End of training

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 2.0,
+    "epoch": 10.0,
     "eval_accuracy": 0.6,
     "eval_loss": 0.7978684306144714,
     "eval_runtime": 0.4021,
     "eval_samples_per_second": 24.87,
     "eval_steps_per_second": 4.974,
-    "total_flos": 2.9601940032774144e+16,
-    "train_loss": 0.4221321940422058,
-    "train_runtime": 20.4794,
-    "train_samples_per_second": 18.653,
-    "train_steps_per_second": 2.344
+    "total_flos": 1.4800970016387072e+17,
+    "train_loss": 0.10321386102586985,
+    "train_runtime": 163.7528,
+    "train_samples_per_second": 11.664,
+    "train_steps_per_second": 1.466
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3522edc173dbdaa9039fc517d75bd21725dd0cbd678fb08e8e609ef3de15bd09
+oid sha256:88a05ddc7c70850a128b91bc2c1894a4f557748f018f62213f888e70df1ace43
 size 343268717

runs/Mar23_08-01-39_4f145e478cc3/events.out.tfevents.1679558509.4f145e478cc3.6994.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eb5a092cf07f9ac837a4ff98b2726b41b3957c1c43c9cdc5773a8d68a9f7be5
-size 7765
+oid sha256:ae8fc01751f92193f24b776ccaac7a8c79eb1b976e360d01da0bf0d58e807a67
+size 8747

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.0,
-    "total_flos": 2.9601940032774144e+16,
-    "train_loss": 0.4221321940422058,
-    "train_runtime": 20.4794,
-    "train_samples_per_second": 18.653,
-    "train_steps_per_second": 2.344
+    "epoch": 10.0,
+    "total_flos": 1.4800970016387072e+17,
+    "train_loss": 0.10321386102586985,
+    "train_runtime": 163.7528,
+    "train_samples_per_second": 11.664,
+    "train_steps_per_second": 1.466
 }