Model save

all_results.json

@@ -1,13 +1,14 @@
 {
     "epoch": 10.0,
     "eval_accuracy": 0.6923076923076923,
-    "eval_loss": 0.6873394846916199,
-    "eval_runtime": 1.5094,
-    "eval_samples_per_second": 17.226,
-    "eval_steps_per_second": 0.663,
-    "total_flos": 2.362275545849856e+16,
-    "train_loss": 0.6464766740798951,
-    "train_runtime": 277.8757,
-    "train_samples_per_second": 8.421,
-    "train_steps_per_second": 0.072
+    "eval_loss": 2.060572751382446e+18,
+    "eval_precision": 0.0,
+    "eval_runtime": 0.6642,
+    "eval_samples_per_second": 10.539,
+    "eval_steps_per_second": 1.506,
+    "total_flos": 5754260945018880.0,
+    "train_loss": 2.490395266277756e+18,
+    "train_runtime": 105.1446,
+    "train_samples_per_second": 5.421,
+    "train_steps_per_second": 0.19
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.6923076923076923,
-    "eval_loss": 0.6873394846916199,
-    "eval_runtime": 1.5094,
-    "eval_samples_per_second": 17.226,
-    "eval_steps_per_second": 0.663
+    "epoch": 10.0,
+    "eval_loss": 2.060572751382446e+18,
+    "eval_precision": 0.0,
+    "eval_runtime": 0.6642,
+    "eval_samples_per_second": 10.539,
+    "eval_steps_per_second": 1.506
 }

runs/May16_15-12-00_goku2/events.out.tfevents.1715872514.goku2.4604.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c7bb032e032219ed65fc8a39937ecb29f862bbd635f5f5c6c8fcee8fab94d1
+size 406

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "total_flos": 2.362275545849856e+16,
-    "train_loss": 0.6464766740798951,
-    "train_runtime": 277.8757,
-    "train_samples_per_second": 8.421,
-    "train_steps_per_second": 0.072
+    "total_flos": 5754260945018880.0,
+    "train_loss": 2.490395266277756e+18,
+    "train_runtime": 105.1446,
+    "train_samples_per_second": 5.421,
+    "train_steps_per_second": 0.19
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6923076923076923,
+  "best_metric": 0.0,
   "best_model_checkpoint": "resnet-18-finetuned-fraud/checkpoint-2",
   "epoch": 10.0,
   "eval_steps": 500,
@@ -10,116 +10,116 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.6821401119232178,
-      "eval_runtime": 1.7618,
-      "eval_samples_per_second": 14.757,
-      "eval_steps_per_second": 0.568,
+      "eval_loss": 2.060572751382446e+18,
+      "eval_precision": 0.0,
+      "eval_runtime": 0.5738,
+      "eval_samples_per_second": 12.2,
+      "eval_steps_per_second": 1.743,
       "step": 2
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.6628227829933167,
-      "eval_runtime": 1.6027,
-      "eval_samples_per_second": 16.223,
-      "eval_steps_per_second": 0.624,
+      "eval_loss": 2.060572751382446e+18,
+      "eval_precision": 0.0,
+      "eval_runtime": 0.5015,
+      "eval_samples_per_second": 13.958,
+      "eval_steps_per_second": 1.994,
       "step": 4
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.6421977281570435,
-      "eval_runtime": 1.6359,
-      "eval_samples_per_second": 15.894,
-      "eval_steps_per_second": 0.611,
+      "eval_loss": 2.060572751382446e+18,
+      "eval_precision": 0.0,
+      "eval_runtime": 0.4768,
+      "eval_samples_per_second": 14.681,
+      "eval_steps_per_second": 2.097,
       "step": 6
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.6217892169952393,
-      "eval_runtime": 1.6129,
-      "eval_samples_per_second": 16.12,
-      "eval_steps_per_second": 0.62,
+      "eval_loss": 2.060572751382446e+18,
+      "eval_precision": 0.0,
+      "eval_runtime": 0.5964,
+      "eval_samples_per_second": 11.737,
+      "eval_steps_per_second": 1.677,
       "step": 8
     },
     {
       "epoch": 5.0,
-      "grad_norm": 3.009413242340088,
+      "grad_norm": 14.733216285705566,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.6696,
+      "loss": 2.5692767593311503e+18,
       "step": 10
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.6059156656265259,
-      "eval_runtime": 1.6613,
-      "eval_samples_per_second": 15.65,
-      "eval_steps_per_second": 0.602,
+      "eval_loss": 2.060572751382446e+18,
+      "eval_precision": 0.0,
+      "eval_runtime": 0.5942,
+      "eval_samples_per_second": 11.781,
+      "eval_steps_per_second": 1.683,
       "step": 10
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.5922008752822876,
-      "eval_runtime": 1.4671,
-      "eval_samples_per_second": 17.723,
-      "eval_steps_per_second": 0.682,
+      "eval_loss": 2.060572751382446e+18,
+      "eval_precision": 0.0,
+      "eval_runtime": 0.5529,
+      "eval_samples_per_second": 12.661,
+      "eval_steps_per_second": 1.809,
       "step": 12
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.5782066583633423,
-      "eval_runtime": 1.5993,
-      "eval_samples_per_second": 16.257,
-      "eval_steps_per_second": 0.625,
+      "eval_loss": 2.060572751382446e+18,
+      "eval_precision": 0.0,
+      "eval_runtime": 0.5729,
+      "eval_samples_per_second": 12.218,
+      "eval_steps_per_second": 1.745,
       "step": 14
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.5681060552597046,
-      "eval_runtime": 1.508,
-      "eval_samples_per_second": 17.242,
-      "eval_steps_per_second": 0.663,
+      "eval_loss": 2.060572751382446e+18,
+      "eval_precision": 0.0,
+      "eval_runtime": 0.5633,
+      "eval_samples_per_second": 12.426,
+      "eval_steps_per_second": 1.775,
       "step": 16
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.5619844198226929,
-      "eval_runtime": 1.6504,
-      "eval_samples_per_second": 15.754,
-      "eval_steps_per_second": 0.606,
+      "eval_loss": 2.060572751382446e+18,
+      "eval_precision": 0.0,
+      "eval_runtime": 0.5508,
+      "eval_samples_per_second": 12.709,
+      "eval_steps_per_second": 1.816,
       "step": 18
     },
     {
       "epoch": 10.0,
-      "grad_norm": 3.1605825424194336,
+      "grad_norm": 18.8521728515625,
       "learning_rate": 0.0,
-      "loss": 0.6234,
+      "loss": 2.411513773224362e+18,
       "step": 20
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.5624192357063293,
-      "eval_runtime": 1.4997,
-      "eval_samples_per_second": 17.337,
-      "eval_steps_per_second": 0.667,
+      "eval_loss": 2.060572751382446e+18,
+      "eval_precision": 0.0,
+      "eval_runtime": 0.5394,
+      "eval_samples_per_second": 12.977,
+      "eval_steps_per_second": 1.854,
       "step": 20
     },
     {
       "epoch": 10.0,
       "step": 20,
-      "total_flos": 2.362275545849856e+16,
-      "train_loss": 0.6464766740798951,
-      "train_runtime": 277.8757,
-      "train_samples_per_second": 8.421,
-      "train_steps_per_second": 0.072
+      "total_flos": 5754260945018880.0,
+      "train_loss": 2.490395266277756e+18,
+      "train_runtime": 105.1446,
+      "train_samples_per_second": 5.421,
+      "train_steps_per_second": 0.19
     }
   ],
   "logging_steps": 10,
@@ -127,8 +127,8 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2.362275545849856e+16,
-  "train_batch_size": 32,
+  "total_flos": 5754260945018880.0,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null
 }