Training in progress, epoch 1

all_results.json

@@ -5,9 +5,9 @@
     "eval_runtime": 0.8467,
     "eval_samples_per_second": 132.281,
     "eval_steps_per_second": 4.724,
-    "total_flos": 7.553368114429133e+16,
-    "train_loss": 0.6847228904565176,
-    "train_runtime": 88.414,
-    "train_samples_per_second": 33.999,
-    "train_steps_per_second": 0.271
+    "total_flos": 6.716617754447462e+16,
+    "train_loss": 0.6701105549221947,
+    "train_runtime": 77.3039,
+    "train_samples_per_second": 34.578,
+    "train_steps_per_second": 0.272
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96a9ba8b32c24bf0fd271566bbdc34808467c739ba45441e395d814d673a16a
+oid sha256:b166e891dba9a24fffbd55e5844735f7f971b319ed09a94b528bd5d4f80cb31b
 size 111349029

runs/Jul24_17-51-34_79617dc78cd9/events.out.tfevents.1690221468.79617dc78cd9.248.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb3e3ee558cfe4cfb2fa15f566fc5b1e858b8e1979407f2c336d2fabafc8bc4
+size 4594

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "total_flos": 7.553368114429133e+16,
-    "train_loss": 0.6847228904565176,
-    "train_runtime": 88.414,
-    "train_samples_per_second": 33.999,
-    "train_steps_per_second": 0.271
+    "total_flos": 6.716617754447462e+16,
+    "train_loss": 0.6701105549221947,
+    "train_runtime": 77.3039,
+    "train_samples_per_second": 34.578,
+    "train_steps_per_second": 0.272
 }

trainer_state.json

@@ -1,64 +1,64 @@
 {
-  "best_metric": 0.6160714285714286,
-  "best_model_checkpoint": "convnext-tiny-224-jvadlamudi2/checkpoint-24",
+  "best_metric": 0.6607142857142857,
+  "best_model_checkpoint": "convnext-tiny-224-jvadlamudi2/checkpoint-21",
   "epoch": 3.0,
-  "global_step": 24,
+  "global_step": 21,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5535714285714286,
-      "eval_loss": 0.6731433272361755,
-      "eval_runtime": 0.8011,
-      "eval_samples_per_second": 139.814,
-      "eval_steps_per_second": 4.993,
-      "step": 8
+      "eval_accuracy": 0.625,
+      "eval_loss": 0.6631578803062439,
+      "eval_runtime": 0.9325,
+      "eval_samples_per_second": 120.101,
+      "eval_steps_per_second": 4.289,
+      "step": 7
     },
     {
-      "epoch": 1.25,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.6901,
+      "epoch": 1.43,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.6772,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5982142857142857,
-      "eval_loss": 0.6700941920280457,
-      "eval_runtime": 0.9327,
-      "eval_samples_per_second": 120.086,
-      "eval_steps_per_second": 4.289,
-      "step": 16
+      "eval_accuracy": 0.6428571428571429,
+      "eval_loss": 0.6559687256813049,
+      "eval_runtime": 0.9318,
+      "eval_samples_per_second": 120.195,
+      "eval_steps_per_second": 4.293,
+      "step": 14
     },
     {
-      "epoch": 2.5,
-      "learning_rate": 9.523809523809523e-06,
-      "loss": 0.6819,
+      "epoch": 2.86,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.6626,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6160714285714286,
-      "eval_loss": 0.6697055697441101,
-      "eval_runtime": 0.846,
-      "eval_samples_per_second": 132.395,
-      "eval_steps_per_second": 4.728,
-      "step": 24
+      "eval_accuracy": 0.6607142857142857,
+      "eval_loss": 0.6522783637046814,
+      "eval_runtime": 0.932,
+      "eval_samples_per_second": 120.174,
+      "eval_steps_per_second": 4.292,
+      "step": 21
     },
     {
       "epoch": 3.0,
-      "step": 24,
-      "total_flos": 7.553368114429133e+16,
-      "train_loss": 0.6847228904565176,
-      "train_runtime": 88.414,
-      "train_samples_per_second": 33.999,
-      "train_steps_per_second": 0.271
+      "step": 21,
+      "total_flos": 6.716617754447462e+16,
+      "train_loss": 0.6701105549221947,
+      "train_runtime": 77.3039,
+      "train_samples_per_second": 34.578,
+      "train_steps_per_second": 0.272
     }
   ],
-  "max_steps": 24,
+  "max_steps": 21,
   "num_train_epochs": 3,
-  "total_flos": 7.553368114429133e+16,
+  "total_flos": 6.716617754447462e+16,
   "trial_name": null,
   "trial_params": null
 }