Training in progress, step 100

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.1631537675857544,
-    "eval_runtime": 4.7342,
-    "eval_samples_per_second": 28.093,
-    "eval_steps_per_second": 3.591,
+    "eval_accuracy": 0.9924812030075187,
+    "eval_loss": 0.01256683561950922,
+    "eval_runtime": 5.9162,
+    "eval_samples_per_second": 22.481,
+    "eval_steps_per_second": 2.873,
     "total_flos": 1.0280724304719053e+17,
-    "train_loss": 0.05168719090436823,
-    "train_runtime": 444.679,
-    "train_samples_per_second": 9.301,
-    "train_steps_per_second": 0.585
+    "train_loss": 0.21192769230558323,
+    "train_runtime": 498.1854,
+    "train_samples_per_second": 8.302,
+    "train_steps_per_second": 0.522
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.1631537675857544,
-    "eval_runtime": 4.7342,
-    "eval_samples_per_second": 28.093,
-    "eval_steps_per_second": 3.591
+    "eval_accuracy": 0.9924812030075187,
+    "eval_loss": 0.01256683561950922,
+    "eval_runtime": 5.9162,
+    "eval_samples_per_second": 22.481,
+    "eval_steps_per_second": 2.873
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724ac03ac1e88d68aa4da491de59212d802933ca734cd9b5aa4e048e0e92413d
+oid sha256:b5409e1c5258c24ac1474c7941dba94fc71772c1ace2449fbd5f3a885a22e019
 size 110345908

runs/Nov22_16-01-39_l-hvjvvxgp4c.local/events.out.tfevents.1732309809.l-hvjvvxgp4c.local.50592.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4124e5ae55e92c8b5ae194866b27277b42656302106c7b24952a198e9dd8d4b7
+size 411

runs/Nov23_19-27-42_l-hvjvvxgp4c.local/events.out.tfevents.1732408063.l-hvjvvxgp4c.local.2129.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:527aa05d7658d35eadb1d38622334d1142bd3838dba3a0cfe7481146c32a4986
+size 7888

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 1.0280724304719053e+17,
-    "train_loss": 0.05168719090436823,
-    "train_runtime": 444.679,
-    "train_samples_per_second": 9.301,
-    "train_steps_per_second": 0.585
+    "train_loss": 0.21192769230558323,
+    "train_runtime": 498.1854,
+    "train_samples_per_second": 8.302,
+    "train_steps_per_second": 0.522
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.1631537675857544,
+  "best_metric": 0.01256683561950922,
   "best_model_checkpoint": "plant_classification/checkpoint-200",
   "epoch": 4.0,
   "eval_steps": 100,
@@ -10,212 +10,212 @@
   "log_history": [
     {
       "epoch": 0.15384615384615385,
-      "grad_norm": 0.0036831500474363565,
-      "learning_rate": 0.00019230769230769233,
-      "loss": 0.2402,
+      "grad_norm": 6.989621639251709,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 1.0566,
       "step": 10
     },
     {
       "epoch": 0.3076923076923077,
-      "grad_norm": 0.37796255946159363,
-      "learning_rate": 0.00018461538461538463,
-      "loss": 0.1955,
+      "grad_norm": 7.209625720977783,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.9636,
       "step": 20
     },
     {
       "epoch": 0.46153846153846156,
-      "grad_norm": 31.321809768676758,
-      "learning_rate": 0.00017692307692307693,
-      "loss": 0.2262,
+      "grad_norm": 7.134735584259033,
+      "learning_rate": 1.965811965811966e-05,
+      "loss": 0.7887,
       "step": 30
     },
     {
       "epoch": 0.6153846153846154,
-      "grad_norm": 5.618703365325928,
-      "learning_rate": 0.00016923076923076923,
-      "loss": 0.1265,
+      "grad_norm": 6.25767183303833,
+      "learning_rate": 1.8803418803418804e-05,
+      "loss": 0.557,
       "step": 40
     },
     {
       "epoch": 0.7692307692307693,
-      "grad_norm": 1.3796021938323975,
-      "learning_rate": 0.00016153846153846155,
-      "loss": 0.1004,
+      "grad_norm": 5.833093643188477,
+      "learning_rate": 1.794871794871795e-05,
+      "loss": 0.3177,
       "step": 50
     },
     {
       "epoch": 0.9230769230769231,
-      "grad_norm": 9.802377700805664,
-      "learning_rate": 0.00015384615384615385,
-      "loss": 0.0927,
+      "grad_norm": 9.08967399597168,
+      "learning_rate": 1.7094017094017095e-05,
+      "loss": 0.3041,
       "step": 60
     },
     {
       "epoch": 1.0769230769230769,
-      "grad_norm": 0.1012055054306984,
-      "learning_rate": 0.00014615384615384615,
-      "loss": 0.01,
+      "grad_norm": 6.379756450653076,
+      "learning_rate": 1.623931623931624e-05,
+      "loss": 0.2086,
       "step": 70
     },
     {
       "epoch": 1.2307692307692308,
-      "grad_norm": 0.03965623676776886,
-      "learning_rate": 0.00013846153846153847,
-      "loss": 0.1504,
+      "grad_norm": 6.944158554077148,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.1889,
       "step": 80
     },
     {
       "epoch": 1.3846153846153846,
-      "grad_norm": 0.01619710959494114,
-      "learning_rate": 0.00013076923076923077,
-      "loss": 0.0473,
+      "grad_norm": 1.658211350440979,
+      "learning_rate": 1.4529914529914531e-05,
+      "loss": 0.1003,
       "step": 90
     },
     {
       "epoch": 1.5384615384615383,
-      "grad_norm": 0.01804116927087307,
-      "learning_rate": 0.0001230769230769231,
-      "loss": 0.0007,
+      "grad_norm": 14.999855995178223,
+      "learning_rate": 1.3675213675213677e-05,
+      "loss": 0.1133,
       "step": 100
     },
     {
       "epoch": 1.5384615384615383,
-      "eval_accuracy": 0.9548872180451128,
-      "eval_loss": 0.2284693568944931,
-      "eval_runtime": 5.8195,
-      "eval_samples_per_second": 22.854,
-      "eval_steps_per_second": 2.921,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.020775081589818,
+      "eval_runtime": 6.1352,
+      "eval_samples_per_second": 21.678,
+      "eval_steps_per_second": 2.771,
       "step": 100
     },
     {
       "epoch": 1.6923076923076923,
-      "grad_norm": 2.150287628173828,
-      "learning_rate": 0.00011538461538461538,
-      "loss": 0.0236,
+      "grad_norm": 5.306297779083252,
+      "learning_rate": 1.2820512820512823e-05,
+      "loss": 0.0773,
       "step": 110
     },
     {
       "epoch": 1.8461538461538463,
-      "grad_norm": 0.004995028022676706,
-      "learning_rate": 0.0001076923076923077,
-      "loss": 0.0006,
+      "grad_norm": 1.1203813552856445,
+      "learning_rate": 1.1965811965811966e-05,
+      "loss": 0.1367,
       "step": 120
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.00010829918755916879,
-      "learning_rate": 0.0001,
-      "loss": 0.0089,
+      "grad_norm": 0.7909039855003357,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.1203,
       "step": 130
     },
     {
       "epoch": 2.1538461538461537,
-      "grad_norm": 0.0008967414614744484,
-      "learning_rate": 9.230769230769232e-05,
-      "loss": 0.0032,
+      "grad_norm": 5.999809741973877,
+      "learning_rate": 1.0256410256410256e-05,
+      "loss": 0.0959,
       "step": 140
     },
     {
       "epoch": 2.3076923076923075,
-      "grad_norm": 0.008112355135381222,
-      "learning_rate": 8.461538461538461e-05,
-      "loss": 0.0258,
+      "grad_norm": 1.5936659574508667,
+      "learning_rate": 9.401709401709402e-06,
+      "loss": 0.0431,
       "step": 150
     },
     {
       "epoch": 2.4615384615384617,
-      "grad_norm": 0.0023394483141601086,
-      "learning_rate": 7.692307692307693e-05,
-      "loss": 0.0001,
+      "grad_norm": 3.5543646812438965,
+      "learning_rate": 8.547008547008548e-06,
+      "loss": 0.0386,
       "step": 160
     },
     {
       "epoch": 2.6153846153846154,
-      "grad_norm": 0.03999931737780571,
-      "learning_rate": 6.923076923076924e-05,
-      "loss": 0.0521,
+      "grad_norm": 2.5531251430511475,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.0392,
       "step": 170
     },
     {
       "epoch": 2.769230769230769,
-      "grad_norm": 0.12175856530666351,
-      "learning_rate": 6.153846153846155e-05,
-      "loss": 0.0064,
+      "grad_norm": 8.51604175567627,
+      "learning_rate": 6.837606837606839e-06,
+      "loss": 0.0567,
       "step": 180
     },
     {
       "epoch": 2.9230769230769234,
-      "grad_norm": 0.0003706614370457828,
-      "learning_rate": 5.384615384615385e-05,
-      "loss": 0.0,
+      "grad_norm": 0.5281253457069397,
+      "learning_rate": 5.982905982905983e-06,
+      "loss": 0.0575,
       "step": 190
     },
     {
       "epoch": 3.076923076923077,
-      "grad_norm": 0.00019209070887882262,
-      "learning_rate": 4.615384615384616e-05,
-      "loss": 0.0005,
+      "grad_norm": 0.26004061102867126,
+      "learning_rate": 5.128205128205128e-06,
+      "loss": 0.0419,
       "step": 200
     },
     {
       "epoch": 3.076923076923077,
-      "eval_accuracy": 0.9699248120300752,
-      "eval_loss": 0.1631537675857544,
-      "eval_runtime": 6.8037,
-      "eval_samples_per_second": 19.548,
-      "eval_steps_per_second": 2.499,
+      "eval_accuracy": 0.9924812030075187,
+      "eval_loss": 0.01256683561950922,
+      "eval_runtime": 8.7266,
+      "eval_samples_per_second": 15.241,
+      "eval_steps_per_second": 1.948,
       "step": 200
     },
     {
       "epoch": 3.230769230769231,
-      "grad_norm": 0.00012901176523882896,
-      "learning_rate": 3.846153846153846e-05,
-      "loss": 0.0024,
+      "grad_norm": 0.5421740412712097,
+      "learning_rate": 4.273504273504274e-06,
+      "loss": 0.0158,
       "step": 210
     },
     {
       "epoch": 3.3846153846153846,
-      "grad_norm": 0.0013422417687252164,
-      "learning_rate": 3.0769230769230774e-05,
-      "loss": 0.0299,
+      "grad_norm": 0.23353244364261627,
+      "learning_rate": 3.4188034188034193e-06,
+      "loss": 0.0097,
       "step": 220
     },
     {
       "epoch": 3.5384615384615383,
-      "grad_norm": 0.0007627483573742211,
-      "learning_rate": 2.307692307692308e-05,
-      "loss": 0.0,
+      "grad_norm": 0.3935740292072296,
+      "learning_rate": 2.564102564102564e-06,
+      "loss": 0.0491,
       "step": 230
     },
     {
       "epoch": 3.6923076923076925,
-      "grad_norm": 2.576974868774414,
-      "learning_rate": 1.5384615384615387e-05,
-      "loss": 0.0002,
+      "grad_norm": 20.858152389526367,
+      "learning_rate": 1.7094017094017097e-06,
+      "loss": 0.0271,
       "step": 240
     },
     {
       "epoch": 3.8461538461538463,
-      "grad_norm": 0.002301289001479745,
-      "learning_rate": 7.692307692307694e-06,
-      "loss": 0.0,
+      "grad_norm": 3.8724491596221924,
+      "learning_rate": 8.547008547008548e-07,
+      "loss": 0.024,
       "step": 250
     },
     {
       "epoch": 4.0,
-      "grad_norm": 5.4764645028626546e-05,
+      "grad_norm": 0.08855155855417252,
       "learning_rate": 0.0,
-      "loss": 0.0002,
+      "loss": 0.0785,
       "step": 260
     },
     {
       "epoch": 4.0,
       "step": 260,
       "total_flos": 1.0280724304719053e+17,
-      "train_loss": 0.05168719090436823,
-      "train_runtime": 444.679,
-      "train_samples_per_second": 9.301,
-      "train_steps_per_second": 0.585
+      "train_loss": 0.21192769230558323,
+      "train_runtime": 498.1854,
+      "train_samples_per_second": 8.302,
+      "train_steps_per_second": 0.522
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3af2c5e1363dbc3c4de721e22264d4edb1193080854b606d782b2a6dc9634c8e
+oid sha256:f0ee0b6504057372f8d994fc4a1a719331eb2bf8ef286e7e6a27edc7bc1c2cb8
 size 5304