Training in progress, step 100

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.9849624060150376,
-    "eval_loss": 0.035541191697120667,
-    "eval_runtime": 5.0153,
-    "eval_samples_per_second": 26.519,
-    "eval_steps_per_second": 3.39,
+    "eval_accuracy": 0.9924812030075187,
+    "eval_loss": 0.03436475992202759,
+    "eval_runtime": 4.5569,
+    "eval_samples_per_second": 29.186,
+    "eval_steps_per_second": 3.731,
     "total_flos": 1.0280724304719053e+17,
-    "train_loss": 0.21376643198040815,
-    "train_runtime": 415.522,
-    "train_samples_per_second": 9.954,
-    "train_steps_per_second": 0.626
+    "train_loss": 0.017011618363456084,
+    "train_runtime": 403.5216,
+    "train_samples_per_second": 10.25,
+    "train_steps_per_second": 0.644
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.9849624060150376,
-    "eval_loss": 0.035541191697120667,
-    "eval_runtime": 5.0153,
-    "eval_samples_per_second": 26.519,
-    "eval_steps_per_second": 3.39
+    "eval_accuracy": 0.9924812030075187,
+    "eval_loss": 0.03436475992202759,
+    "eval_runtime": 4.5569,
+    "eval_samples_per_second": 29.186,
+    "eval_steps_per_second": 3.731
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e23293bf56455be1847dd5c38cb8464ea5f9d1b9fa092eb8f7603cee6c277ead
+oid sha256:dd9dde6e484a8b575f3d69270e749ee6a77628f4acffc59a630202abaebcc7d2
 size 110345908

runs/Dec03_15-59-41_l-hvjvvxgp4c.local/events.out.tfevents.1733260003.l-hvjvvxgp4c.local.87043.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1b34547965252bc6e939dae9b9f1799702480f0ec67d3dfa337fd05c8c38b0
+size 411

runs/Dec03_16-15-32_l-hvjvvxgp4c.local/events.out.tfevents.1733260536.l-hvjvvxgp4c.local.87043.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb74418ffb02c2b590cbca0d2b624db67a496b18668d016480e43e57fd36beba
+size 7898

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 1.0280724304719053e+17,
-    "train_loss": 0.21376643198040815,
-    "train_runtime": 415.522,
-    "train_samples_per_second": 9.954,
-    "train_steps_per_second": 0.626
+    "train_loss": 0.017011618363456084,
+    "train_runtime": 403.5216,
+    "train_samples_per_second": 10.25,
+    "train_steps_per_second": 0.644
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.035541191697120667,
+  "best_metric": 0.03436475992202759,
   "best_model_checkpoint": "plant_classification/checkpoint-200",
   "epoch": 4.0,
   "eval_steps": 100,
@@ -10,212 +10,212 @@
   "log_history": [
     {
       "epoch": 0.15384615384615385,
-      "grad_norm": 6.145578384399414,
-      "learning_rate": 7.692307692307694e-06,
-      "loss": 1.078,
+      "grad_norm": 2.763857841491699,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 0.0382,
       "step": 10
     },
     {
       "epoch": 0.3076923076923077,
-      "grad_norm": 6.7720441818237305,
-      "learning_rate": 1.5384615384615387e-05,
-      "loss": 0.9303,
+      "grad_norm": 12.728006362915039,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.0264,
       "step": 20
     },
     {
       "epoch": 0.46153846153846156,
-      "grad_norm": 7.24746561050415,
-      "learning_rate": 1.965811965811966e-05,
-      "loss": 0.7624,
+      "grad_norm": 0.14380256831645966,
+      "learning_rate": 5.769230769230769e-06,
+      "loss": 0.0588,
       "step": 30
     },
     {
       "epoch": 0.6153846153846154,
-      "grad_norm": 7.476565837860107,
-      "learning_rate": 1.8803418803418804e-05,
-      "loss": 0.5213,
+      "grad_norm": 1.625977635383606,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.0259,
       "step": 40
     },
     {
       "epoch": 0.7692307692307693,
-      "grad_norm": 11.678607940673828,
-      "learning_rate": 1.794871794871795e-05,
-      "loss": 0.309,
+      "grad_norm": 0.28217747807502747,
+      "learning_rate": 9.615384615384616e-06,
+      "loss": 0.0119,
       "step": 50
     },
     {
       "epoch": 0.9230769230769231,
-      "grad_norm": 13.353544235229492,
-      "learning_rate": 1.7094017094017095e-05,
-      "loss": 0.3275,
+      "grad_norm": 17.04554557800293,
+      "learning_rate": 9.615384615384616e-06,
+      "loss": 0.0696,
       "step": 60
     },
     {
       "epoch": 1.0769230769230769,
-      "grad_norm": 11.612092971801758,
-      "learning_rate": 1.623931623931624e-05,
-      "loss": 0.2435,
+      "grad_norm": 2.1516802310943604,
+      "learning_rate": 9.134615384615384e-06,
+      "loss": 0.0193,
       "step": 70
     },
     {
       "epoch": 1.2307692307692308,
-      "grad_norm": 6.987435817718506,
-      "learning_rate": 1.5384615384615387e-05,
-      "loss": 0.1946,
+      "grad_norm": 1.7008322477340698,
+      "learning_rate": 8.653846153846155e-06,
+      "loss": 0.0446,
       "step": 80
     },
     {
       "epoch": 1.3846153846153846,
-      "grad_norm": 1.3243111371994019,
-      "learning_rate": 1.4529914529914531e-05,
-      "loss": 0.1017,
+      "grad_norm": 0.13665564358234406,
+      "learning_rate": 8.173076923076923e-06,
+      "loss": 0.0064,
       "step": 90
     },
     {
       "epoch": 1.5384615384615383,
-      "grad_norm": 16.304893493652344,
-      "learning_rate": 1.3675213675213677e-05,
-      "loss": 0.1031,
+      "grad_norm": 0.5729480385780334,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.0079,
       "step": 100
     },
     {
       "epoch": 1.5384615384615383,
-      "eval_accuracy": 0.9849624060150376,
-      "eval_loss": 0.040253832936286926,
-      "eval_runtime": 5.7782,
-      "eval_samples_per_second": 23.017,
-      "eval_steps_per_second": 2.942,
+      "eval_accuracy": 0.9924812030075187,
+      "eval_loss": 0.03526682406663895,
+      "eval_runtime": 5.1896,
+      "eval_samples_per_second": 25.628,
+      "eval_steps_per_second": 3.276,
       "step": 100
     },
     {
       "epoch": 1.6923076923076923,
-      "grad_norm": 1.3267813920974731,
-      "learning_rate": 1.2820512820512823e-05,
-      "loss": 0.0926,
+      "grad_norm": 0.028321973979473114,
+      "learning_rate": 7.211538461538462e-06,
+      "loss": 0.0038,
       "step": 110
     },
     {
       "epoch": 1.8461538461538463,
-      "grad_norm": 1.3231496810913086,
-      "learning_rate": 1.1965811965811966e-05,
-      "loss": 0.1027,
+      "grad_norm": 0.02708490751683712,
+      "learning_rate": 6.730769230769232e-06,
+      "loss": 0.0087,
       "step": 120
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.6598650217056274,
-      "learning_rate": 1.1111111111111113e-05,
-      "loss": 0.096,
+      "grad_norm": 0.005777100566774607,
+      "learning_rate": 6.25e-06,
+      "loss": 0.0171,
       "step": 130
     },
     {
       "epoch": 2.1538461538461537,
-      "grad_norm": 4.875283241271973,
-      "learning_rate": 1.0256410256410256e-05,
-      "loss": 0.1066,
+      "grad_norm": 0.606082022190094,
+      "learning_rate": 5.769230769230769e-06,
+      "loss": 0.0242,
       "step": 140
     },
     {
       "epoch": 2.3076923076923075,
-      "grad_norm": 0.7839311361312866,
-      "learning_rate": 9.401709401709402e-06,
-      "loss": 0.0662,
+      "grad_norm": 0.3665677011013031,
+      "learning_rate": 5.288461538461539e-06,
+      "loss": 0.0036,
       "step": 150
     },
     {
       "epoch": 2.4615384615384617,
-      "grad_norm": 3.084962844848633,
-      "learning_rate": 8.547008547008548e-06,
-      "loss": 0.0887,
+      "grad_norm": 0.07272122800350189,
+      "learning_rate": 4.807692307692308e-06,
+      "loss": 0.0098,
       "step": 160
     },
     {
       "epoch": 2.6153846153846154,
-      "grad_norm": 4.014326095581055,
-      "learning_rate": 7.692307692307694e-06,
-      "loss": 0.0444,
+      "grad_norm": 0.27849578857421875,
+      "learning_rate": 4.326923076923077e-06,
+      "loss": 0.0035,
       "step": 170
     },
     {
       "epoch": 2.769230769230769,
-      "grad_norm": 13.623960494995117,
-      "learning_rate": 6.837606837606839e-06,
-      "loss": 0.0707,
+      "grad_norm": 2.9973416328430176,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.0064,
       "step": 180
     },
     {
       "epoch": 2.9230769230769234,
-      "grad_norm": 1.9218041896820068,
-      "learning_rate": 5.982905982905983e-06,
-      "loss": 0.0493,
+      "grad_norm": 0.30117306113243103,
+      "learning_rate": 3.365384615384616e-06,
+      "loss": 0.0042,
       "step": 190
     },
     {
       "epoch": 3.076923076923077,
-      "grad_norm": 0.4377898573875427,
-      "learning_rate": 5.128205128205128e-06,
-      "loss": 0.059,
+      "grad_norm": 0.04479280859231949,
+      "learning_rate": 2.8846153846153845e-06,
+      "loss": 0.0079,
       "step": 200
     },
     {
       "epoch": 3.076923076923077,
-      "eval_accuracy": 0.9849624060150376,
-      "eval_loss": 0.035541191697120667,
-      "eval_runtime": 5.14,
-      "eval_samples_per_second": 25.875,
-      "eval_steps_per_second": 3.307,
+      "eval_accuracy": 0.9924812030075187,
+      "eval_loss": 0.03436475992202759,
+      "eval_runtime": 5.5035,
+      "eval_samples_per_second": 24.166,
+      "eval_steps_per_second": 3.089,
       "step": 200
     },
     {
       "epoch": 3.230769230769231,
-      "grad_norm": 0.859157919883728,
-      "learning_rate": 4.273504273504274e-06,
-      "loss": 0.0203,
+      "grad_norm": 0.20207858085632324,
+      "learning_rate": 2.403846153846154e-06,
+      "loss": 0.0093,
       "step": 210
     },
     {
       "epoch": 3.3846153846153846,
-      "grad_norm": 6.222720623016357,
-      "learning_rate": 3.4188034188034193e-06,
-      "loss": 0.0184,
+      "grad_norm": 0.8401392698287964,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 0.003,
       "step": 220
     },
     {
       "epoch": 3.5384615384615383,
-      "grad_norm": 0.6217049956321716,
-      "learning_rate": 2.564102564102564e-06,
-      "loss": 0.0636,
+      "grad_norm": 0.17295202612876892,
+      "learning_rate": 1.4423076923076922e-06,
+      "loss": 0.0087,
       "step": 230
     },
     {
       "epoch": 3.6923076923076925,
-      "grad_norm": 8.089138984680176,
-      "learning_rate": 1.7094017094017097e-06,
-      "loss": 0.0171,
+      "grad_norm": 2.996504068374634,
+      "learning_rate": 9.615384615384617e-07,
+      "loss": 0.0063,
       "step": 240
     },
     {
       "epoch": 3.8461538461538463,
-      "grad_norm": 10.144171714782715,
-      "learning_rate": 8.547008547008548e-07,
-      "loss": 0.0423,
+      "grad_norm": 8.349090576171875,
+      "learning_rate": 4.807692307692308e-07,
+      "loss": 0.0105,
       "step": 250
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.059058304876089096,
+      "grad_norm": 0.021630151197314262,
       "learning_rate": 0.0,
-      "loss": 0.0486,
+      "loss": 0.0063,
       "step": 260
     },
     {
       "epoch": 4.0,
       "step": 260,
       "total_flos": 1.0280724304719053e+17,
-      "train_loss": 0.21376643198040815,
-      "train_runtime": 415.522,
-      "train_samples_per_second": 9.954,
-      "train_steps_per_second": 0.626
+      "train_loss": 0.017011618363456084,
+      "train_runtime": 403.5216,
+      "train_samples_per_second": 10.25,
+      "train_steps_per_second": 0.644
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a3ad171bc8bafbbf592063ce1b1f803e5628e3ee6763929051e05ef06daa55
+oid sha256:a2172a118df2fc41a3f44f9ae01e303ef57d73b0c3a30809bc6fb91ad6fa327c
 size 5304