Training in progress, epoch 0

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 109.994,
     "eval_steps_per_second": 2.529,
     "total_flos": 1.6971202035873792e+17,
-    "train_loss": 1.6099809010823567,
-    "train_runtime": 79.448,
-    "train_samples_per_second": 29.264,
-    "train_steps_per_second": 0.113
+    "train_loss": 1.5557504230075412,
+    "train_runtime": 77.6328,
+    "train_samples_per_second": 29.949,
+    "train_steps_per_second": 0.116
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eac3dbc9d6b60611648e9ec1b78d465dca05683beb5782a16d740faa25ff58cb
+oid sha256:79f013803fe4ee867f2d4ca2d2d7354b504f1c08cc7b938bbfb541eb1805fc52
 size 343233204

runs/Mar13_08-01-19_83e1a6899153/events.out.tfevents.1710316897.83e1a6899153.35.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bbcf6f404accfd500dc85ee8d80ebfd1a56d1cc964429ef06697bff8582636
+size 5101

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.77,
     "total_flos": 1.6971202035873792e+17,
-    "train_loss": 1.6099809010823567,
-    "train_runtime": 79.448,
-    "train_samples_per_second": 29.264,
-    "train_steps_per_second": 0.113
+    "train_loss": 1.5557504230075412,
+    "train_runtime": 77.6328,
+    "train_samples_per_second": 29.949,
+    "train_steps_per_second": 0.116
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.20689655172413793,
-  "best_model_checkpoint": "vit-base-patch16-224-in21k-finetune/checkpoint-3",
+  "best_metric": 0.3103448275862069,
+  "best_model_checkpoint": "vit-base-patch16-224-in21k-finetune/checkpoint-9",
   "epoch": 2.769230769230769,
   "eval_steps": 500,
   "global_step": 9,
@@ -10,39 +10,39 @@
   "log_history": [
     {
       "epoch": 0.92,
-      "eval_accuracy": 0.20689655172413793,
-      "eval_loss": 1.6120638847351074,
-      "eval_runtime": 0.8547,
-      "eval_samples_per_second": 101.793,
-      "eval_steps_per_second": 2.34,
+      "eval_accuracy": 0.26436781609195403,
+      "eval_loss": 1.6164019107818604,
+      "eval_runtime": 0.759,
+      "eval_samples_per_second": 114.622,
+      "eval_steps_per_second": 2.635,
       "step": 3
     },
     {
       "epoch": 1.85,
-      "eval_accuracy": 0.20689655172413793,
-      "eval_loss": 1.6115880012512207,
-      "eval_runtime": 0.7383,
-      "eval_samples_per_second": 117.841,
-      "eval_steps_per_second": 2.709,
+      "eval_accuracy": 0.2988505747126437,
+      "eval_loss": 1.6093627214431763,
+      "eval_runtime": 0.7415,
+      "eval_samples_per_second": 117.336,
+      "eval_steps_per_second": 2.697,
       "step": 6
     },
     {
       "epoch": 2.77,
-      "eval_accuracy": 0.20689655172413793,
-      "eval_loss": 1.610766887664795,
-      "eval_runtime": 0.7435,
-      "eval_samples_per_second": 117.015,
-      "eval_steps_per_second": 2.69,
+      "eval_accuracy": 0.3103448275862069,
+      "eval_loss": 1.607041835784912,
+      "eval_runtime": 0.7261,
+      "eval_samples_per_second": 119.824,
+      "eval_steps_per_second": 2.755,
       "step": 9
     },
     {
       "epoch": 2.77,
       "step": 9,
       "total_flos": 1.6971202035873792e+17,
-      "train_loss": 1.6099809010823567,
-      "train_runtime": 79.448,
-      "train_samples_per_second": 29.264,
-      "train_steps_per_second": 0.113
+      "train_loss": 1.5557504230075412,
+      "train_runtime": 77.6328,
+      "train_samples_per_second": 29.949,
+      "train_steps_per_second": 0.116
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e53ac7c055a975fd42c1c29faf7b92eec89e3c3d4ff3c020f6581111c5df85
+oid sha256:bae9dfdcd4cda7947f23be609e923a6fe7b965c7e7097d6555ee8f493dd72e15
 size 4984