Training in progress, epoch 1

all_results.json

@@ -1,13 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.9777131782945736,
-    "eval_loss": 0.06364382058382034,
-    "eval_runtime": 43.0533,
-    "eval_samples_per_second": 95.881,
-    "eval_steps_per_second": 11.985,
     "total_flos": 5.373364651307827e+17,
-    "train_loss": 0.5084914574327395,
-    "train_runtime": 598.2279,
-    "train_samples_per_second": 27.598,
-    "train_steps_per_second": 0.863
+    "train_loss": 0.5028278545815815,
+    "train_runtime": 599.3147,
+    "train_samples_per_second": 27.548,
+    "train_steps_per_second": 0.861
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bea936062e51133429ae8560fcbacec8c560473ab8cec312e85be757f3a671d
+oid sha256:58cb5a9ab20204b6d5e3f0588d7a9d9d73f1278a4c2387b33ee1b8c2533803d9
 size 110390140

runs/Nov18_15-23-22_55f2c01d5672/events.out.tfevents.1731944528.55f2c01d5672.280.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bce8ecf1dcab33476273f53317c59c0f3c6ff3eef9eea7c76469aea2f670047
+size 17330

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 5.373364651307827e+17,
-    "train_loss": 0.5084914574327395,
-    "train_runtime": 598.2279,
-    "train_samples_per_second": 27.598,
-    "train_steps_per_second": 0.863
+    "train_loss": 0.5028278545815815,
+    "train_runtime": 599.3147,
+    "train_samples_per_second": 27.548,
+    "train_steps_per_second": 0.861
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9777131782945736,
+  "best_metric": 0.9798934108527132,
   "best_model_checkpoint": "swinv2-tiny-patch4-window16-256-finetuned-plantdisease/checkpoint-516",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,378 +10,378 @@
   "log_history": [
     {
       "epoch": 0.01937984496124031,
-      "grad_norm": 6.709539890289307,
+      "grad_norm": 25.043317794799805,
       "learning_rate": 9.615384615384616e-06,
-      "loss": 2.7078,
+      "loss": 2.7216,
       "step": 10
     },
     {
       "epoch": 0.03875968992248062,
-      "grad_norm": 7.255009651184082,
+      "grad_norm": 28.33056640625,
       "learning_rate": 1.923076923076923e-05,
-      "loss": 2.5761,
+      "loss": 2.5612,
       "step": 20
     },
     {
       "epoch": 0.05813953488372093,
-      "grad_norm": 7.875271320343018,
+      "grad_norm": 29.639535903930664,
       "learning_rate": 2.8846153846153845e-05,
-      "loss": 2.331,
+      "loss": 2.351,
       "step": 30
     },
     {
       "epoch": 0.07751937984496124,
-      "grad_norm": 9.543013572692871,
+      "grad_norm": 37.78919219970703,
       "learning_rate": 3.846153846153846e-05,
-      "loss": 2.1674,
+      "loss": 2.0721,
       "step": 40
     },
     {
       "epoch": 0.09689922480620156,
-      "grad_norm": 13.559645652770996,
+      "grad_norm": 43.523765563964844,
       "learning_rate": 4.8076923076923084e-05,
-      "loss": 1.7745,
+      "loss": 1.7632,
       "step": 50
     },
     {
       "epoch": 0.11627906976744186,
-      "grad_norm": 16.62691307067871,
+      "grad_norm": 57.11870574951172,
       "learning_rate": 4.913793103448276e-05,
-      "loss": 1.3937,
+      "loss": 1.2954,
       "step": 60
     },
     {
       "epoch": 0.13565891472868216,
-      "grad_norm": 15.683610916137695,
+      "grad_norm": 77.69208526611328,
       "learning_rate": 4.806034482758621e-05,
-      "loss": 1.0158,
+      "loss": 1.0353,
       "step": 70
     },
     {
       "epoch": 0.15503875968992248,
-      "grad_norm": 14.473851203918457,
+      "grad_norm": 58.72177505493164,
       "learning_rate": 4.698275862068966e-05,
-      "loss": 0.8055,
+      "loss": 0.7396,
       "step": 80
     },
     {
       "epoch": 0.1744186046511628,
-      "grad_norm": 14.953446388244629,
+      "grad_norm": 45.172569274902344,
       "learning_rate": 4.590517241379311e-05,
-      "loss": 0.6449,
+      "loss": 0.5802,
       "step": 90
     },
     {
       "epoch": 0.1937984496124031,
-      "grad_norm": 11.831011772155762,
+      "grad_norm": 101.80105590820312,
       "learning_rate": 4.482758620689655e-05,
-      "loss": 0.6051,
+      "loss": 0.6721,
       "step": 100
     },
     {
       "epoch": 0.2131782945736434,
-      "grad_norm": 13.278793334960938,
+      "grad_norm": 35.118316650390625,
       "learning_rate": 4.375e-05,
-      "loss": 0.5566,
+      "loss": 0.604,
       "step": 110
     },
     {
       "epoch": 0.23255813953488372,
-      "grad_norm": 11.702147483825684,
+      "grad_norm": 51.14491653442383,
       "learning_rate": 4.267241379310345e-05,
-      "loss": 0.4845,
+      "loss": 0.4788,
       "step": 120
     },
     {
       "epoch": 0.25193798449612403,
-      "grad_norm": 10.426274299621582,
+      "grad_norm": 55.622344970703125,
       "learning_rate": 4.1594827586206896e-05,
-      "loss": 0.3641,
+      "loss": 0.352,
       "step": 130
     },
     {
       "epoch": 0.2713178294573643,
-      "grad_norm": 17.529104232788086,
+      "grad_norm": 51.51637649536133,
       "learning_rate": 4.0517241379310344e-05,
-      "loss": 0.3593,
+      "loss": 0.3522,
       "step": 140
     },
     {
       "epoch": 0.29069767441860467,
-      "grad_norm": 12.532708168029785,
+      "grad_norm": 51.93968963623047,
       "learning_rate": 3.94396551724138e-05,
-      "loss": 0.3459,
+      "loss": 0.3595,
       "step": 150
     },
     {
       "epoch": 0.31007751937984496,
-      "grad_norm": 16.44886589050293,
+      "grad_norm": 62.32090759277344,
       "learning_rate": 3.8362068965517246e-05,
-      "loss": 0.4475,
+      "loss": 0.4144,
       "step": 160
     },
     {
       "epoch": 0.32945736434108525,
-      "grad_norm": 8.827244758605957,
+      "grad_norm": 49.8425407409668,
       "learning_rate": 3.7284482758620694e-05,
-      "loss": 0.3544,
+      "loss": 0.3176,
       "step": 170
     },
     {
       "epoch": 0.3488372093023256,
-      "grad_norm": 6.035519123077393,
+      "grad_norm": 65.97383880615234,
       "learning_rate": 3.620689655172414e-05,
-      "loss": 0.3214,
+      "loss": 0.3074,
       "step": 180
     },
     {
       "epoch": 0.3682170542635659,
-      "grad_norm": 7.568902969360352,
+      "grad_norm": 41.63103103637695,
       "learning_rate": 3.512931034482759e-05,
-      "loss": 0.2359,
+      "loss": 0.2868,
       "step": 190
     },
     {
       "epoch": 0.3875968992248062,
-      "grad_norm": 13.209157943725586,
+      "grad_norm": 54.208648681640625,
       "learning_rate": 3.405172413793103e-05,
-      "loss": 0.34,
+      "loss": 0.3902,
       "step": 200
     },
     {
       "epoch": 0.4069767441860465,
-      "grad_norm": 19.102611541748047,
+      "grad_norm": 63.819393157958984,
       "learning_rate": 3.297413793103448e-05,
-      "loss": 0.3697,
+      "loss": 0.3249,
       "step": 210
     },
     {
       "epoch": 0.4263565891472868,
-      "grad_norm": 12.98582649230957,
+      "grad_norm": 40.1036376953125,
       "learning_rate": 3.1896551724137935e-05,
-      "loss": 0.2864,
+      "loss": 0.2938,
       "step": 220
     },
     {
       "epoch": 0.44573643410852715,
-      "grad_norm": 14.064764976501465,
+      "grad_norm": 43.186614990234375,
       "learning_rate": 3.081896551724138e-05,
-      "loss": 0.2606,
+      "loss": 0.2598,
       "step": 230
     },
     {
       "epoch": 0.46511627906976744,
-      "grad_norm": 13.41550064086914,
+      "grad_norm": 38.62468719482422,
       "learning_rate": 2.974137931034483e-05,
-      "loss": 0.2949,
+      "loss": 0.2023,
       "step": 240
     },
     {
       "epoch": 0.4844961240310077,
-      "grad_norm": 7.437551498413086,
+      "grad_norm": 48.45721435546875,
       "learning_rate": 2.866379310344828e-05,
-      "loss": 0.1955,
+      "loss": 0.2323,
       "step": 250
     },
     {
       "epoch": 0.5038759689922481,
-      "grad_norm": 8.963953018188477,
+      "grad_norm": 41.89044189453125,
       "learning_rate": 2.7586206896551727e-05,
-      "loss": 0.2536,
+      "loss": 0.276,
       "step": 260
     },
     {
       "epoch": 0.5232558139534884,
-      "grad_norm": 11.374913215637207,
+      "grad_norm": 55.60496520996094,
       "learning_rate": 2.650862068965517e-05,
-      "loss": 0.2592,
+      "loss": 0.2405,
       "step": 270
     },
     {
       "epoch": 0.5426356589147286,
-      "grad_norm": 7.7792768478393555,
+      "grad_norm": 145.46893310546875,
       "learning_rate": 2.543103448275862e-05,
-      "loss": 0.2024,
+      "loss": 0.1902,
       "step": 280
     },
     {
       "epoch": 0.562015503875969,
-      "grad_norm": 14.774372100830078,
+      "grad_norm": 52.95439147949219,
       "learning_rate": 2.435344827586207e-05,
-      "loss": 0.228,
+      "loss": 0.173,
       "step": 290
     },
     {
       "epoch": 0.5813953488372093,
-      "grad_norm": 8.32029914855957,
+      "grad_norm": 45.259090423583984,
       "learning_rate": 2.327586206896552e-05,
-      "loss": 0.1849,
+      "loss": 0.1893,
       "step": 300
     },
     {
       "epoch": 0.6007751937984496,
-      "grad_norm": 14.661565780639648,
+      "grad_norm": 26.136516571044922,
       "learning_rate": 2.2198275862068967e-05,
-      "loss": 0.1835,
+      "loss": 0.2305,
       "step": 310
     },
     {
       "epoch": 0.6201550387596899,
-      "grad_norm": 15.804061889648438,
+      "grad_norm": 16.7691593170166,
       "learning_rate": 2.1120689655172415e-05,
-      "loss": 0.1828,
+      "loss": 0.2272,
       "step": 320
     },
     {
       "epoch": 0.6395348837209303,
-      "grad_norm": 19.60464859008789,
+      "grad_norm": 33.225093841552734,
       "learning_rate": 2.0043103448275863e-05,
-      "loss": 0.1874,
+      "loss": 0.1852,
       "step": 330
     },
     {
       "epoch": 0.6589147286821705,
-      "grad_norm": 5.921483516693115,
+      "grad_norm": 46.34248352050781,
       "learning_rate": 1.896551724137931e-05,
-      "loss": 0.1741,
+      "loss": 0.1849,
       "step": 340
     },
     {
       "epoch": 0.6782945736434108,
-      "grad_norm": 8.562132835388184,
+      "grad_norm": 39.95323944091797,
       "learning_rate": 1.7887931034482762e-05,
-      "loss": 0.2541,
+      "loss": 0.2435,
       "step": 350
     },
     {
       "epoch": 0.6976744186046512,
-      "grad_norm": 7.037123680114746,
+      "grad_norm": 30.731279373168945,
       "learning_rate": 1.6810344827586207e-05,
-      "loss": 0.2101,
+      "loss": 0.1624,
       "step": 360
     },
     {
       "epoch": 0.7170542635658915,
-      "grad_norm": 4.712380886077881,
+      "grad_norm": 8.740701675415039,
       "learning_rate": 1.5732758620689655e-05,
-      "loss": 0.2088,
+      "loss": 0.2548,
       "step": 370
     },
     {
       "epoch": 0.7364341085271318,
-      "grad_norm": 5.721762180328369,
+      "grad_norm": 82.22977447509766,
       "learning_rate": 1.4655172413793103e-05,
-      "loss": 0.2245,
+      "loss": 0.2045,
       "step": 380
     },
     {
       "epoch": 0.7558139534883721,
-      "grad_norm": 8.76972484588623,
+      "grad_norm": 63.77909851074219,
       "learning_rate": 1.3577586206896553e-05,
-      "loss": 0.1713,
+      "loss": 0.1882,
       "step": 390
     },
     {
       "epoch": 0.7751937984496124,
-      "grad_norm": 8.067720413208008,
+      "grad_norm": 45.88880157470703,
       "learning_rate": 1.25e-05,
-      "loss": 0.1822,
+      "loss": 0.2073,
       "step": 400
     },
     {
       "epoch": 0.7945736434108527,
-      "grad_norm": 8.3314208984375,
+      "grad_norm": 17.87135887145996,
       "learning_rate": 1.1422413793103449e-05,
-      "loss": 0.1781,
+      "loss": 0.1445,
       "step": 410
     },
     {
       "epoch": 0.813953488372093,
-      "grad_norm": 22.368515014648438,
+      "grad_norm": 43.013282775878906,
       "learning_rate": 1.0344827586206897e-05,
-      "loss": 0.1921,
+      "loss": 0.1474,
       "step": 420
     },
     {
       "epoch": 0.8333333333333334,
-      "grad_norm": 11.097426414489746,
+      "grad_norm": 40.31475067138672,
       "learning_rate": 9.267241379310346e-06,
-      "loss": 0.1627,
+      "loss": 0.2041,
       "step": 430
     },
     {
       "epoch": 0.8527131782945736,
-      "grad_norm": 20.73263168334961,
+      "grad_norm": 49.196441650390625,
       "learning_rate": 8.189655172413793e-06,
-      "loss": 0.1884,
+      "loss": 0.2133,
       "step": 440
     },
     {
       "epoch": 0.872093023255814,
-      "grad_norm": 2.5283663272857666,
+      "grad_norm": 20.448143005371094,
       "learning_rate": 7.112068965517242e-06,
-      "loss": 0.2005,
+      "loss": 0.1946,
       "step": 450
     },
     {
       "epoch": 0.8914728682170543,
-      "grad_norm": 4.581237316131592,
+      "grad_norm": 21.7471923828125,
       "learning_rate": 6.03448275862069e-06,
-      "loss": 0.1945,
+      "loss": 0.1013,
       "step": 460
     },
     {
       "epoch": 0.9108527131782945,
-      "grad_norm": 4.513861656188965,
+      "grad_norm": 40.28746795654297,
       "learning_rate": 4.9568965517241384e-06,
-      "loss": 0.1427,
+      "loss": 0.1489,
       "step": 470
     },
     {
       "epoch": 0.9302325581395349,
-      "grad_norm": 13.439146041870117,
+      "grad_norm": 39.44319534301758,
       "learning_rate": 3.8793103448275865e-06,
-      "loss": 0.1233,
+      "loss": 0.1403,
       "step": 480
     },
     {
       "epoch": 0.9496124031007752,
-      "grad_norm": 9.163981437683105,
+      "grad_norm": 38.28104782104492,
       "learning_rate": 2.8017241379310345e-06,
-      "loss": 0.1171,
+      "loss": 0.1278,
       "step": 490
     },
     {
       "epoch": 0.9689922480620154,
-      "grad_norm": 6.725685119628906,
+      "grad_norm": 30.639806747436523,
       "learning_rate": 1.724137931034483e-06,
-      "loss": 0.2016,
+      "loss": 0.1281,
       "step": 500
     },
     {
       "epoch": 0.9883720930232558,
-      "grad_norm": 5.155745029449463,
+      "grad_norm": 51.52839660644531,
       "learning_rate": 6.46551724137931e-07,
-      "loss": 0.103,
+      "loss": 0.1279,
       "step": 510
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9777131782945736,
-      "eval_loss": 0.06364382058382034,
-      "eval_runtime": 43.5867,
-      "eval_samples_per_second": 94.708,
-      "eval_steps_per_second": 11.838,
+      "eval_accuracy": 0.9798934108527132,
+      "eval_loss": 0.05675136297941208,
+      "eval_runtime": 44.1069,
+      "eval_samples_per_second": 93.591,
+      "eval_steps_per_second": 11.699,
       "step": 516
     },
     {
       "epoch": 1.0,
       "step": 516,
       "total_flos": 5.373364651307827e+17,
-      "train_loss": 0.5084914574327395,
-      "train_runtime": 598.2279,
-      "train_samples_per_second": 27.598,
-      "train_steps_per_second": 0.863
+      "train_loss": 0.5028278545815815,
+      "train_runtime": 599.3147,
+      "train_samples_per_second": 27.548,
+      "train_steps_per_second": 0.861
     }
   ],
   "logging_steps": 10,