Training in progress, epoch 1

all_results.json

@@ -1,8 +1,13 @@
 {
     "epoch": 5.0,
+    "eval_loss": 0.934228241443634,
+    "eval_precision": 0.6190476190476191,
+    "eval_runtime": 4.6731,
+    "eval_samples_per_second": 8.988,
+    "eval_steps_per_second": 0.428,
     "total_flos": 6.035622766903296e+16,
-    "train_loss": 1.064906406402588,
-    "train_runtime": 283.2596,
-    "train_samples_per_second": 6.549,
-    "train_steps_per_second": 0.053
+    "train_loss": 0.9754562060038249,
+    "train_runtime": 289.4698,
+    "train_samples_per_second": 6.408,
+    "train_steps_per_second": 0.052
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.934228241443634,
+    "eval_precision": 0.6190476190476191,
+    "eval_runtime": 4.6731,
+    "eval_samples_per_second": 8.988,
+    "eval_steps_per_second": 0.428
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c887b93ebd3e60fc4963ddb9ac8ef927349759aa71e3a213750c437e3922b38f
+oid sha256:61457363201b2c21368b3764a6d5249c3c587648f3e371337a529e7195e493d9
 size 110414814

runs/Apr02_15-14-15_70a6fb968f98/events.out.tfevents.1712071948.70a6fb968f98.231.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299582aaa75cb7a7a77797bfd3f6999890025f92c07c99bab9cff30ad3e04526
+size 406

runs/Apr02_15-39-40_70a6fb968f98/events.out.tfevents.1712072392.70a6fb968f98.231.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac7a61c9504517804d7bbe9cbe1e975a9ebe0ed5bf5af9b6b219511a0752e37
+size 4577

runs/Apr02_15-39-40_70a6fb968f98/events.out.tfevents.1712072512.70a6fb968f98.231.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f3847d65d79d5ea085e06a8194c5a81a4c76e0f997822a842abb9732aa872b
+size 4577

runs/Apr02_15-39-40_70a6fb968f98/events.out.tfevents.1712072629.70a6fb968f98.231.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b1e469311f957a3d0cff6d62e06c0cb96cf70d861bd3828cc8bdec4c172300
+size 4843

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 6.035622766903296e+16,
-    "train_loss": 1.064906406402588,
-    "train_runtime": 283.2596,
-    "train_samples_per_second": 6.549,
-    "train_steps_per_second": 0.053
+    "train_loss": 0.9754562060038249,
+    "train_runtime": 289.4698,
+    "train_samples_per_second": 6.408,
+    "train_steps_per_second": 0.052
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.5952380952380952,
-  "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-IDRiD-2/checkpoint-6",
+  "best_metric": 0.6190476190476191,
+  "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-IDRiD-2/checkpoint-12",
   "epoch": 5.0,
   "global_step": 15,
   "is_hyper_param_search": false,
@@ -9,63 +9,63 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 1.1601347923278809,
-      "eval_precision": 0.4523809523809524,
-      "eval_runtime": 5.1577,
-      "eval_samples_per_second": 8.143,
-      "eval_steps_per_second": 0.388,
+      "eval_loss": 1.1319794654846191,
+      "eval_precision": 0.5476190476190477,
+      "eval_runtime": 4.7174,
+      "eval_samples_per_second": 8.903,
+      "eval_steps_per_second": 0.424,
       "step": 3
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.0430445671081543,
-      "eval_precision": 0.5952380952380952,
-      "eval_runtime": 5.2678,
-      "eval_samples_per_second": 7.973,
-      "eval_steps_per_second": 0.38,
+      "eval_loss": 1.0103864669799805,
+      "eval_precision": 0.5714285714285714,
+      "eval_runtime": 4.4732,
+      "eval_samples_per_second": 9.389,
+      "eval_steps_per_second": 0.447,
       "step": 6
     },
     {
       "epoch": 3.0,
-      "eval_loss": 1.0825681686401367,
-      "eval_precision": 0.5952380952380952,
-      "eval_runtime": 4.5523,
-      "eval_samples_per_second": 9.226,
-      "eval_steps_per_second": 0.439,
+      "eval_loss": 0.9261651039123535,
+      "eval_precision": 0.5714285714285714,
+      "eval_runtime": 4.5112,
+      "eval_samples_per_second": 9.31,
+      "eval_steps_per_second": 0.443,
       "step": 9
     },
     {
       "epoch": 3.33,
       "learning_rate": 1.923076923076923e-05,
-      "loss": 1.0591,
+      "loss": 0.9507,
       "step": 10
     },
     {
       "epoch": 4.0,
-      "eval_loss": 1.1325061321258545,
-      "eval_precision": 0.5952380952380952,
-      "eval_runtime": 4.5727,
-      "eval_samples_per_second": 9.185,
-      "eval_steps_per_second": 0.437,
+      "eval_loss": 0.934228241443634,
+      "eval_precision": 0.6190476190476191,
+      "eval_runtime": 5.2346,
+      "eval_samples_per_second": 8.024,
+      "eval_steps_per_second": 0.382,
       "step": 12
     },
     {
       "epoch": 5.0,
-      "eval_loss": 1.1388750076293945,
-      "eval_precision": 0.5238095238095238,
-      "eval_runtime": 5.0741,
-      "eval_samples_per_second": 8.277,
-      "eval_steps_per_second": 0.394,
+      "eval_loss": 0.9575217962265015,
+      "eval_precision": 0.6190476190476191,
+      "eval_runtime": 4.948,
+      "eval_samples_per_second": 8.488,
+      "eval_steps_per_second": 0.404,
       "step": 15
     },
     {
       "epoch": 5.0,
       "step": 15,
       "total_flos": 6.035622766903296e+16,
-      "train_loss": 1.064906406402588,
-      "train_runtime": 283.2596,
-      "train_samples_per_second": 6.549,
-      "train_steps_per_second": 0.053
+      "train_loss": 0.9754562060038249,
+      "train_runtime": 289.4698,
+      "train_samples_per_second": 6.408,
+      "train_steps_per_second": 0.052
     }
   ],
   "max_steps": 15,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fefc3da0842dec7951220ca4ef56f94545ce188d2c0e73cd6691e34d1b74be61
+oid sha256:5527f2826856eb5e77b159160b9371426803d12b205cc9caa46c456501eb3ae9
 size 4472