Outer Step 0. Inner Step 181. Batch Size 40

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5156352,
-    5156357,
-    5156362,
-    5156367,
-    5156372,
-    5156378,
-    5156382,
-    5156387,
-    5156392,
-    5156398
+    5156433,
+    5156438,
+    5156443,
+    5156448,
+    5156454,
+    5156459,
+    5156464,
+    5156470,
+    5156475,
+    5156481
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 172,
+  "inner_step": 181,
   "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 sha256:73d49e8f3d4be43b48c9701ea93e197f097fa72270757bdc375e15f527b9e496
+oid sha256:f0a48bccfb3bde6bb5afde51668f29fee982b543d8e2529f0ff824887c7c6f20
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93200775cf737d6f979e7297b3fcee562de0e72b805fc6c1f90109b3a01fdd7a
+oid sha256:ef2eeea251b96fb7455ec2dc6a809652d73e8017c24e3231b1cb13f12f18872c
 size 4040701744