Outer Step 0. Inner Step 154. Batch Size 412

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5156137,
-    5156145,
-    5156153,
-    5156160,
-    5156169,
-    5156177,
-    5156184,
-    5156195,
-    5156201,
-    5156205
+    5156237,
+    5156241,
+    5156246,
+    5156251,
+    5156255,
+    5156260,
+    5156265,
+    5156270,
+    5156275,
+    5156280
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 146,
+  "inner_step": 154,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6df2f0589d2f88fff86e117a14ed0f01b6bd9d338b5b7bba621e30e8b536bda2
+oid sha256:fcabda0d27def7f9d2226cf176e6ec27789e57dd9ec306d8e27c1a64575f7234
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:869abb342cc549c094ab72f0f61e60fedaf4d4c769337d5ae984006e2030edaa
+oid sha256:f8b2c02949ade7efdc8d6c5fd7f5ba677ea07dcde2f0dffce78fa58fd9eec9c9
 size 4040701744