtime": 0.5519,
+      "eval_samples_per_second": 181.185,
+      "eval_steps_per_second": 7.247,
       "step": 27
     },
     {
       "epoch": 10.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.5576053261756897,
-      "eval_runtime": 0.653,
-      "eval_samples_per_second": 145.478,
-      "eval_steps_per_second": 4.594,
+      "eval_f1": 0.8709677419354839,
+      "eval_loss": 0.5912619829177856,
+      "eval_runtime": 0.5573,
+      "eval_samples_per_second": 179.441,
+      "eval_steps_per_second": 7.178,
       "step": 30
     },
     {
       "epoch": 11.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.5474461913108826,
-      "eval_runtime": 0.651,
-      "eval_samples_per_second": 145.928,
-      "eval_steps_per_second": 4.608,
+      "eval_f1": 0.8780487804878049,
+      "eval_loss": 0.5805598497390747,
+      "eval_runtime": 0.5574,
+      "eval_samples_per_second": 179.394,
+      "eval_steps_per_second": 7.176,
       "step": 33
     },
     {
       "epoch": 12.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.5376133322715759,
-      "eval_runtime": 0.6594,
-      "eval_samples_per_second": 144.075,
-      "eval_steps_per_second": 4.55,
+      "eval_f1": 0.8688524590163933,
+      "eval_loss": 0.5723507404327393,
+      "eval_runtime": 0.5544,
+      "eval_samples_per_second": 180.362,
+      "eval_steps_per_second": 7.214,
       "step": 36
     },
     {
       "epoch": 13.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.5282223224639893,
-      "eval_runtime": 0.6631,
-      "eval_samples_per_second": 143.267,
-      "eval_steps_per_second": 4.524,
+      "eval_f1": 0.8688524590163933,
+      "eval_loss": 0.5652728080749512,
+      "eval_runtime": 0.5588,
+      "eval_samples_per_second": 178.951,
+      "eval_steps_per_second": 7.158,
       "step": 39
     },
     {
       "epoch": 14.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.5196569561958313,
-      "eval_runtime": 0.6551,
-      "eval_samples_per_second": 145.016,
-      "eval_steps_per_second": 4.579,
+      "eval_f1": 0.8688524590163933,
+      "eval_loss": 0.5592342019081116,
+      "eval_runtime": 0.5516,
+      "eval_samples_per_second": 181.294,
+      "eval_steps_per_second": 7.252,
       "step": 42
     },
     {
       "epoch": 15.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.5118635296821594,
-      "eval_runtime": 0.6658,
-      "eval_samples_per_second": 142.69,
-      "eval_steps_per_second": 4.506,
+      "eval_f1": 0.8760330578512396,
+      "eval_loss": 0.553566575050354,
+      "eval_runtime": 0.558,
+      "eval_samples_per_second": 179.226,
+      "eval_steps_per_second": 7.169,
       "step": 45
     },
     {
       "epoch": 16.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.5053044557571411,
-      "eval_runtime": 0.6565,
-      "eval_samples_per_second": 144.71,
-      "eval_steps_per_second": 4.57,
+      "eval_f1": 0.8760330578512396,
+      "eval_loss": 0.5487043857574463,
+      "eval_runtime": 0.5688,
+      "eval_samples_per_second": 175.802,
+      "eval_steps_per_second": 7.032,
       "step": 48
     },
     {
       "epoch": 16.67,
       "learning_rate": 4.938271604938272e-06,
-      "loss": 0.4926,
+      "loss": 0.5096,
       "step": 50
     },
     {
       "epoch": 17.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.49933797121047974,
-      "eval_runtime": 0.6612,
-      "eval_samples_per_second": 143.679,
-      "eval_steps_per_second": 4.537,
+      "eval_f1": 0.8760330578512396,
+      "eval_loss": 0.5434445142745972,
+      "eval_runtime": 0.5636,
+      "eval_samples_per_second": 177.42,
+      "eval_steps_per_second": 7.097,
       "step": 51
     },
     {
       "epoch": 18.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.4940946102142334,
-      "eval_runtime": 0.661,
-      "eval_samples_per_second": 143.726,
-      "eval_steps_per_second": 4.539,
+      "eval_f1": 0.8760330578512396,
+      "eval_loss": 0.5385234951972961,
+      "eval_runtime": 0.561,
+      "eval_samples_per_second": 178.247,
+      "eval_steps_per_second": 7.13,
       "step": 54
     },
     {
       "epoch": 19.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.4895910918712616,
-      "eval_runtime": 0.6623,
-      "eval_samples_per_second": 143.44,
-      "eval_steps_per_second": 4.53,
+      "eval_f1": 0.8760330578512396,
+      "eval_loss": 0.5339138507843018,
+      "eval_runtime": 0.5531,
+      "eval_samples_per_second": 180.806,
+      "eval_steps_per_second": 7.232,
       "step": 57
     },
     {
       "epoch": 20.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.4853971004486084,
-      "eval_runtime": 0.6837,
-      "eval_samples_per_second": 138.946,
-      "eval_steps_per_second": 4.388,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.5293477177619934,
+      "eval_runtime": 0.5612,
+      "eval_samples_per_second": 178.191,
+      "eval_steps_per_second": 7.128,
       "step": 60
     },
     {
       "epoch": 21.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.48188260197639465,
-      "eval_runtime": 0.6669,
-      "eval_samples_per_second": 142.45,
-      "eval_steps_per_second": 4.498,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.5248751640319824,
+      "eval_runtime": 0.554,
+      "eval_samples_per_second": 180.518,
+      "eval_steps_per_second": 7.221,
       "step": 63
     },
     {
       "epoch": 22.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.4790306091308594,
-      "eval_runtime": 0.6675,
-      "eval_samples_per_second": 142.322,
-      "eval_steps_per_second": 4.494,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.5204405784606934,
+      "eval_runtime": 0.564,
+      "eval_samples_per_second": 177.317,
+      "eval_steps_per_second": 7.093,
       "step": 66
     },
     {
       "epoch": 23.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.47673219442367554,
-      "eval_runtime": 0.6755,
-      "eval_samples_per_second": 140.639,
-      "eval_steps_per_second": 4.441,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.5157800912857056,
+      "eval_runtime": 0.5507,
+      "eval_samples_per_second": 181.589,
+      "eval_steps_per_second": 7.264,
       "step": 69
     },
     {
       "epoch": 24.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.4748006761074066,
-      "eval_runtime": 0.6675,
-      "eval_samples_per_second": 142.313,
-      "eval_steps_per_second": 4.494,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.5112195014953613,
+      "eval_runtime": 0.5502,
+      "eval_samples_per_second": 181.737,
+      "eval_steps_per_second": 7.269,
       "step": 72
     },
     {
       "epoch": 25.0,
       "learning_rate": 1.8518518518518519e-06,
-      "loss": 0.4289,
+      "loss": 0.4584,
       "step": 75
     },
     {
       "epoch": 25.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.4731859564781189,
-      "eval_runtime": 0.6627,
-      "eval_samples_per_second": 143.353,
-      "eval_steps_per_second": 4.527,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.5078128576278687,
+      "eval_runtime": 0.5542,
+      "eval_samples_per_second": 180.427,
+      "eval_steps_per_second": 7.217,
       "step": 75
     },
     {
       "epoch": 26.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.4718676507472992,
-      "eval_runtime": 0.6719,
-      "eval_samples_per_second": 141.397,
-      "eval_steps_per_second": 4.465,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.5054234266281128,
+      "eval_runtime": 0.5564,
+      "eval_samples_per_second": 179.717,
+      "eval_steps_per_second": 7.189,
       "step": 78
     },
     {
       "epoch": 27.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.4708217680454254,
-      "eval_runtime": 0.68,
-      "eval_samples_per_second": 139.706,
-      "eval_steps_per_second": 4.412,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.503419041633606,
+      "eval_runtime": 0.5536,
+      "eval_samples_per_second": 180.639,
+      "eval_steps_per_second": 7.226,
       "step": 81
     },
     {
       "epoch": 28.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.47011542320251465,
-      "eval_runtime": 0.6739,
-      "eval_samples_per_second": 140.966,
-      "eval_steps_per_second": 4.452,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.5020792484283447,
+      "eval_runtime": 0.5563,
+      "eval_samples_per_second": 179.771,
+      "eval_steps_per_second": 7.191,
       "step": 84
     },
     {
       "epoch": 29.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.4697326123714447,
-      "eval_runtime": 0.6728,
-      "eval_samples_per_second": 141.199,
-      "eval_steps_per_second": 4.459,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.5012262463569641,
+      "eval_runtime": 0.5542,
+      "eval_samples_per_second": 180.449,
+      "eval_steps_per_second": 7.218,
       "step": 87
     },
     {
       "epoch": 30.0,
-      "eval_f1": 0.8837209302325582,
-      "eval_loss": 0.4695647060871124,
-      "eval_runtime": 0.6801,
-      "eval_samples_per_second": 139.689,
-      "eval_steps_per_second": 4.411,
+      "eval_f1": 0.8739495798319329,
+      "eval_loss": 0.50089430809021,
+      "eval_runtime": 0.553,
+      "eval_samples_per_second": 180.845,
+      "eval_steps_per_second": 7.234,
       "step": 90
     },
     {
       "epoch": 30.0,
       "step": 90,
-      "total_flos": 2.8570124903878656e+17,
-      "train_loss": 0.5013438595665826,
-      "train_runtime": 222.831,
-      "train_samples_per_second": 51.025,
-      "train_steps_per_second": 0.404
+      "total_flos": 2.7816295750742016e+17,
+      "train_loss": 0.517905675040351,
+      "train_runtime": 173.4592,
+      "train_samples_per_second": 63.819,
+      "train_steps_per_second": 0.519
     }
   ],
   "max_steps": 90,
   "num_train_epochs": 30,
-  "total_flos": 2.8570124903878656e+17,
+  "total_flos": 2.7816295750742016e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6605b4550676653f6a9e7bbcb528bc7fd05170d1b839094df3e2a84195ed6b46
+oid sha256:bc0e695a5fa30200b1f5ebbb0c0f59e54cb992144a4b6448fa0dabb43ede9cbf
 size 3311