Training in progress, step 500

all_results.json

@@ -1,8 +1,13 @@
 {
     "epoch": 4.0,
+    "eval_accuracy": 0.9849624060150376,
+    "eval_loss": 0.03612133860588074,
+    "eval_runtime": 2.2122,
+    "eval_samples_per_second": 60.122,
+    "eval_steps_per_second": 7.685,
     "total_flos": 3.205097416476426e+17,
-    "train_loss": 0.12466401972163182,
-    "train_runtime": 874.3126,
-    "train_samples_per_second": 4.731,
-    "train_steps_per_second": 0.595
+    "train_loss": 0.12559190638936482,
+    "train_runtime": 410.5328,
+    "train_samples_per_second": 10.075,
+    "train_steps_per_second": 1.267
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9849624060150376,
+    "eval_loss": 0.03612133860588074,
+    "eval_runtime": 2.2122,
+    "eval_samples_per_second": 60.122,
+    "eval_steps_per_second": 7.685
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2ac00e3d628c0bb664bbc247b57647d9b4a54e626a53046e45ff3cc13d51e7
+oid sha256:b5e7f663c3febf3356f2babe916bd3ce91224f457f5ba1335cebfa3a9d3b103c
 size 343227052

runs/Jan21_01-10-15_df71247a6df6/events.out.tfevents.1737422633.df71247a6df6.832.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1031a0657bdf0100bd89a2a4869784b66ad0a6e594329a752903b8c1adca34
+size 6042

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 3.205097416476426e+17,
-    "train_loss": 0.12466401972163182,
-    "train_runtime": 874.3126,
-    "train_samples_per_second": 4.731,
-    "train_steps_per_second": 0.595
+    "train_loss": 0.12559190638936482,
+    "train_runtime": 410.5328,
+    "train_samples_per_second": 10.075,
+    "train_steps_per_second": 1.267
 }