Training in progress, epoch 1

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 132.281,
     "eval_steps_per_second": 4.724,
     "total_flos": 6.716617754447462e+16,
-    "train_loss": 0.642929474512736,
-    "train_runtime": 92.7694,
-    "train_samples_per_second": 28.813,
-    "train_steps_per_second": 0.226
+    "train_loss": 0.630237170628139,
+    "train_runtime": 87.2731,
+    "train_samples_per_second": 30.628,
+    "train_steps_per_second": 0.241
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b2c2b1413b42944b9ae0df2cf346feef3026d6e754bbad15e404e814d18547
+oid sha256:fe733b12e80dc32a5d3038c144657e73ee755096cf10005a41955e4c27a9ff68
 size 111349029

runs/Jul24_17-51-34_79617dc78cd9/events.out.tfevents.1690221823.79617dc78cd9.248.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15cd42c63dadb6adcea864e3e1927d50f59f1c418b0fa836b32f5be3baaec530
+size 4594

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.716617754447462e+16,
-    "train_loss": 0.642929474512736,
-    "train_runtime": 92.7694,
-    "train_samples_per_second": 28.813,
-    "train_steps_per_second": 0.226
+    "train_loss": 0.630237170628139,
+    "train_runtime": 87.2731,
+    "train_samples_per_second": 30.628,
+    "train_steps_per_second": 0.241
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.75,
-  "best_model_checkpoint": "convnext-tiny-224-jvadlamudi2/checkpoint-21",
+  "best_metric": 0.7946428571428571,
+  "best_model_checkpoint": "convnext-tiny-224-jvadlamudi2/checkpoint-14",
   "epoch": 3.0,
   "global_step": 21,
   "is_hyper_param_search": false,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6964285714285714,
-      "eval_loss": 0.6321507692337036,
-      "eval_runtime": 0.9364,
-      "eval_samples_per_second": 119.604,
-      "eval_steps_per_second": 4.272,
+      "eval_accuracy": 0.7678571428571429,
+      "eval_loss": 0.6085006594657898,
+      "eval_runtime": 0.7752,
+      "eval_samples_per_second": 144.48,
+      "eval_steps_per_second": 5.16,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.6503,
+      "loss": 0.6388,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7142857142857143,
-      "eval_loss": 0.6245036721229553,
-      "eval_runtime": 0.788,
-      "eval_samples_per_second": 142.126,
-      "eval_steps_per_second": 5.076,
+      "eval_accuracy": 0.7946428571428571,
+      "eval_loss": 0.5984492897987366,
+      "eval_runtime": 0.82,
+      "eval_samples_per_second": 136.58,
+      "eval_steps_per_second": 4.878,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.6372,
+      "loss": 0.6218,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.75,
-      "eval_loss": 0.6208862662315369,
-      "eval_runtime": 0.7892,
-      "eval_samples_per_second": 141.913,
-      "eval_steps_per_second": 5.068,
+      "eval_accuracy": 0.7857142857142857,
+      "eval_loss": 0.5960062742233276,
+      "eval_runtime": 0.8803,
+      "eval_samples_per_second": 127.229,
+      "eval_steps_per_second": 4.544,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.716617754447462e+16,
-      "train_loss": 0.642929474512736,
-      "train_runtime": 92.7694,
-      "train_samples_per_second": 28.813,
-      "train_steps_per_second": 0.226
+      "train_loss": 0.630237170628139,
+      "train_runtime": 87.2731,
+      "train_samples_per_second": 30.628,
+      "train_steps_per_second": 0.241
     }
   ],
   "max_steps": 21,