Outer Step 3. Inner Step 170. Batch Size 276

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5227727,
-    5227731,
-    5227736,
-    5227740,
-    5227744,
-    5227748,
-    5227752,
-    5227757,
-    5227762,
-    5227766
+    5227796,
+    5227801,
+    5227805,
+    5227809,
+    5227814,
+    5227818,
+    5227822,
+    5227826,
+    5227831,
+    5227835
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 160,
+  "inner_step": 170,
   "inner_steps": 0,
   "last_allreduce_block": 5226437,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def01ac082aab46de3eb00551ff781a40f8a9c5482d2d78b29eb2130f7395fd8
+oid sha256:8c85fe30a46b9f0ebbccc520447ca05e004301307221790063569277ba1fbbb4
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50627547d68ff6fb96fae9800a434f3dd366447140faa75003e69b2ab38c2b5b
+oid sha256:2c3dd3c700c43ff49c22c836024ae69e8503b92e34e4758a3f35e134019363bd
 size 4040701744